======================================== correctness_align_bounds.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_argmax.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_assertion_failure_in_parallel_for.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_async.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_async_copy_chain.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_async_device_copy.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_atomics.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_atomic_tuples.exe Error: Did not understand Halide target d3d12compute Expected format is arch-bits-os-processor-feature1-feature2-... Where arch is: arch_unknown, arm, hexagon, powerpc, riscv, wasm, x86. bits is either 32 or 64. os is: android, fuchsia, ios, linux, noos, os_unknown, osx, qurt, wasmrt, windows. processor is: tune_amdfam10, tune_bdver1, tune_bdver2, tune_bdver3, tune_bdver4, tune_btver1, tune_btver2, tune_generic, tune_k8, tune_k8_sse3, tune_znver1, tune_znver2, tune_znver3. If arch, bits, or os are omitted, they default to the host. If processor is omitted, it defaults to tune_generic. Features are: arm_dot_prod, arm_fp16, armv7s, armv81a, asan, avx, avx2, avx512 avx512_cannonlake, avx512_knl, avx512_sapphirerapids, avx512_skylake, c_plus_plus_name_mangling check_unsafe_promises, cl_atomics64, cl_doubles, cl_half, cuda, cuda_capability_30 cuda_capability_32, cuda_capability_35, cuda_capability_50, cuda_capability_61 cuda_capability_70, cuda_capability_75, cuda_capability_80, cuda_capability_86 d3d12compute, debug, egl, embed_bitcode, enable_llvm_loop_opt, f16c, fma fma4, fuzz_float_stores, hexagon_dma, hvx, hvx_128, hvx_v62, hvx_v65, hvx_v66 jit, large_buffers, llvm_large_code_model, metal, msan, no_asserts, no_bounds_query no_neon, no_runtime, opencl, openglcompute, power_arch_2_07, profile, profile_by_timer rvv, sanitizer_coverage, semihosting, soft_float_abi, spirv, sse41, strict_float sve, sve2, trace_loads, trace_pipeline, trace_realizations, trace_stores tsan, user_context, vsx, wasm_bulk_memory, wasm_sat_float_to_int, wasm_signext wasm_simd128, wasm_threads, webgpu. The target can also begin with "host", which sets the host's architecture, os, and feature set, with the exception of the GPU runtimes, which default to off. On this platform, the host target is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 ======================================== ======================================== correctness_align_bounds.exe Success! ======================================== ======================================== correctness_argmax.exe ======================================== ======================================== correctness_assertion_failure_in_parallel_for.exe Expected: Bounds given for h in x (from 0 to 9) do not cover required region (from 0 to 10) Expected: Bounds given for h in x (from 0 to 9) do not cover required region (from 0 to 10) Expected: Bounds given for h in x (from 0 to 9) do not cover required region (from 0 to 10) Expected: Bounds given for h in x (from 0 to 9) do not cover required region (from 0 to 10) Success! ======================================== ======================================== correctness_async.exe Success! ======================================== ======================================== correctness_async_copy_chain.exe ======================================== ======================================== correctness_async_device_copy.exe ======================================== ======================================== correctness_atomics.exe Warning: In function f485_par_for_f485_s1_r1368__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f489_par_for_f489_s1_r1379__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f493_par_for_f493_s1_r1390__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f493_par_for_f493_s2_r1390__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f493_par_for_f493_s3_r1390__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f493, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f498_par_for_f498_s0_v404_rebased_par_for_f497_s1_r1414__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f505_par_for_f505_s0_v408_rebased_par_for_f504_s1_r1435__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f511_par_for_f511_s1_r1457__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f517_par_for_f517_s1_r1468__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f527_par_for_f527_s1_r1479__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f527, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f539_par_for_f539_s1_r1488__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f539, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f552_par_for_f552_s0_v424_rebased_par_for_f551_s1_r1497__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f562_par_for_f562_s1_r1518__x_r1521, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f566_par_for_f566_s1_r1532__x_r1535, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f571_par_for_f571_s0_v442_rebased_par_for_f570_s1_r1546__x_r1553, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f578_par_for_f578_s0_v450_rebased_par_for_f577_s1_r1570__x_r1578, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f584_par_for_f584_s1_r1595__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f588_par_for_f588_s1_r1606__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f592_par_for_f592_s1_r1617__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f592_par_for_f592_s2_r1617__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f592_par_for_f592_s3_r1617__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f592, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f597_par_for_f597_s0_v473_rebased_par_for_f596_s1_r1641__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f604_par_for_f604_s0_v477_rebased_par_for_f603_s1_r1662__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f610_par_for_f610_s1_r1684__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f616_par_for_f616_s1_r1695__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f626_par_for_f626_s1_r1706__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f626, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f638_par_for_f638_s1_r1715__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f638, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f651_par_for_f651_s0_v493_rebased_par_for_f650_s1_r1724__x, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f661_par_for_f661_s1_r1745__x_r1748, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f665_par_for_f665_s1_r1759__x_r1762, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f670_par_for_f670_s0_v511_rebased_par_for_f669_s1_r1773__x_r1780, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f677_par_for_f677_s0_v519_rebased_par_for_f676_s1_r1797__x_r1805, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Success! ======================================== ======================================== correctness_atomic_tuples.exe Success! ======================================== ======================================== correctness_autodiff.exe Warning: Dropping gradients at call to round Warning: Dropping gradients at call to round Warning: Dropping gradients at call to round Warning: Dropping gradients at call to round [autodiff] Success! ======================================== ======================================== correctness_bad_likely.exe Success! ======================================== ======================================== correctness_bitwise_ops.exe Success! ======================================== ======================================== correctness_bit_counting.exe Success! ======================================== ======================================== correctness_bool_compute_root_vectorize.exe ======================================== ======================================== correctness_bound.exe Success! ======================================== ======================================== correctness_boundary_conditions.exe ======================================== ======================================== correctness_bounds.exe ======================================== ======================================== correctness_bounds_inference.exe ======================================== ======================================== correctness_bounds_inference_chunk.exe Success! ======================================== ======================================== correctness_bounds_inference_complex.exe Success! ======================================== ======================================== correctness_bounds_inference_outer_split.exe Success! ======================================== ======================================== correctness_bounds_of_abs.exe Success! ======================================== ======================================== correctness_bounds_of_cast.exe Success! ======================================== ======================================== correctness_bounds_of_func.exe Success! ======================================== ======================================== correctness_bounds_of_monotonic_math.exe Success! ======================================== ======================================== correctness_bounds_of_multiply.exe Trying int32_t Trying int16_t Success! ======================================== ======================================== correctness_bounds_of_split.exe Success! ======================================== ======================================== correctness_bounds_query.exe Success! ======================================== ======================================== correctness_bound_small_allocations.exe Success! ======================================== ======================================== correctness_bound_storage.exe Success! ======================================== ======================================== correctness_buffer_t.exe Success! ======================================== ======================================== correctness_callable.exe Success! ======================================== ======================================== correctness_callable_errors.exe Saw expected: (NO ERROR) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Argument 1 of 4 ('p_img') was expected to be a buffer of type 'uint8' and dimension 2) Saw expected: (Argument 2 of 4 ('p_int') was expected to be a scalar of type 'int32' and dimension 0) Saw expected: (Argument 3 of 4 ('p_float') was expected to be a scalar of type 'float32' and dimension 0) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (Buffer argument fn1 is nullptr) Saw expected: (NO ERROR) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Argument 1 of 4 ('p_img') was expected to be a buffer of type 'uint8' and dimension 2) Saw expected: (Argument 2 of 4 ('p_int') was expected to be a scalar of type 'int32' and dimension 0) Saw expected: (Argument 3 of 4 ('p_float') was expected to be a scalar of type 'float32' and dimension 0) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (Buffer argument fn2 is nullptr) Saw expected: (NO ERROR) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument fn3 is nullptr) Saw expected: (Buffer argument fn3 is nullptr) Saw expected: (Buffer argument fn3 is nullptr) Saw expected: (Buffer argument fn3 is nullptr) Saw expected: (Argument 1 of 4 ('p_img') was expected to be a buffer of type 'uint8' and dimension 2) Saw expected: (Argument 2 of 4 ('p_int') was expected to be a scalar of type 'int32' and dimension 0) Saw expected: (Argument 3 of 4 ('p_float') was expected to be a scalar of type 'float32' and dimension 0) Saw expected: (Argument 4 of 4 ('fn3') was expected to be a buffer of type 'uint8' and dimension 2) Saw expected: (NO ERROR) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument p_img is nullptr) Saw expected: (Buffer argument fn4 is nullptr) Saw expected: (Buffer argument fn4 is nullptr) Saw expected: (Buffer argument fn4 is nullptr) Saw expected: (Buffer argument fn4 is nullptr) Success! ======================================== ======================================== correctness_callable_generator.exe Success! ======================================== ======================================== correctness_callable_typed.exe Success! ======================================== ======================================== correctness_cascaded_filters.exe ======================================== ======================================== correctness_cast.exe Success! ======================================== ======================================== correctness_cast_handle.exe Success! ======================================== ======================================== correctness_chunk.exe ======================================== ======================================== correctness_chunk_sharing.exe Defining function... Realizing function... Success! ======================================== ======================================== correctness_circular_reference_leak.exe Success! ======================================== ======================================== correctness_code_explosion.exe Success! ======================================== ======================================== correctness_compare_vars.exe Success! ======================================== ======================================== correctness_compile_to.exe fn_object is D:\ThirdParty\Halide\build\msvc\bin\Release\compile_to_native.o Success! ======================================== ======================================== correctness_compile_to_bitcode.exe Success! ======================================== ======================================== correctness_compile_to_lowered_stmt.exe Success! ======================================== ======================================== correctness_compile_to_multitarget.exe Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_set_current_func' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_acquire_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_release_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_init_sampling_token' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_incr_active_threads' seen multiple times in library. Warning: Warning: symbol 'halide_profiler_decr_active_threads' seen multiple times in library. Success! ======================================== ======================================== correctness_computed_index.exe Success! ======================================== ======================================== correctness_compute_at_reordered_update_stage.exe Success! ======================================== ======================================== correctness_compute_at_split_rvar.exe Success! ======================================== ======================================== correctness_compute_inside_guard.exe Success! ======================================== ======================================== correctness_compute_outermost.exe Success! ======================================== ======================================== correctness_compute_with.exe ======================================== ======================================== correctness_compute_with_in.exe Success! ======================================== ======================================== correctness_compute_with_inlined.exe Success! ======================================== ======================================== correctness_concat.exe Success! ======================================== ======================================== correctness_constant_expr.exe Success! ======================================== ======================================== correctness_constant_type.exe Success! ======================================== ======================================== correctness_constraints.exe Success! ======================================== ======================================== correctness_convolution.exe ======================================== ======================================== correctness_convolution_multiple_kernels.exe ======================================== ======================================== correctness_cross_compilation.exe Test generating: target(arm-32-android) Test generating: target(arm-32-ios) Test generating: target(arm-32-linux) Test generating: target(arm-32-noos-semihosting) Test generating: target(arm-64-android) Test generating: target(arm-64-ios) Test generating: target(arm-64-linux) Test generating: target(arm-64-windows) Test generating: target(arm-64-windows-d3d12compute) Test generating: target(arm-64-noos-semihosting) Test generating: target(x86-32-linux) Test generating: target(x86-32-osx) Test generating: target(x86-32-windows) Test generating: target(x86-64-linux) Test generating: target(x86-64-osx) Test generating: target(x86-64-windows) Test generating: target(x86-64-windows-d3d12compute) Test generating: target(wasm-32-wasmrt) Success! ======================================== ======================================== correctness_cse_nan.exe Success! ======================================== ======================================== correctness_cuda_8_bit_dot_product.exe [SKIP] Cuda (with compute capability 6.1) is not enabled in target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 ======================================== ======================================== correctness_custom_allocator.exe Success! ======================================== ======================================== correctness_custom_auto_scheduler.exe Success! ======================================== ======================================== correctness_custom_cuda_context.exe [SKIP] CUDA not enabled. ======================================== ======================================== correctness_custom_error_reporter.exe Custom warn: Warning(semicolon) Here is a warning. Should be evaluated Custom err: Error(semicolon) 0 Success! ======================================== ======================================== correctness_custom_jit_context.exe Success! ======================================== ======================================== correctness_custom_lowering_pass.exe Success! ======================================== ======================================== correctness_c_function.exe Success! ======================================== ======================================== correctness_dead_realization_in_specialization.exe Success! ======================================== ======================================== correctness_debug_to_file.exe ======================================== ======================================== correctness_debug_to_file_multiple_outputs.exe Success! ======================================== ======================================== correctness_debug_to_file_reorder.exe ======================================== ======================================== correctness_deferred_loop_level.exe Success! ======================================== ======================================== correctness_deinterleave4.exe Success! ======================================== ======================================== correctness_device_buffer_copy.exe ======================================== ======================================== correctness_device_copy_at_inner_loop.exe ======================================== ======================================== correctness_device_crop.exe ======================================== ======================================== correctness_device_slice.exe ======================================== ======================================== correctness_dilate3x3.exe ======================================== ======================================== correctness_div_by_zero.exe Success! ======================================== ======================================== correctness_div_round_to_zero.exe Success! ======================================== ======================================== correctness_dynamic_allocation_in_gpu_kernel.exe ======================================== ======================================== correctness_dynamic_reduction_bounds.exe Success! ======================================== ======================================== correctness_early_out.exe Success! ======================================== ======================================== correctness_embed_bitcode.exe Success! ======================================== ======================================== correctness_erf.exe Maximum number of incorrect mantissa bits: 4 @ -0.0248 Success! ======================================== ======================================== correctness_exception.exe Expected compile error: Error: Implicit cast from float32 to int in argument 1 in call to "f0" is not allowed. Use an explicit cast. Expected compile error: Error: Can't index into a reference to Func "f0", because it does not return a Tuple. Expected compile error: Error: In update definition 0 of Func "f0": Tuple element 0 of update definition has type float32, but pure definition has type int32 Expected compile error: Error: In update definition 0 of Func "f0": Undefined expression in right-hand-side of update. Expected internal error: Internal Error at D:\ThirdParty\Halide\src\IR.cpp:40 triggered by user code at : Condition failed: a.defined(): Add of undefined Expected internal error: Internal Error at D:\ThirdParty\Halide\src\ModulusRemainder.cpp:160 triggered by user code at : modulus_remainder of bool Expected runtime error: Error: Buffer argument p0 is nullptr Expected runtime error: Error: Parameter p1 is -4 but must be at least 0 Success! ======================================== ======================================== correctness_explicit_inline_reductions.exe Success! ======================================== ======================================== correctness_extern_bounds_inference.exe Success! ======================================== ======================================== correctness_extern_consumer.exe Success! ======================================== ======================================== correctness_extern_consumer_tiled.exe Success! ======================================== ======================================== correctness_extern_error.exe Expected: Bounds inference call to external stage extern_error returned non-zero value: -1 Expected: Bounds inference call to external stage extern_error returned non-zero value: -1 Success! ======================================== ======================================== correctness_extern_output_expansion.exe in: 0 102, out: 0 17 in: 0 102, out: 10 17 in: 0 102, out: 20 17 in: 0 102, out: 30 17 in: 0 102, out: 40 17 in: 0 102, out: 50 17 in: 0 102, out: 60 17 in: 0 102, out: 70 17 in: 0 102, out: 80 17 in: 0 102, out: 85 17 in: 0 102, out: 0 102 Success! ======================================== ======================================== correctness_extern_partial.exe Success! ======================================== ======================================== correctness_extern_producer.exe ======================================== ======================================== correctness_extern_reorder_storage.exe Success! ======================================== ======================================== correctness_extern_sort.exe ======================================== ======================================== correctness_extern_stage.exe Doing flip_x bounds inference over [0 99] Doing flip_x bounds inference over [0 99] Doing flip_x bounds inference over [0 99] Doing flip_x bounds inference over [0 99] Doing flip_x bounds inference over [0 63] Doing flip_x bounds inference over [0 63] Computing flip_x over [0 63] Doing flip_x bounds inference over [64 99] Doing flip_x bounds inference over [64 99] Computing flip_x over [64 99] Success! ======================================== ======================================== correctness_extern_stage_on_device.exe ======================================== ======================================== correctness_extract_concat_bits.exe reinterpret((struct halide_buffer_t *)f1.buffer) 1 1 reinterpret<(void *)>((uint64)0) 1 1 reinterpret<(struct halide_device_interface_t *)>((uint64)0) 1 1 reinterpret<(void *)>((uint64)0) 1 1 1 0 0 reinterpret((struct halide_buffer_t *)f7.buffer) 1 1 reinterpret<(void *)>((uint64)0) 1 1 reinterpret<(struct halide_device_interface_t *)>((uint64)0) 1 1 reinterpret<(void *)>((uint64)0) 1 1 reinterpret((uint32x8)f6[ramp(f7.s0.v1.v3.base.s - t29, 1, 8)]) 32 8 Got one reinterpret((uint32x8)f6[ramp(((t31 + -29)/4) - t32, 1, 8)]) 32 8 Got one 0 2 0 reinterpret((struct halide_buffer_t *)f13.buffer) 1 1 reinterpret<(void *)>((uint64)0) 1 1 reinterpret<(struct halide_device_interface_t *)>((uint64)0) 1 1 reinterpret<(void *)>((uint64)0) 1 1 reinterpret((uint8x4)f12[ramp(f13.s0.v4.rebased*4, 1, 4) aligned(4, 0)]) 1 4 Got one reinterpret((struct halide_buffer_t *)f19.buffer) 1 1 reinterpret<(void *)>((uint64)0) 1 1 reinterpret<(struct halide_device_interface_t *)>((uint64)0) 1 1 reinterpret<(void *)>((uint64)0) 1 1 reinterpret((uint8x32)t47) 8 32 Got one reinterpret((uint8x32)t48) 8 32 Got one Success! ======================================== ======================================== correctness_failed_unroll.exe [SKIP] Windows does not have a working setenv ======================================== ======================================== correctness_fast_trigonometric.exe Success! ======================================== ======================================== correctness_fibonacci.exe Success! ======================================== ======================================== correctness_fit_function.exe Iteration 0 Coefficients: 1 -0.166667 0.00833333 -0.000198413 2.75573e-06 -2.50521e-08 1.6059e-10 -7.64716e-13 Err: 1.02327e-24 Iteration 5000 Coefficients: 1 -0.166667 0.00833333 -0.000198413 2.75573e-06 -2.50521e-08 1.60587e-10 -7.55237e-13 Err: 2.04173e-28 Iteration 10000 Coefficients: 1 -0.166667 0.00833333 -0.000198413 2.75573e-06 -2.50521e-08 1.60586e-10 -7.55031e-13 Err: 1.87354e-28 [fit_function] Success! ======================================== ======================================== correctness_float16_t.exe Testing float16_t... Testing _Float16... [Compiler does not support _Float16, skipping] Success! ======================================== ======================================== correctness_float16_t_comparison.exe Success! ======================================== ======================================== correctness_float16_t_constants.exe Checking positive zero... Checking negative zero... Checking positive infinity... Checking negative infinity... Checking NaN... Success! ======================================== ======================================== correctness_float16_t_image_type.exe Success! ======================================== ======================================== correctness_float16_t_neon_op_check.exe host is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 HL_TARGET is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41 HL_JIT_TARGET is: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 [SKIP] To run this test, set HL_TARGET=arm-64--arm_fp16. ======================================== ======================================== correctness_force_onto_stack.exe Success! ======================================== ======================================== correctness_for_each_element.exe Success! ======================================== ======================================== correctness_func_clone.exe Running calling clone no op test Running func clone test Running multiple funcs sharing clone test Running update is defined after clone test Running clone depend on mutated func test Running clone on clone test Running clone reduction test Success! ======================================== ======================================== correctness_func_lifetime.exe ======================================== ======================================== correctness_func_lifetime_2.exe ======================================== ======================================== correctness_func_wrapper.exe Running calling wrap no op test Running func wrap test Running multiple funcs sharing wrapper test Running global wrap test Running update is defined after wrap test Running rdom wrapper test Running global + custom wrapper test Running wrapper depend on mutated func test Running wrapper on wrapper test Running wrapper on rdom predicate test Running two fold wrapper test Running multi folds wrapper test Running lots of wrappers test Success! ======================================== ======================================== correctness_fuse.exe ======================================== ======================================== correctness_fused_where_inner_extent_is_zero.exe Success! ======================================== ======================================== correctness_fuse_gpu_threads.exe Success! ======================================== ======================================== correctness_fuzz_bounds.exe bounds inference fuzz test seed: 1680898961 Success! ======================================== ======================================== correctness_fuzz_cse.exe Success! ======================================== ======================================== correctness_fuzz_float_stores.exe Success! ======================================== ======================================== correctness_fuzz_simplify.exe Simplify fuzz test seed: 1680898964 Success! ======================================== ======================================== correctness_gameoflife.exe Success! ======================================== ======================================== correctness_gather.exe Success! ======================================== ======================================== correctness_gpu_allocation_cache.exe [SKIP] Allocation cache not yet implemented for D3D12Compute. ======================================== ======================================== correctness_gpu_arg_types.exe ======================================== ======================================== correctness_gpu_assertion_in_kernel.exe [SKIP] CUDA not enabled ======================================== ======================================== correctness_gpu_bounds_inference_failure.exe [SKIP] CUDA not enabled ======================================== ======================================== correctness_gpu_condition_lifting.exe ======================================== ======================================== correctness_gpu_cpu_simultaneous_read.exe ======================================== ======================================== correctness_gpu_data_flows.exe ======================================== ======================================== correctness_gpu_different_blocks_threads_dimensions.exe Success! ======================================== ======================================== correctness_gpu_dynamic_shared.exe ======================================== ======================================== correctness_gpu_error_1.exe Success! ======================================== ======================================== correctness_gpu_error_2.exe Saw expected error message. Success! ======================================== ======================================== correctness_gpu_free_sync.exe Success! ======================================== ======================================== correctness_gpu_give_input_buffers_device_allocations.exe ======================================== ======================================== correctness_gpu_jit_explicit_copy_to_device.exe ======================================== ======================================== correctness_gpu_large_alloc.exe ======================================== ======================================== correctness_gpu_many_kernels.exe ======================================== ======================================== correctness_gpu_mixed_dimensionality.exe ======================================== ======================================== correctness_gpu_mixed_shared_mem_types.exe ======================================== ======================================== correctness_gpu_multi_kernel.exe ======================================== ======================================== correctness_gpu_non_contiguous_copy.exe ======================================== ======================================== correctness_gpu_non_monotonic_shared_mem_size.exe ======================================== ======================================== correctness_gpu_object_lifetime_1.exe Entering Pipeline f0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0xdc35bbe090 Output Buffer f0: buffer(0, 0x0, 0x0, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x0 [@] d3d12_create_context [@] D3D12CreateSystemDefaultDevice [@] D3D12LoadDependencies [@] d3d12_load_library Loaded runtime library 'd3d12.dll' at location 0x7ffe29520000 Time [d3d12_load_library]: 1932 us [@] d3d12_load_library Loaded runtime library 'D3DCompiler_47.dll' at location 0x7ffe31060000 Time [d3d12_load_library]: 1926 us [@] d3d12_load_library Loaded runtime library 'dxgi.dll' at location 0x7ffe33d00000 Time [d3d12_load_library]: 849 us [@] d3d12_get_library_symbol Symbol 'D3D12CreateDevice' found @ 0x7ffe29526af0 [@] d3d12_get_library_symbol Symbol 'D3D12GetDebugInterface' found @ 0x7ffe29530270 [@] d3d12_get_library_symbol Symbol 'D3D12SerializeRootSignature' found @ 0x7ffe295302b0 [@] d3d12_get_library_symbol Symbol 'D3DCompile' found @ 0x7ffe311523f0 [@] d3d12_get_library_symbol Symbol 'CreateDXGIFactory1' found @ 0x7ffe33d1e680 Time [D3D12LoadDependencies]: 4723 us Using Direct3D 12 Debug Layer [@] D3DErrorCheck SUCCESS: ID3D12Debug object created: 0x232eb9079a0 [@] D3DErrorCheck SUCCESS: IDXGIFactory1 object created: 0x232e912bcf0 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x232e9156790 Adapter #0: NVIDIA RTX A4000 (this is the best device so far...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x0 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x232eac46850 Adapter #1: Microsoft Basic Render Driver (this is a software adapter; skipping...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x232eac46850 [@] D3D12CreateDeviceForAdapter Device selected: NVIDIA RTX A4000 [@] D3DErrorCheck SUCCESS: ID3D12Device object created: 0x232eac52c18 Time [D3D12CreateDeviceForAdapter]: 194264 us [@] Release_ID3D12Object IDXGIFactory1 @ 0x232e912bcf0 Time [D3D12CreateSystemDefaultDevice]: 213919 us [@] D3D12CreateMasterRootSignature [@] D3DErrorCheck SUCCESS: ID3DBlob object created: 0x232eb14e710 [@] D3DErrorCheck SUCCESS: ID3D12RootSignature object created: 0x232eac31aa0 Time [D3D12CreateMasterRootSignature]: 185 us [@] new_command_queue [@] D3DErrorCheck SUCCESS: ID3D12CommandQueue object created: 0x232eace3a10 [@] D3DErrorCheck SUCCESS: ID3D12Fence object created: 0x232eb337700 Time [new_command_queue]: 11792 us [@] new_command_allocator [@] D3DErrorCheck SUCCESS: ID3D12CommandAllocator object created: 0x232eb7c93a0 [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x232eac60bf0 Time [new_buffer_resource]: 690 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x232ede50000 Time [new_upload_buffer]: 845 us [@] new_readback_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x232eadd6ab0 Time [new_buffer_resource]: 489 us Time [new_readback_buffer]: 490 us Time [d3d12_create_context]: 227256 us Time [halide_d3d12compute_acquire_context]: 9223372037082035 us [@] new_library_with_source [@] d3d12_malloc allocated 4617 bytes @ 0x232e90191c0 Caching compiled kernel: 0x232e90191c0 id 2 context 0x232eac52c18 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_initialize_kernels]: 9223372037082051 us Exiting Pipeline f0 [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] halide_d3d12compute_release_context Entering Pipeline f0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0xdc35bbe090 Output Buffer f0: buffer(0, 0x0, 0x232eb2d9b80, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0xdc35bbe090 | halide_buffer_t: 0x232e90799e8 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x232ebd46180 Time [new_buffer_resource]: 176 us Time [new_device_buffer]: 178 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x232e901bc00 Time [new_buffer]: 182 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 187 us [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x232ead130b0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x232e9017790 Time [new_command_list]: 1297 us Time [new_compute_command_list]: 1298 us [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x232eb7d5e90 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x232e901bc70 descriptor heap base for CPU: 1 (0x1) descriptor heap base for GPU: 1841471858671616 (0x68acf14000000) Time [new_descriptor_binder]: 438 us Time [acquire_frame]: 1739 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f0_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x232e901bcd0 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x232eacd5980 Time [new_compute_pipeline_state_with_function]: 9400 us Time [d3d12_compile_shader]: 17497 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x232e901bcf0 [@] d3d12_malloc allocated 53 bytes @ 0x232e901bd40 Exiting halide_memoization_cache_store Time [new_function_with_name]: 17506 us [@] set_compute_pipeline_state Time [set_compute_pipeline_state]: 245 us Time [kernel shader selection]: 17757 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x232ebf552d0 Time [new_buffer_resource]: 236 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x232f2001000 Time [new_upload_buffer]: 247 us Time [new_constant_buffer]: 249 us [@] buffer_contents args[1] -> int32 = 256 args[2] -> int32 = 0 args[3] -> int32 = 8 Time [argument buffer packing]: 256 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x232e901bc00 | offset 0 | 256elements (1024bytes) Time [kernel argument setup]: 282 us [@] pipeline barriers [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 0) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #1... Time [commit_command_list]: 775 us Time [enqueue_frame]: 777 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 20624 us Exiting Pipeline f0 [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_copy_to_host [@] halide_d3d12compute_acquire_context user_context: 0x0 | create: 1 current d3d12_device: 0x232eac52c18 [@] peel_buffer [@] suballocate [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x232ebf665d0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x232e901bd80 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x232eb7d7400 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x232e901bda0 descriptor heap base for CPU: 2 (0x2) descriptor heap base for GPU: 6345071486042112 (0x168acf14000000) Time [new_descriptor_binder]: 365 us Time [acquire_frame]: 436 us [@] synchronize_host_and_device_buffer_contents reading-back buffer from device [@] unmap_buffer --- 0x232e901bc00 | int32 | 0 : 0 : 1024 [@] buffer_copy_command Time [buffer_copy_command]: 292 us Time [synchronize_host_and_device_buffer_contents]: 297 us [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #2... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #2... Time [d3d12compute_device_sync_internal]: 859 us Time [d3d12compute_buffer_copy]: 861 us [@] buffer_contents [@] map_buffer [ Begin: 0 , End: 4194304 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x232f04f4000 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_host]: 876 us [@] halide_d3d12compute_device_free user_context: 0x0 | halide_buffer_t: 0x232e90799e8 [@] peel_buffer d3d12_buffer: 0x232e901bc00 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x232ebd46180 Time [Release_ID3D12Object]: 121 us freeing data structure 'd3d12_buffer' @ 0x232e901bc00 [@] d3d12_free freeing bytes @ 0x232e901bc00 Time [release_d3d12_object]: 125 us Time [halide_d3d12compute_device_free]: 131 us Entering Pipeline f3 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0xdc35bbe090 Output Buffer f3: buffer(0, 0x0, 0x0, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] new_library_with_source [@] d3d12_malloc allocated 4642 bytes @ 0x232e901be00 Caching compiled kernel: 0x232e901be00 id 3 context 0x232eac52c18 [@] halide_d3d12compute_release_context Exiting Pipeline f3 [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] halide_d3d12compute_release_context Entering Pipeline f3 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0xdc35bbe090 Output Buffer f3: buffer(0, 0x0, 0x232eb2d9b80, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0xdc35bbe090 | halide_buffer_t: 0x232eaf2a538 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x232e915fed0 Time [D3DErrorCheck]: 103 us Time [new_buffer_resource]: 383 us Time [new_device_buffer]: 384 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x232e901bc00 Time [new_buffer]: 389 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 395 us [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x232eb2a5b80 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x232e901d1c0 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x232eb7d5b80 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x232e901d440 descriptor heap base for CPU: 3 (0x3) descriptor heap base for GPU: 10848671113412608 (0x268acf14000000) Time [new_descriptor_binder]: 396 us Time [acquire_frame]: 485 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f3_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x232e901d100 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x232eacd6f70 Time [new_compute_pipeline_state_with_function]: 1157 us Time [d3d12_compile_shader]: 4752 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x232e901d4a0 [@] d3d12_malloc allocated 53 bytes @ 0x232e901d4f0 Exiting halide_memoization_cache_store Time [new_function_with_name]: 4760 us [@] set_compute_pipeline_state Time [kernel shader selection]: 4785 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x232eb2976f0 Time [new_buffer_resource]: 239 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x232f2066000 Time [new_upload_buffer]: 255 us Time [new_constant_buffer]: 256 us [@] buffer_contents args[1] -> int32 = 256 args[2] -> int32 = 0 args[3] -> int32 = 8 Time [argument buffer packing]: 264 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x232e901bc00 | offset 0 | 256elements (1024bytes) Time [descriptor binding]: 102 us Time [kernel argument setup]: 370 us [@] pipeline barriers [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 1) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #3... Time [commit_command_list]: 302 us Time [enqueue_frame]: 303 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 5972 us Exiting Pipeline f3 [@] halide_d3d12compute_acquire_context user_context: 0xdc35bbe090 | create: 1 current d3d12_device: 0x232eac52c18 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_copy_to_host [@] halide_d3d12compute_acquire_context user_context: 0x0 | create: 1 current d3d12_device: 0x232eac52c18 [@] peel_buffer [@] suballocate [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x232ebb7b5e0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x232e901d1e0 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x232eb1e3990 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x232e901d530 descriptor heap base for CPU: 4 (0x4) descriptor heap base for GPU: 15352270740783104 (0x368acf14000000) Time [new_descriptor_binder]: 506 us Time [acquire_frame]: 573 us [@] synchronize_host_and_device_buffer_contents reading-back buffer from device [@] unmap_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x232f04f4000 --- 0x232e901bc00 | int32 | 0 : 0 : 1024 [@] buffer_copy_command [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #4... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #4... Time [d3d12compute_device_sync_internal]: 719 us Time [d3d12compute_buffer_copy]: 721 us [@] buffer_contents [@] map_buffer [ Begin: 0 , End: 4194304 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x232f04f4000 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_host]: 735 us [@] halide_d3d12compute_device_free user_context: 0x0 | halide_buffer_t: 0x232eaf2a538 [@] peel_buffer d3d12_buffer: 0x232e901bc00 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x232e915fed0 Time [Release_ID3D12Object]: 120 us freeing data structure 'd3d12_buffer' @ 0x232e901bc00 [@] d3d12_free freeing bytes @ 0x232e901bc00 Time [release_d3d12_object]: 124 us Time [halide_d3d12compute_device_free]: 176 us [@] halide_d3d12compute_cleanup Releasing cached compilation: 0x232e90191c0 id 2 context 0x232eac52c18 [@] release_object [@] release_d3d12_object halide_memoization_cache_cleanup [@] d3d12_free freeing bytes @ 0x232e901bd40 [@] d3d12_free freeing bytes @ 0x232e901bcf0 [@] d3d12_free freeing bytes @ 0x232e90191c0 Releasing cached compilation: 0x232e901be00 id 3 context 0x232eac52c18 [@] release_object [@] release_d3d12_object halide_memoization_cache_cleanup [@] d3d12_free freeing bytes @ 0x232e901d4f0 [@] d3d12_free freeing bytes @ 0x232e901d4a0 [@] d3d12_free freeing bytes @ 0x232e901be00 [@] halide_d3d12compute_device_release [@] halide_d3d12compute_acquire_context user_context: 0x0 | create: 0 current d3d12_device: 0x232eac52c18 [@] d3d12compute_device_sync_internal [@] wait_until_idle [@] wait_until_signaled Already synced up! [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x232ead130b0 [@] d3d12_free freeing bytes @ 0x232e9017790 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x232eb7d5e90 [@] d3d12_free freeing bytes @ 0x232e901bc70 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x232ebf552d0 Time [Release_ID3D12Object]: 141 us Time [release_d3d12_object]: 143 us Time [release_object]: 144 us Time [release_d3d12_object]: 215 us Time [release_object]: 216 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x232ebf665d0 [@] d3d12_free freeing bytes @ 0x232e901bd80 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x232eb7d7400 [@] d3d12_free freeing bytes @ 0x232e901bda0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x232eb2a5b80 [@] d3d12_free freeing bytes @ 0x232e901d1c0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x232eb7d5b80 [@] d3d12_free freeing bytes @ 0x232e901d440 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x232eb2976f0 Time [Release_ID3D12Object]: 113 us Time [release_d3d12_object]: 115 us Time [release_object]: 158 us Time [release_d3d12_object]: 195 us Time [release_object]: 196 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x232ebb7b5e0 [@] d3d12_free freeing bytes @ 0x232e901d1e0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x232eb1e3990 [@] d3d12_free freeing bytes @ 0x232e901d530 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be ======================================== ======================================== correctness_gpu_object_lifetime_2.exe Entering Pipeline f2 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0x2cfa0fda50 Output Buffer f2: buffer(0, 0x0, 0x0, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x0 [@] d3d12_create_context [@] D3D12CreateSystemDefaultDevice [@] D3D12LoadDependencies [@] d3d12_load_library Loaded runtime library 'd3d12.dll' at location 0x7ffe29520000 Time [d3d12_load_library]: 1929 us [@] d3d12_load_library Loaded runtime library 'D3DCompiler_47.dll' at location 0x7ffe31060000 Time [d3d12_load_library]: 1909 us [@] d3d12_load_library Loaded runtime library 'dxgi.dll' at location 0x7ffe33d00000 Time [d3d12_load_library]: 853 us [@] d3d12_get_library_symbol Symbol 'D3D12CreateDevice' found @ 0x7ffe29526af0 [@] d3d12_get_library_symbol Symbol 'D3D12GetDebugInterface' found @ 0x7ffe29530270 [@] d3d12_get_library_symbol Symbol 'D3D12SerializeRootSignature' found @ 0x7ffe295302b0 [@] d3d12_get_library_symbol Symbol 'D3DCompile' found @ 0x7ffe311523f0 [@] d3d12_get_library_symbol Symbol 'CreateDXGIFactory1' found @ 0x7ffe33d1e680 Time [D3D12LoadDependencies]: 4708 us Using Direct3D 12 Debug Layer [@] D3DErrorCheck SUCCESS: ID3D12Debug object created: 0x1f71b8b2ff0 [@] D3DErrorCheck SUCCESS: IDXGIFactory1 object created: 0x1f71ae71b50 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x1f7192d0d40 Adapter #0: NVIDIA RTX A4000 (this is the best device so far...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x0 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x1f71b3915f0 Adapter #1: Microsoft Basic Render Driver (this is a software adapter; skipping...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x1f71b3915f0 [@] D3D12CreateDeviceForAdapter Device selected: NVIDIA RTX A4000 [@] D3DErrorCheck SUCCESS: ID3D12Device object created: 0x1f71b1d0238 Time [D3D12CreateDeviceForAdapter]: 179233 us [@] Release_ID3D12Object IDXGIFactory1 @ 0x1f71ae71b50 Time [D3D12CreateSystemDefaultDevice]: 190211 us [@] D3D12CreateMasterRootSignature [@] D3DErrorCheck SUCCESS: ID3DBlob object created: 0x1f71c0716b0 [@] D3DErrorCheck SUCCESS: ID3D12RootSignature object created: 0x1f71ae7b340 [@] new_command_queue [@] D3DErrorCheck SUCCESS: ID3D12CommandQueue object created: 0x1f71b625d90 [@] D3DErrorCheck SUCCESS: ID3D12Fence object created: 0x1f71b3d3610 Time [new_command_queue]: 11572 us [@] new_command_allocator [@] D3DErrorCheck SUCCESS: ID3D12CommandAllocator object created: 0x1f71bdaa3f0 [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1f71aee64e0 Time [new_buffer_resource]: 487 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1f71e050000 Time [map_buffer]: 148 us Time [new_upload_buffer]: 638 us [@] new_readback_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1f71aead910 Time [new_buffer_resource]: 464 us Time [new_readback_buffer]: 466 us Time [d3d12_create_context]: 202964 us Time [halide_d3d12compute_acquire_context]: 9223372037057744 us [@] new_library_with_source [@] d3d12_malloc allocated 4530 bytes @ 0x1f7191a91c0 Caching compiled kernel: 0x1f7191a91c0 id 2 context 0x1f71b1d0238 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_initialize_kernels]: 9223372037057759 us Exiting Pipeline f2 [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] halide_d3d12compute_release_context Entering Pipeline f2 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0x2cfa0fda50 Output Buffer f2: buffer(0, 0x0, 0x1f71bdb6f80, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x2cfa0fda50 | halide_buffer_t: 0x2cfa0fd570 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1f71b481cc0 Time [new_buffer_resource]: 174 us Time [new_device_buffer]: 175 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1f7191abff0 Time [new_buffer]: 181 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 187 us Time [halide_d3d12compute_device_and_host_malloc]: 189 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x2cfa0fda50 | halide_buffer_t: 0x2cfa0fd530 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1f71bb3ab70 Time [new_buffer_resource]: 163 us Time [new_device_buffer]: 164 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1f7191ac4b0 Time [new_buffer]: 167 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 173 us Time [halide_d3d12compute_device_and_host_malloc]: 174 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x2cfa0fda50 | halide_buffer_t: 0x2cfa0fd530 (this buffer already has a device allocation...) [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_copy_to_device [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] peel_buffer [@] suballocate [@] buffer_contents [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1f71b3ae180 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1f7191a7790 Time [new_command_list]: 710 us Time [new_compute_command_list]: 711 us [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1f71b4640f0 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1f7191ac520 descriptor heap base for CPU: 1 (0x1) descriptor heap base for GPU: 1841471858671616 (0x68acf14000000) Time [new_descriptor_binder]: 554 us Time [acquire_frame]: 1269 us [@] synchronize_host_and_device_buffer_contents uploading buffer to device --- 0x1f7191abff0 | int32 | 0 : 0 : 1024 [@] buffer_copy_command Time [buffer_copy_command]: 164 us Time [synchronize_host_and_device_buffer_contents]: 167 us [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #1... Time [commit_command_list]: 779 us Time [enqueue_frame]: 780 us [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled Already synced up! Time [d3d12compute_device_sync_internal]: 2224 us Time [d3d12compute_buffer_copy]: 2226 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_device]: 2232 us [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1f71b18d110 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1f7191ac580 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1f71b464710 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1f7191ac5a0 descriptor heap base for CPU: 2 (0x2) descriptor heap base for GPU: 6345071486042112 (0x168acf14000000) Time [new_descriptor_binder]: 294 us Time [acquire_frame]: 368 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f1_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x1f7191ac600 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x1f71bcd1aa0 Time [new_compute_pipeline_state_with_function]: 9944 us Time [d3d12_compile_shader]: 14772 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x1f7191ac620 [@] d3d12_malloc allocated 53 bytes @ 0x1f7191ac670 Exiting halide_memoization_cache_store Time [new_function_with_name]: 14779 us [@] set_compute_pipeline_state Time [kernel shader selection]: 14825 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1f71b18f720 Time [new_buffer_resource]: 495 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1f722256000 Time [new_upload_buffer]: 511 us Time [new_constant_buffer]: 513 us [@] buffer_contents args[2] -> int32 = 8 args[3] -> int32 = -32 args[4] -> int32 = 224 Time [argument buffer packing]: 519 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x1f7191abff0 | offset 0 | 256elements (1024bytes) [@] set_input_buffer UAV [1] : 0x1f7191ac4b0 | offset 0 | 256elements (1024bytes) Time [kernel argument setup]: 553 us [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 0) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #2... Time [commit_command_list]: 417 us Time [enqueue_frame]: 418 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 16209 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x2cfa0fda50 | halide_buffer_t: 0x2cfa0fd570 [@] peel_buffer d3d12_buffer: 0x1f7191abff0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #2... Time [block_until_signaled]: 123 us Time [wait_until_signaled]: 127 us [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1f71b481cc0 Time [Release_ID3D12Object]: 119 us freeing data structure 'd3d12_buffer' @ 0x1f7191abff0 [@] d3d12_free freeing bytes @ 0x1f7191abff0 Time [release_d3d12_object]: 123 us Time [halide_d3d12compute_device_free]: 256 us Time [halide_d3d12compute_device_and_host_free]: 259 us [@] halide_d3d12compute_copy_to_host [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] peel_buffer [@] suballocate [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1f71bafa2f0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1f7191ab560 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1f71b463de0 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1f7191abff0 descriptor heap base for CPU: 3 (0x3) descriptor heap base for GPU: 10848671113412608 (0x268acf14000000) Time [new_descriptor_binder]: 322 us Time [acquire_frame]: 389 us [@] synchronize_host_and_device_buffer_contents reading-back buffer from device [@] unmap_buffer --- 0x1f7191ac4b0 | int32 | 0 : 0 : 1024 [@] buffer_copy_command [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #3... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #3... Time [d3d12compute_device_sync_internal]: 532 us Time [d3d12compute_buffer_copy]: 533 us [@] buffer_contents [@] map_buffer [ Begin: 0 , End: 4194304 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1f7206f4000 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_host]: 641 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x2cfa0fda50 | halide_buffer_t: 0x2cfa0fd530 [@] peel_buffer d3d12_buffer: 0x1f7191ac4b0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1f71bb3ab70 Time [Release_ID3D12Object]: 110 us freeing data structure 'd3d12_buffer' @ 0x1f7191ac4b0 [@] d3d12_free freeing bytes @ 0x1f7191ac4b0 Time [release_d3d12_object]: 114 us Time [halide_d3d12compute_device_free]: 120 us Time [halide_d3d12compute_device_and_host_free]: 122 us Exiting Pipeline f2 [@] halide_d3d12compute_acquire_context user_context: 0x2cfa0fda50 | create: 1 current d3d12_device: 0x1f71b1d0238 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_cleanup Releasing cached compilation: 0x1f7191a91c0 id 2 context 0x1f71b1d0238 [@] release_object [@] release_d3d12_object halide_memoization_cache_cleanup [@] d3d12_free freeing bytes @ 0x1f7191ac670 [@] d3d12_free freeing bytes @ 0x1f7191ac620 [@] d3d12_free freeing bytes @ 0x1f7191a91c0 [@] halide_d3d12compute_device_release [@] halide_d3d12compute_acquire_context user_context: 0x0 | create: 0 current d3d12_device: 0x1f71b1d0238 [@] d3d12compute_device_sync_internal [@] wait_until_idle [@] wait_until_signaled Already synced up! [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1f71b3ae180 [@] d3d12_free freeing bytes @ 0x1f7191a7790 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1f71b4640f0 [@] d3d12_free freeing bytes @ 0x1f7191ac520 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1f71b18d110 [@] d3d12_free freeing bytes @ 0x1f7191ac580 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1f71b464710 [@] d3d12_free freeing bytes @ 0x1f7191ac5a0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1f71b18f720 Time [Release_ID3D12Object]: 148 us Time [release_d3d12_object]: 150 us Time [release_object]: 151 us Time [release_d3d12_object]: 194 us Time [release_object]: 195 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1f71bafa2f0 [@] d3d12_free freeing bytes @ 0x1f7191ab560 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1f71b463de0 [@] d3d12_free freeing bytes @ 0x1f7191abff0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1f71aee64e0 Time [Release_ID3D12Object]: 142 us Time [release_d3d12_object]: 144 us Time [release_object]: 145 us [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1f71aead910 Time [Release_ID3D12Object]: 153 us Time [release_d3d12_object]: 159 us Time [release_object]: 160 us [@] Release_ID3D12Object ID3D12RootSignature @ 0x1f71ae7b340 [@] release_object ======================================== ======================================== correctness_gpu_object_lifetime_3.exe Entering Pipeline f9 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0x37457ddc90 Output Buffer f9: buffer(0, 0x0, 0x0, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x0 [@] d3d12_create_context [@] D3D12CreateSystemDefaultDevice [@] D3D12LoadDependencies [@] d3d12_load_library Loaded runtime library 'd3d12.dll' at location 0x7ffe29520000 Time [d3d12_load_library]: 1973 us [@] d3d12_load_library Loaded runtime library 'D3DCompiler_47.dll' at location 0x7ffe31060000 Time [d3d12_load_library]: 1961 us [@] d3d12_load_library Loaded runtime library 'dxgi.dll' at location 0x7ffe33d00000 Time [d3d12_load_library]: 859 us [@] d3d12_get_library_symbol Symbol 'D3D12CreateDevice' found @ 0x7ffe29526af0 [@] d3d12_get_library_symbol Symbol 'D3D12GetDebugInterface' found @ 0x7ffe29530270 [@] d3d12_get_library_symbol Symbol 'D3D12SerializeRootSignature' found @ 0x7ffe295302b0 [@] d3d12_get_library_symbol Symbol 'D3DCompile' found @ 0x7ffe311523f0 [@] d3d12_get_library_symbol Symbol 'CreateDXGIFactory1' found @ 0x7ffe33d1e680 Time [D3D12LoadDependencies]: 4811 us Using Direct3D 12 Debug Layer [@] D3DErrorCheck SUCCESS: ID3D12Debug object created: 0x1e82749b230 [@] D3DErrorCheck SUCCESS: IDXGIFactory1 object created: 0x1e8270f5d20 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x1e8250f9420 Adapter #0: NVIDIA RTX A4000 (this is the best device so far...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x0 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x1e8250de4d0 Adapter #1: Microsoft Basic Render Driver (this is a software adapter; skipping...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x1e8250de4d0 [@] D3D12CreateDeviceForAdapter Device selected: NVIDIA RTX A4000 [@] D3DErrorCheck SUCCESS: ID3D12Device object created: 0x1e826e479f8 Time [D3D12CreateDeviceForAdapter]: 180166 us [@] Release_ID3D12Object IDXGIFactory1 @ 0x1e8270f5d20 Time [D3D12CreateSystemDefaultDevice]: 191054 us [@] D3D12CreateMasterRootSignature [@] D3DErrorCheck SUCCESS: ID3DBlob object created: 0x1e82736ddb0 [@] D3DErrorCheck SUCCESS: ID3D12RootSignature object created: 0x1e827d52c40 [@] new_command_queue [@] D3DErrorCheck SUCCESS: ID3D12CommandQueue object created: 0x1e826f316a0 [@] D3DErrorCheck SUCCESS: ID3D12Fence object created: 0x1e8270d8560 Time [new_command_queue]: 11843 us [@] new_command_allocator [@] D3DErrorCheck SUCCESS: ID3D12CommandAllocator object created: 0x1e827311200 [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e8274dc5b0 Time [new_buffer_resource]: 488 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e829f80000 Time [map_buffer]: 149 us Time [new_upload_buffer]: 640 us [@] new_readback_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e8274df7e0 Time [new_buffer_resource]: 479 us Time [new_readback_buffer]: 481 us Time [d3d12_create_context]: 204095 us Time [halide_d3d12compute_acquire_context]: 9223372037058874 us [@] new_library_with_source [@] d3d12_malloc allocated 8084 bytes @ 0x1e8254291c0 Caching compiled kernel: 0x1e8254291c0 id 2 context 0x1e826e479f8 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_initialize_kernels]: 9223372037058891 us Exiting Pipeline f9 [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] halide_d3d12compute_release_context Entering Pipeline f9 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input (void const *) __user_context: 0x37457ddc90 Output Buffer f9: buffer(0, 0x0, 0x1e827ba4680, 0, int32, {0, 256, 1}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd4e0 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e8274dc120 Time [new_buffer_resource]: 172 us Time [new_device_buffer]: 174 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542cdd0 Time [new_buffer]: 178 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 184 us Time [halide_d3d12compute_device_and_host_malloc]: 187 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd320 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e8274dea30 Time [new_buffer_resource]: 185 us Time [new_device_buffer]: 186 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542ce90 Time [new_buffer]: 190 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 195 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_copy_to_device [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] peel_buffer [@] suballocate [@] buffer_contents [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827321d50 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e825427790 Time [new_command_list]: 682 us Time [new_compute_command_list]: 684 us [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e82738a540 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542cf00 descriptor heap base for CPU: 1 (0x1) descriptor heap base for GPU: 1841471858671616 (0x68acf14000000) Time [new_descriptor_binder]: 351 us Time [acquire_frame]: 1124 us [@] synchronize_host_and_device_buffer_contents uploading buffer to device --- 0x1e82542cdd0 | int32 | 0 : 0 : 1024 [@] buffer_copy_command Time [buffer_copy_command]: 158 us Time [synchronize_host_and_device_buffer_contents]: 161 us [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #1... Time [commit_command_list]: 756 us Time [enqueue_frame]: 758 us [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled Already synced up! Time [d3d12compute_device_sync_internal]: 2051 us Time [d3d12compute_buffer_copy]: 2053 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_device]: 2059 us [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827f4c190 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e82542cf60 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e8273886a0 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542cf80 descriptor heap base for CPU: 2 (0x2) descriptor heap base for GPU: 6345071486042112 (0x168acf14000000) Time [new_descriptor_binder]: 281 us Time [acquire_frame]: 351 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f1_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x1e82542cfe0 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x1e826dd5f90 Time [new_compute_pipeline_state_with_function]: 9301 us Time [d3d12_compile_shader]: 14374 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x1e82542d000 [@] d3d12_malloc allocated 53 bytes @ 0x1e82542d050 Exiting halide_memoization_cache_store Time [new_function_with_name]: 14382 us [@] set_compute_pipeline_state Time [kernel shader selection]: 14426 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d794d0 Time [new_buffer_resource]: 374 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82e186000 Time [new_upload_buffer]: 390 us Time [new_constant_buffer]: 391 us [@] buffer_contents args[2] -> int32 = 8 args[3] -> int32 = -32 args[4] -> int32 = 224 Time [argument buffer packing]: 398 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x1e82542cdd0 | offset 0 | 256elements (1024bytes) [@] set_input_buffer UAV [1] : 0x1e82542ce90 | offset 0 | 256elements (1024bytes) Time [kernel argument setup]: 431 us [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 0) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #2... Time [commit_command_list]: 287 us Time [enqueue_frame]: 288 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 15541 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd4e0 [@] peel_buffer d3d12_buffer: 0x1e82542cdd0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #2... Time [block_until_signaled]: 124 us Time [wait_until_signaled]: 128 us [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e8274dc120 Time [Release_ID3D12Object]: 118 us freeing data structure 'd3d12_buffer' @ 0x1e82542cdd0 [@] d3d12_free freeing bytes @ 0x1e82542cdd0 Time [release_d3d12_object]: 122 us Time [halide_d3d12compute_device_free]: 257 us Time [halide_d3d12compute_device_and_host_free]: 259 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd3d0 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d72be0 Time [new_buffer_resource]: 274 us Time [new_device_buffer]: 276 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542cdd0 Time [new_buffer]: 280 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 286 us Time [halide_d3d12compute_device_and_host_malloc]: 288 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd3d0 (this buffer already has a device allocation...) [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827d79df0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e82542d100 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e82738a230 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542d4a0 descriptor heap base for CPU: 3 (0x3) descriptor heap base for GPU: 10848671113412608 (0x268acf14000000) Time [new_descriptor_binder]: 320 us Time [acquire_frame]: 387 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f2_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x1e82542d140 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x1e826dd3b00 Time [new_compute_pipeline_state_with_function]: 1147 us Time [d3d12_compile_shader]: 5204 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x1e82542d500 [@] d3d12_malloc allocated 53 bytes @ 0x1e82542d550 Exiting halide_memoization_cache_store Time [new_function_with_name]: 5211 us [@] set_compute_pipeline_state Time [kernel shader selection]: 5231 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d76bc0 Time [new_buffer_resource]: 232 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82e19b000 Time [new_upload_buffer]: 243 us Time [new_constant_buffer]: 244 us [@] buffer_contents args[2] -> int32 = 8 args[3] -> int32 = -32 args[4] -> int32 = 224 Time [argument buffer packing]: 299 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x1e82542ce90 | offset 0 | 256elements (1024bytes) [@] set_input_buffer UAV [1] : 0x1e82542cdd0 | offset 0 | 256elements (1024bytes) Time [kernel argument setup]: 314 us [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 1) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #3... [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 6033 us [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd320 [@] peel_buffer d3d12_buffer: 0x1e82542ce90 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #3... Time [block_until_signaled]: 151 us Time [wait_until_signaled]: 155 us [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e8274dea30 Time [Release_ID3D12Object]: 110 us freeing data structure 'd3d12_buffer' @ 0x1e82542ce90 [@] d3d12_free freeing bytes @ 0x1e82542ce90 Time [release_d3d12_object]: 114 us Time [halide_d3d12compute_device_free]: 276 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd520 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d754f0 Time [new_buffer_resource]: 201 us Time [new_device_buffer]: 202 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542ce40 Time [new_buffer]: 206 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 212 us Time [halide_d3d12compute_device_and_host_malloc]: 215 us [@] halide_d3d12compute_copy_to_host [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] peel_buffer [@] suballocate [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827d8e250 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e82542d180 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e827d8db10 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542d9e0 descriptor heap base for CPU: 4 (0x4) descriptor heap base for GPU: 15352270740783104 (0x368acf14000000) Time [new_descriptor_binder]: 333 us Time [acquire_frame]: 393 us [@] synchronize_host_and_device_buffer_contents reading-back buffer from device [@] unmap_buffer --- 0x1e82542cdd0 | int32 | 0 : 0 : 1024 [@] buffer_copy_command [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #4... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #4... Time [d3d12compute_device_sync_internal]: 538 us Time [d3d12compute_buffer_copy]: 540 us [@] buffer_contents [@] map_buffer [ Begin: 0 , End: 4194304 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82c624000 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_host]: 555 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd3d0 [@] peel_buffer d3d12_buffer: 0x1e82542cdd0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d72be0 Time [Release_ID3D12Object]: 107 us freeing data structure 'd3d12_buffer' @ 0x1e82542cdd0 [@] d3d12_free freeing bytes @ 0x1e82542cdd0 Time [release_d3d12_object]: 111 us Time [halide_d3d12compute_device_free]: 117 us Time [halide_d3d12compute_device_and_host_free]: 119 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd410 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d77970 Time [new_buffer_resource]: 184 us Time [new_device_buffer]: 185 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542cdd0 Time [new_buffer]: 189 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 195 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_copy_to_device [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] peel_buffer [@] suballocate [@] buffer_contents [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827d984d0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e82542d3a0 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e827d8de20 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542c170 descriptor heap base for CPU: 5 (0x5) descriptor heap base for GPU: 19855870368153600 (0x468acf14000000) Time [new_descriptor_binder]: 332 us Time [acquire_frame]: 391 us [@] synchronize_host_and_device_buffer_contents uploading buffer to device --- 0x1e82542ce40 | int32 | 0 : 0 : 1024 [@] buffer_copy_command [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #5... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #5... Time [d3d12compute_device_sync_internal]: 530 us Time [d3d12compute_buffer_copy]: 532 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_device]: 537 us [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827da2750 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e82542d380 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e827d8d800 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542c1d0 descriptor heap base for CPU: 6 (0x6) descriptor heap base for GPU: 24359469995524096 (0x568acf14000000) Time [new_descriptor_binder]: 314 us Time [acquire_frame]: 370 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f4_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x1e82542d2a0 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x1e826dd4250 Time [new_compute_pipeline_state_with_function]: 1084 us Time [d3d12_compile_shader]: 4871 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x1e82542c230 [@] d3d12_malloc allocated 53 bytes @ 0x1e82542c280 Exiting halide_memoization_cache_store Time [new_function_with_name]: 4878 us [@] set_compute_pipeline_state Time [kernel shader selection]: 4898 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d75e10 Time [new_buffer_resource]: 267 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82e1cc000 Time [new_upload_buffer]: 279 us Time [new_constant_buffer]: 372 us [@] buffer_contents args[2] -> int32 = 8 args[3] -> int32 = -32 args[4] -> int32 = 224 Time [argument buffer packing]: 379 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x1e82542ce40 | offset 0 | 256elements (1024bytes) [@] set_input_buffer UAV [1] : 0x1e82542cdd0 | offset 0 | 256elements (1024bytes) Time [kernel argument setup]: 394 us [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 2) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #6... [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 5759 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd520 [@] peel_buffer d3d12_buffer: 0x1e82542ce40 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #6... [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d754f0 Time [Release_ID3D12Object]: 106 us freeing data structure 'd3d12_buffer' @ 0x1e82542ce40 [@] d3d12_free freeing bytes @ 0x1e82542ce40 Time [release_d3d12_object]: 110 us Time [halide_d3d12compute_device_free]: 196 us Time [halide_d3d12compute_device_and_host_free]: 198 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd560 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d73990 Time [new_buffer_resource]: 190 us Time [new_device_buffer]: 191 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542ce40 Time [new_buffer]: 195 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 201 us Time [halide_d3d12compute_device_and_host_malloc]: 203 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd560 (this buffer already has a device allocation...) [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827dda7f0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e82542d3c0 Time [new_compute_command_list]: 144 us [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e827d8ced0 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542c2c0 descriptor heap base for CPU: 7 (0x7) descriptor heap base for GPU: 28863069622894592 (0x668acf14000000) Time [new_descriptor_binder]: 313 us Time [acquire_frame]: 460 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f5_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x1e82542d240 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x1e827ab2530 Time [new_compute_pipeline_state_with_function]: 1151 us Time [d3d12_compile_shader]: 5078 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x1e82542c320 [@] d3d12_malloc allocated 53 bytes @ 0x1e82542c370 Exiting halide_memoization_cache_store Time [new_function_with_name]: 5085 us [@] set_compute_pipeline_state Time [kernel shader selection]: 5105 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d79040 Time [new_buffer_resource]: 233 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82e1dd000 Time [new_upload_buffer]: 243 us Time [new_constant_buffer]: 245 us [@] buffer_contents args[2] -> int32 = 8 args[3] -> int32 = -32 args[4] -> int32 = 224 Time [argument buffer packing]: 251 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x1e82542cdd0 | offset 0 | 256elements (1024bytes) [@] set_input_buffer UAV [1] : 0x1e82542ce40 | offset 0 | 256elements (1024bytes) Time [kernel argument setup]: 266 us [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 3) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #7... [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 5935 us [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd410 [@] peel_buffer d3d12_buffer: 0x1e82542cdd0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d77970 Time [Release_ID3D12Object]: 118 us freeing data structure 'd3d12_buffer' @ 0x1e82542cdd0 [@] d3d12_free freeing bytes @ 0x1e82542cdd0 Time [release_d3d12_object]: 122 us Time [halide_d3d12compute_device_free]: 128 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd5a0 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d73070 Time [new_buffer_resource]: 183 us Time [new_device_buffer]: 184 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542cdd0 Time [new_buffer]: 188 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 195 us Time [halide_d3d12compute_device_and_host_malloc]: 197 us [@] halide_d3d12compute_copy_to_host [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] peel_buffer [@] suballocate [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x1e827ade340 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x1e82542d1a0 Time [new_command_list]: 396 us Time [new_compute_command_list]: 398 us [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x1e827dd8b40 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x1e82542c3b0 descriptor heap base for CPU: 8 (0x8) descriptor heap base for GPU: 33366669250265088 (0x768acf14000000) Time [new_descriptor_binder]: 285 us Time [acquire_frame]: 686 us [@] synchronize_host_and_device_buffer_contents reading-back buffer from device [@] unmap_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82c624000 --- 0x1e82542ce40 | int32 | 0 : 0 : 1024 [@] buffer_copy_command [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #8... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #8... Time [d3d12compute_device_sync_internal]: 827 us Time [d3d12compute_buffer_copy]: 830 us [@] buffer_contents [@] map_buffer [ Begin: 0 , End: 4194304 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82c624000 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_host]: 841 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd560 [@] peel_buffer d3d12_buffer: 0x1e82542ce40 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d73990 Time [Release_ID3D12Object]: 104 us freeing data structure 'd3d12_buffer' @ 0x1e82542ce40 [@] d3d12_free freeing bytes @ 0x1e82542ce40 Time [release_d3d12_object]: 109 us Time [halide_d3d12compute_device_free]: 115 us Time [halide_d3d12compute_device_and_host_free]: 117 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd5e0 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d73500 Time [new_buffer_resource]: 175 us Time [new_device_buffer]: 176 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542ce90 Time [new_buffer]: 180 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 185 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_copy_to_device [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] peel_buffer [@] suballocate [@] buffer_contents [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] synchronize_host_and_device_buffer_contents uploading buffer to device --- 0x1e82542cdd0 | int32 | 0 : 0 : 1024 [@] buffer_copy_command [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #9... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #9... Time [d3d12compute_device_sync_internal]: 151 us Time [d3d12compute_buffer_copy]: 153 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_device]: 158 us [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] acquire_frame [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f7_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x1e82542d440 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x1e827ab0f40 Time [new_compute_pipeline_state_with_function]: 1091 us Time [d3d12_compile_shader]: 5159 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x1e82542c410 [@] d3d12_malloc allocated 53 bytes @ 0x1e82542c460 Exiting halide_memoization_cache_store Time [new_function_with_name]: 5166 us [@] set_compute_pipeline_state Time [kernel shader selection]: 5186 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] buffer_contents args[2] -> int32 = 8 args[3] -> int32 = -32 args[4] -> int32 = 224 [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x1e82542cdd0 | offset 0 | 256elements (1024bytes) [@] set_input_buffer UAV [1] : 0x1e82542ce90 | offset 0 | 256elements (1024bytes) [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 4) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #10... [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 5311 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd5a0 [@] peel_buffer d3d12_buffer: 0x1e82542cdd0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #10... [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d73070 Time [Release_ID3D12Object]: 108 us freeing data structure 'd3d12_buffer' @ 0x1e82542cdd0 [@] d3d12_free freeing bytes @ 0x1e82542cdd0 Time [release_d3d12_object]: 112 us Time [halide_d3d12compute_device_free]: 186 us Time [halide_d3d12compute_device_and_host_free]: 188 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_and_host_malloc [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd620 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x1e827d762a0 Time [new_buffer_resource]: 187 us Time [new_device_buffer]: 188 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x1e82542cdd0 Time [new_buffer]: 192 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 198 us Time [halide_d3d12compute_device_and_host_malloc]: 200 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd620 (this buffer already has a device allocation...) [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] acquire_frame [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 32, 1, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f8_s0_v0_v0___block_id_x'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x1e82542d460 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x1e827ab07f0 Time [new_compute_pipeline_state_with_function]: 1074 us Time [d3d12_compile_shader]: 4944 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x1e82542c4a0 [@] d3d12_malloc allocated 53 bytes @ 0x1e82542c4f0 Exiting halide_memoization_cache_store Time [new_function_with_name]: 4951 us [@] set_compute_pipeline_state Time [kernel shader selection]: 4971 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] buffer_contents args[2] -> int32 = 8 args[3] -> int32 = -32 args[4] -> int32 = 224 [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x1e82542ce90 | offset 0 | 256elements (1024bytes) [@] set_input_buffer UAV [1] : 0x1e82542cdd0 | offset 0 | 256elements (1024bytes) [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 5) blocks(8, 1, 1) threads(32, 1, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #11... [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 5105 us [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd5e0 [@] peel_buffer d3d12_buffer: 0x1e82542ce90 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #11... [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d73500 Time [Release_ID3D12Object]: 107 us freeing data structure 'd3d12_buffer' @ 0x1e82542ce90 [@] d3d12_free freeing bytes @ 0x1e82542ce90 Time [release_d3d12_object]: 111 us Time [halide_d3d12compute_device_free]: 186 us [@] halide_d3d12compute_copy_to_host [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] peel_buffer [@] suballocate [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] synchronize_host_and_device_buffer_contents reading-back buffer from device [@] unmap_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82c624000 --- 0x1e82542cdd0 | int32 | 0 : 0 : 1024 [@] buffer_copy_command [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #12... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #12... Time [d3d12compute_device_sync_internal]: 200 us Time [d3d12compute_buffer_copy]: 202 us [@] buffer_contents [@] map_buffer [ Begin: 0 , End: 4194304 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x1e82c624000 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_host]: 214 us [@] halide_d3d12compute_device_and_host_free [@] halide_d3d12compute_device_free user_context: 0x37457ddc90 | halide_buffer_t: 0x37457dd620 [@] peel_buffer d3d12_buffer: 0x1e82542cdd0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d762a0 freeing data structure 'd3d12_buffer' @ 0x1e82542cdd0 [@] d3d12_free freeing bytes @ 0x1e82542cdd0 Time [halide_d3d12compute_device_free]: 104 us Time [halide_d3d12compute_device_and_host_free]: 106 us Exiting Pipeline f9 [@] halide_d3d12compute_acquire_context user_context: 0x37457ddc90 | create: 1 current d3d12_device: 0x1e826e479f8 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_cleanup Releasing cached compilation: 0x1e8254291c0 id 2 context 0x1e826e479f8 [@] release_object [@] release_d3d12_object halide_memoization_cache_cleanup [@] d3d12_free freeing bytes @ 0x1e82542c280 [@] d3d12_free freeing bytes @ 0x1e82542c230 [@] d3d12_free freeing bytes @ 0x1e82542c460 [@] d3d12_free freeing bytes @ 0x1e82542c410 [@] d3d12_free freeing bytes @ 0x1e82542d550 [@] d3d12_free freeing bytes @ 0x1e82542d500 [@] d3d12_free freeing bytes @ 0x1e82542c370 [@] d3d12_free freeing bytes @ 0x1e82542c320 [@] d3d12_free freeing bytes @ 0x1e82542c4f0 [@] d3d12_free freeing bytes @ 0x1e82542c4a0 [@] d3d12_free freeing bytes @ 0x1e82542d050 [@] d3d12_free freeing bytes @ 0x1e82542d000 [@] d3d12_free freeing bytes @ 0x1e8254291c0 [@] halide_d3d12compute_device_release [@] halide_d3d12compute_acquire_context user_context: 0x0 | create: 0 current d3d12_device: 0x1e826e479f8 [@] d3d12compute_device_sync_internal [@] wait_until_idle [@] wait_until_signaled Already synced up! [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827321d50 [@] d3d12_free freeing bytes @ 0x1e825427790 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e82738a540 [@] d3d12_free freeing bytes @ 0x1e82542cf00 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 Time [release_d3d12_object]: 115 us Time [release_object]: 116 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827f4c190 [@] d3d12_free freeing bytes @ 0x1e82542cf60 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e8273886a0 [@] d3d12_free freeing bytes @ 0x1e82542cf80 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d794d0 Time [Release_ID3D12Object]: 114 us Time [release_d3d12_object]: 116 us Time [release_object]: 117 us Time [release_d3d12_object]: 159 us Time [release_object]: 160 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827d79df0 [@] d3d12_free freeing bytes @ 0x1e82542d100 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e82738a230 [@] d3d12_free freeing bytes @ 0x1e82542d4a0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d76bc0 Time [Release_ID3D12Object]: 109 us Time [release_d3d12_object]: 111 us Time [release_object]: 112 us Time [release_d3d12_object]: 146 us Time [release_object]: 147 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827d8e250 [@] d3d12_free freeing bytes @ 0x1e82542d180 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e827d8db10 [@] d3d12_free freeing bytes @ 0x1e82542d9e0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827d984d0 [@] d3d12_free freeing bytes @ 0x1e82542d3a0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e827d8de20 [@] d3d12_free freeing bytes @ 0x1e82542c170 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827da2750 [@] d3d12_free freeing bytes @ 0x1e82542d380 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e827d8d800 [@] d3d12_free freeing bytes @ 0x1e82542c1d0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d75e10 Time [Release_ID3D12Object]: 124 us Time [release_d3d12_object]: 126 us Time [release_object]: 127 us Time [release_d3d12_object]: 162 us Time [release_object]: 163 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827dda7f0 [@] d3d12_free freeing bytes @ 0x1e82542d3c0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e827d8ced0 [@] d3d12_free freeing bytes @ 0x1e82542c2c0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x1e827d79040 Time [Release_ID3D12Object]: 109 us Time [release_d3d12_object]: 111 us Time [release_object]: 112 us Time [release_d3d12_object]: 144 us Time [release_object]: 145 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x1e827ade340 Time [Release_ID3D12Object]: 131 us [@] d3d12_free freeing bytes @ 0x1e82542d1a0 Time [release_d3d12_object]: 134 us Time [release_object]: 135 us [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x1e827dd8b40 [@] d3d12_free freeing bytes @ 0x1e82542c3b0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 Time [release_d3d12_object]: 156 us Time [release_object]: 157 us [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. ======================================== ======================================== correctness_gpu_param_allocation.exe ======================================== ======================================== correctness_gpu_reuse_shared_memory.exe ======================================== ======================================== correctness_gpu_specialize.exe ======================================== ======================================== correctness_gpu_store_in_register_with_no_lanes_loop.exe ======================================== ======================================== correctness_gpu_sum_scan.exe ======================================== ======================================== correctness_gpu_texture.exe [SKIP] No OpenCL target enabled. ======================================== ======================================== correctness_gpu_thread_barrier.exe Warning: Update definition 3 of function f6 has not been scheduled, even though some other definitions have been. You may have forgotten to schedule it. If this was intentional, call f6.update(3).unscheduled() to suppress this warning. ======================================== ======================================== correctness_gpu_transpose.exe ======================================== ======================================== correctness_gpu_vectorize.exe ======================================== ======================================== correctness_gpu_vectorized_shared_memory.exe [SKIP] OpenCL not enabled. ======================================== ======================================== correctness_growing_stack.exe Success! ======================================== ======================================== correctness_half_native_interleave.exe Success! ======================================== ======================================== correctness_halide_buffer.exe Success! ======================================== ======================================== correctness_handle.exe Success! ======================================== ======================================== correctness_heap_cleanup.exe 1 1 Success! ======================================== ======================================== correctness_hello_gpu.exe ======================================== ======================================== correctness_hexagon_scatter.exe [SKIP] hexagon_scatter is only useful when targeting HVX. ======================================== ======================================== correctness_histogram.exe Success! ======================================== ======================================== correctness_histogram_equalize.exe Success! ======================================== ======================================== correctness_hoist_loop_invariant_if_statements.exe Success! ======================================== ======================================== correctness_host_alignment.exe Success! ======================================== ======================================== correctness_image_io.exe Testing static -> static image conversion for uint8 Testing static -> dynamic image conversion for uint8 Testing dynamic -> static image conversion for uint8 Testing dynamic -> dynamic image conversion for uint8 Testing format: ppm for uint8x3 Testing format: pgm for uint8x1 Testing format: tmp for uint8x4 Testing format: tmp for uint8x4 Testing format: mat for uint8x3 Testing format: mat for uint8x1 Testing format: tiff for uint8x3 Testing format: tiff for uint8x1 Testing format: jpg for uint8x3 Testing format: jpg for uint8x1 Testing format: png for uint8x3 Testing format: png for uint8x1 Testing static -> static image conversion for uint16 Testing static -> dynamic image conversion for uint16 Testing dynamic -> static image conversion for uint16 Testing dynamic -> dynamic image conversion for uint16 Testing format: ppm for uint16x3 Testing format: pgm for uint16x1 Testing format: tmp for uint16x4 Testing format: tmp for uint16x4 Testing format: mat for uint16x3 Testing format: mat for uint16x1 Testing format: tiff for uint16x3 Testing format: tiff for uint16x1 Testing format: png for uint16x3 Testing format: png for uint16x1 Success! ======================================== ======================================== correctness_image_of_lists.exe Success! ======================================== ======================================== correctness_image_wrapper.exe Running calling wrap no op test Running func wrap test Running multiple funcs sharing wrapper test Running global wrap test Running update is defined after wrap test Running rdom wrapper test Running global + custom wrapper test Running wrapper depend on mutated func test Running wrapper on wrapper test Running wrapper on rdom predicate test Running two fold wrapper test Running multi folds wrapper test Success! ======================================== ======================================== correctness_implicit_args.exe Success! ======================================== ======================================== correctness_implicit_args_tests.exe Success! ======================================== ======================================== correctness_indexing_access_undef.exe Success! ======================================== ======================================== correctness_infer_arguments.exe Success! ======================================== ======================================== correctness_inlined_generator.exe Success! ======================================== ======================================== correctness_inline_reduction.exe Success! ======================================== ======================================== correctness_input_image_bounds_check.exe Input buffer b0 is accessed at 22, which is beyond the max (18) in dimension 0 Input buffer b15 is accessed at 3, which is beyond the max (2) in dimension 0 Success! ======================================== ======================================== correctness_input_larger_than_two_gigs.exe Expected: Product of extents for buffer p0 is 4294967296, which exceeds the maximum size of 2147483647 Success! ======================================== ======================================== correctness_integer_powers.exe Success! ======================================== ======================================== correctness_interleave.exe Success! ======================================== ======================================== correctness_interleave_rgb.exe ======================================== ======================================== correctness_interleave_x.exe ======================================== ======================================== correctness_interpreter.exe [SKIP] workaround for issue #5738 ======================================== ======================================== correctness_interval.exe Success! ======================================== ======================================== correctness_intrinsics.exe Success! ======================================== ======================================== correctness_introspection.exe [SKIP] Halide C++ introspection doesn't claim to work with this build config. ======================================== ======================================== correctness_inverse.exe ======================================== ======================================== correctness_in_place.exe ======================================== ======================================== correctness_isnan.exe ======================================== ======================================== correctness_issue_3926.exe Success! ======================================== ======================================== correctness_iterate_over_circle.exe Success! ======================================== ======================================== correctness_lambda.exe Success! ======================================== ======================================== correctness_lazy_convolution.exe Success! ======================================== ======================================== correctness_leak_device_memory.exe Entering Pipeline f0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input Buffer b0: buffer(0, 0x0, 0x216f874b000, 0, float32, {0, 100, 1}, {0, 100, 100}) Input (void const *) __user_context: 0x5c832fd940 Output Buffer f0: buffer(0, 0x0, 0x0, 0, float32, {0, 50, 1}, {0, 50, 50}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0x5c832fd940 | create: 1 current d3d12_device: 0x0 [@] d3d12_create_context [@] D3D12CreateSystemDefaultDevice [@] D3D12LoadDependencies [@] d3d12_load_library Loaded runtime library 'd3d12.dll' at location 0x7ffe29520000 Time [d3d12_load_library]: 2157 us [@] d3d12_load_library Loaded runtime library 'D3DCompiler_47.dll' at location 0x7ffe31060000 Time [d3d12_load_library]: 2068 us [@] d3d12_load_library Loaded runtime library 'dxgi.dll' at location 0x7ffe33d00000 Time [d3d12_load_library]: 880 us [@] d3d12_get_library_symbol Symbol 'D3D12CreateDevice' found @ 0x7ffe29526af0 [@] d3d12_get_library_symbol Symbol 'D3D12GetDebugInterface' found @ 0x7ffe29530270 [@] d3d12_get_library_symbol Symbol 'D3D12SerializeRootSignature' found @ 0x7ffe295302b0 [@] d3d12_get_library_symbol Symbol 'D3DCompile' found @ 0x7ffe311523f0 [@] d3d12_get_library_symbol Symbol 'CreateDXGIFactory1' found @ 0x7ffe33d1e680 Time [D3D12LoadDependencies]: 5124 us Using Direct3D 12 Debug Layer [@] D3DErrorCheck SUCCESS: ID3D12Debug object created: 0x216fa8284f0 [@] D3DErrorCheck SUCCESS: IDXGIFactory1 object created: 0x216f8784b70 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x216fa60d780 Adapter #0: NVIDIA RTX A4000 (this is the best device so far...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x0 [@] D3DErrorCheck SUCCESS: IDXGIAdapter1 object created: 0x216fa60dc10 Adapter #1: Microsoft Basic Render Driver (this is a software adapter; skipping...) [@] Release_ID3D12Object IDXGIAdapter1 @ 0x216fa60dc10 [@] D3D12CreateDeviceForAdapter Device selected: NVIDIA RTX A4000 [@] D3DErrorCheck SUCCESS: ID3D12Device object created: 0x216fa9c7fd8 Time [D3D12CreateDeviceForAdapter]: 203148 us [@] Release_ID3D12Object IDXGIFactory1 @ 0x216f8784b70 Time [D3D12CreateSystemDefaultDevice]: 214996 us [@] D3D12CreateMasterRootSignature [@] D3DErrorCheck SUCCESS: ID3DBlob object created: 0x216fab427d0 [@] D3DErrorCheck SUCCESS: ID3D12RootSignature object created: 0x216faaf3600 [@] new_command_queue [@] D3DErrorCheck SUCCESS: ID3D12CommandQueue object created: 0x216fb09b940 [@] D3DErrorCheck SUCCESS: ID3D12Fence object created: 0x216faaad070 Time [new_command_queue]: 12237 us [@] new_command_allocator [@] D3DErrorCheck SUCCESS: ID3D12CommandAllocator object created: 0x216fb5175f0 [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x216fa505110 Time [D3DErrorCheck]: 134 us Time [new_buffer_resource]: 662 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x216fd600000 Time [new_upload_buffer]: 685 us [@] new_readback_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x216fa83afb0 Time [new_buffer_resource]: 497 us Time [new_readback_buffer]: 498 us Time [d3d12_create_context]: 228502 us Time [halide_d3d12compute_acquire_context]: 9223372037083282 us [@] new_library_with_source [@] d3d12_malloc allocated 5320 bytes @ 0x216f8b591c0 Caching compiled kernel: 0x216f8b591c0 id 2 context 0x216fa9c7fd8 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_initialize_kernels]: 9223372037083297 us Exiting Pipeline f0 [@] halide_d3d12compute_acquire_context user_context: 0x5c832fd940 | create: 1 current d3d12_device: 0x216fa9c7fd8 [@] halide_d3d12compute_release_context Entering Pipeline f0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-debug-f16c-fma-jit-sse41-user_context Input Buffer b0: buffer(0, 0x0, 0x216f874b000, 0, float32, {0, 100, 1}, {0, 100, 100}) Input (void const *) __user_context: 0x5c832fd940 Output Buffer f0: buffer(0, 0x0, 0x216fb4fa100, 0, float32, {0, 50, 1}, {0, 50, 50}) [@] halide_d3d12compute_initialize_kernels [@] halide_d3d12compute_acquire_context user_context: 0x5c832fd940 | create: 1 current d3d12_device: 0x216fa9c7fd8 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x5c832fd940 | halide_buffer_t: 0x216f86f24a8 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x5c832fd940 | create: 1 current d3d12_device: 0x216fa9c7fd8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x216fa8fd6f0 Time [new_buffer_resource]: 182 us Time [new_device_buffer]: 183 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x216f8b5beb0 Time [new_buffer]: 187 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 193 us [@] halide_d3d12compute_device_interface [@] halide_d3d12compute_device_malloc user_context: 0x5c832fd940 | halide_buffer_t: 0x216f86cf178 [@] d3d12_allocation_cache_get_buffer (allocation cache is disabled...) [@] halide_d3d12compute_acquire_context user_context: 0x5c832fd940 | create: 1 current d3d12_device: 0x216fa9c7fd8 [@] new_buffer [@] new_device_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x216fac38a70 Time [new_buffer_resource]: 187 us Time [new_device_buffer]: 188 us [@] malloct allocating d3d12_buffer [@] d3d12_malloc allocated 96 bytes @ 0x216f8b5bf20 Time [new_buffer]: 191 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_device_malloc]: 197 us [@] halide_d3d12compute_run [@] halide_d3d12compute_acquire_context user_context: 0x5c832fd940 | create: 1 current d3d12_device: 0x216fa9c7fd8 [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x216fb51e6c0 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x216f8b57790 Time [new_command_list]: 817 us Time [new_compute_command_list]: 818 us [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x216fb3c2f30 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x216f8b5bf90 descriptor heap base for CPU: 1 (0x1) descriptor heap base for GPU: 1841471858671616 (0x68acf14000000) Time [new_descriptor_binder]: 367 us Time [acquire_frame]: 1188 us [@] kernel shader selection [@] new_function_with_name [@] d3d12_compile_shader groupshared memory size before modification: 0 bytes groupshared memory size after modification: 16 bytes. numthreads( 8, 8, 1 ) SUCCESS while compiling D3D12 compute shader with entry name '_kernel_f0_s0_v1_v1___block_id_y'! [@] malloct allocating d3d12_function [@] d3d12_malloc allocated 24 bytes @ 0x216f8b5bff0 [@] new_compute_pipeline_state_with_function [@] D3DErrorCheck SUCCESS: ID3D12PipelineState object created: 0x216fad8fe20 Time [new_compute_pipeline_state_with_function]: 10111 us Time [d3d12_compile_shader]: 15473 us halide_memoization_cache_store [@] d3d12_malloc allocated 72 bytes @ 0x216f8b5c010 [@] d3d12_malloc allocated 52 bytes @ 0x216f8b5c060 Exiting halide_memoization_cache_store Time [new_function_with_name]: 15481 us [@] set_compute_pipeline_state Time [kernel shader selection]: 15536 us [@] kernel argument setup [@] kernel args introspection [@] peel_buffer [@] peel_buffer [@] argument buffer packing [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] new_constant_buffer [@] new_upload_buffer [@] new_buffer_resource [@] D3DErrorCheck SUCCESS: ID3D12Resource object created: 0x216fb90ca70 Time [new_buffer_resource]: 243 us [@] map_buffer [ Begin: 0 , End: 0 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x21682770000 Time [new_upload_buffer]: 254 us Time [new_constant_buffer]: 255 us [@] buffer_contents args[2] -> int32 = 50 args[3] -> int32 = 0 args[4] -> int32 = 0 args[5] -> int32 = 50 args[6] -> int32 = 6 args[7] -> int32 = 50 args[8] -> int32 = 0 Time [argument buffer packing]: 264 us [@] descriptor binding [@] set_input_buffer CBV [@] set_input_buffer UAV [0] : 0x216f8b5beb0 | offset 0 | 10000elements (40000bytes) [@] set_input_buffer UAV [1] : 0x216f8b5bf20 | offset 0 | 2500elements (10000bytes) Time [kernel argument setup]: 294 us [@] pipeline barriers [@] compute_barrier [@] compute_barrier [@] dispatch_threadgroups Dispatching threadgroups (number 0) blocks(7, 7, 1) threads(8, 8, 1) [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #1... Time [commit_command_list]: 776 us Time [enqueue_frame]: 832 us [@] halide_d3d12compute_release_context Time [halide_d3d12compute_run]: 17918 us Exiting Pipeline f0 [@] halide_d3d12compute_acquire_context user_context: 0x5c832fd940 | create: 1 current d3d12_device: 0x216fa9c7fd8 [@] halide_d3d12compute_release_context [@] halide_d3d12compute_copy_to_host [@] halide_d3d12compute_acquire_context user_context: 0x0 | create: 1 current d3d12_device: 0x216fa9c7fd8 [@] peel_buffer [@] suballocate [@] d3d12compute_buffer_copy [@] d3d12compute_device_sync_internal [@] acquire_frame [@] new_compute_command_list [@] new_command_list [@] D3DErrorCheck SUCCESS: ID3D12GraphicsCommandList object created: 0x216fa721910 [@] malloct allocating d3d12_command_list [@] d3d12_malloc allocated 16 bytes @ 0x216f8b5c0a0 [@] new_descriptor_binder [@] D3DErrorCheck SUCCESS: ID3D12DescriptorHeap object created: 0x216fb3c3b70 descriptor handle increment size: 32 [@] malloct allocating d3d12_binder [@] d3d12_malloc allocated 80 bytes @ 0x216f8b5c0c0 descriptor heap base for CPU: 2 (0x2) descriptor heap base for GPU: 6345071486042112 (0x168acf14000000) Time [new_descriptor_binder]: 306 us Time [acquire_frame]: 378 us [@] synchronize_host_and_device_buffer_contents reading-back buffer from device [@] unmap_buffer --- 0x216f8b5bf20 | float32 | 0 : 0 : 10000 [@] buffer_copy_command Time [buffer_copy_command]: 108 us Time [synchronize_host_and_device_buffer_contents]: 112 us [@] enqueue_frame [@] commit_command_list [@] end_recording [@] queue_insert_checkpoint latest queue checkpoint is now #2... [@] wait_until_completed [@] wait_until_completed [@] wait_until_signaled [@] block_until_signaled Now syncing on queue signal #2... Time [d3d12compute_device_sync_internal]: 616 us Time [d3d12compute_buffer_copy]: 618 us [@] buffer_contents [@] map_buffer [ Begin: 0 , End: 4194304 ] [@] D3DErrorCheck SUCCESS: ID3D12MemoryMappedResourceFAUX object created: 0x21680d74000 [@] halide_d3d12compute_release_context Time [halide_d3d12compute_copy_to_host]: 636 us [@] halide_d3d12compute_device_free user_context: 0x0 | halide_buffer_t: 0x216f86cf178 [@] peel_buffer d3d12_buffer: 0x216f8b5bf20 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x216fac38a70 Time [Release_ID3D12Object]: 116 us freeing data structure 'd3d12_buffer' @ 0x216f8b5bf20 [@] d3d12_free freeing bytes @ 0x216f8b5bf20 Time [release_d3d12_object]: 120 us Time [halide_d3d12compute_device_free]: 127 us [@] halide_d3d12compute_device_free user_context: 0x0 | halide_buffer_t: 0x216f86f24a8 [@] peel_buffer d3d12_buffer: 0x216f8b5beb0 [@] d3d12_allocation_cache_put_buffer (allocation cache is disabled...) [@] unwrap_buffer [@] peel_buffer [@] wait_until_signaled Already synced up! [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x216fa8fd6f0 freeing data structure 'd3d12_buffer' @ 0x216f8b5beb0 [@] d3d12_free freeing bytes @ 0x216f8b5beb0 Time [release_d3d12_object]: 194 us Time [halide_d3d12compute_device_free]: 200 us [@] halide_d3d12compute_cleanup Releasing cached compilation: 0x216f8b591c0 id 2 context 0x216fa9c7fd8 [@] release_object [@] release_d3d12_object halide_memoization_cache_cleanup [@] d3d12_free freeing bytes @ 0x216f8b5c060 [@] d3d12_free freeing bytes @ 0x216f8b5c010 [@] d3d12_free freeing bytes @ 0x216f8b591c0 [@] halide_d3d12compute_device_release [@] halide_d3d12compute_acquire_context user_context: 0x0 | create: 0 current d3d12_device: 0x216fa9c7fd8 [@] d3d12compute_device_sync_internal [@] wait_until_idle [@] wait_until_signaled Already synced up! [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x216fb51e6c0 [@] d3d12_free freeing bytes @ 0x216f8b57790 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x216fb3c2f30 [@] d3d12_free freeing bytes @ 0x216f8b5bf90 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x216fb90ca70 Time [Release_ID3D12Object]: 139 us Time [release_d3d12_object]: 141 us Time [release_object]: 143 us Time [release_d3d12_object]: 199 us Time [release_object]: 200 us [@] release_object [@] release_d3d12_object [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12GraphicsCommandList @ 0x216fa721910 [@] d3d12_free freeing bytes @ 0x216f8b5c0a0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12DescriptorHeap @ 0x216fb3c3b70 [@] d3d12_free freeing bytes @ 0x216f8b5c0c0 [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object [@] release_d3d12_object [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x0 [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object null object -- nothing to be released. [@] release_object [@] release_d3d12_object [@] Release_ID3D12Object ID3D12Resource @ 0x216fa505110 Time [Release_ID3D12Object]: 109 us T======================================== ======================================== correctness_left_shift_negative.exe Success! ======================================== ======================================== correctness_legal_race_condition.exe Success! ======================================== ======================================== correctness_lerp.exe Success! ======================================== ======================================== correctness_let_in_rdom_bound.exe Success! ======================================== ======================================== correctness_likely.exe Success! ======================================== ======================================== correctness_load_library.exe [SKIP] OpenCL not enabled. ======================================== ======================================== correctness_logical.exe ======================================== ======================================== correctness_loop_invariant_extern_calls.exe ======================================== ======================================== correctness_loop_level_generator_param.exe Success! ======================================== ======================================== correctness_lossless_cast.exe Success! ======================================== ======================================== correctness_lots_of_dimensions.exe Success! ======================================== ======================================== correctness_lots_of_loop_invariants.exe ======================================== ======================================== correctness_low_bit_depth_noise.exe Success! ======================================== ======================================== correctness_make_struct.exe Success! ======================================== ======================================== correctness_many_dimensions.exe Success! ======================================== ======================================== correctness_many_small_extern_stages.exe Success! ======================================== ======================================== correctness_many_updates.exe Success! ======================================== ======================================== correctness_math.exe ======================================== ======================================== correctness_median3x3.exe ======================================== ======================================== correctness_memoize.exe Call count is 783. Call count before oversize realize is 798. Call count after oversize realize is 1. Call count is 782. Call count for thread 0 is 1. Call count for thread 1 is 1. Call count for thread 2 is 1. Call count for thread 3 is 1. Call count for thread 4 is 1. Call count for thread 5 is 1. Call count for thread 6 is 1. Call count for thread 7 is 1. Call count for stage 0 is 1. Call count for stage 1 is 1. Call count for stage 2 is 1. Call count for stage 3 is 1. Call count for stage 0 is 2. Call count for stage 1 is 2. Call count for stage 2 is 2. Call count for stage 3 is 1. In 100 attempts with flakey malloc, 59 errors and 41 full completions occured. Success! ======================================== ======================================== correctness_memoize_cloned.exe Success! ======================================== ======================================== correctness_min_extent.exe Success! ======================================== ======================================== correctness_mod.exe Success! ======================================== ======================================== correctness_multipass_constraints.exe Success! ======================================== ======================================== correctness_multiple_outputs.exe Warning: Update definition 0 of function f9 has not been scheduled, even though some other definitions have been. You may have forgotten to schedule it. If this was intentional, call f9.update(0).unscheduled() to suppress this warning. ======================================== ======================================== correctness_multiple_outputs_extern.exe Doing flip_x_and_sum bounds inference over [0 99] Doing flip_x_and_sum bounds inference over [0 99] Computing flip_x_and_sum over [0 99] Success! ======================================== ======================================== correctness_multiple_scatter.exe Success! ======================================== ======================================== correctness_multi_gpu_gpu_multi_device.exe [SKIP] Need two or more GPU targets enabled. ======================================== ======================================== correctness_multi_output_pipeline_with_bad_sizes.exe Constraint violated: f0.1.extent.0 (101) == f0.0.extent.0 (100) Success! ======================================== ======================================== correctness_multi_pass_reduction.exe Success! ======================================== ======================================== correctness_multi_splits_with_diff_tail_strategies.exe Success! ======================================== ======================================== correctness_multi_way_select.exe ======================================== ======================================== correctness_mul_div_mod.exe ======================================== ======================================== correctness_mux.exe Success! ======================================== ======================================== correctness_named_updates.exe Success! ======================================== ======================================== correctness_narrow_predicates.exe Success! ======================================== ======================================== correctness_nested_shiftinwards.exe Success! ======================================== ======================================== correctness_nested_tail_strategies.exe Success! ======================================== ======================================== correctness_newtons_method.exe D3DCompile(): D:\ThirdParty\Halide\build\msvc\bin\Release\_kernel_f7_s0___outermost___outermost_v4___block_id_x(89,19-27): warning X4008: floating point division by zero D:\ThirdParty\Halide\build\msvc\bin\Release\_kernel_f7_s0___outermost___outermost_v4___block_id_x(89,19-27): warning X4008: floating point division by zero D:\ThirdParty\Halide\build\msvc\bin\Release\_kernel_f7_s0___outermost___outermost_v4___block_id_x(89,19-27): warning X4008: floating point division by zero D:\ThirdParty\Halide\build\msvc\bin\Release\_kernel_f7_s0___outermost___outermost_v4___block_id_x(89,19-27): warning X4008: floating point division by zero D:\ThirdParty\Halide\build\msvc\bin\Release\_kernel_f7_s0___outermost___outermost_v4___block_id_x(89,19-27): warning X4008: floating point division by zero D:\ThirdParty\Halide\build\msvc\bin\Release\_kernel_f7_s0___outermost___outermost_v4___block_id_x(89,19-27): warning X4008: floating point division by zero >>> HLSL shader source dump <<< #pragma warning( disable : 3078 ) #pragma warning( disable : 3557 ) #pragma warning( disable : 3556 ) #pragma warning( disable : 3571 ) #pragma warning( disable : 4714 ) #define halide_maybe_unused(x) (void)(x) float nan_f32() { return 1.#IND; } float neg_inf_f32() { return -1.#INF; } float inf_f32() { return +1.#INF; } #define is_inf_f32 isinf #define is_finite_f32 isfinite #define is_nan_f32 isnan #define float_from_bits asfloat #define sqrt_f32 sqrt #define sin_f32 sin #define cos_f32 cos #define exp_f32 exp #define log_f32 log #define abs_f32 abs #define floor_f32 floor #define ceil_f32 ceil #define trunc_f32 trunc float pow_f32(float x, float y) { if (x > 0.0) { return pow(x, y); } else if (y == 0.0) { return 1.0f; } else if (trunc(y) == y) { if (fmod(y, 2) == 0) { return pow(abs(x), y); } else { return -pow(abs(x), y); } } else { return nan_f32(); } } #define asin_f32 asin #define acos_f32 acos #define tan_f32 tan #define atan_f32 atan #define atan2_f32 atan2 #define sinh_f32 sinh #define cosh_f32 cosh #define tanh_f32 tanh #define asinh_f32(x) (log_f32(x + sqrt_f32(x*x + 1))) #define acosh_f32(x) (log_f32(x + sqrt_f32(x*x - 1))) #define atanh_f32(x) (log_f32((1+x)/(1-x))/2) #define fast_inverse_f32 rcp #define fast_inverse_sqrt_f32 rsqrt [ numthreads( 1, 1, 1) ] void _kernel_f7_s0___outermost___outermost_v4___block_id_x( uint3 tgroup_index : SV_GroupID, uint3 tid_in_tgroup : SV_GroupThreadID, RWBuffer _f7) { int _f7_s0___outermost___outermost_v4___block_id_x = tgroup_index.x; int ___thread_id_x = tid_in_tgroup.x; { float _f6_3_3[1]; { float _f6_2_2[1]; { float _f6_1_1[1]; { float _f6_0_0[1]; // produce f6 float _7 = float_from_bits(1077936128 /* 3 */); _f6_0_0[0] = _7; float _8 = float_from_bits(1041269187 /* 0.14112 */); _f6_1_1[0] = _8; float _9 = float_from_bits(1082130432 /* 4 */); _f6_2_2[0] = _9; float _10 = float_from_bits(3208756687 /* -0.756802 */); _f6_3_3[0] = _10; for (int _f6_s1_r4__x = 0; _f6_s1_r4__x < 0 + 10; _f6_s1_r4__x++) { float _11 = _f6_3_3[0]; float _12 = _f6_1_1[0]; float _13 = _f6_0_0[0]; float _14 = float_from_bits(0 /* 0 */); float _15 = _f6_2_2[0]; float _16 = _13 - _15; float _17 = _16 * _12; float _18 = _12 - _11; float _19 = _17 / _18; float _20 = _14 - _19; float _21 = _11 - _12; float _22 = _14 - _21; bool _23 = _21 > _14; float _24 = float(_23 ? _21 : _22); float _25 = _24; bool _26 = _14 < _25; float _27 = float(_26 ? _20 : _14); float _28 = _27 + _13; float _29 = sin_f32(_28); _f6_0_0[0] = _28; _f6_1_1[0] = _29; _f6_2_2[0] = _13; _f6_3_3[0] = _12; } // for _f6_s1_r4__x // consume f6 float _30 = _f6_0_0[0]; _f7[0] = _30; } // alloc _f6_0_0 } // alloc _f6_1_1 } // alloc _f6_2_2 } // alloc _f6_3_3 } // kernel _kernel_f7_s0___outermost___outermost_v4___block_id_x ======================================== ======================================== correctness_non_nesting_extern_bounds_query.exe Success! ======================================== ======================================== correctness_non_vector_aligned_embeded_buffer.exe Success! ======================================== ======================================== correctness_obscure_image_references.exe Success! ======================================== ======================================== correctness_oddly_sized_output.exe Success! ======================================== ======================================== correctness_output_larger_than_two_gigs.exe Expected: Product of extents for buffer f0 is 4294967296, which exceeds the maximum size of 2147483647 Success! ======================================== ======================================== correctness_out_constraint.exe for(f1.s0.v0, 0, 10) for(f4.s1.p0$x, 0, 10) Success! ======================================== ======================================== correctness_out_of_memory.exe Out of memory (halide_malloc returned nullptr) Success! ======================================== ======================================== correctness_parallel.exe Success! ======================================== ======================================== correctness_parallel_alloc.exe Success! ======================================== ======================================== correctness_parallel_fork.exe Serial time 3.124856 for 200 calls. Parallel time 1.561824 for 200 calls. Async root time 1.557981 for 200 calls. AsyncComputeAt time 1.560976 for 200 calls. Success! ======================================== ======================================== correctness_parallel_gpu_nested.exe ======================================== ======================================== correctness_parallel_nested.exe Success! ======================================== ======================================== correctness_parallel_nested_1.exe Using Target = x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Success! ======================================== ======================================== correctness_parallel_reductions.exe Success! ======================================== ======================================== correctness_parallel_rvar.exe Success! ======================================== ======================================== correctness_parallel_scatter.exe Success! ======================================== ======================================== correctness_param.exe ======================================== ======================================== correctness_parameter_constraints.exe Success! ======================================== ======================================== correctness_param_map.exe Success! ======================================== ======================================== correctness_partial_application.exe Defining function... Realizing function... Success! ======================================== ======================================== correctness_partial_realization.exe Success! ======================================== ======================================== correctness_partition_loops.exe Success! ======================================== ======================================== correctness_partition_loops_bug.exe Success! ======================================== ======================================== correctness_partition_max_filter.exe Success! ======================================== ======================================== correctness_pipeline_set_jit_externs_func.exe Success! ======================================== ======================================== correctness_plain_c_includes.exe Success! ======================================== ======================================== correctness_popc_clz_ctz_bounds.exe Success! ======================================== ======================================== correctness_predicated_store_load.exe Running vectorized dense load test Running vectorized dense load with scalar test Running vectorized dense load with stride minus one test Running multiple vectorized predicate test Running vectorized predicated store scalarized predicated load test Running scalar load test Running scalar store test Running not dependent on vectorized var test Running no-op store test Running vectorized predicated with pure call test Running vectorized predicated load with constant index test Running vectorized predicated load lut test Success! ======================================== ======================================== correctness_prefetch.exe Testing target: target(x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41) Running prefetch test 1 Running prefetch test 2 Running prefetch test 3 Running prefetch test 4 Warning: Removing prefetch of f$3 at loop nest of g$3.s0.x from location g$3.s0.x + offset 1) since the prefetched area will always be empty. Running prefetch test 5 Running prefetch test 6 Running prefetch test 7 Running prefetch test 8 Warning: Removing prefetch of f$7 at loop nest of g$7.s0.x from location g$7.s0.y + offset 1) since the prefetched area will always be empty. Running prefetch test 9 Running prefetch test 10 Running prefetch test 11 Running prefetch test 12 Success! ======================================== ======================================== correctness_print.exe Success! ======================================== ======================================== correctness_print_loop_nest.exe produce f0: produce f2: produce f1: for v1.fused.v3: for v0.fused.v2: for v1.v5 in [0, 1]: for v0.v4 in [0, 7]: f0(...) = ... for v0.v4 in [0, 3]: f1(...) = ... for v0.v4 in [0, 3]: f2(...) = ... Success! ======================================== ======================================== correctness_process_some_tiles.exe Success! ======================================== ======================================== correctness_pseudostack_shares_slots.exe Success! ======================================== ======================================== correctness_python_extension_gen.exe Success! ======================================== ======================================== correctness_pytorch.exe Success! ======================================== ======================================== correctness_random.exe Success! ======================================== ======================================== correctness_realize_condition_depends_on_tuple.exe Success! ======================================== ======================================== correctness_realize_larger_than_two_gigs.exe Expected: Total allocation for buffer f0 is 9223653511831486464, which exceeds the maximum size of 9223372036854775807 Expected: Total allocation for buffer f0 is 2164260864, which exceeds the maximum size of 2147483647 Success! ======================================== ======================================== correctness_realize_over_shifted_domain.exe Success! ======================================== ======================================== correctness_recursive_box_filters.exe Warning: Update definition 0 of function f1 has not been scheduled, even though some other definitions have been. You may have forgotten to schedule it. If this was intentional, call f1.update(0).unscheduled() to suppress this warning. Warning: Update definition 1 of function f1 has not been scheduled, even though some other definitions have been. You may have forgotten to schedule it. If this was intentional, call f1.update(1).unscheduled() to suppress this warning. Success! ======================================== ======================================== correctness_reduction_chain.exe Success! ======================================== ======================================== correctness_reduction_non_rectangular.exe Running equality inequality bound test Running split fuse test Running bound depend on free variable test Running function call inside bound test Running function call inside bound inline test Running two linear bounds test Running circular bound test Running intermediate only computed if param is bigger than certain value test ....Set p to 5, expect g to be computed ....Set p to 0, expect g to be not computed Running tile intermediate stage depend on output bound test Running intermediate stage depend on output bound Running self reference bound test Running random float bound test Running newton's method test Running vectorize predicated rvar test Running initialization on gpu and update on cpu test Warning: Update definition 0 of function f_12 has not been scheduled, even though some other definitions have been. You may have forgotten to schedule it. If this was intentional, call f_12.update(0).unscheduled() to suppress this warning. Running initialization on cpu and update on gpu test Running gpu intermediate only computed if param is bigger than certain value test ....Set p to 5, expect g to be computed Warning: Update definition 1 of function f_14 has not been scheduled, even though some other definitions have been. You may have forgotten to schedule it. If this was intentional, call f_14.update(1).unscheduled() to suppress this warning. ======================================== ======================================== correctness_reduction_predicate_racing.exe Success! ======================================== ======================================== correctness_reduction_schedule.exe Success! ======================================== ======================================== correctness_register_shuffle.exe [SKIP] CUDA with capability greater than or equal to 5.0 required, cap:-1 ======================================== ======================================== correctness_reorder_rvars.exe ======================================== ======================================== correctness_reorder_storage.exe Success! ======================================== ======================================== correctness_require.exe Saw (Expected) Halide Err: Requirement Failed: (false) 23757 The parameters should add to exactly 7829 but were 3 for vector_width 0 Saw (Expected) Halide Err: Requirement Failed: (false) 16 Saw (Expected) Halide Err: Requirement Failed: (false) 23757 The parameters should add to exactly 7829 but were 3 for vector_width 4 Saw (Expected) Halide Err: Requirement Failed: (false) 16 Saw (Expected) Halide Err: Requirement Failed: (false) 23757 The parameters should add to exactly 7829 but were 3 for vector_width 32 Saw (Expected) Halide Err: Requirement Failed: (false) 16 Success! ======================================== ======================================== correctness_reschedule.exe Success! ======================================== ======================================== correctness_reuse_stack_alloc.exe Success! ======================================== ======================================== correctness_rfactor.exe self assignment rfactor test simple rfactor test: checking call graphs... simple rfactor test: checking output img correctness... reorder split rfactor test: checking call graphs... reorder split rfactor test: checking output img correctness... multiple split rfactor test: checking call graphs... multiple split rfactor test: checking output img correctness... reorder fuse wrapper rfactor test: checking call graphs... reorder fuse wrapper rfactor test: checking output img correctness... non trivial lhs rfactor test: checking call graphs... non trivial lhs rfactor test: checking output img correctness... simple rfactor with specialization test: checking call graphs... simple rfactor with specialization test: checking output img correctness... rdom with predicate rfactor test: checking call graphs... rdom with predicate rfactor test: checking output img correctness... histogram rfactor test: checking call graphs... histogram rfactor test: checking output img correctness... parallel dot product rfactor test: checking call graphs... parallel dot product rfactor test: checking output img correctness... tuple rfactor test: checking call graphs... tuple rfactor test: checking output img correctness... tuple specialize rdom predicate rfactor test: checking call graphs... tuple specialize rdom predicate rfactor test: checking output img correctness... parallel dot product rfactor test: checking call graphs... parallel dot product rfactor test: checking output img correctness... tuple partial reduction rfactor test: checking call graphs... tuple partial reduction rfactor test: checking output img correctness... check allocation bound test rfactor tile reorder test: checking output img correctness... complex multiply rfactor test argmin rfactor test Success! ======================================== ======================================== correctness_round.exe ======================================== ======================================== correctness_saturating_casts.exe Success! ======================================== ======================================== correctness_scatter.exe Success! ======================================== ======================================== correctness_set_custom_trace.exe Success! ======================================== ======================================== correctness_shadowed_bound.exe Success! ======================================== ======================================== correctness_shared_self_references.exe Success! ======================================== ======================================== correctness_shifted_image.exe Success! ======================================== ======================================== correctness_shift_by_unsigned_negated.exe Success! ======================================== ======================================== correctness_side_effects.exe ..............::::::::::::-------------------:::::::::::::::::::::::::: ............::::::::----------------~~~~*=**~~~----:::::::::::::::::::: ...........:::::----------------~~~~~~**={#&# *~~~~----:::::::::::::::: ..........:::----------------~~~~~~~***{@#@ @&=**~~~~-----::::::::::::: ........:::---------------~~~~~~**==={{&@ @}{==***~~-----::::::::::: ........:--------------~~~~****={@ @@@ @&@%@&*~------::::::::: .......:-----------~~*******===}@@ @{=*~------:::::::: ......:-----~~~~~*={@}{{&}{{{}}@ @ @*~~------::::::: ......--~~~~~~****{{&@ @ @@#@ @}*~~~------:::::: ......~~~~~**=={}@%#@ @ @=*~~~------:::::: ...... @}{=*~~~------:::::: ......~~~~~**=={}@%#@ @ @=*~~~------:::::: ......--~~~~~~****{{&@ @ @@#@ @}*~~~------:::::: ......:-----~~~~~*={@}{{&}{{{}}@ @ @*~~------::::::: .......:-----------~~*******===}@@ @{=*~------:::::::: ........:--------------~~~~****={@ @@@ @&@%@&*~------::::::::: ........:::---------------~~~~~~**==={{&@ @}{==***~~-----::::::::::: ..........:::----------------~~~~~~~***{@#@ @&=**~~~~-----::::::::::::: ...........:::::----------------~~~~~~**={#&# *~~~~----:::::::::::::::: ............::::::::----------------~~~~*=**~~~----:::::::::::::::::::: ..............::::::::::::-------------------:::::::::::::::::::::::::: Success! ======================================== ======================================== correctness_simd_op_check_arm.exe host is: target(x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41) simd_op_check test seed: 1680899289 vaba.s8 (arm-32-linux) vaba.u8 (arm-32-linux) vaba.s16 (arm-32-linux) vaba.u16 (arm-32-linux) vaba.s32 (arm-32-linux) vaba.u32 (arm-32-linux) vabal.s8 (arm-32-linux) vabal.u8 (arm-32-linux) vabal.s16 (arm-32-linux) vabal.u16 (arm-32-linux) vabal.s32 (arm-32-linux) vabal.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabs.f32 (arm-32-linux) vabs.s32 (arm-32-linux) vabs.s16 (arm-32-linux) vabs.s8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.f32 (arm-32-linux) vadd.i64 (arm-32-linux) vadd.i64 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddl.s8 (arm-32-linux) vaddl.u8 (arm-32-linux) vaddl.s16 (arm-32-linux) vaddl.u16 (arm-32-linux) vaddl.s32 (arm-32-linux) vaddl.u32 (arm-32-linux) vaddw.s8 (arm-32-linux) vaddw.u8 (arm-32-linux) vaddw.s16 (arm-32-linux) vaddw.u16 (arm-32-linux) vaddw.s32 (arm-32-linux) vaddw.u32 (arm-32-linux) vbsl (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.f32 (arm-32-linux) vcgt.s8 (arm-32-linux) vcgt.u8 (arm-32-linux) vcgt.s16 (arm-32-linux) vcgt.u16 (arm-32-linux) vcgt.s32 (arm-32-linux) vcgt.u32 (arm-32-linux) vcgt.f32 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i32 (arm-32-linux) vclz.i32 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcvt.f32.u32 (arm-32-linux) vcvt.f32.s32 (arm-32-linux) vcvt.u32.f32 (arm-32-linux) vcvt.s32.f32 (arm-32-linux) vdiv.f32 (arm-32-linux) vdiv.f64 (arm-32-linux) vdup.8 (arm-32-linux) vdup.8 (arm-32-linux) vdup.16 (arm-32-linux) vdup.16 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vhadd.s8 (arm-32-linux) vhadd.u8 (arm-32-linux) vhadd.s16 (arm-32-linux) vhadd.u16 (arm-32-linux) vhadd.s32 (arm-32-linux) vhadd.u32 (arm-32-linux) vhadd.s32 (arm-32-linux) vhsub.s8 (arm-32-linux) vhsub.u8 (arm-32-linux) vhsub.s16 (arm-32-linux) vhsub.u16 (arm-32-linux) vhsub.s32 (arm-32-linux) vhsub.u32 (arm-32-linux) vhsub.s32 (arm-32-linux) vld1.8 (arm-32-linux) vld1.8 (arm-32-linux) vld1.16 (arm-32-linux) vld1.16 (arm-32-linux) vld2.8 (arm-32-linux) vld2.8 (arm-32-linux) vld2.16 (arm-32-linux) vld2.16 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld3.8 (arm-32-linux) vld3.8 (arm-32-linux) vld3.16 (arm-32-linux) vld3.16 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld4.8 (arm-32-linux) vld4.8 (arm-32-linux) vld4.16 (arm-32-linux) vld4.16 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vmax.s8 (arm-32-linux) vmax.u8 (arm-32-linux) vmax.s16 (arm-32-linux) vmax.u16 (arm-32-linux) vmax.s32 (arm-32-linux) vmax.u32 (arm-32-linux) vmax.f32 (arm-32-linux) vmin.s8 (arm-32-linux) vmin.u8 (arm-32-linux) vmin.s16 (arm-32-linux) vmin.u16 (arm-32-linux) vmin.s32 (arm-32-linux) vmin.u32 (arm-32-linux) vmin.f32 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i32 (arm-32-linux) vmla.i32 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i32 (arm-32-linux) vmls.i32 (arm-32-linux) vmlal.s8 (arm-32-linux) vmlal.u8 (arm-32-linux) vmlal.s16 (arm-32-linux) vmlal.u16 (arm-32-linux) vmlal.s32 (arm-32-linux) vmlal.u32 (arm-32-linux) vmlsl.s8 (arm-32-linux) vmlsl.u8 (arm-32-linux) vmlsl.s16 (arm-32-linux) vmlsl.u16 (arm-32-linux) vmlsl.s32 (arm-32-linux) vmlsl.u32 (arm-32-linux) vmovl.s8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.s16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.s32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i64 (arm-32-linux) vmovn.i64 (arm-32-linux) vmul.f64 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.f32 (arm-32-linux) vmull.s8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.s16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.s32 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u32 (arm-32-linux) vneg.s8 (arm-32-linux) vneg.s16 (arm-32-linux) vneg.s32 (arm-32-linux) vneg.f32 (arm-32-linux) vneg.f64 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpadal.s8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.s32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vqadd.s8 (arm-32-linux) vqadd.s16 (arm-32-linux) vqadd.s32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqdmulh.s16 (arm-32-linux) vqdmulh.s32 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s64 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u64 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s64 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqneg.s8 (arm-32-linux) vqneg.s16 (arm-32-linux) vqneg.s32 (arm-32-linux) vqrdmulh.s16 (arm-32-linux) vqrdmulh.s32 (arm-32-linux) vqrshrn.s16 (arm-32-linux) vqrshrn.s32 (arm-32-linux) vqrshrn.s64 (arm-32-linux) vqrshrun.s16 (arm-32-linux) vqrshrun.s32 (arm-32-linux) vqrshrun.s64 (arm-32-linux) vqrshrn.u16 (arm-32-linux) vqrshrn.u32 (arm-32-linux) vqshl.s8 (arm-32-linux) vqshl.s16 (arm-32-linux) vqshl.s32 (arm-32-linux) vqshl.u8 (arm-32-linux) vqshl.u16 (arm-32-linux) vqshl.u32 (arm-32-linux) vqshlu.s8 (arm-32-linux) vqshlu.s16 (arm-32-linux) vqshlu.s32 (arm-32-linux) vqshrn.s16 (arm-32-linux) vqshrn.s32 (arm-32-linux) vqshrn.s64 (arm-32-linux) vqshrun.s16 (arm-32-linux) vqshrun.s32 (arm-32-linux) vqshrun.s64 (arm-32-linux) vqshrn.u16 (arm-32-linux) vqshrn.u32 (arm-32-linux) vqshrn.u64 (arm-32-linux) vqsub.s8 (arm-32-linux) vqsub.s16 (arm-32-linux) vqsub.s32 (arm-32-linux) vqsub.u8 (arm-32-linux) vqsub.u16 (arm-32-linux) vqsub.u32 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i64 (arm-32-linux) vrecpe.f32 (arm-32-linux) vrecps.f32 (arm-32-linux) vrhadd.s8 (arm-32-linux) vrhadd.u8 (arm-32-linux) vrhadd.s16 (arm-32-linux) vrhadd.u16 (arm-32-linux) vrhadd.s32 (arm-32-linux) vrhadd.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshr.s8 (arm-32-linux) vrshr.s16 (arm-32-linux) vrshr.s32 (arm-32-linux) vrshr.u8 (arm-32-linux) vrshr.u16 (arm-32-linux) vrshr.u32 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrshrn.i64 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrsqrte.f32 (arm-32-linux) vrsqrts.f32 (arm-32-linux) vrsra.s8 (arm-32-linux) vrsra.s16 (arm-32-linux) vrsra.s32 (arm-32-linux) vrsra.u8 (arm-32-linux) vrsra.u16 (arm-32-linux) vrsra.u32 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u64 (arm-32-linux) vshl.u64 (arm-32-linux) vshll.s8 (arm-32-linux) vshll.s16 (arm-32-linux) vshll.s32 (arm-32-linux) vshll.u8 (arm-32-linux) vshll.u16 (arm-32-linux) vshll.u32 (arm-32-linux) vshr.s8 (arm-32-linux) vshr.s16 (arm-32-linux) vshr.s32 (arm-32-linux) vshr.s64 (arm-32-linux) vshr.u8 (arm-32-linux) vshr.u16 (arm-32-linux) vshr.u32 (arm-32-linux) vshr.u64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vsqrt.f32 (arm-32-linux) vsqrt.f64 (arm-32-linux) vsra.s8 (arm-32-linux) vsra.s16 (arm-32-linux) vsra.s32 (arm-32-linux) vsra.s64 (arm-32-linux) vsra.u8 (arm-32-linux) vsra.u16 (arm-32-linux) vsra.u32 (arm-32-linux) vsra.u64 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.f32 (arm-32-linux) vsub.f32 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubw.s8 (arm-32-linux) vsubw.u8 (arm-32-linux) vsubw.s16 (arm-32-linux) vsubw.u16 (arm-32-linux) vsubw.s32 (arm-32-linux) vsubw.u32 (arm-32-linux) vaba.s8 (arm-32-linux) vaba.u8 (arm-32-linux) vaba.s16 (arm-32-linux) vaba.u16 (arm-32-linux) vaba.s32 (arm-32-linux) vaba.u32 (arm-32-linux) vabal.s8 (arm-32-linux) vabal.u8 (arm-32-linux) vabal.s16 (arm-32-linux) vabal.u16 (arm-32-linux) vabal.s32 (arm-32-linux) vabal.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabs.f32 (arm-32-linux) vabs.s32 (arm-32-linux) vabs.s16 (arm-32-linux) vabs.s8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.f32 (arm-32-linux) vadd.i64 (arm-32-linux) vadd.i64 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddl.s8 (arm-32-linux) vaddl.u8 (arm-32-linux) vaddl.s16 (arm-32-linux) vaddl.u16 (arm-32-linux) vaddl.s32 (arm-32-linux) vaddl.u32 (arm-32-linux) vaddw.s8 (arm-32-linux) vaddw.u8 (arm-32-linux) vaddw.s16 (arm-32-linux) vaddw.u16 (arm-32-linux) vaddw.s32 (arm-32-linux) vaddw.u32 (arm-32-linux) vbsl (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.f32 (arm-32-linux) vcgt.s8 (arm-32-linux) vcgt.u8 (arm-32-linux) vcgt.s16 (arm-32-linux) vcgt.u16 (arm-32-linux) vcgt.s32 (arm-32-linux) vcgt.u32 (arm-32-linux) vcgt.f32 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i32 (arm-32-linux) vclz.i32 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcvt.f32.u32 (arm-32-linux) vcvt.f32.s32 (arm-32-linux) vcvt.u32.f32 (arm-32-linux) vcvt.s32.f32 (arm-32-linux) vdiv.f32 (arm-32-linux) vdiv.f64 (arm-32-linux) vdup.8 (arm-32-linux) vdup.8 (arm-32-linux) vdup.16 (arm-32-linux) vdup.16 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vhadd.s8 (arm-32-linux) vhadd.u8 (arm-32-linux) vhadd.s16 (arm-32-linux) vhadd.u16 (arm-32-linux) vhadd.s32 (arm-32-linux) vhadd.u32 (arm-32-linux) vhadd.s32 (arm-32-linux) vhsub.s8 (arm-32-linux) vhsub.u8 (arm-32-linux) vhsub.s16 (arm-32-linux) vhsub.u16 (arm-32-linux) vhsub.s32 (arm-32-linux) vhsub.u32 (arm-32-linux) vhsub.s32 (arm-32-linux) vld1.8 (arm-32-linux) vld1.8 (arm-32-linux) vld1.16 (arm-32-linux) vld1.16 (arm-32-linux) vld1.32 (arm-32-linux) vld1.32 (arm-32-linux) vld1.32 (arm-32-linux) vld2.8 (arm-32-linux) vld2.8 (arm-32-linux) vld2.16 (arm-32-linux) vld2.16 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld3.8 (arm-32-linux) vld3.8 (arm-32-linux) vld3.16 (arm-32-linux) vld3.16 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld4.8 (arm-32-linux) vld4.8 (arm-32-linux) vld4.16 (arm-32-linux) vld4.16 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vmax.s8 (arm-32-linux) vmax.u8 (arm-32-linux) vmax.s16 (arm-32-linux) vmax.u16 (arm-32-linux) vmax.s32 (arm-32-linux) vmax.u32 (arm-32-linux) vmax.f32 (arm-32-linux) vmin.s8 (arm-32-linux) vmin.u8 (arm-32-linux) vmin.s16 (arm-32-linux) vmin.u16 (arm-32-linux) vmin.s32 (arm-32-linux) vmin.u32 (arm-32-linux) vmin.f32 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i32 (arm-32-linux) vmla.i32 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i32 (arm-32-linux) vmls.i32 (arm-32-linux) vmlal.s8 (arm-32-linux) vmlal.u8 (arm-32-linux) vmlal.s16 (arm-32-linux) vmlal.u16 (arm-32-linux) vmlal.s32 (arm-32-linux) vmlal.u32 (arm-32-linux) vmlsl.s8 (arm-32-linux) vmlsl.u8 (arm-32-linux) vmlsl.s16 (arm-32-linux) vmlsl.u16 (arm-32-linux) vmlsl.s32 (arm-32-linux) vmlsl.u32 (arm-32-linux) vmovl.s8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.s16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.s32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i64 (arm-32-linux) vmovn.i64 (arm-32-linux) vmul.f64 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.f32 (arm-32-linux) vmull.s8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.s16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.s32 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u32 (arm-32-linux) vneg.s8 (arm-32-linux) vneg.s16 (arm-32-linux) vneg.s32 (arm-32-linux) vneg.f32 (arm-32-linux) vneg.f64 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpadal.s8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.s32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vqadd.s8 (arm-32-linux) vqadd.s16 (arm-32-linux) vqadd.s32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqdmulh.s16 (arm-32-linux) vqdmulh.s32 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s64 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u64 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s64 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqneg.s8 (arm-32-linux) vqneg.s16 (arm-32-linux) vqneg.s32 (arm-32-linux) vqrdmulh.s16 (arm-32-linux) vqrdmulh.s32 (arm-32-linux) vqrshrn.s16 (arm-32-linux) vqrshrn.s32 (arm-32-linux) vqrshrn.s64 (arm-32-linux) vqrshrun.s16 (arm-32-linux) vqrshrun.s32 (arm-32-linux) vqrshrun.s64 (arm-32-linux) vqrshrn.u16 (arm-32-linux) vqrshrn.u32 (arm-32-linux) vqshl.s8 (arm-32-linux) vqshl.s16 (arm-32-linux) vqshl.s32 (arm-32-linux) vqshl.u8 (arm-32-linux) vqshl.u16 (arm-32-linux) vqshl.u32 (arm-32-linux) vqshlu.s8 (arm-32-linux) vqshlu.s16 (arm-32-linux) vqshlu.s32 (arm-32-linux) vqshrn.s16 (arm-32-linux) vqshrn.s32 (arm-32-linux) vqshrn.s64 (arm-32-linux) vqshrun.s16 (arm-32-linux) vqshrun.s32 (arm-32-linux) vqshrun.s64 (arm-32-linux) vqshrn.u16 (arm-32-linux) vqshrn.u32 (arm-32-linux) vqshrn.u64 (arm-32-linux) vqsub.s8 (arm-32-linux) vqsub.s16 (arm-32-linux) vqsub.s32 (arm-32-linux) vqsub.u8 (arm-32-linux) vqsub.u16 (arm-32-linux) vqsub.u32 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i64 (arm-32-linux) vrecpe.f32 (arm-32-linux) vrecps.f32 (arm-32-linux) vrhadd.s8 (arm-32-linux) vrhadd.u8 (arm-32-linux) vrhadd.s16 (arm-32-linux) vrhadd.u16 (arm-32-linux) vrhadd.s32 (arm-32-linux) vrhadd.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshr.s8 (arm-32-linux) vrshr.s16 (arm-32-linux) vrshr.s32 (arm-32-linux) vrshr.u8 (arm-32-linux) vrshr.u16 (arm-32-linux) vrshr.u32 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrshrn.i64 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrsqrte.f32 (arm-32-linux) vrsqrts.f32 (arm-32-linux) vrsra.s8 (arm-32-linux) vrsra.s16 (arm-32-linux) vrsra.s32 (arm-32-linux) vrsra.u8 (arm-32-linux) vrsra.u16 (arm-32-linux) vrsra.u32 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u64 (arm-32-linux) vshl.u64 (arm-32-linux) vshll.s8 (arm-32-linux) vshll.s16 (arm-32-linux) vshll.s32 (arm-32-linux) vshll.u8 (arm-32-linux) vshll.u16 (arm-32-linux) vshll.u32 (arm-32-linux) vshr.s8 (arm-32-linux) vshr.s16 (arm-32-linux) vshr.s32 (arm-32-linux) vshr.s64 (arm-32-linux) vshr.u8 (arm-32-linux) vshr.u16 (arm-32-linux) vshr.u32 (arm-32-linux) vshr.u64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vsqrt.f32 (arm-32-linux) vsqrt.f64 (arm-32-linux) vsra.s8 (arm-32-linux) vsra.s16 (arm-32-linux) vsra.s32 (arm-32-linux) vsra.s64 (arm-32-linux) vsra.u8 (arm-32-linux) vsra.u16 (arm-32-linux) vsra.u32 (arm-32-linux) vsra.u64 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.f32 (arm-32-linux) vsub.f32 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubw.s8 (arm-32-linux) vsubw.u8 (arm-32-linux) vsubw.s16 (arm-32-linux) vsubw.u16 (arm-32-linux) vsubw.s32 (arm-32-linux) vsubw.u32 (arm-32-linux) vaba.s8 (arm-32-linux) vaba.u8 (arm-32-linux) vaba.s16 (arm-32-linux) vaba.u16 (arm-32-linux) vaba.s32 (arm-32-linux) vaba.u32 (arm-32-linux) vabal.s8 (arm-32-linux) vabal.u8 (arm-32-linux) vabal.s16 (arm-32-linux) vabal.u16 (arm-32-linux) vabal.s32 (arm-32-linux) vabal.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabs.f32 (arm-32-linux) vabs.s32 (arm-32-linux) vabs.s16 (arm-32-linux) vabs.s8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.f32 (arm-32-linux) vadd.i64 (arm-32-linux) vadd.i64 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddl.s8 (arm-32-linux) vaddl.u8 (arm-32-linux) vaddl.s16 (arm-32-linux) vaddl.u16 (arm-32-linux) vaddl.s32 (arm-32-linux) vaddl.u32 (arm-32-linux) vaddw.s8 (arm-32-linux) vaddw.u8 (arm-32-linux) vaddw.s16 (arm-32-linux) vaddw.u16 (arm-32-linux) vaddw.s32 (arm-32-linux) vaddw.u32 (arm-32-linux) vbsl (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.f32 (arm-32-linux) vcgt.s8 (arm-32-linux) vcgt.u8 (arm-32-linux) vcgt.s16 (arm-32-linux) vcgt.u16 (arm-32-linux) vcgt.s32 (arm-32-linux) vcgt.u32 (arm-32-linux) vcgt.f32 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i32 (arm-32-linux) vclz.i32 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcvt.f32.u32 (arm-32-linux) vcvt.f32.s32 (arm-32-linux) vcvt.u32.f32 (arm-32-linux) vcvt.s32.f32 (arm-32-linux) vdiv.f32 (arm-32-linux) vdiv.f64 (arm-32-linux) vdup.8 (arm-32-linux) vdup.8 (arm-32-linux) vdup.16 (arm-32-linux) vdup.16 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vhadd.s8 (arm-32-linux) vhadd.u8 (arm-32-linux) vhadd.s16 (arm-32-linux) vhadd.u16 (arm-32-linux) vhadd.s32 (arm-32-linux) vhadd.u32 (arm-32-linux) vhadd.s32 (arm-32-linux) vhsub.s8 (arm-32-linux) vhsub.u8 (arm-32-linux) vhsub.s16 (arm-32-linux) vhsub.u16 (arm-32-linux) vhsub.s32 (arm-32-linux) vhsub.u32 (arm-32-linux) vhsub.s32 (arm-32-linux) vld1.8 (arm-32-linux) vld1.8 (arm-32-linux) vld1.16 (arm-32-linux) vld1.16 (arm-32-linux) vld1.32 (arm-32-linux) vld1.32 (arm-32-linux) vld1.32 (arm-32-linux) vld2.8 (arm-32-linux) vld2.8 (arm-32-linux) vld2.16 (arm-32-linux) vld2.16 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld3.8 (arm-32-linux) vld3.8 (arm-32-linux) vld3.16 (arm-32-linux) vld3.16 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld4.8 (arm-32-linux) vld4.8 (arm-32-linux) vld4.16 (arm-32-linux) vld4.16 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vmax.s8 (arm-32-linux) vmax.u8 (arm-32-linux) vmax.s16 (arm-32-linux) vmax.u16 (arm-32-linux) vmax.s32 (arm-32-linux) vmax.u32 (arm-32-linux) vmax.f32 (arm-32-linux) vmin.s8 (arm-32-linux) vmin.u8 (arm-32-linux) vmin.s16 (arm-32-linux) vmin.u16 (arm-32-linux) vmin.s32 (arm-32-linux) vmin.u32 (arm-32-linux) vmin.f32 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i32 (arm-32-linux) vmla.i32 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i32 (arm-32-linux) vmls.i32 (arm-32-linux) vmlal.s8 (arm-32-linux) vmlal.u8 (arm-32-linux) vmlal.s16 (arm-32-linux) vmlal.u16 (arm-32-linux) vmlal.s32 (arm-32-linux) vmlal.u32 (arm-32-linux) vmlsl.s8 (arm-32-linux) vmlsl.u8 (arm-32-linux) vmlsl.s16 (arm-32-linux) vmlsl.u16 (arm-32-linux) vmlsl.s32 (arm-32-linux) vmlsl.u32 (arm-32-linux) vmovl.s8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.s16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.s32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i64 (arm-32-linux) vmovn.i64 (arm-32-linux) vmul.f64 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.f32 (arm-32-linux) vmull.s8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.s16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.s32 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u32 (arm-32-linux) vneg.s8 (arm-32-linux) vneg.s16 (arm-32-linux) vneg.s32 (arm-32-linux) vneg.f32 (arm-32-linux) vneg.f64 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpadal.s8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.s32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vqadd.s8 (arm-32-linux) vqadd.s16 (arm-32-linux) vqadd.s32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqdmulh.s16 (arm-32-linux) vqdmulh.s32 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s64 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u64 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s64 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqneg.s8 (arm-32-linux) vqneg.s16 (arm-32-linux) vqneg.s32 (arm-32-linux) vqrdmulh.s16 (arm-32-linux) vqrdmulh.s32 (arm-32-linux) vqrshrn.s16 (arm-32-linux) vqrshrn.s32 (arm-32-linux) vqrshrn.s64 (arm-32-linux) vqrshrun.s16 (arm-32-linux) vqrshrun.s32 (arm-32-linux) vqrshrun.s64 (arm-32-linux) vqrshrn.u16 (arm-32-linux) vqrshrn.u32 (arm-32-linux) vqshl.s8 (arm-32-linux) vqshl.s16 (arm-32-linux) vqshl.s32 (arm-32-linux) vqshl.u8 (arm-32-linux) vqshl.u16 (arm-32-linux) vqshl.u32 (arm-32-linux) vqshlu.s8 (arm-32-linux) vqshlu.s16 (arm-32-linux) vqshlu.s32 (arm-32-linux) vqshrn.s16 (arm-32-linux) vqshrn.s32 (arm-32-linux) vqshrn.s64 (arm-32-linux) vqshrun.s16 (arm-32-linux) vqshrun.s32 (arm-32-linux) vqshrun.s64 (arm-32-linux) vqshrn.u16 (arm-32-linux) vqshrn.u32 (arm-32-linux) vqshrn.u64 (arm-32-linux) vqsub.s8 (arm-32-linux) vqsub.s16 (arm-32-linux) vqsub.s32 (arm-32-linux) vqsub.u8 (arm-32-linux) vqsub.u16 (arm-32-linux) vqsub.u32 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i64 (arm-32-linux) vrecpe.f32 (arm-32-linux) vrecps.f32 (arm-32-linux) vrhadd.s8 (arm-32-linux) vrhadd.u8 (arm-32-linux) vrhadd.s16 (arm-32-linux) vrhadd.u16 (arm-32-linux) vrhadd.s32 (arm-32-linux) vrhadd.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshr.s8 (arm-32-linux) vrshr.s16 (arm-32-linux) vrshr.s32 (arm-32-linux) vrshr.u8 (arm-32-linux) vrshr.u16 (arm-32-linux) vrshr.u32 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrshrn.i64 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrsqrte.f32 (arm-32-linux) vrsqrts.f32 (arm-32-linux) vrsra.s8 (arm-32-linux) vrsra.s16 (arm-32-linux) vrsra.s32 (arm-32-linux) vrsra.u8 (arm-32-linux) vrsra.u16 (arm-32-linux) vrsra.u32 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u64 (arm-32-linux) vshl.u64 (arm-32-linux) vshll.s8 (arm-32-linux) vshll.s16 (arm-32-linux) vshll.s32 (arm-32-linux) vshll.u8 (arm-32-linux) vshll.u16 (arm-32-linux) vshll.u32 (arm-32-linux) vshr.s8 (arm-32-linux) vshr.s16 (arm-32-linux) vshr.s32 (arm-32-linux) vshr.s64 (arm-32-linux) vshr.u8 (arm-32-linux) vshr.u16 (arm-32-linux) vshr.u32 (arm-32-linux) vshr.u64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vsqrt.f32 (arm-32-linux) vsqrt.f64 (arm-32-linux) vsra.s8 (arm-32-linux) vsra.s16 (arm-32-linux) vsra.s32 (arm-32-linux) vsra.s64 (arm-32-linux) vsra.u8 (arm-32-linux) vsra.u16 (arm-32-linux) vsra.u32 (arm-32-linux) vsra.u64 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.f32 (arm-32-linux) vsub.f32 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubw.s8 (arm-32-linux) vsubw.u8 (arm-32-linux) vsubw.s16 (arm-32-linux) vsubw.u16 (arm-32-linux) vsubw.s32 (arm-32-linux) vsubw.u32 (arm-32-linux) vaba.s8 (arm-32-linux) vaba.u8 (arm-32-linux) vaba.s16 (arm-32-linux) vaba.u16 (arm-32-linux) vaba.s32 (arm-32-linux) vaba.u32 (arm-32-linux) vabal.s8 (arm-32-linux) vabal.u8 (arm-32-linux) vabal.s16 (arm-32-linux) vabal.u16 (arm-32-linux) vabal.s32 (arm-32-linux) vabal.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabd.s8 (arm-32-linux) vabd.u8 (arm-32-linux) vabd.s16 (arm-32-linux) vabd.u16 (arm-32-linux) vabd.s32 (arm-32-linux) vabd.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabdl.s8 (arm-32-linux) vabdl.u8 (arm-32-linux) vabdl.s16 (arm-32-linux) vabdl.u16 (arm-32-linux) vabdl.s32 (arm-32-linux) vabdl.u32 (arm-32-linux) vabs.f32 (arm-32-linux) vabs.s32 (arm-32-linux) vabs.s16 (arm-32-linux) vabs.s8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i8 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i16 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.i32 (arm-32-linux) vadd.f32 (arm-32-linux) vadd.i64 (arm-32-linux) vadd.i64 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i16 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i32 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddhn.i64 (arm-32-linux) vaddl.s8 (arm-32-linux) vaddl.u8 (arm-32-linux) vaddl.s16 (arm-32-linux) vaddl.u16 (arm-32-linux) vaddl.s32 (arm-32-linux) vaddl.u32 (arm-32-linux) vaddw.s8 (arm-32-linux) vaddw.u8 (arm-32-linux) vaddw.s16 (arm-32-linux) vaddw.u16 (arm-32-linux) vaddw.s32 (arm-32-linux) vaddw.u32 (arm-32-linux) vbsl (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i8 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i16 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.i32 (arm-32-linux) vceq.f32 (arm-32-linux) vcgt.s8 (arm-32-linux) vcgt.u8 (arm-32-linux) vcgt.s16 (arm-32-linux) vcgt.u16 (arm-32-linux) vcgt.s32 (arm-32-linux) vcgt.u32 (arm-32-linux) vcgt.f32 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i8 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i16 (arm-32-linux) vclz.i32 (arm-32-linux) vclz.i32 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcnt.8 (arm-32-linux) vcvt.f32.u32 (arm-32-linux) vcvt.f32.s32 (arm-32-linux) vcvt.u32.f32 (arm-32-linux) vcvt.s32.f32 (arm-32-linux) vdiv.f32 (arm-32-linux) vdiv.f64 (arm-32-linux) vdup.8 (arm-32-linux) vdup.8 (arm-32-linux) vdup.16 (arm-32-linux) vdup.16 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vdup.32 (arm-32-linux) vhadd.s8 (arm-32-linux) vhadd.u8 (arm-32-linux) vhadd.s16 (arm-32-linux) vhadd.u16 (arm-32-linux) vhadd.s32 (arm-32-linux) vhadd.u32 (arm-32-linux) vhadd.s32 (arm-32-linux) vhsub.s8 (arm-32-linux) vhsub.u8 (arm-32-linux) vhsub.s16 (arm-32-linux) vhsub.u16 (arm-32-linux) vhsub.s32 (arm-32-linux) vhsub.u32 (arm-32-linux) vhsub.s32 (arm-32-linux) vld1.8 (arm-32-linux) vld1.8 (arm-32-linux) vld1.16 (arm-32-linux) vld1.16 (arm-32-linux) vld1.32 (arm-32-linux) vld1.32 (arm-32-linux) vld1.32 (arm-32-linux) vld2.8 (arm-32-linux) vld2.8 (arm-32-linux) vld2.16 (arm-32-linux) vld2.16 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld2.32 (arm-32-linux) vld3.8 (arm-32-linux) vld3.8 (arm-32-linux) vld3.16 (arm-32-linux) vld3.16 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld3.32 (arm-32-linux) vld4.8 (arm-32-linux) vld4.8 (arm-32-linux) vld4.16 (arm-32-linux) vld4.16 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vld4.32 (arm-32-linux) vmax.s8 (arm-32-linux) vmax.u8 (arm-32-linux) vmax.s16 (arm-32-linux) vmax.u16 (arm-32-linux) vmax.s32 (arm-32-linux) vmax.u32 (arm-32-linux) vmax.f32 (arm-32-linux) vmin.s8 (arm-32-linux) vmin.u8 (arm-32-linux) vmin.s16 (arm-32-linux) vmin.u16 (arm-32-linux) vmin.s32 (arm-32-linux) vmin.u32 (arm-32-linux) vmin.f32 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i8 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i16 (arm-32-linux) vmla.i32 (arm-32-linux) vmla.i32 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i8 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i16 (arm-32-linux) vmls.i32 (arm-32-linux) vmls.i32 (arm-32-linux) vmlal.s8 (arm-32-linux) vmlal.u8 (arm-32-linux) vmlal.s16 (arm-32-linux) vmlal.u16 (arm-32-linux) vmlal.s32 (arm-32-linux) vmlal.u32 (arm-32-linux) vmlsl.s8 (arm-32-linux) vmlsl.u8 (arm-32-linux) vmlsl.s16 (arm-32-linux) vmlsl.u16 (arm-32-linux) vmlsl.s32 (arm-32-linux) vmlsl.u32 (arm-32-linux) vmovl.s8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.u8 (arm-32-linux) vmovl.s16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.u16 (arm-32-linux) vmovl.s32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovl.u32 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i16 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i32 (arm-32-linux) vmovn.i64 (arm-32-linux) vmovn.i64 (arm-32-linux) vmul.f64 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i8 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i16 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.i32 (arm-32-linux) vmul.f32 (arm-32-linux) vmull.s8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.s16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.s32 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u8 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u16 (arm-32-linux) vmull.u32 (arm-32-linux) vmull.u32 (arm-32-linux) vneg.s8 (arm-32-linux) vneg.s16 (arm-32-linux) vneg.s32 (arm-32-linux) vneg.f32 (arm-32-linux) vneg.f64 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpadal.s8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.u8 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i8 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i16 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.i32 (arm-32-linux) vpadd.f32 (arm-32-linux) vadd.f64 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.s32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.u32 (arm-32-linux) vpaddl.s8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.u8 (arm-32-linux) vpaddl.s16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpaddl.u16 (arm-32-linux) vpadal.s16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.u16 (arm-32-linux) vpadal.s32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpadal.u32 (arm-32-linux) vpmax.s8 (arm-32-linux) vpmax.u8 (arm-32-linux) vpmax.s16 (arm-32-linux) vpmax.u16 (arm-32-linux) vpmax.s32 (arm-32-linux) vpmax.u32 (arm-32-linux) vpmin.s8 (arm-32-linux) vpmin.u8 (arm-32-linux) vpmin.s16 (arm-32-linux) vpmin.u16 (arm-32-linux) vpmin.s32 (arm-32-linux) vpmin.u32 (arm-32-linux) vqadd.s8 (arm-32-linux) vqadd.s16 (arm-32-linux) vqadd.s32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqadd.u8 (arm-32-linux) vqadd.u16 (arm-32-linux) vqadd.u32 (arm-32-linux) vqdmulh.s16 (arm-32-linux) vqdmulh.s32 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovn.s64 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u16 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u32 (arm-32-linux) vqmovn.u64 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s16 (arm-32-linux) vqmovn.s32 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqmovun.s64 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s16 (arm-32-linux) vqmovun.s32 (arm-32-linux) vqneg.s8 (arm-32-linux) vqneg.s16 (arm-32-linux) vqneg.s32 (arm-32-linux) vqrdmulh.s16 (arm-32-linux) vqrdmulh.s32 (arm-32-linux) vqrshrn.s16 (arm-32-linux) vqrshrn.s32 (arm-32-linux) vqrshrn.s64 (arm-32-linux) vqrshrun.s16 (arm-32-linux) vqrshrun.s32 (arm-32-linux) vqrshrun.s64 (arm-32-linux) vqrshrn.u16 (arm-32-linux) vqrshrn.u32 (arm-32-linux) vqshl.s8 (arm-32-linux) vqshl.s16 (arm-32-linux) vqshl.s32 (arm-32-linux) vqshl.u8 (arm-32-linux) vqshl.u16 (arm-32-linux) vqshl.u32 (arm-32-linux) vqshlu.s8 (arm-32-linux) vqshlu.s16 (arm-32-linux) vqshlu.s32 (arm-32-linux) vqshrn.s16 (arm-32-linux) vqshrn.s32 (arm-32-linux) vqshrn.s64 (arm-32-linux) vqshrun.s16 (arm-32-linux) vqshrun.s32 (arm-32-linux) vqshrun.s64 (arm-32-linux) vqshrn.u16 (arm-32-linux) vqshrn.u32 (arm-32-linux) vqshrn.u64 (arm-32-linux) vqsub.s8 (arm-32-linux) vqsub.s16 (arm-32-linux) vqsub.s32 (arm-32-linux) vqsub.u8 (arm-32-linux) vqsub.u16 (arm-32-linux) vqsub.u32 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i16 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i32 (arm-32-linux) vraddhn.i64 (arm-32-linux) vrecpe.f32 (arm-32-linux) vrecps.f32 (arm-32-linux) vrhadd.s8 (arm-32-linux) vrhadd.u8 (arm-32-linux) vrhadd.s16 (arm-32-linux) vrhadd.u16 (arm-32-linux) vrhadd.s32 (arm-32-linux) vrhadd.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshl.s8 (arm-32-linux) vrshl.s16 (arm-32-linux) vrshl.s32 (arm-32-linux) vrshl.u8 (arm-32-linux) vrshl.u16 (arm-32-linux) vrshl.u32 (arm-32-linux) vrshr.s8 (arm-32-linux) vrshr.s16 (arm-32-linux) vrshr.s32 (arm-32-linux) vrshr.u8 (arm-32-linux) vrshr.u16 (arm-32-linux) vrshr.u32 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrshrn.i64 (arm-32-linux) vrshrn.i16 (arm-32-linux) vrshrn.i32 (arm-32-linux) vrsqrte.f32 (arm-32-linux) vrsqrts.f32 (arm-32-linux) vrsra.s8 (arm-32-linux) vrsra.s16 (arm-32-linux) vrsra.s32 (arm-32-linux) vrsra.u8 (arm-32-linux) vrsra.u16 (arm-32-linux) vrsra.u32 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i16 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i32 (arm-32-linux) vrsubhn.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.i8 (arm-32-linux) vshl.i16 (arm-32-linux) vshl.i32 (arm-32-linux) vshl.i64 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s8 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s16 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s32 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.s64 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u8 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u16 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u32 (arm-32-linux) vshl.u64 (arm-32-linux) vshl.u64 (arm-32-linux) vshll.s8 (arm-32-linux) vshll.s16 (arm-32-linux) vshll.s32 (arm-32-linux) vshll.u8 (arm-32-linux) vshll.u16 (arm-32-linux) vshll.u32 (arm-32-linux) vshr.s8 (arm-32-linux) vshr.s16 (arm-32-linux) vshr.s32 (arm-32-linux) vshr.s64 (arm-32-linux) vshr.u8 (arm-32-linux) vshr.u16 (arm-32-linux) vshr.u32 (arm-32-linux) vshr.u64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vshrn.i16 (arm-32-linux) vshrn.i32 (arm-32-linux) vshrn.i64 (arm-32-linux) vsqrt.f32 (arm-32-linux) vsqrt.f64 (arm-32-linux) vsra.s8 (arm-32-linux) vsra.s16 (arm-32-linux) vsra.s32 (arm-32-linux) vsra.s64 (arm-32-linux) vsra.u8 (arm-32-linux) vsra.u16 (arm-32-linux) vsra.u32 (arm-32-linux) vsra.u64 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i8 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i16 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i32 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.i64 (arm-32-linux) vsub.f32 (arm-32-linux) vsub.f32 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i16 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i32 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubhn.i64 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubl.s8 (arm-32-linux) vsubl.u8 (arm-32-linux) vsubl.s16 (arm-32-linux) vsubl.u16 (arm-32-linux) vsubl.s32 (arm-32-linux) vsubl.u32 (arm-32-linux) vsubw.s8 (arm-32-linux) vsubw.u8 (arm-32-linux) vsubw.s16 (arm-32-linux) vsubw.u16 (arm-32-linux) vsubw.s32 (arm-32-linux) vsubw.u32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst2.8 (arm-32-linux) vst2.16 (arm-32-linux) vst2.32 (arm-32-linux) vst3.8 (arm-32-linux) vst3.16 (arm-32-linux) vst3.32 (arm-32-linux) vst3.8 (arm-32-linux) vst3.16 (arm-32-linux) vst3.32 (arm-32-linux) vst3.8 (arm-32-linux) vst3.16 (arm-32-linux) vst3.32 (arm-32-linux) vst3.8 (arm-32-linux) vst3.16 (arm-32-linux) vst3.32 (arm-32-linux) vst3.8 (arm-32-linux) vst3.16 (arm-32-linux) vst3.32 (arm-32-linux) vst3.8 (arm-32-linux) vst3.16 (arm-32-linux) vst3.32 (arm-32-linux) vst4.8 (arm-32-linux) vst4.16 (arm-32-linux) vst4.32 (arm-32-linux) vst4.8 (arm-32-linux) vst4.16 (arm-32-linux) vst4.32 (arm-32-linux) vst4.8 (arm-32-linux) vst4.16 (arm-32-linux) vst4.32 (arm-32-linux) vst4.8 (arm-32-linux) vst4.16 (arm-32-linux) vst4.32 (arm-32-linux) vst4.8 (arm-32-linux) vst4.16 (arm-32-linux) vst4.32 (arm-32-linux) vst4.8 (arm-32-linux) vst4.16 (arm-32-linux) vst4.32 (arm-32-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) fabs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) fadd (arm-64-linux) add (arm-64-linux) add (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) bsl (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) fcmeq (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) fcmgt (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) ucvtf (arm-64-linux) scvtf (arm-64-linux) fcvtzu (arm-64-linux) fcvtzs (arm-64-linux) fdiv (arm-64-linux) fdiv (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) fmax (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) fmin (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) fmla (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) fmls (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) xtn (arm-64-linux) xtn (arm-64-linux) xtn (arm-64-linux) xtn (arm-64-linux) xtn (arm-64-linux) xtn (arm-64-linux) fmul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) fmul (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) fneg (arm-64-linux) fneg (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp* (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) sqdmulh (arm-64-linux) sqdmulh (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqrdmulh (arm-64-linux) sqrdmulh (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) uqrshrn (arm-64-linux) uqrshrn (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) frecpe (arm-64-linux) frecps (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) rshrn (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) frsqrte (arm-64-linux) frsqrts (arm-64-linux) Warning: In function test_op_frintn_406, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux) frintn (arm-64-linux) frintn (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) fsqrt (arm-64-linux) fsqrt (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) fsub (arm-64-linux) fsub (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) fabs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) fadd (arm-64-linux) add (arm-64-linux) add (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) bsl (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) fcmeq (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) fcmgt (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) ucvtf (arm-64-linux) scvtf (arm-64-linux) fcvtzu (arm-64-linux) fcvtzs (arm-64-linux) fdiv (arm-64-linux) fdiv (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) fmax (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) fmin (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) fmla (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) fmls (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) fmul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) fmul (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) fneg (arm-64-linux) fneg (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp* (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) sqdmulh (arm-64-linux) sqdmulh (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqrdmulh (arm-64-linux) sqrdmulh (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) uqrshrn (arm-64-linux) uqrshrn (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) frecpe (arm-64-linux) frecps (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) rshrn (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) frsqrte (arm-64-linux) frsqrts (arm-64-linux) Warning: In function test_op_frintn_923, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux) frintn (arm-64-linux) frintn (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) fsqrt (arm-64-linux) fsqrt (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) fsub (arm-64-linux) fsub (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) fabs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) fadd (arm-64-linux) add (arm-64-linux) add (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) bsl (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) fcmeq (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) fcmgt (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) ucvtf (arm-64-linux) scvtf (arm-64-linux) fcvtzu (arm-64-linux) fcvtzs (arm-64-linux) fdiv (arm-64-linux) fdiv (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) fmax (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) fmin (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) fmul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) fmul (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) fneg (arm-64-linux) fneg (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp* (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) sqdmulh (arm-64-linux) sqdmulh (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqrdmulh (arm-64-linux) sqrdmulh (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) uqrshrn (arm-64-linux) uqrshrn (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) frecpe (arm-64-linux) frecps (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) rshrn (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) frsqrte (arm-64-linux) frsqrts (arm-64-linux) Warning: In function test_op_frintn_1438, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux) frintn (arm-64-linux) frintn (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) fsqrt (arm-64-linux) fsqrt (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) fsub (arm-64-linux) fsub (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) saba (arm-64-linux) uaba (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabal (arm-64-linux) uabal (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabd (arm-64-linux) uabd (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) sabdl (arm-64-linux) uabdl (arm-64-linux) fabs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) abs (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) add (arm-64-linux) fadd (arm-64-linux) add (arm-64-linux) add (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) addhn (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddl (arm-64-linux) uaddl (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) saddw (arm-64-linux) uaddw (arm-64-linux) bsl (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) cmeq (arm-64-linux) fcmeq (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) cmgt (arm-64-linux) cmhi (arm-64-linux) fcmgt (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) clz (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) cnt (arm-64-linux) ucvtf (arm-64-linux) scvtf (arm-64-linux) fcvtzu (arm-64-linux) fcvtzs (arm-64-linux) fdiv (arm-64-linux) fdiv (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) dup (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) uhadd (arm-64-linux) shadd (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) uhsub (arm-64-linux) shsub (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ldr (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld2 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld3 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) ld4 (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) smax (arm-64-linux) umax (arm-64-linux) fmax (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) smin (arm-64-linux) umin (arm-64-linux) fmin (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mla (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) mls (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlal (arm-64-linux) umlal (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) smlsl (arm-64-linux) umlsl (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) uzp1 (arm-64-linux) fmul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) mul (arm-64-linux) fmul (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) smull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) umull (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) neg (arm-64-linux) fneg (arm-64-linux) fneg (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp* (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) addp (arm-64-linux) faddp (arm-64-linux) faddp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) saddlp (arm-64-linux) uaddlp (arm-64-linux) uaddlp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) sadalp (arm-64-linux) uadalp (arm-64-linux) uadalp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) smaxp (arm-64-linux) umaxp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sminp (arm-64-linux) uminp (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) sqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) uqadd (arm-64-linux) sqdmulh (arm-64-linux) sqdmulh (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) uqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtn (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqxtun (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqneg (arm-64-linux) sqrdmulh (arm-64-linux) sqrdmulh (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrn (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) sqrshrun (arm-64-linux) uqrshrn (arm-64-linux) uqrshrn (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) sqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) uqshl (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshlu (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrn (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) sqshrun (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) uqshrn (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) sqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) uqsub (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) raddhn (arm-64-linux) frecpe (arm-64-linux) frecps (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srhadd (arm-64-linux) urhadd (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) srshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) urshl (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) srshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) urshr (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) rshrn (arm-64-linux) raddhn (arm-64-linux) rshrn (arm-64-linux) frsqrte (arm-64-linux) frsqrts (arm-64-linux) Warning: In function test_op_frintn_1953, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux) frintn (arm-64-linux) frintn (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) srsra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) ursra (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) rsubhn (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) shl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) sshl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) ushl (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) sshll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) ushll (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) sshr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) ushr (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) shrn (arm-64-linux) fsqrt (arm-64-linux) fsqrt (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) ssra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) usra (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) sub (arm-64-linux) fsub (arm-64-linux) fsub (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) subhn (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubl (arm-64-linux) usubl (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) ssubw (arm-64-linux) usubw (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st2 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st3 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) st4 (arm-64-linux) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) fabs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) fadd (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) bsl (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) fcmeq (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) fcmgt (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) ucvtf (arm-64-linux-arm_dot_prod) scvtf (arm-64-linux-arm_dot_prod) fcvtzu (arm-64-linux-arm_dot_prod) fcvtzs (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) fmax (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) fmin (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) fmla (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) fmls (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) xtn (arm-64-linux-arm_dot_prod) xtn (arm-64-linux-arm_dot_prod) xtn (arm-64-linux-arm_dot_prod) xtn (arm-64-linux-arm_dot_prod) xtn (arm-64-linux-arm_dot_prod) xtn (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp* (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) frecpe (arm-64-linux-arm_dot_prod) frecps (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) frsqrte (arm-64-linux-arm_dot_prod) frsqrts (arm-64-linux-arm_dot_prod) Warning: In function test_op_frintn_418, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) fabs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) fadd (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) bsl (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) fcmeq (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) fcmgt (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) ucvtf (arm-64-linux-arm_dot_prod) scvtf (arm-64-linux-arm_dot_prod) fcvtzu (arm-64-linux-arm_dot_prod) fcvtzs (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) fmax (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) fmin (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) fmla (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) fmls (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp* (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) frecpe (arm-64-linux-arm_dot_prod) frecps (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) frsqrte (arm-64-linux-arm_dot_prod) frsqrts (arm-64-linux-arm_dot_prod) Warning: In function test_op_frintn_947, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) fabs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) fadd (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) bsl (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) fcmeq (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) fcmgt (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) ucvtf (arm-64-linux-arm_dot_prod) scvtf (arm-64-linux-arm_dot_prod) fcvtzu (arm-64-linux-arm_dot_prod) fcvtzs (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) fmax (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) fmin (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp* (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) frecpe (arm-64-linux-arm_dot_prod) frecps (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) frsqrte (arm-64-linux-arm_dot_prod) frsqrts (arm-64-linux-arm_dot_prod) Warning: In function test_op_frintn_1474, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) saba (arm-64-linux-arm_dot_prod) uaba (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabal (arm-64-linux-arm_dot_prod) uabal (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabd (arm-64-linux-arm_dot_prod) uabd (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) sabdl (arm-64-linux-arm_dot_prod) uabdl (arm-64-linux-arm_dot_prod) fabs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) abs (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) fadd (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) add (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) addhn (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddl (arm-64-linux-arm_dot_prod) uaddl (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) saddw (arm-64-linux-arm_dot_prod) uaddw (arm-64-linux-arm_dot_prod) bsl (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) cmeq (arm-64-linux-arm_dot_prod) fcmeq (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) cmgt (arm-64-linux-arm_dot_prod) cmhi (arm-64-linux-arm_dot_prod) fcmgt (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) clz (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) cnt (arm-64-linux-arm_dot_prod) ucvtf (arm-64-linux-arm_dot_prod) scvtf (arm-64-linux-arm_dot_prod) fcvtzu (arm-64-linux-arm_dot_prod) fcvtzs (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) fdiv (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) dup (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) uhadd (arm-64-linux-arm_dot_prod) shadd (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) uhsub (arm-64-linux-arm_dot_prod) shsub (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ldr (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld2 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld3 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) ld4 (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) smax (arm-64-linux-arm_dot_prod) umax (arm-64-linux-arm_dot_prod) fmax (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) smin (arm-64-linux-arm_dot_prod) umin (arm-64-linux-arm_dot_prod) fmin (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mla (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) mls (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlal (arm-64-linux-arm_dot_prod) umlal (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) smlsl (arm-64-linux-arm_dot_prod) umlsl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) uzp1 (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) mul (arm-64-linux-arm_dot_prod) fmul (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) smull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) umull (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) neg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) fneg (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp* (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) addp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) faddp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) saddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) uaddlp (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) uadalp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) smaxp (arm-64-linux-arm_dot_prod) umaxp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) sminp (arm-64-linux-arm_dot_prod) uminp (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) udot (arm-64-linux-arm_dot_prod) sdot (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) sqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) uqadd (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqdmulh (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) uqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtn (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqxtun (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqneg (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrdmulh (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrn (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) sqrshrun (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) uqrshrn (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) sqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) uqshl (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshlu (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrn (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) sqshrun (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) uqshrn (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) sqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) uqsub (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) frecpe (arm-64-linux-arm_dot_prod) frecps (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srhadd (arm-64-linux-arm_dot_prod) urhadd (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) srshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) urshl (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) srshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) urshr (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) raddhn (arm-64-linux-arm_dot_prod) rshrn (arm-64-linux-arm_dot_prod) frsqrte (arm-64-linux-arm_dot_prod) frsqrts (arm-64-linux-arm_dot_prod) Warning: In function test_op_frintn_2001, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) frintn (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) srsra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) ursra (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) rsubhn (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) shl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) sshl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) ushl (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) sshll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) ushll (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) sshr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) ushr (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) shrn (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) fsqrt (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) ssra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) usra (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) sub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) fsub (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) subhn (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubl (arm-64-linux-arm_dot_prod) usubl (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) ssubw (arm-64-linux-arm_dot_prod) usubw (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st2 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st3 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) st4 (arm-64-linux-arm_dot_prod) Success! ======================================== ======================================== correctness_simd_op_check_hvx.exe host is: target(x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41) simd_op_check test seed: 1680899556 valign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128) vlalign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128) vlalign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.h = vadd(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vadd(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.w = vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.uw,v*.uw):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*:*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*:*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.w = vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.uw,v*:*.uw):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128) vavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vavg(v*.ub,v*.ub):rnd (hexagon-32-noos-hvx-hvx_128) vavg(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vavg(v*.uh,v*.uh):rnd (hexagon-32-noos-hvx-hvx_128) vavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vavg(v*.h,v*.h):rnd (hexagon-32-noos-hvx-hvx_128) vavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vavg(v*.w,v*.w):rnd (hexagon-32-noos-hvx-hvx_128) vnavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vnavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vnavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h,r*):sat (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) v*.h = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) v*.ub = vsat(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.uh = vsat(v*.uw, v*.uw) (hexagon-32-noos-hvx-hvx_128) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vround(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) v*.ub = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.b = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.uw,v*.uw,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vmax(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vmax(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmax(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmax(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vmin(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vmin(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmin(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmin(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vnot(v*) (hexagon-32-noos-hvx-hvx_128) vnot(v*) (hexagon-32-noos-hvx-hvx_128) vnot(v*) (hexagon-32-noos-hvx-hvx_128) vsplat(r*) (hexagon-32-noos-hvx-hvx_128) vsplat(r*) (hexagon-32-noos-hvx-hvx_128) vsplat(r*) (hexagon-32-noos-hvx-hvx_128) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128) vabs(v*.h) (hexagon-32-noos-hvx-hvx_128) vabs(v*.w) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyio(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpyieo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.uh += vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h += vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vcl0(v*.uh) (hexagon-32-noos-hvx-hvx_128) vcl0(v*.uw) (hexagon-32-noos-hvx-hvx_128) vnormamt(v*.h) (hexagon-32-noos-hvx-hvx_128) vnormamt(v*.w) (hexagon-32-noos-hvx-hvx_128) vpopcount(v*.h) (hexagon-32-noos-hvx-hvx_128) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w = vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128) v*.h += vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h = vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.h += vtmpy(v*:*.b, r*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.h += vtmpy(v*:*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.w += vtmpy(v*:*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128) vlalign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128) vlalign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.h = vadd(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vadd(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.w = vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*.uw,v*.uw):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*:*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*:*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.w = vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128) vadd(v*:*.uw,v*:*.uw):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128) vsub(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128) vavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vavg(v*.ub,v*.ub):rnd (hexagon-32-noos-hvx-hvx_128) vavg(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vavg(v*.uh,v*.uh):rnd (hexagon-32-noos-hvx-hvx_128) vavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vavg(v*.h,v*.h):rnd (hexagon-32-noos-hvx-hvx_128) vavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vavg(v*.w,v*.w):rnd (hexagon-32-noos-hvx-hvx_128) vnavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vnavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vnavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h,r*):sat (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) v*.h = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128) v*.ub = vsat(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) v*.uh = vsat(v*.uw, v*.uw) (hexagon-32-noos-hvx-hvx_128) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vround(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vround(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) v*.ub = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.b = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) v*.uh = vasr(v*.uw,v*.uw,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128) vmax(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vmax(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmax(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmax(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vmin(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vmin(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmin(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmin(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vabsdiff(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128) vnot(v*) (hexagon-32-noos-hvx-hvx_128) vnot(v*) (hexagon-32-noos-hvx-hvx_128) vnot(v*) (hexagon-32-noos-hvx-hvx_128) vsplat(r*) (hexagon-32-noos-hvx-hvx_128) vsplat(r*) (hexagon-32-noos-hvx-hvx_128) vsplat(r*) (hexagon-32-noos-hvx-hvx_128) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128) vabs(v*.h) (hexagon-32-noos-hvx-hvx_128) vabs(v*.w) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyio(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpyieo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.uh += vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h += vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h += vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128) vcl0(v*.uh) (hexagon-32-noos-hvx-hvx_128) vcl0(v*.uw) (hexagon-32-noos-hvx-hvx_128) vnormamt(v*.h) (hexagon-32-noos-hvx-hvx_128) vnormamt(v*.w) (hexagon-32-noos-hvx-hvx_128) vpopcount(v*.h) (hexagon-32-noos-hvx-hvx_128) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w = vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w = vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128) v*.h += vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.h = vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.h += vtmpy(v*:*.b, r*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.h += vtmpy(v*:*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128) v*:*.w += vtmpy(v*:*.h, r*.b) (hexagon-32-noos-hvx-hvx_128) valign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlalign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128-hvx_v62) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) valign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlalign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128-hvx_v62) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vadd(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vadd(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*.uw,v*.uw):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vadd(v*:*.uw,v*:*.uw):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsub(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.ub,v*.ub):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.uh,v*.uh):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.h,v*.h):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vavg(v*.w,v*.w):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,v*.h,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.w,v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.ub = vsat(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh = vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh = vsat(v*.uw, v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vround(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.ub = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.b = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh = vasr(v*.uw,v*.uw,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmax(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmax(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmax(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmax(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmin(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmin(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmin(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmin(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vabsdiff(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vabsdiff(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vabsdiff(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vabsdiff(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vabs(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vabs(v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyio(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyieo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh += vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcl0(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vcl0(v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnormamt(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vnormamt(v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v62) vpopcount(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw = vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h += vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.h = vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.h += vtmpy(v*:*.b, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.h += vtmpy(v*:*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) v*:*.w += vtmpy(v*:*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v62) valign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlalign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128-hvx_v65) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) valign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlalign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128-hvx_v65) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vadd(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vadd(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*.uw,v*.uw):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vadd(v*:*.uw,v*:*.uw):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsub(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.ub,v*.ub):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.uh,v*.uh):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.h,v*.h):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.w,v*.w):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.b,v*.b):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vavg(v*.uw,v*.uw):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnavg(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,v*.h,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.w,v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.ub = vsat(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh = vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh = vsat(v*.uw, v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vround(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.ub = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.b = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.ub = vasr(v*.uh,v*.uh,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh = vasr(v*.uw,v*.uw,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmax(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmax(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmax(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmax(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmin(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmin(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmin(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmin(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vabsdiff(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vabsdiff(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vabsdiff(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vabsdiff(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vabs(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vabs(v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vabs(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyio(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyieo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh += vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcl0(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vcl0(v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnormamt(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vnormamt(v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v65) vpopcount(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw = vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h += vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.h = vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.h += vtmpy(v*:*.b, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.h += vtmpy(v*:*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) v*:*.w += vtmpy(v*:*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v65) valign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlalign(v*,v*,#7) (hexagon-32-noos-hvx-hvx_128-hvx_v66) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) valign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlalign(v*,v*,#6) (hexagon-32-noos-hvx-hvx_128-hvx_v66) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) valign(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vunpack(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vadd(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vadd(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vadd(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*.uw,v*.uw):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.h = vsub(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.w = vsub(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vsub(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.ub,v*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.uh,v*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vadd(v*:*.uw,v*:*.uw):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.b,v*:*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.h,v*:*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.w,v*:*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.ub,v*:*.ub):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.uh,v*:*.uh):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.h,v*:*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsub(v*:*.w,v*:*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.ub,v*.ub):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.uh,v*.uh):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.h,v*.h):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.w,v*.w):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnavg(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnavg(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnavg(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.b,v*.b):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vavg(v*.uw,v*.uw):rnd (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnavg(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,v*.h,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.w,v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.uh,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlsr(v*.uw,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffe(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuffo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacke(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpacko(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdeal(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdelta(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlut32(v*.b,v*.b,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vlut16(v*.b,v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vpack(v*.w,v*.w):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.ub = vsat(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh = vasr(v*.w,v*.w,r*):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.ub = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.b = vpack(v*.h,v*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vsat(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh = vsat(v*.uw, v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vround(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.ub = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.b = vasr(v*.h,v*.h,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.ub = vasr(v*.uh,v*.uh,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vasr(v*.w,v*.w,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh = vasr(v*.uw,v*.uw,r*):rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vshuff(v*,v*,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmax(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmax(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmax(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmax(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmin(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmin(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmin(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmin(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.gt(v*.uw,v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcmp.eq(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vabsdiff(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vabsdiff(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vabsdiff(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vabsdiff(v*.w,v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vand(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vxor(v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnot(v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vsplat(r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmux(q*,v*,v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vabs(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vabs(v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vabs(v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyio(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyie(v*.w,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyieo(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpyi(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpyi(v*.w,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh += vmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vmpy(v*.uh,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h,v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h, r*.h):sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uh += vmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vmpy(v*.uh,r*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpyi(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpy(v*.h,r*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpy(v*.h,r*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpyo(v*.w,v*.h):<<1:rnd:sat (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vmpa(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vdmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vdmpy(v*.h,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vmpa(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vasl(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vasr(v*.w,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vasl(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vasr(v*.h,r*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcl0(v*.uh) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vcl0(v*.uw) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnormamt(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vnormamt(v*.w) (hexagon-32-noos-hvx-hvx_128-hvx_v66) vpopcount(v*.h) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v* = vdelta(v*, v*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw = vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw = vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vrmpy(v*.ub,r*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.ub,r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.uw += vrmpy(v*.ub,v*.ub) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.ub,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vrmpy(v*.b,v*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.uw = vrmpy(v*:*.ub, r*.ub, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.w = vrmpy(v*:*.ub, r*.b, #*) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h += vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.h = vdmpy(v*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w += vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*.w = vdmpy(v*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.h += vtmpy(v*:*.b, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.h += vtmpy(v*:*.ub, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) v*:*.w += vtmpy(v*:*.h, r*.b) (hexagon-32-noos-hvx-hvx_128-hvx_v66) Success! ======================================== ======================================== correctness_simd_op_check_powerpc.exe host is: target(x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41) simd_op_check test seed: 1680899783 vaddsbs (powerpc-32-linux) vaddshs (powerpc-32-linux) vaddsws (powerpc-32-linux) vaddubm (powerpc-32-linux) vadduhm (powerpc-32-linux) vadduwm (powerpc-32-linux) vaddubs (powerpc-32-linux) vadduhs (powerpc-32-linux) vadduws (powerpc-32-linux) vsubsbs (powerpc-32-linux) vsubshs (powerpc-32-linux) vsubsws (powerpc-32-linux) vsububm (powerpc-32-linux) vsubuhm (powerpc-32-linux) vsubuwm (powerpc-32-linux) vsububs (powerpc-32-linux) vsubuhs (powerpc-32-linux) vsubuws (powerpc-32-linux) vavgsb (powerpc-32-linux) vavgub (powerpc-32-linux) vavgsh (powerpc-32-linux) vavguh (powerpc-32-linux) vavgsw (powerpc-32-linux) vavguw (powerpc-32-linux) vmaxsb (powerpc-32-linux) vmaxub (powerpc-32-linux) vmaxsh (powerpc-32-linux) vmaxuh (powerpc-32-linux) vmaxsw (powerpc-32-linux) vmaxuw (powerpc-32-linux) vminsb (powerpc-32-linux) vminub (powerpc-32-linux) vminsh (powerpc-32-linux) vminuh (powerpc-32-linux) vminsw (powerpc-32-linux) vminuw (powerpc-32-linux) vaddfp (powerpc-32-linux) vsubfp (powerpc-32-linux) vmaddfp (powerpc-32-linux) vmaxfp (powerpc-32-linux) vminfp (powerpc-32-linux) vaddsbs (powerpc-32-linux) vaddshs (powerpc-32-linux) vaddsws (powerpc-32-linux) vaddubm (powerpc-32-linux) vadduhm (powerpc-32-linux) vadduwm (powerpc-32-linux) vaddubs (powerpc-32-linux) vadduhs (powerpc-32-linux) vadduws (powerpc-32-linux) vsubsbs (powerpc-32-linux) vsubshs (powerpc-32-linux) vsubsws (powerpc-32-linux) vsububm (powerpc-32-linux) vsubuhm (powerpc-32-linux) vsubuwm (powerpc-32-linux) vsububs (powerpc-32-linux) vsubuhs (powerpc-32-linux) vsubuws (powerpc-32-linux) vavgsb (powerpc-32-linux) vavgub (powerpc-32-linux) vavgsh (powerpc-32-linux) vavguh (powerpc-32-linux) vavgsw (powerpc-32-linux) vavguw (powerpc-32-linux) vmaxsb (powerpc-32-linux) vmaxub (powerpc-32-linux) vmaxsh (powerpc-32-linux) vmaxuh (powerpc-32-linux) vmaxsw (powerpc-32-linux) vmaxuw (powerpc-32-linux) vminsb (powerpc-32-linux) vminub (powerpc-32-linux) vminsh (powerpc-32-linux) vminuh (powerpc-32-linux) vminsw (powerpc-32-linux) vminuw (powerpc-32-linux) vaddfp (powerpc-32-linux) vsubfp (powerpc-32-linux) vmaddfp (powerpc-32-linux) vmaxfp (powerpc-32-linux) vminfp (powerpc-32-linux) vaddsbs (powerpc-32-linux) vaddshs (powerpc-32-linux) vaddsws (powerpc-32-linux) vaddubm (powerpc-32-linux) vadduhm (powerpc-32-linux) vadduwm (powerpc-32-linux) vaddubs (powerpc-32-linux) vadduhs (powerpc-32-linux) vadduws (powerpc-32-linux) vsubsbs (powerpc-32-linux) vsubshs (powerpc-32-linux) vsubsws (powerpc-32-linux) vsububm (powerpc-32-linux) vsubuhm (powerpc-32-linux) vsubuwm (powerpc-32-linux) vsububs (powerpc-32-linux) vsubuhs (powerpc-32-linux) vsubuws (powerpc-32-linux) vavgsb (powerpc-32-linux) vavgub (powerpc-32-linux) vavgsh (powerpc-32-linux) vavguh (powerpc-32-linux) vavgsw (powerpc-32-linux) vavguw (powerpc-32-linux) vmaxsb (powerpc-32-linux) vmaxub (powerpc-32-linux) vmaxsh (powerpc-32-linux) vmaxuh (powerpc-32-linux) vmaxsw (powerpc-32-linux) vmaxuw (powerpc-32-linux) vminsb (powerpc-32-linux) vminub (powerpc-32-linux) vminsh (powerpc-32-linux) vminuh (powerpc-32-linux) vminsw (powerpc-32-linux) vminuw (powerpc-32-linux) vaddfp (powerpc-32-linux) vsubfp (powerpc-32-linux) vmaddfp (powerpc-32-linux) vmaxfp (powerpc-32-linux) vminfp (powerpc-32-linux) vaddsbs (powerpc-32-linux) vaddshs (powerpc-32-linux) vaddsws (powerpc-32-linux) vaddubm (powerpc-32-linux) vadduhm (powerpc-32-linux) vadduwm (powerpc-32-linux) vaddubs (powerpc-32-linux) vadduhs (powerpc-32-linux) vadduws (powerpc-32-linux) vsubsbs (powerpc-32-linux) vsubshs (powerpc-32-linux) vsubsws (powerpc-32-linux) vsububm (powerpc-32-linux) vsubuhm (powerpc-32-linux) vsubuwm (powerpc-32-linux) vsububs (powerpc-32-linux) vsubuhs (powerpc-32-linux) vsubuws (powerpc-32-linux) vavgsb (powerpc-32-linux) vavgub (powerpc-32-linux) vavgsh (powerpc-32-linux) vavguh (powerpc-32-linux) vavgsw (powerpc-32-linux) vavguw (powerpc-32-linux) vmaxsb (powerpc-32-linux) vmaxub (powerpc-32-linux) vmaxsh (powerpc-32-linux) vmaxuh (powerpc-32-linux) vmaxsw (powerpc-32-linux) vmaxuw (powerpc-32-linux) vminsb (powerpc-32-linux) vminub (powerpc-32-linux) vminsh (powerpc-32-linux) vminuh (powerpc-32-linux) vminsw (powerpc-32-linux) vminuw (powerpc-32-linux) vaddfp (powerpc-32-linux) vsubfp (powerpc-32-linux) vmaddfp (powerpc-32-linux) vmaxfp (powerpc-32-linux) vminfp (powerpc-32-linux) vaddsbs (powerpc-32-linux-vsx) vaddshs (powerpc-32-linux-vsx) vaddsws (powerpc-32-linux-vsx) vaddubm (powerpc-32-linux-vsx) vadduhm (powerpc-32-linux-vsx) vadduwm (powerpc-32-linux-vsx) vaddubs (powerpc-32-linux-vsx) vadduhs (powerpc-32-linux-vsx) vadduws (powerpc-32-linux-vsx) vsubsbs (powerpc-32-linux-vsx) vsubshs (powerpc-32-linux-vsx) vsubsws (powerpc-32-linux-vsx) vsububm (powerpc-32-linux-vsx) vsubuhm (powerpc-32-linux-vsx) vsubuwm (powerpc-32-linux-vsx) vsububs (powerpc-32-linux-vsx) vsubuhs (powerpc-32-linux-vsx) vsubuws (powerpc-32-linux-vsx) vavgsb (powerpc-32-linux-vsx) vavgub (powerpc-32-linux-vsx) vavgsh (powerpc-32-linux-vsx) vavguh (powerpc-32-linux-vsx) vavgsw (powerpc-32-linux-vsx) vavguw (powerpc-32-linux-vsx) vmaxsb (powerpc-32-linux-vsx) vmaxub (powerpc-32-linux-vsx) vmaxsh (powerpc-32-linux-vsx) vmaxuh (powerpc-32-linux-vsx) vmaxsw (powerpc-32-linux-vsx) vmaxuw (powerpc-32-linux-vsx) vminsb (powerpc-32-linux-vsx) vminub (powerpc-32-linux-vsx) vminsh (powerpc-32-linux-vsx) vminuh (powerpc-32-linux-vsx) vminsw (powerpc-32-linux-vsx) vminuw (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaddasp (powerpc-32-linux-vsx) vmaxfp (powerpc-32-linux-vsx) vminfp (powerpc-32-linux-vsx) vaddsbs (powerpc-32-linux-vsx) vaddshs (powerpc-32-linux-vsx) vaddsws (powerpc-32-linux-vsx) vaddubm (powerpc-32-linux-vsx) vadduhm (powerpc-32-linux-vsx) vadduwm (powerpc-32-linux-vsx) vaddubs (powerpc-32-linux-vsx) vadduhs (powerpc-32-linux-vsx) vadduws (powerpc-32-linux-vsx) vsubsbs (powerpc-32-linux-vsx) vsubshs (powerpc-32-linux-vsx) vsubsws (powerpc-32-linux-vsx) vsububm (powerpc-32-linux-vsx) vsubuhm (powerpc-32-linux-vsx) vsubuwm (powerpc-32-linux-vsx) vsububs (powerpc-32-linux-vsx) vsubuhs (powerpc-32-linux-vsx) vsubuws (powerpc-32-linux-vsx) vavgsb (powerpc-32-linux-vsx) vavgub (powerpc-32-linux-vsx) vavgsh (powerpc-32-linux-vsx) vavguh (powerpc-32-linux-vsx) vavgsw (powerpc-32-linux-vsx) vavguw (powerpc-32-linux-vsx) vmaxsb (powerpc-32-linux-vsx) vmaxub (powerpc-32-linux-vsx) vmaxsh (powerpc-32-linux-vsx) vmaxuh (powerpc-32-linux-vsx) vmaxsw (powerpc-32-linux-vsx) vmaxuw (powerpc-32-linux-vsx) vminsb (powerpc-32-linux-vsx) vminub (powerpc-32-linux-vsx) vminsh (powerpc-32-linux-vsx) vminuh (powerpc-32-linux-vsx) vminsw (powerpc-32-linux-vsx) vminuw (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaddasp (powerpc-32-linux-vsx) vmaxfp (powerpc-32-linux-vsx) vminfp (powerpc-32-linux-vsx) vaddsbs (powerpc-32-linux-vsx) vaddshs (powerpc-32-linux-vsx) vaddsws (powerpc-32-linux-vsx) vaddubm (powerpc-32-linux-vsx) vadduhm (powerpc-32-linux-vsx) vadduwm (powerpc-32-linux-vsx) vaddubs (powerpc-32-linux-vsx) vadduhs (powerpc-32-linux-vsx) vadduws (powerpc-32-linux-vsx) vsubsbs (powerpc-32-linux-vsx) vsubshs (powerpc-32-linux-vsx) vsubsws (powerpc-32-linux-vsx) vsububm (powerpc-32-linux-vsx) vsubuhm (powerpc-32-linux-vsx) vsubuwm (powerpc-32-linux-vsx) vsububs (powerpc-32-linux-vsx) vsubuhs (powerpc-32-linux-vsx) vsubuws (powerpc-32-linux-vsx) vavgsb (powerpc-32-linux-vsx) vavgub (powerpc-32-linux-vsx) vavgsh (powerpc-32-linux-vsx) vavguh (powerpc-32-linux-vsx) vavgsw (powerpc-32-linux-vsx) vavguw (powerpc-32-linux-vsx) vmaxsb (powerpc-32-linux-vsx) vmaxub (powerpc-32-linux-vsx) vmaxsh (powerpc-32-linux-vsx) vmaxuh (powerpc-32-linux-vsx) vmaxsw (powerpc-32-linux-vsx) vmaxuw (powerpc-32-linux-vsx) vminsb (powerpc-32-linux-vsx) vminub (powerpc-32-linux-vsx) vminsh (powerpc-32-linux-vsx) vminuh (powerpc-32-linux-vsx) vminsw (powerpc-32-linux-vsx) vminuw (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaddasp (powerpc-32-linux-vsx) vmaxfp (powerpc-32-linux-vsx) vminfp (powerpc-32-linux-vsx) vaddsbs (powerpc-32-linux-vsx) vaddshs (powerpc-32-linux-vsx) vaddsws (powerpc-32-linux-vsx) vaddubm (powerpc-32-linux-vsx) vadduhm (powerpc-32-linux-vsx) vadduwm (powerpc-32-linux-vsx) vaddubs (powerpc-32-linux-vsx) vadduhs (powerpc-32-linux-vsx) vadduws (powerpc-32-linux-vsx) vsubsbs (powerpc-32-linux-vsx) vsubshs (powerpc-32-linux-vsx) vsubsws (powerpc-32-linux-vsx) vsububm (powerpc-32-linux-vsx) vsubuhm (powerpc-32-linux-vsx) vsubuwm (powerpc-32-linux-vsx) vsububs (powerpc-32-linux-vsx) vsubuhs (powerpc-32-linux-vsx) vsubuws (powerpc-32-linux-vsx) vavgsb (powerpc-32-linux-vsx) vavgub (powerpc-32-linux-vsx) vavgsh (powerpc-32-linux-vsx) vavguh (powerpc-32-linux-vsx) vavgsw (powerpc-32-linux-vsx) vavguw (powerpc-32-linux-vsx) vmaxsb (powerpc-32-linux-vsx) vmaxub (powerpc-32-linux-vsx) vmaxsh (powerpc-32-linux-vsx) vmaxuh (powerpc-32-linux-vsx) vmaxsw (powerpc-32-linux-vsx) vmaxuw (powerpc-32-linux-vsx) vminsb (powerpc-32-linux-vsx) vminub (powerpc-32-linux-vsx) vminsh (powerpc-32-linux-vsx) vminuh (powerpc-32-linux-vsx) vminsw (powerpc-32-linux-vsx) vminuw (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaddasp (powerpc-32-linux-vsx) vmaxfp (powerpc-32-linux-vsx) vminfp (powerpc-32-linux-vsx) xvadddp (powerpc-32-linux-vsx) xvmuldp (powerpc-32-linux-vsx) xvsubdp (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvmulsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaxdp (powerpc-32-linux-vsx) xvmindp (powerpc-32-linux-vsx) xvadddp (powerpc-32-linux-vsx) xvmuldp (powerpc-32-linux-vsx) xvsubdp (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvmulsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaxdp (powerpc-32-linux-vsx) xvmindp (powerpc-32-linux-vsx) xvadddp (powerpc-32-linux-vsx) xvmuldp (powerpc-32-linux-vsx) xvsubdp (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvmulsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaxdp (powerpc-32-linux-vsx) xvmindp (powerpc-32-linux-vsx) xvadddp (powerpc-32-linux-vsx) xvmuldp (powerpc-32-linux-vsx) xvsubdp (powerpc-32-linux-vsx) xvaddsp (powerpc-32-linux-vsx) xvmulsp (powerpc-32-linux-vsx) xvsubsp (powerpc-32-linux-vsx) xvmaxdp (powerpc-32-linux-vsx) xvmindp (powerpc-32-linux-vsx) vaddsbs (powerpc-32-linux-power_arch_2_07) vaddshs (powerpc-32-linux-power_arch_2_07) vaddsws (powerpc-32-linux-power_arch_2_07) vaddubm (powerpc-32-linux-power_arch_2_07) vadduhm (powerpc-32-linux-power_arch_2_07) vadduwm (powerpc-32-linux-power_arch_2_07) vaddubs (powerpc-32-linux-power_arch_2_07) vadduhs (powerpc-32-linux-power_arch_2_07) vadduws (powerpc-32-linux-power_arch_2_07) vsubsbs (powerpc-32-linux-power_arch_2_07) vsubshs (powerpc-32-linux-power_arch_2_07) vsubsws (powerpc-32-linux-power_arch_2_07) vsububm (powerpc-32-linux-power_arch_2_07) vsubuhm (powerpc-32-linux-power_arch_2_07) vsubuwm (powerpc-32-linux-power_arch_2_07) vsububs (powerpc-32-linux-power_arch_2_07) vsubuhs (powerpc-32-linux-power_arch_2_07) vsubuws (powerpc-32-linux-power_arch_2_07) vavgsb (powerpc-32-linux-power_arch_2_07) vavgub (powerpc-32-linux-power_arch_2_07) vavgsh (powerpc-32-linux-power_arch_2_07) vavguh (powerpc-32-linux-power_arch_2_07) vavgsw (powerpc-32-linux-power_arch_2_07) vavguw (powerpc-32-linux-power_arch_2_07) vmaxsb (powerpc-32-linux-power_arch_2_07) vmaxub (powerpc-32-linux-power_arch_2_07) vmaxsh (powerpc-32-linux-power_arch_2_07) vmaxuh (powerpc-32-linux-power_arch_2_07) vmaxsw (powerpc-32-linux-power_arch_2_07) vmaxuw (powerpc-32-linux-power_arch_2_07) vminsb (powerpc-32-linux-power_arch_2_07) vminub (powerpc-32-linux-power_arch_2_07) vminsh (powerpc-32-linux-power_arch_2_07) vminuh (powerpc-32-linux-power_arch_2_07) vminsw (powerpc-32-linux-power_arch_2_07) vminuw (powerpc-32-linux-power_arch_2_07) xvaddsp (powerpc-32-linux-power_arch_2_07) xvsubsp (powerpc-32-linux-power_arch_2_07) xvmaddasp (powerpc-32-linux-power_arch_2_07) vmaxfp (powerpc-32-linux-power_arch_2_07) vminfp (powerpc-32-linux-power_arch_2_07) vaddsbs (powerpc-32-linux-power_arch_2_07) vaddshs (powerpc-32-linux-power_arch_2_07) vaddsws (powerpc-32-linux-power_arch_2_07) vaddubm (powerpc-32-linux-power_arch_2_07) vadduhm (powerpc-32-linux-power_arch_2_07) vadduwm (powerpc-32-linux-power_arch_2_07) vaddubs (powerpc-32-linux-power_arch_2_07) vadduhs (powerpc-32-linux-power_arch_2_07) vadduws (powerpc-32-linux-power_arch_2_07) vsubsbs (powerpc-32-linux-power_arch_2_07) vsubshs (powerpc-32-linux-power_arch_2_07) vsubsws (powerpc-32-linux-power_arch_2_07) vsububm (powerpc-32-linux-power_arch_2_07) vsubuhm (powerpc-32-linux-power_arch_2_07) vsubuwm (powerpc-32-linux-power_arch_2_07) vsububs (powerpc-32-linux-power_arch_2_07) vsubuhs (powerpc-32-linux-power_arch_2_07) vsubuws (powerpc-32-linux-power_arch_2_07) vavgsb (powerpc-32-linux-power_arch_2_07) vavgub (powerpc-32-linux-power_arch_2_07) vavgsh (powerpc-32-linux-power_arch_2_07) vavguh (powerpc-32-linux-power_arch_2_07) vavgsw (powerpc-32-linux-power_arch_2_07) vavguw (powerpc-32-linux-power_arch_2_07) vmaxsb (powerpc-32-linux-power_arch_2_07) vmaxub (powerpc-32-linux-power_arch_2_07) vmaxsh (powerpc-32-linux-power_arch_2_07) vmaxuh (powerpc-32-linux-power_arch_2_07) vmaxsw (powerpc-32-linux-power_arch_2_07) vmaxuw (powerpc-32-linux-power_arch_2_07) vminsb (powerpc-32-linux-power_arch_2_07) vminub (powerpc-32-linux-power_arch_2_07) vminsh (powerpc-32-linux-power_arch_2_07) vminuh (powerpc-32-linux-power_arch_2_07) vminsw (powerpc-32-linux-power_arch_2_07) vminuw (powerpc-32-linux-power_arch_2_07) xvaddsp (powerpc-32-linux-power_arch_2_07) xvsubsp (powerpc-32-linux-power_arch_2_07) xvmaddasp (powerpc-32-linux-power_arch_2_07) vmaxfp (powerpc-32-linux-power_arch_2_07) vminfp (powerpc-32-linux-power_arch_2_07) vaddsbs (powerpc-32-linux-power_arch_2_07) vaddshs (powerpc-32-linux-power_arch_2_07) vaddsws (powerpc-32-linux-power_arch_2_07) vaddubm (powerpc-32-linux-power_arch_2_07) vadduhm (powerpc-32-linux-power_arch_2_07) vadduwm (powerpc-32-linux-power_arch_2_07) vaddubs (powerpc-32-linux-power_arch_2_07) vadduhs (powerpc-32-linux-power_arch_2_07) vadduws (powerpc-32-linux-power_arch_2_07) vsubsbs (powerpc-32-linux-power_arch_2_07) vsubshs (powerpc-32-linux-power_arch_2_07) vsubsws (powerpc-32-linux-power_arch_2_07) vsububm (powerpc-32-linux-power_arch_2_07) vsubuhm (powerpc-32-linux-power_arch_2_07) vsubuwm (powerpc-32-linux-power_arch_2_07) vsububs (powerpc-32-linux-power_arch_2_07) vsubuhs (powerpc-32-linux-power_arch_2_07) vsubuws (powerpc-32-linux-power_arch_2_07) vavgsb (powerpc-32-linux-power_arch_2_07) vavgub (powerpc-32-linux-power_arch_2_07) vavgsh (powerpc-32-linux-power_arch_2_07) vavguh (powerpc-32-linux-power_arch_2_07) vavgsw (powerpc-32-linux-power_arch_2_07) vavguw (powerpc-32-linux-power_arch_2_07) vmaxsb (powerpc-32-linux-power_arch_2_07) vmaxub (powerpc-32-linux-power_arch_2_07) vmaxsh (powerpc-32-linux-power_arch_2_07) vmaxuh (powerpc-32-linux-power_arch_2_07) vmaxsw (powerpc-32-linux-power_arch_2_07) vmaxuw (powerpc-32-linux-power_arch_2_07) vminsb (powerpc-32-linux-power_arch_2_07) vminub (powerpc-32-linux-power_arch_2_07) vminsh (powerpc-32-linux-power_arch_2_07) vminuh (powerpc-32-linux-power_arch_2_07) vminsw (powerpc-32-linux-power_arch_2_07) vminuw (powerpc-32-linux-power_arch_2_07) xvaddsp (powerpc-32-linux-power_arch_2_07) xvsubsp (powerpc-32-linux-power_arch_2_07) xvmaddasp (powerpc-32-linux-power_arch_2_07) vmaxfp (powerpc-32-linux-power_arch_2_07) vminfp (powerpc-32-linux-power_arch_2_07) vaddsbs (powerpc-32-linux-power_arch_2_07) vaddshs (powerpc-32-linux-power_arch_2_07) vaddsws (powerpc-32-linux-power_arch_2_07) vaddubm (powerpc-32-linux-power_arch_2_07) vadduhm (powerpc-32-linux-power_arch_2_07) vadduwm (powerpc-32-linux-power_arch_2_07) vaddubs (powerpc-32-linux-power_arch_2_07) vadduhs (powerpc-32-linux-power_arch_2_07) vadduws (powerpc-32-linux-power_arch_2_07) vsubsbs (powerpc-32-linux-power_arch_2_07) vsubshs (powerpc-32-linux-power_arch_2_07) vsubsws (powerpc-32-linux-power_arch_2_07) vsububm (powerpc-32-linux-power_arch_2_07) vsubuhm (powerpc-32-linux-power_arch_2_07) vsubuwm (powerpc-32-linux-power_arch_2_07) vsububs (powerpc-32-linux-power_arch_2_07) vsubuhs (powerpc-32-linux-power_arch_2_07) vsubuws (powerpc-32-linux-power_arch_2_07) vavgsb (powerpc-32-linux-power_arch_2_07) vavgub (powerpc-32-linux-power_arch_2_07) vavgsh (powerpc-32-linux-power_arch_2_07) vavguh (powerpc-32-linux-power_arch_2_07) vavgsw (powerpc-32-linux-power_arch_2_07) vavguw (powerpc-32-linux-power_arch_2_07) vmaxsb (powerpc-32-linux-power_arch_2_07) vmaxub (powerpc-32-linux-power_arch_2_07) vmaxsh (powerpc-32-linux-power_arch_2_07) vmaxuh (powerpc-32-linux-power_arch_2_07) vmaxsw (powerpc-32-linux-power_arch_2_07) vmaxuw (powerpc-32-linux-power_arch_2_07) vminsb (powerpc-32-linux-power_arch_2_07) vminub (powerpc-32-linux-power_arch_2_07) vminsh (powerpc-32-linux-power_arch_2_07) vminuh (powerpc-32-linux-power_arch_2_07) vminsw (powerpc-32-linux-power_arch_2_07) vminuw (powerpc-32-linux-power_arch_2_07) xvaddsp (powerpc-32-linux-power_arch_2_07) xvsubsp (powerpc-32-linux-power_arch_2_07) xvmaddasp (powerpc-32-linux-power_arch_2_07) vmaxfp (powerpc-32-linux-power_arch_2_07) vminfp (powerpc-32-linux-power_arch_2_07) vaddudm (powerpc-32-linux-power_arch_2_07) vsubudm (powerpc-32-linux-power_arch_2_07) vmaxsd (powerpc-32-linux-power_arch_2_07) vmaxud (powerpc-32-linux-power_arch_2_07) vminsd (powerpc-32-linux-power_arch_2_07) vminud (powerpc-32-linux-power_arch_2_07) vaddudm (powerpc-32-linux-power_arch_2_07) vsubudm (powerpc-32-linux-power_arch_2_07) vmaxsd (powerpc-32-linux-power_arch_2_07) vmaxud (powerpc-32-linux-power_arch_2_07) vminsd (powerpc-32-linux-power_arch_2_07) vminud (powerpc-32-linux-power_arch_2_07) vaddudm (powerpc-32-linux-power_arch_2_07) vsubudm (powerpc-32-linux-power_arch_2_07) vmaxsd (powerpc-32-linux-power_arch_2_07) vmaxud (powerpc-32-linux-power_arch_2_07) vminsd (powerpc-32-linux-power_arch_2_07) vminud (powerpc-32-linux-power_arch_2_07) vaddudm (powerpc-32-linux-power_arch_2_07) vsubudm (powerpc-32-linux-power_arch_2_07) vmaxsd (powerpc-32-linux-power_arch_2_07) vmaxud (powerpc-32-linux-power_arch_2_07) vminsd (powerpc-32-linux-power_arch_2_07) vminud (powerpc-32-linux-power_arch_2_07) vaddsbs (powerpc-32-linux-power_arch_2_07-vsx) vaddshs (powerpc-32-linux-power_arch_2_07-vsx) vaddsws (powerpc-32-linux-power_arch_2_07-vsx) vaddubm (powerpc-32-linux-power_arch_2_07-vsx) vadduhm (powerpc-32-linux-power_arch_2_07-vsx) vadduwm (powerpc-32-linux-power_arch_2_07-vsx) vaddubs (powerpc-32-linux-power_arch_2_07-vsx) vadduhs (powerpc-32-linux-power_arch_2_07-vsx) vadduws (powerpc-32-linux-power_arch_2_07-vsx) vsubsbs (powerpc-32-linux-power_arch_2_07-vsx) vsubshs (powerpc-32-linux-power_arch_2_07-vsx) vsubsws (powerpc-32-linux-power_arch_2_07-vsx) vsububm (powerpc-32-linux-power_arch_2_07-vsx) vsubuhm (powerpc-32-linux-power_arch_2_07-vsx) vsubuwm (powerpc-32-linux-power_arch_2_07-vsx) vsububs (powerpc-32-linux-power_arch_2_07-vsx) vsubuhs (powerpc-32-linux-power_arch_2_07-vsx) vsubuws (powerpc-32-linux-power_arch_2_07-vsx) vavgsb (powerpc-32-linux-power_arch_2_07-vsx) vavgub (powerpc-32-linux-power_arch_2_07-vsx) vavgsh (powerpc-32-linux-power_arch_2_07-vsx) vavguh (powerpc-32-linux-power_arch_2_07-vsx) vavgsw (powerpc-32-linux-power_arch_2_07-vsx) vavguw (powerpc-32-linux-power_arch_2_07-vsx) vmaxsb (powerpc-32-linux-power_arch_2_07-vsx) vmaxub (powerpc-32-linux-power_arch_2_07-vsx) vmaxsh (powerpc-32-linux-power_arch_2_07-vsx) vmaxuh (powerpc-32-linux-power_arch_2_07-vsx) vmaxsw (powerpc-32-linux-power_arch_2_07-vsx) vmaxuw (powerpc-32-linux-power_arch_2_07-vsx) vminsb (powerpc-32-linux-power_arch_2_07-vsx) vminub (powerpc-32-linux-power_arch_2_07-vsx) vminsh (powerpc-32-linux-power_arch_2_07-vsx) vminuh (powerpc-32-linux-power_arch_2_07-vsx) vminsw (powerpc-32-linux-power_arch_2_07-vsx) vminuw (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-32-linux-power_arch_2_07-vsx) vmaxfp (powerpc-32-linux-power_arch_2_07-vsx) vminfp (powerpc-32-linux-power_arch_2_07-vsx) vaddsbs (powerpc-32-linux-power_arch_2_07-vsx) vaddshs (powerpc-32-linux-power_arch_2_07-vsx) vaddsws (powerpc-32-linux-power_arch_2_07-vsx) vaddubm (powerpc-32-linux-power_arch_2_07-vsx) vadduhm (powerpc-32-linux-power_arch_2_07-vsx) vadduwm (powerpc-32-linux-power_arch_2_07-vsx) vaddubs (powerpc-32-linux-power_arch_2_07-vsx) vadduhs (powerpc-32-linux-power_arch_2_07-vsx) vadduws (powerpc-32-linux-power_arch_2_07-vsx) vsubsbs (powerpc-32-linux-power_arch_2_07-vsx) vsubshs (powerpc-32-linux-power_arch_2_07-vsx) vsubsws (powerpc-32-linux-power_arch_2_07-vsx) vsububm (powerpc-32-linux-power_arch_2_07-vsx) vsubuhm (powerpc-32-linux-power_arch_2_07-vsx) vsubuwm (powerpc-32-linux-power_arch_2_07-vsx) vsububs (powerpc-32-linux-power_arch_2_07-vsx) vsubuhs (powerpc-32-linux-power_arch_2_07-vsx) vsubuws (powerpc-32-linux-power_arch_2_07-vsx) vavgsb (powerpc-32-linux-power_arch_2_07-vsx) vavgub (powerpc-32-linux-power_arch_2_07-vsx) vavgsh (powerpc-32-linux-power_arch_2_07-vsx) vavguh (powerpc-32-linux-power_arch_2_07-vsx) vavgsw (powerpc-32-linux-power_arch_2_07-vsx) vavguw (powerpc-32-linux-power_arch_2_07-vsx) vmaxsb (powerpc-32-linux-power_arch_2_07-vsx) vmaxub (powerpc-32-linux-power_arch_2_07-vsx) vmaxsh (powerpc-32-linux-power_arch_2_07-vsx) vmaxuh (powerpc-32-linux-power_arch_2_07-vsx) vmaxsw (powerpc-32-linux-power_arch_2_07-vsx) vmaxuw (powerpc-32-linux-power_arch_2_07-vsx) vminsb (powerpc-32-linux-power_arch_2_07-vsx) vminub (powerpc-32-linux-power_arch_2_07-vsx) vminsh (powerpc-32-linux-power_arch_2_07-vsx) vminuh (powerpc-32-linux-power_arch_2_07-vsx) vminsw (powerpc-32-linux-power_arch_2_07-vsx) vminuw (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-32-linux-power_arch_2_07-vsx) vmaxfp (powerpc-32-linux-power_arch_2_07-vsx) vminfp (powerpc-32-linux-power_arch_2_07-vsx) vaddsbs (powerpc-32-linux-power_arch_2_07-vsx) vaddshs (powerpc-32-linux-power_arch_2_07-vsx) vaddsws (powerpc-32-linux-power_arch_2_07-vsx) vaddubm (powerpc-32-linux-power_arch_2_07-vsx) vadduhm (powerpc-32-linux-power_arch_2_07-vsx) vadduwm (powerpc-32-linux-power_arch_2_07-vsx) vaddubs (powerpc-32-linux-power_arch_2_07-vsx) vadduhs (powerpc-32-linux-power_arch_2_07-vsx) vadduws (powerpc-32-linux-power_arch_2_07-vsx) vsubsbs (powerpc-32-linux-power_arch_2_07-vsx) vsubshs (powerpc-32-linux-power_arch_2_07-vsx) vsubsws (powerpc-32-linux-power_arch_2_07-vsx) vsububm (powerpc-32-linux-power_arch_2_07-vsx) vsubuhm (powerpc-32-linux-power_arch_2_07-vsx) vsubuwm (powerpc-32-linux-power_arch_2_07-vsx) vsububs (powerpc-32-linux-power_arch_2_07-vsx) vsubuhs (powerpc-32-linux-power_arch_2_07-vsx) vsubuws (powerpc-32-linux-power_arch_2_07-vsx) vavgsb (powerpc-32-linux-power_arch_2_07-vsx) vavgub (powerpc-32-linux-power_arch_2_07-vsx) vavgsh (powerpc-32-linux-power_arch_2_07-vsx) vavguh (powerpc-32-linux-power_arch_2_07-vsx) vavgsw (powerpc-32-linux-power_arch_2_07-vsx) vavguw (powerpc-32-linux-power_arch_2_07-vsx) vmaxsb (powerpc-32-linux-power_arch_2_07-vsx) vmaxub (powerpc-32-linux-power_arch_2_07-vsx) vmaxsh (powerpc-32-linux-power_arch_2_07-vsx) vmaxuh (powerpc-32-linux-power_arch_2_07-vsx) vmaxsw (powerpc-32-linux-power_arch_2_07-vsx) vmaxuw (powerpc-32-linux-power_arch_2_07-vsx) vminsb (powerpc-32-linux-power_arch_2_07-vsx) vminub (powerpc-32-linux-power_arch_2_07-vsx) vminsh (powerpc-32-linux-power_arch_2_07-vsx) vminuh (powerpc-32-linux-power_arch_2_07-vsx) vminsw (powerpc-32-linux-power_arch_2_07-vsx) vminuw (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-32-linux-power_arch_2_07-vsx) vmaxfp (powerpc-32-linux-power_arch_2_07-vsx) vminfp (powerpc-32-linux-power_arch_2_07-vsx) vaddsbs (powerpc-32-linux-power_arch_2_07-vsx) vaddshs (powerpc-32-linux-power_arch_2_07-vsx) vaddsws (powerpc-32-linux-power_arch_2_07-vsx) vaddubm (powerpc-32-linux-power_arch_2_07-vsx) vadduhm (powerpc-32-linux-power_arch_2_07-vsx) vadduwm (powerpc-32-linux-power_arch_2_07-vsx) vaddubs (powerpc-32-linux-power_arch_2_07-vsx) vadduhs (powerpc-32-linux-power_arch_2_07-vsx) vadduws (powerpc-32-linux-power_arch_2_07-vsx) vsubsbs (powerpc-32-linux-power_arch_2_07-vsx) vsubshs (powerpc-32-linux-power_arch_2_07-vsx) vsubsws (powerpc-32-linux-power_arch_2_07-vsx) vsububm (powerpc-32-linux-power_arch_2_07-vsx) vsubuhm (powerpc-32-linux-power_arch_2_07-vsx) vsubuwm (powerpc-32-linux-power_arch_2_07-vsx) vsububs (powerpc-32-linux-power_arch_2_07-vsx) vsubuhs (powerpc-32-linux-power_arch_2_07-vsx) vsubuws (powerpc-32-linux-power_arch_2_07-vsx) vavgsb (powerpc-32-linux-power_arch_2_07-vsx) vavgub (powerpc-32-linux-power_arch_2_07-vsx) vavgsh (powerpc-32-linux-power_arch_2_07-vsx) vavguh (powerpc-32-linux-power_arch_2_07-vsx) vavgsw (powerpc-32-linux-power_arch_2_07-vsx) vavguw (powerpc-32-linux-power_arch_2_07-vsx) vmaxsb (powerpc-32-linux-power_arch_2_07-vsx) vmaxub (powerpc-32-linux-power_arch_2_07-vsx) vmaxsh (powerpc-32-linux-power_arch_2_07-vsx) vmaxuh (powerpc-32-linux-power_arch_2_07-vsx) vmaxsw (powerpc-32-linux-power_arch_2_07-vsx) vmaxuw (powerpc-32-linux-power_arch_2_07-vsx) vminsb (powerpc-32-linux-power_arch_2_07-vsx) vminub (powerpc-32-linux-power_arch_2_07-vsx) vminsh (powerpc-32-linux-power_arch_2_07-vsx) vminuh (powerpc-32-linux-power_arch_2_07-vsx) vminsw (powerpc-32-linux-power_arch_2_07-vsx) vminuw (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-32-linux-power_arch_2_07-vsx) vmaxfp (powerpc-32-linux-power_arch_2_07-vsx) vminfp (powerpc-32-linux-power_arch_2_07-vsx) xvadddp (powerpc-32-linux-power_arch_2_07-vsx) xvmuldp (powerpc-32-linux-power_arch_2_07-vsx) xvsubdp (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvmulsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-32-linux-power_arch_2_07-vsx) xvmindp (powerpc-32-linux-power_arch_2_07-vsx) xvadddp (powerpc-32-linux-power_arch_2_07-vsx) xvmuldp (powerpc-32-linux-power_arch_2_07-vsx) xvsubdp (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvmulsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-32-linux-power_arch_2_07-vsx) xvmindp (powerpc-32-linux-power_arch_2_07-vsx) xvadddp (powerpc-32-linux-power_arch_2_07-vsx) xvmuldp (powerpc-32-linux-power_arch_2_07-vsx) xvsubdp (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvmulsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-32-linux-power_arch_2_07-vsx) xvmindp (powerpc-32-linux-power_arch_2_07-vsx) xvadddp (powerpc-32-linux-power_arch_2_07-vsx) xvmuldp (powerpc-32-linux-power_arch_2_07-vsx) xvsubdp (powerpc-32-linux-power_arch_2_07-vsx) xvaddsp (powerpc-32-linux-power_arch_2_07-vsx) xvmulsp (powerpc-32-linux-power_arch_2_07-vsx) xvsubsp (powerpc-32-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-32-linux-power_arch_2_07-vsx) xvmindp (powerpc-32-linux-power_arch_2_07-vsx) vaddudm (powerpc-32-linux-power_arch_2_07-vsx) vsubudm (powerpc-32-linux-power_arch_2_07-vsx) vmaxsd (powerpc-32-linux-power_arch_2_07-vsx) vmaxud (powerpc-32-linux-power_arch_2_07-vsx) vminsd (powerpc-32-linux-power_arch_2_07-vsx) vminud (powerpc-32-linux-power_arch_2_07-vsx) vaddudm (powerpc-32-linux-power_arch_2_07-vsx) vsubudm (powerpc-32-linux-power_arch_2_07-vsx) vmaxsd (powerpc-32-linux-power_arch_2_07-vsx) vmaxud (powerpc-32-linux-power_arch_2_07-vsx) vminsd (powerpc-32-linux-power_arch_2_07-vsx) vminud (powerpc-32-linux-power_arch_2_07-vsx) vaddudm (powerpc-32-linux-power_arch_2_07-vsx) vsubudm (powerpc-32-linux-power_arch_2_07-vsx) vmaxsd (powerpc-32-linux-power_arch_2_07-vsx) vmaxud (powerpc-32-linux-power_arch_2_07-vsx) vminsd (powerpc-32-linux-power_arch_2_07-vsx) vminud (powerpc-32-linux-power_arch_2_07-vsx) vaddudm (powerpc-32-linux-power_arch_2_07-vsx) vsubudm (powerpc-32-linux-power_arch_2_07-vsx) vmaxsd (powerpc-32-linux-power_arch_2_07-vsx) vmaxud (powerpc-32-linux-power_arch_2_07-vsx) vminsd (powerpc-32-linux-power_arch_2_07-vsx) vminud (powerpc-32-linux-power_arch_2_07-vsx) vaddsbs (powerpc-64-linux) vaddshs (powerpc-64-linux) vaddsws (powerpc-64-linux) vaddubm (powerpc-64-linux) vadduhm (powerpc-64-linux) vadduwm (powerpc-64-linux) vaddubs (powerpc-64-linux) vadduhs (powerpc-64-linux) vadduws (powerpc-64-linux) vsubsbs (powerpc-64-linux) vsubshs (powerpc-64-linux) vsubsws (powerpc-64-linux) vsububm (powerpc-64-linux) vsubuhm (powerpc-64-linux) vsubuwm (powerpc-64-linux) vsububs (powerpc-64-linux) vsubuhs (powerpc-64-linux) vsubuws (powerpc-64-linux) vavgsb (powerpc-64-linux) vavgub (powerpc-64-linux) vavgsh (powerpc-64-linux) vavguh (powerpc-64-linux) vavgsw (powerpc-64-linux) vavguw (powerpc-64-linux) vmaxsb (powerpc-64-linux) vmaxub (powerpc-64-linux) vmaxsh (powerpc-64-linux) vmaxuh (powerpc-64-linux) vmaxsw (powerpc-64-linux) vmaxuw (powerpc-64-linux) vminsb (powerpc-64-linux) vminub (powerpc-64-linux) vminsh (powerpc-64-linux) vminuh (powerpc-64-linux) vminsw (powerpc-64-linux) vminuw (powerpc-64-linux) vaddfp (powerpc-64-linux) vsubfp (powerpc-64-linux) vmaddfp (powerpc-64-linux) vmaxfp (powerpc-64-linux) vminfp (powerpc-64-linux) vaddsbs (powerpc-64-linux) vaddshs (powerpc-64-linux) vaddsws (powerpc-64-linux) vaddubm (powerpc-64-linux) vadduhm (powerpc-64-linux) vadduwm (powerpc-64-linux) vaddubs (powerpc-64-linux) vadduhs (powerpc-64-linux) vadduws (powerpc-64-linux) vsubsbs (powerpc-64-linux) vsubshs (powerpc-64-linux) vsubsws (powerpc-64-linux) vsububm (powerpc-64-linux) vsubuhm (powerpc-64-linux) vsubuwm (powerpc-64-linux) vsububs (powerpc-64-linux) vsubuhs (powerpc-64-linux) vsubuws (powerpc-64-linux) vavgsb (powerpc-64-linux) vavgub (powerpc-64-linux) vavgsh (powerpc-64-linux) vavguh (powerpc-64-linux) vavgsw (powerpc-64-linux) vavguw (powerpc-64-linux) vmaxsb (powerpc-64-linux) vmaxub (powerpc-64-linux) vmaxsh (powerpc-64-linux) vmaxuh (powerpc-64-linux) vmaxsw (powerpc-64-linux) vmaxuw (powerpc-64-linux) vminsb (powerpc-64-linux) vminub (powerpc-64-linux) vminsh (powerpc-64-linux) vminuh (powerpc-64-linux) vminsw (powerpc-64-linux) vminuw (powerpc-64-linux) vaddfp (powerpc-64-linux) vsubfp (powerpc-64-linux) vmaddfp (powerpc-64-linux) vmaxfp (powerpc-64-linux) vminfp (powerpc-64-linux) vaddsbs (powerpc-64-linux) vaddshs (powerpc-64-linux) vaddsws (powerpc-64-linux) vaddubm (powerpc-64-linux) vadduhm (powerpc-64-linux) vadduwm (powerpc-64-linux) vaddubs (powerpc-64-linux) vadduhs (powerpc-64-linux) vadduws (powerpc-64-linux) vsubsbs (powerpc-64-linux) vsubshs (powerpc-64-linux) vsubsws (powerpc-64-linux) vsububm (powerpc-64-linux) vsubuhm (powerpc-64-linux) vsubuwm (powerpc-64-linux) vsububs (powerpc-64-linux) vsubuhs (powerpc-64-linux) vsubuws (powerpc-64-linux) vavgsb (powerpc-64-linux) vavgub (powerpc-64-linux) vavgsh (powerpc-64-linux) vavguh (powerpc-64-linux) vavgsw (powerpc-64-linux) vavguw (powerpc-64-linux) vmaxsb (powerpc-64-linux) vmaxub (powerpc-64-linux) vmaxsh (powerpc-64-linux) vmaxuh (powerpc-64-linux) vmaxsw (powerpc-64-linux) vmaxuw (powerpc-64-linux) vminsb (powerpc-64-linux) vminub (powerpc-64-linux) vminsh (powerpc-64-linux) vminuh (powerpc-64-linux) vminsw (powerpc-64-linux) vminuw (powerpc-64-linux) vaddfp (powerpc-64-linux) vsubfp (powerpc-64-linux) vmaddfp (powerpc-64-linux) vmaxfp (powerpc-64-linux) vminfp (powerpc-64-linux) vaddsbs (powerpc-64-linux) vaddshs (powerpc-64-linux) vaddsws (powerpc-64-linux) vaddubm (powerpc-64-linux) vadduhm (powerpc-64-linux) vadduwm (powerpc-64-linux) vaddubs (powerpc-64-linux) vadduhs (powerpc-64-linux) vadduws (powerpc-64-linux) vsubsbs (powerpc-64-linux) vsubshs (powerpc-64-linux) vsubsws (powerpc-64-linux) vsububm (powerpc-64-linux) vsubuhm (powerpc-64-linux) vsubuwm (powerpc-64-linux) vsububs (powerpc-64-linux) vsubuhs (powerpc-64-linux) vsubuws (powerpc-64-linux) vavgsb (powerpc-64-linux) vavgub (powerpc-64-linux) vavgsh (powerpc-64-linux) vavguh (powerpc-64-linux) vavgsw (powerpc-64-linux) vavguw (powerpc-64-linux) vmaxsb (powerpc-64-linux) vmaxub (powerpc-64-linux) vmaxsh (powerpc-64-linux) vmaxuh (powerpc-64-linux) vmaxsw (powerpc-64-linux) vmaxuw (powerpc-64-linux) vminsb (powerpc-64-linux) vminub (powerpc-64-linux) vminsh (powerpc-64-linux) vminuh (powerpc-64-linux) vminsw (powerpc-64-linux) vminuw (powerpc-64-linux) vaddfp (powerpc-64-linux) vsubfp (powerpc-64-linux) vmaddfp (powerpc-64-linux) vmaxfp (powerpc-64-linux) vminfp (powerpc-64-linux) vaddsbs (powerpc-64-linux-vsx) vaddshs (powerpc-64-linux-vsx) vaddsws (powerpc-64-linux-vsx) vaddubm (powerpc-64-linux-vsx) vadduhm (powerpc-64-linux-vsx) vadduwm (powerpc-64-linux-vsx) vaddubs (powerpc-64-linux-vsx) vadduhs (powerpc-64-linux-vsx) vadduws (powerpc-64-linux-vsx) vsubsbs (powerpc-64-linux-vsx) vsubshs (powerpc-64-linux-vsx) vsubsws (powerpc-64-linux-vsx) vsububm (powerpc-64-linux-vsx) vsubuhm (powerpc-64-linux-vsx) vsubuwm (powerpc-64-linux-vsx) vsububs (powerpc-64-linux-vsx) vsubuhs (powerpc-64-linux-vsx) vsubuws (powerpc-64-linux-vsx) vavgsb (powerpc-64-linux-vsx) vavgub (powerpc-64-linux-vsx) vavgsh (powerpc-64-linux-vsx) vavguh (powerpc-64-linux-vsx) vavgsw (powerpc-64-linux-vsx) vavguw (powerpc-64-linux-vsx) vmaxsb (powerpc-64-linux-vsx) vmaxub (powerpc-64-linux-vsx) vmaxsh (powerpc-64-linux-vsx) vmaxuh (powerpc-64-linux-vsx) vmaxsw (powerpc-64-linux-vsx) vmaxuw (powerpc-64-linux-vsx) vminsb (powerpc-64-linux-vsx) vminub (powerpc-64-linux-vsx) vminsh (powerpc-64-linux-vsx) vminuh (powerpc-64-linux-vsx) vminsw (powerpc-64-linux-vsx) vminuw (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaddasp (powerpc-64-linux-vsx) vmaxfp (powerpc-64-linux-vsx) vminfp (powerpc-64-linux-vsx) vaddsbs (powerpc-64-linux-vsx) vaddshs (powerpc-64-linux-vsx) vaddsws (powerpc-64-linux-vsx) vaddubm (powerpc-64-linux-vsx) vadduhm (powerpc-64-linux-vsx) vadduwm (powerpc-64-linux-vsx) vaddubs (powerpc-64-linux-vsx) vadduhs (powerpc-64-linux-vsx) vadduws (powerpc-64-linux-vsx) vsubsbs (powerpc-64-linux-vsx) vsubshs (powerpc-64-linux-vsx) vsubsws (powerpc-64-linux-vsx) vsububm (powerpc-64-linux-vsx) vsubuhm (powerpc-64-linux-vsx) vsubuwm (powerpc-64-linux-vsx) vsububs (powerpc-64-linux-vsx) vsubuhs (powerpc-64-linux-vsx) vsubuws (powerpc-64-linux-vsx) vavgsb (powerpc-64-linux-vsx) vavgub (powerpc-64-linux-vsx) vavgsh (powerpc-64-linux-vsx) vavguh (powerpc-64-linux-vsx) vavgsw (powerpc-64-linux-vsx) vavguw (powerpc-64-linux-vsx) vmaxsb (powerpc-64-linux-vsx) vmaxub (powerpc-64-linux-vsx) vmaxsh (powerpc-64-linux-vsx) vmaxuh (powerpc-64-linux-vsx) vmaxsw (powerpc-64-linux-vsx) vmaxuw (powerpc-64-linux-vsx) vminsb (powerpc-64-linux-vsx) vminub (powerpc-64-linux-vsx) vminsh (powerpc-64-linux-vsx) vminuh (powerpc-64-linux-vsx) vminsw (powerpc-64-linux-vsx) vminuw (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaddasp (powerpc-64-linux-vsx) vmaxfp (powerpc-64-linux-vsx) vminfp (powerpc-64-linux-vsx) vaddsbs (powerpc-64-linux-vsx) vaddshs (powerpc-64-linux-vsx) vaddsws (powerpc-64-linux-vsx) vaddubm (powerpc-64-linux-vsx) vadduhm (powerpc-64-linux-vsx) vadduwm (powerpc-64-linux-vsx) vaddubs (powerpc-64-linux-vsx) vadduhs (powerpc-64-linux-vsx) vadduws (powerpc-64-linux-vsx) vsubsbs (powerpc-64-linux-vsx) vsubshs (powerpc-64-linux-vsx) vsubsws (powerpc-64-linux-vsx) vsububm (powerpc-64-linux-vsx) vsubuhm (powerpc-64-linux-vsx) vsubuwm (powerpc-64-linux-vsx) vsububs (powerpc-64-linux-vsx) vsubuhs (powerpc-64-linux-vsx) vsubuws (powerpc-64-linux-vsx) vavgsb (powerpc-64-linux-vsx) vavgub (powerpc-64-linux-vsx) vavgsh (powerpc-64-linux-vsx) vavguh (powerpc-64-linux-vsx) vavgsw (powerpc-64-linux-vsx) vavguw (powerpc-64-linux-vsx) vmaxsb (powerpc-64-linux-vsx) vmaxub (powerpc-64-linux-vsx) vmaxsh (powerpc-64-linux-vsx) vmaxuh (powerpc-64-linux-vsx) vmaxsw (powerpc-64-linux-vsx) vmaxuw (powerpc-64-linux-vsx) vminsb (powerpc-64-linux-vsx) vminub (powerpc-64-linux-vsx) vminsh (powerpc-64-linux-vsx) vminuh (powerpc-64-linux-vsx) vminsw (powerpc-64-linux-vsx) vminuw (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaddasp (powerpc-64-linux-vsx) vmaxfp (powerpc-64-linux-vsx) vminfp (powerpc-64-linux-vsx) vaddsbs (powerpc-64-linux-vsx) vaddshs (powerpc-64-linux-vsx) vaddsws (powerpc-64-linux-vsx) vaddubm (powerpc-64-linux-vsx) vadduhm (powerpc-64-linux-vsx) vadduwm (powerpc-64-linux-vsx) vaddubs (powerpc-64-linux-vsx) vadduhs (powerpc-64-linux-vsx) vadduws (powerpc-64-linux-vsx) vsubsbs (powerpc-64-linux-vsx) vsubshs (powerpc-64-linux-vsx) vsubsws (powerpc-64-linux-vsx) vsububm (powerpc-64-linux-vsx) vsubuhm (powerpc-64-linux-vsx) vsubuwm (powerpc-64-linux-vsx) vsububs (powerpc-64-linux-vsx) vsubuhs (powerpc-64-linux-vsx) vsubuws (powerpc-64-linux-vsx) vavgsb (powerpc-64-linux-vsx) vavgub (powerpc-64-linux-vsx) vavgsh (powerpc-64-linux-vsx) vavguh (powerpc-64-linux-vsx) vavgsw (powerpc-64-linux-vsx) vavguw (powerpc-64-linux-vsx) vmaxsb (powerpc-64-linux-vsx) vmaxub (powerpc-64-linux-vsx) vmaxsh (powerpc-64-linux-vsx) vmaxuh (powerpc-64-linux-vsx) vmaxsw (powerpc-64-linux-vsx) vmaxuw (powerpc-64-linux-vsx) vminsb (powerpc-64-linux-vsx) vminub (powerpc-64-linux-vsx) vminsh (powerpc-64-linux-vsx) vminuh (powerpc-64-linux-vsx) vminsw (powerpc-64-linux-vsx) vminuw (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaddasp (powerpc-64-linux-vsx) vmaxfp (powerpc-64-linux-vsx) vminfp (powerpc-64-linux-vsx) xvadddp (powerpc-64-linux-vsx) xvmuldp (powerpc-64-linux-vsx) xvsubdp (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvmulsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaxdp (powerpc-64-linux-vsx) xvmindp (powerpc-64-linux-vsx) xvadddp (powerpc-64-linux-vsx) xvmuldp (powerpc-64-linux-vsx) xvsubdp (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvmulsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaxdp (powerpc-64-linux-vsx) xvmindp (powerpc-64-linux-vsx) xvadddp (powerpc-64-linux-vsx) xvmuldp (powerpc-64-linux-vsx) xvsubdp (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvmulsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaxdp (powerpc-64-linux-vsx) xvmindp (powerpc-64-linux-vsx) xvadddp (powerpc-64-linux-vsx) xvmuldp (powerpc-64-linux-vsx) xvsubdp (powerpc-64-linux-vsx) xvaddsp (powerpc-64-linux-vsx) xvmulsp (powerpc-64-linux-vsx) xvsubsp (powerpc-64-linux-vsx) xvmaxdp (powerpc-64-linux-vsx) xvmindp (powerpc-64-linux-vsx) vaddsbs (powerpc-64-linux-power_arch_2_07) vaddshs (powerpc-64-linux-power_arch_2_07) vaddsws (powerpc-64-linux-power_arch_2_07) vaddubm (powerpc-64-linux-power_arch_2_07) vadduhm (powerpc-64-linux-power_arch_2_07) vadduwm (powerpc-64-linux-power_arch_2_07) vaddubs (powerpc-64-linux-power_arch_2_07) vadduhs (powerpc-64-linux-power_arch_2_07) vadduws (powerpc-64-linux-power_arch_2_07) vsubsbs (powerpc-64-linux-power_arch_2_07) vsubshs (powerpc-64-linux-power_arch_2_07) vsubsws (powerpc-64-linux-power_arch_2_07) vsububm (powerpc-64-linux-power_arch_2_07) vsubuhm (powerpc-64-linux-power_arch_2_07) vsubuwm (powerpc-64-linux-power_arch_2_07) vsububs (powerpc-64-linux-power_arch_2_07) vsubuhs (powerpc-64-linux-power_arch_2_07) vsubuws (powerpc-64-linux-power_arch_2_07) vavgsb (powerpc-64-linux-power_arch_2_07) vavgub (powerpc-64-linux-power_arch_2_07) vavgsh (powerpc-64-linux-power_arch_2_07) vavguh (powerpc-64-linux-power_arch_2_07) vavgsw (powerpc-64-linux-power_arch_2_07) vavguw (powerpc-64-linux-power_arch_2_07) vmaxsb (powerpc-64-linux-power_arch_2_07) vmaxub (powerpc-64-linux-power_arch_2_07) vmaxsh (powerpc-64-linux-power_arch_2_07) vmaxuh (powerpc-64-linux-power_arch_2_07) vmaxsw (powerpc-64-linux-power_arch_2_07) vmaxuw (powerpc-64-linux-power_arch_2_07) vminsb (powerpc-64-linux-power_arch_2_07) vminub (powerpc-64-linux-power_arch_2_07) vminsh (powerpc-64-linux-power_arch_2_07) vminuh (powerpc-64-linux-power_arch_2_07) vminsw (powerpc-64-linux-power_arch_2_07) vminuw (powerpc-64-linux-power_arch_2_07) xvaddsp (powerpc-64-linux-power_arch_2_07) xvsubsp (powerpc-64-linux-power_arch_2_07) xvmaddasp (powerpc-64-linux-power_arch_2_07) vmaxfp (powerpc-64-linux-power_arch_2_07) vminfp (powerpc-64-linux-power_arch_2_07) vaddsbs (powerpc-64-linux-power_arch_2_07) vaddshs (powerpc-64-linux-power_arch_2_07) vaddsws (powerpc-64-linux-power_arch_2_07) vaddubm (powerpc-64-linux-power_arch_2_07) vadduhm (powerpc-64-linux-power_arch_2_07) vadduwm (powerpc-64-linux-power_arch_2_07) vaddubs (powerpc-64-linux-power_arch_2_07) vadduhs (powerpc-64-linux-power_arch_2_07) vadduws (powerpc-64-linux-power_arch_2_07) vsubsbs (powerpc-64-linux-power_arch_2_07) vsubshs (powerpc-64-linux-power_arch_2_07) vsubsws (powerpc-64-linux-power_arch_2_07) vsububm (powerpc-64-linux-power_arch_2_07) vsubuhm (powerpc-64-linux-power_arch_2_07) vsubuwm (powerpc-64-linux-power_arch_2_07) vsububs (powerpc-64-linux-power_arch_2_07) vsubuhs (powerpc-64-linux-power_arch_2_07) vsubuws (powerpc-64-linux-power_arch_2_07) vavgsb (powerpc-64-linux-power_arch_2_07) vavgub (powerpc-64-linux-power_arch_2_07) vavgsh (powerpc-64-linux-power_arch_2_07) vavguh (powerpc-64-linux-power_arch_2_07) vavgsw (powerpc-64-linux-power_arch_2_07) vavguw (powerpc-64-linux-power_arch_2_07) vmaxsb (powerpc-64-linux-power_arch_2_07) vmaxub (powerpc-64-linux-power_arch_2_07) vmaxsh (powerpc-64-linux-power_arch_2_07) vmaxuh (powerpc-64-linux-power_arch_2_07) vmaxsw (powerpc-64-linux-power_arch_2_07) vmaxuw (powerpc-64-linux-power_arch_2_07) vminsb (powerpc-64-linux-power_arch_2_07) vminub (powerpc-64-linux-power_arch_2_07) vminsh (powerpc-64-linux-power_arch_2_07) vminuh (powerpc-64-linux-power_arch_2_07) vminsw (powerpc-64-linux-power_arch_2_07) vminuw (powerpc-64-linux-power_arch_2_07) xvaddsp (powerpc-64-linux-power_arch_2_07) xvsubsp (powerpc-64-linux-power_arch_2_07) xvmaddasp (powerpc-64-linux-power_arch_2_07) vmaxfp (powerpc-64-linux-power_arch_2_07) vminfp (powerpc-64-linux-power_arch_2_07) vaddsbs (powerpc-64-linux-power_arch_2_07) vaddshs (powerpc-64-linux-power_arch_2_07) vaddsws (powerpc-64-linux-power_arch_2_07) vaddubm (powerpc-64-linux-power_arch_2_07) vadduhm (powerpc-64-linux-power_arch_2_07) vadduwm (powerpc-64-linux-power_arch_2_07) vaddubs (powerpc-64-linux-power_arch_2_07) vadduhs (powerpc-64-linux-power_arch_2_07) vadduws (powerpc-64-linux-power_arch_2_07) vsubsbs (powerpc-64-linux-power_arch_2_07) vsubshs (powerpc-64-linux-power_arch_2_07) vsubsws (powerpc-64-linux-power_arch_2_07) vsububm (powerpc-64-linux-power_arch_2_07) vsubuhm (powerpc-64-linux-power_arch_2_07) vsubuwm (powerpc-64-linux-power_arch_2_07) vsububs (powerpc-64-linux-power_arch_2_07) vsubuhs (powerpc-64-linux-power_arch_2_07) vsubuws (powerpc-64-linux-power_arch_2_07) vavgsb (powerpc-64-linux-power_arch_2_07) vavgub (powerpc-64-linux-power_arch_2_07) vavgsh (powerpc-64-linux-power_arch_2_07) vavguh (powerpc-64-linux-power_arch_2_07) vavgsw (powerpc-64-linux-power_arch_2_07) vavguw (powerpc-64-linux-power_arch_2_07) vmaxsb (powerpc-64-linux-power_arch_2_07) vmaxub (powerpc-64-linux-power_arch_2_07) vmaxsh (powerpc-64-linux-power_arch_2_07) vmaxuh (powerpc-64-linux-power_arch_2_07) vmaxsw (powerpc-64-linux-power_arch_2_07) vmaxuw (powerpc-64-linux-power_arch_2_07) vminsb (powerpc-64-linux-power_arch_2_07) vminub (powerpc-64-linux-power_arch_2_07) vminsh (powerpc-64-linux-power_arch_2_07) vminuh (powerpc-64-linux-power_arch_2_07) vminsw (powerpc-64-linux-power_arch_2_07) vminuw (powerpc-64-linux-power_arch_2_07) xvaddsp (powerpc-64-linux-power_arch_2_07) xvsubsp (powerpc-64-linux-power_arch_2_07) xvmaddasp (powerpc-64-linux-power_arch_2_07) vmaxfp (powerpc-64-linux-power_arch_2_07) vminfp (powerpc-64-linux-power_arch_2_07) vaddsbs (powerpc-64-linux-power_arch_2_07) vaddshs (powerpc-64-linux-power_arch_2_07) vaddsws (powerpc-64-linux-power_arch_2_07) vaddubm (powerpc-64-linux-power_arch_2_07) vadduhm (powerpc-64-linux-power_arch_2_07) vadduwm (powerpc-64-linux-power_arch_2_07) vaddubs (powerpc-64-linux-power_arch_2_07) vadduhs (powerpc-64-linux-power_arch_2_07) vadduws (powerpc-64-linux-power_arch_2_07) vsubsbs (powerpc-64-linux-power_arch_2_07) vsubshs (powerpc-64-linux-power_arch_2_07) vsubsws (powerpc-64-linux-power_arch_2_07) vsububm (powerpc-64-linux-power_arch_2_07) vsubuhm (powerpc-64-linux-power_arch_2_07) vsubuwm (powerpc-64-linux-power_arch_2_07) vsububs (powerpc-64-linux-power_arch_2_07) vsubuhs (powerpc-64-linux-power_arch_2_07) vsubuws (powerpc-64-linux-power_arch_2_07) vavgsb (powerpc-64-linux-power_arch_2_07) vavgub (powerpc-64-linux-power_arch_2_07) vavgsh (powerpc-64-linux-power_arch_2_07) vavguh (powerpc-64-linux-power_arch_2_07) vavgsw (powerpc-64-linux-power_arch_2_07) vavguw (powerpc-64-linux-power_arch_2_07) vmaxsb (powerpc-64-linux-power_arch_2_07) vmaxub (powerpc-64-linux-power_arch_2_07) vmaxsh (powerpc-64-linux-power_arch_2_07) vmaxuh (powerpc-64-linux-power_arch_2_07) vmaxsw (powerpc-64-linux-power_arch_2_07) vmaxuw (powerpc-64-linux-power_arch_2_07) vminsb (powerpc-64-linux-power_arch_2_07) vminub (powerpc-64-linux-power_arch_2_07) vminsh (powerpc-64-linux-power_arch_2_07) vminuh (powerpc-64-linux-power_arch_2_07) vminsw (powerpc-64-linux-power_arch_2_07) vminuw (powerpc-64-linux-power_arch_2_07) xvaddsp (powerpc-64-linux-power_arch_2_07) xvsubsp (powerpc-64-linux-power_arch_2_07) xvmaddasp (powerpc-64-linux-power_arch_2_07) vmaxfp (powerpc-64-linux-power_arch_2_07) vminfp (powerpc-64-linux-power_arch_2_07) vaddudm (powerpc-64-linux-power_arch_2_07) vsubudm (powerpc-64-linux-power_arch_2_07) vmaxsd (powerpc-64-linux-power_arch_2_07) vmaxud (powerpc-64-linux-power_arch_2_07) vminsd (powerpc-64-linux-power_arch_2_07) vminud (powerpc-64-linux-power_arch_2_07) vaddudm (powerpc-64-linux-power_arch_2_07) vsubudm (powerpc-64-linux-power_arch_2_07) vmaxsd (powerpc-64-linux-power_arch_2_07) vmaxud (powerpc-64-linux-power_arch_2_07) vminsd (powerpc-64-linux-power_arch_2_07) vminud (powerpc-64-linux-power_arch_2_07) vaddudm (powerpc-64-linux-power_arch_2_07) vsubudm (powerpc-64-linux-power_arch_2_07) vmaxsd (powerpc-64-linux-power_arch_2_07) vmaxud (powerpc-64-linux-power_arch_2_07) vminsd (powerpc-64-linux-power_arch_2_07) vminud (powerpc-64-linux-power_arch_2_07) vaddudm (powerpc-64-linux-power_arch_2_07) vsubudm (powerpc-64-linux-power_arch_2_07) vmaxsd (powerpc-64-linux-power_arch_2_07) vmaxud (powerpc-64-linux-power_arch_2_07) vminsd (powerpc-64-linux-power_arch_2_07) vminud (powerpc-64-linux-power_arch_2_07) vaddsbs (powerpc-64-linux-power_arch_2_07-vsx) vaddshs (powerpc-64-linux-power_arch_2_07-vsx) vaddsws (powerpc-64-linux-power_arch_2_07-vsx) vaddubm (powerpc-64-linux-power_arch_2_07-vsx) vadduhm (powerpc-64-linux-power_arch_2_07-vsx) vadduwm (powerpc-64-linux-power_arch_2_07-vsx) vaddubs (powerpc-64-linux-power_arch_2_07-vsx) vadduhs (powerpc-64-linux-power_arch_2_07-vsx) vadduws (powerpc-64-linux-power_arch_2_07-vsx) vsubsbs (powerpc-64-linux-power_arch_2_07-vsx) vsubshs (powerpc-64-linux-power_arch_2_07-vsx) vsubsws (powerpc-64-linux-power_arch_2_07-vsx) vsububm (powerpc-64-linux-power_arch_2_07-vsx) vsubuhm (powerpc-64-linux-power_arch_2_07-vsx) vsubuwm (powerpc-64-linux-power_arch_2_07-vsx) vsububs (powerpc-64-linux-power_arch_2_07-vsx) vsubuhs (powerpc-64-linux-power_arch_2_07-vsx) vsubuws (powerpc-64-linux-power_arch_2_07-vsx) vavgsb (powerpc-64-linux-power_arch_2_07-vsx) vavgub (powerpc-64-linux-power_arch_2_07-vsx) vavgsh (powerpc-64-linux-power_arch_2_07-vsx) vavguh (powerpc-64-linux-power_arch_2_07-vsx) vavgsw (powerpc-64-linux-power_arch_2_07-vsx) vavguw (powerpc-64-linux-power_arch_2_07-vsx) vmaxsb (powerpc-64-linux-power_arch_2_07-vsx) vmaxub (powerpc-64-linux-power_arch_2_07-vsx) vmaxsh (powerpc-64-linux-power_arch_2_07-vsx) vmaxuh (powerpc-64-linux-power_arch_2_07-vsx) vmaxsw (powerpc-64-linux-power_arch_2_07-vsx) vmaxuw (powerpc-64-linux-power_arch_2_07-vsx) vminsb (powerpc-64-linux-power_arch_2_07-vsx) vminub (powerpc-64-linux-power_arch_2_07-vsx) vminsh (powerpc-64-linux-power_arch_2_07-vsx) vminuh (powerpc-64-linux-power_arch_2_07-vsx) vminsw (powerpc-64-linux-power_arch_2_07-vsx) vminuw (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-64-linux-power_arch_2_07-vsx) vmaxfp (powerpc-64-linux-power_arch_2_07-vsx) vminfp (powerpc-64-linux-power_arch_2_07-vsx) vaddsbs (powerpc-64-linux-power_arch_2_07-vsx) vaddshs (powerpc-64-linux-power_arch_2_07-vsx) vaddsws (powerpc-64-linux-power_arch_2_07-vsx) vaddubm (powerpc-64-linux-power_arch_2_07-vsx) vadduhm (powerpc-64-linux-power_arch_2_07-vsx) vadduwm (powerpc-64-linux-power_arch_2_07-vsx) vaddubs (powerpc-64-linux-power_arch_2_07-vsx) vadduhs (powerpc-64-linux-power_arch_2_07-vsx) vadduws (powerpc-64-linux-power_arch_2_07-vsx) vsubsbs (powerpc-64-linux-power_arch_2_07-vsx) vsubshs (powerpc-64-linux-power_arch_2_07-vsx) vsubsws (powerpc-64-linux-power_arch_2_07-vsx) vsububm (powerpc-64-linux-power_arch_2_07-vsx) vsubuhm (powerpc-64-linux-power_arch_2_07-vsx) vsubuwm (powerpc-64-linux-power_arch_2_07-vsx) vsububs (powerpc-64-linux-power_arch_2_07-vsx) vsubuhs (powerpc-64-linux-power_arch_2_07-vsx) vsubuws (powerpc-64-linux-power_arch_2_07-vsx) vavgsb (powerpc-64-linux-power_arch_2_07-vsx) vavgub (powerpc-64-linux-power_arch_2_07-vsx) vavgsh (powerpc-64-linux-power_arch_2_07-vsx) vavguh (powerpc-64-linux-power_arch_2_07-vsx) vavgsw (powerpc-64-linux-power_arch_2_07-vsx) vavguw (powerpc-64-linux-power_arch_2_07-vsx) vmaxsb (powerpc-64-linux-power_arch_2_07-vsx) vmaxub (powerpc-64-linux-power_arch_2_07-vsx) vmaxsh (powerpc-64-linux-power_arch_2_07-vsx) vmaxuh (powerpc-64-linux-power_arch_2_07-vsx) vmaxsw (powerpc-64-linux-power_arch_2_07-vsx) vmaxuw (powerpc-64-linux-power_arch_2_07-vsx) vminsb (powerpc-64-linux-power_arch_2_07-vsx) vminub (powerpc-64-linux-power_arch_2_07-vsx) vminsh (powerpc-64-linux-power_arch_2_07-vsx) vminuh (powerpc-64-linux-power_arch_2_07-vsx) vminsw (powerpc-64-linux-power_arch_2_07-vsx) vminuw (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-64-linux-power_arch_2_07-vsx) vmaxfp (powerpc-64-linux-power_arch_2_07-vsx) vminfp (powerpc-64-linux-power_arch_2_07-vsx) vaddsbs (powerpc-64-linux-power_arch_2_07-vsx) vaddshs (powerpc-64-linux-power_arch_2_07-vsx) vaddsws (powerpc-64-linux-power_arch_2_07-vsx) vaddubm (powerpc-64-linux-power_arch_2_07-vsx) vadduhm (powerpc-64-linux-power_arch_2_07-vsx) vadduwm (powerpc-64-linux-power_arch_2_07-vsx) vaddubs (powerpc-64-linux-power_arch_2_07-vsx) vadduhs (powerpc-64-linux-power_arch_2_07-vsx) vadduws (powerpc-64-linux-power_arch_2_07-vsx) vsubsbs (powerpc-64-linux-power_arch_2_07-vsx) vsubshs (powerpc-64-linux-power_arch_2_07-vsx) vsubsws (powerpc-64-linux-power_arch_2_07-vsx) vsububm (powerpc-64-linux-power_arch_2_07-vsx) vsubuhm (powerpc-64-linux-power_arch_2_07-vsx) vsubuwm (powerpc-64-linux-power_arch_2_07-vsx) vsububs (powerpc-64-linux-power_arch_2_07-vsx) vsubuhs (powerpc-64-linux-power_arch_2_07-vsx) vsubuws (powerpc-64-linux-power_arch_2_07-vsx) vavgsb (powerpc-64-linux-power_arch_2_07-vsx) vavgub (powerpc-64-linux-power_arch_2_07-vsx) vavgsh (powerpc-64-linux-power_arch_2_07-vsx) vavguh (powerpc-64-linux-power_arch_2_07-vsx) vavgsw (powerpc-64-linux-power_arch_2_07-vsx) vavguw (powerpc-64-linux-power_arch_2_07-vsx) vmaxsb (powerpc-64-linux-power_arch_2_07-vsx) vmaxub (powerpc-64-linux-power_arch_2_07-vsx) vmaxsh (powerpc-64-linux-power_arch_2_07-vsx) vmaxuh (powerpc-64-linux-power_arch_2_07-vsx) vmaxsw (powerpc-64-linux-power_arch_2_07-vsx) vmaxuw (powerpc-64-linux-power_arch_2_07-vsx) vminsb (powerpc-64-linux-power_arch_2_07-vsx) vminub (powerpc-64-linux-power_arch_2_07-vsx) vminsh (powerpc-64-linux-power_arch_2_07-vsx) vminuh (powerpc-64-linux-power_arch_2_07-vsx) vminsw (powerpc-64-linux-power_arch_2_07-vsx) vminuw (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-64-linux-power_arch_2_07-vsx) vmaxfp (powerpc-64-linux-power_arch_2_07-vsx) vminfp (powerpc-64-linux-power_arch_2_07-vsx) vaddsbs (powerpc-64-linux-power_arch_2_07-vsx) vaddshs (powerpc-64-linux-power_arch_2_07-vsx) vaddsws (powerpc-64-linux-power_arch_2_07-vsx) vaddubm (powerpc-64-linux-power_arch_2_07-vsx) vadduhm (powerpc-64-linux-power_arch_2_07-vsx) vadduwm (powerpc-64-linux-power_arch_2_07-vsx) vaddubs (powerpc-64-linux-power_arch_2_07-vsx) vadduhs (powerpc-64-linux-power_arch_2_07-vsx) vadduws (powerpc-64-linux-power_arch_2_07-vsx) vsubsbs (powerpc-64-linux-power_arch_2_07-vsx) vsubshs (powerpc-64-linux-power_arch_2_07-vsx) vsubsws (powerpc-64-linux-power_arch_2_07-vsx) vsububm (powerpc-64-linux-power_arch_2_07-vsx) vsubuhm (powerpc-64-linux-power_arch_2_07-vsx) vsubuwm (powerpc-64-linux-power_arch_2_07-vsx) vsububs (powerpc-64-linux-power_arch_2_07-vsx) vsubuhs (powerpc-64-linux-power_arch_2_07-vsx) vsubuws (powerpc-64-linux-power_arch_2_07-vsx) vavgsb (powerpc-64-linux-power_arch_2_07-vsx) vavgub (powerpc-64-linux-power_arch_2_07-vsx) vavgsh (powerpc-64-linux-power_arch_2_07-vsx) vavguh (powerpc-64-linux-power_arch_2_07-vsx) vavgsw (powerpc-64-linux-power_arch_2_07-vsx) vavguw (powerpc-64-linux-power_arch_2_07-vsx) vmaxsb (powerpc-64-linux-power_arch_2_07-vsx) vmaxub (powerpc-64-linux-power_arch_2_07-vsx) vmaxsh (powerpc-64-linux-power_arch_2_07-vsx) vmaxuh (powerpc-64-linux-power_arch_2_07-vsx) vmaxsw (powerpc-64-linux-power_arch_2_07-vsx) vmaxuw (powerpc-64-linux-power_arch_2_07-vsx) vminsb (powerpc-64-linux-power_arch_2_07-vsx) vminub (powerpc-64-linux-power_arch_2_07-vsx) vminsh (powerpc-64-linux-power_arch_2_07-vsx) vminuh (powerpc-64-linux-power_arch_2_07-vsx) vminsw (powerpc-64-linux-power_arch_2_07-vsx) vminuw (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaddasp (powerpc-64-linux-power_arch_2_07-vsx) vmaxfp (powerpc-64-linux-power_arch_2_07-vsx) vminfp (powerpc-64-linux-power_arch_2_07-vsx) xvadddp (powerpc-64-linux-power_arch_2_07-vsx) xvmuldp (powerpc-64-linux-power_arch_2_07-vsx) xvsubdp (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvmulsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-64-linux-power_arch_2_07-vsx) xvmindp (powerpc-64-linux-power_arch_2_07-vsx) xvadddp (powerpc-64-linux-power_arch_2_07-vsx) xvmuldp (powerpc-64-linux-power_arch_2_07-vsx) xvsubdp (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvmulsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-64-linux-power_arch_2_07-vsx) xvmindp (powerpc-64-linux-power_arch_2_07-vsx) xvadddp (powerpc-64-linux-power_arch_2_07-vsx) xvmuldp (powerpc-64-linux-power_arch_2_07-vsx) xvsubdp (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvmulsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-64-linux-power_arch_2_07-vsx) xvmindp (powerpc-64-linux-power_arch_2_07-vsx) xvadddp (powerpc-64-linux-power_arch_2_07-vsx) xvmuldp (powerpc-64-linux-power_arch_2_07-vsx) xvsubdp (powerpc-64-linux-power_arch_2_07-vsx) xvaddsp (powerpc-64-linux-power_arch_2_07-vsx) xvmulsp (powerpc-64-linux-power_arch_2_07-vsx) xvsubsp (powerpc-64-linux-power_arch_2_07-vsx) xvmaxdp (powerpc-64-linux-power_arch_2_07-vsx) xvmindp (powerpc-64-linux-power_arch_2_07-vsx) vaddudm (powerpc-64-linux-power_arch_2_07-vsx) vsubudm (powerpc-64-linux-power_arch_2_07-vsx) vmaxsd (powerpc-64-linux-power_arch_2_07-vsx) vmaxud (powerpc-64-linux-power_arch_2_07-vsx) vminsd (powerpc-64-linux-power_arch_2_07-vsx) vminud (powerpc-64-linux-power_arch_2_07-vsx) vaddudm (powerpc-64-linux-power_arch_2_07-vsx) vsubudm (powerpc-64-linux-power_arch_2_07-vsx) vmaxsd (powerpc-64-linux-power_arch_2_07-vsx) vmaxud (powerpc-64-linux-power_arch_2_07-vsx) vminsd (powerpc-64-linux-power_arch_2_07-vsx) vminud (powerpc-64-linux-power_arch_2_07-vsx) vaddudm (powerpc-64-linux-power_arch_2_07-vsx) vsubudm (powerpc-64-linux-power_arch_2_07-vsx) vmaxsd (powerpc-64-linux-power_arch_2_07-vsx) vmaxud (powerpc-64-linux-power_arch_2_07-vsx) vminsd (powerpc-64-linux-power_arch_2_07-vsx) vminud (powerpc-64-linux-power_arch_2_07-vsx) vaddudm (powerpc-64-linux-power_arch_2_07-vsx) vsubudm (powerpc-64-linux-power_arch_2_07-vsx) vmaxsd (powerpc-64-linux-power_arch_2_07-vsx) vmaxud (powerpc-64-linux-power_arch_2_07-vsx) vminsd (powerpc-64-linux-power_arch_2_07-vsx) vminud (powerpc-64-linux-power_arch_2_07-vsx) Success! ======================================== ======================================== correctness_simd_op_check_riscv.exe [SKIP] simd_op_check_riscv requires LLVM 16 or later. ======================================== ======================================== correctness_simd_op_check_wasm.exe host is: target(x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41) simd_op_check test seed: 1680899849 f32.sqrt (wasm-32-wasmrt) f32.min (wasm-32-wasmrt) f32.max (wasm-32-wasmrt) f32.ceil (wasm-32-wasmrt) f32.floor (wasm-32-wasmrt) f32.trunc (wasm-32-wasmrt) f32.nearest (wasm-32-wasmrt) f32.abs (wasm-32-wasmrt) f32.neg (wasm-32-wasmrt) f32.sqrt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.min (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.max (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.ceil (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.floor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.trunc (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.nearest (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32.trunc_sat_f32_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32.trunc_sat_f32_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32.trunc_sat_f64_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32.trunc_sat_f64_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64.trunc_sat_f32_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64.trunc_sat_f32_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64.trunc_sat_f64_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64.trunc_sat_f64_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.q15mulr_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.popcnt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.popcnt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.lt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.lt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.le (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.le (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load8_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load16_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load32_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load64_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.load8x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.load8x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.load16x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.load16x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.load32x2_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.load32x2_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.min (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.min (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.max (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.max (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.div (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.div (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.sqrt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.sqrt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.ceil (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.ceil (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.floor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.floor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.trunc (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.trunc (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.nearest (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.nearest (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.convert_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.convert_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.convert_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.convert_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.trunc_sat_f32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.trunc_sat_f32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.promote_low_f32x4 (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.narrow_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.narrow_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_low_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_high_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_low_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_high_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_low_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_high_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_low_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_high_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_high_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_high_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_low_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_low_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_low_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_low_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_high_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_high_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_high_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_high_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_high_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_high_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.q15mulr_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.popcnt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.popcnt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.lt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.lt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.le (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.le (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load8_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load16_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load32_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load64_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.min (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.min (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.max (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.max (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.div (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.div (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.sqrt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.sqrt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.ceil (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.ceil (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.floor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.floor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.trunc (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.trunc (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.nearest (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.nearest (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.convert_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.convert_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.convert_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.convert_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.trunc_sat_f32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.trunc_sat_f32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.narrow_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.narrow_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_low_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_high_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_low_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_high_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_low_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_high_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_low_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_high_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_high_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_high_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.const (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shuffle (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.dot_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_low_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_low_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_low_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_low_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_high_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_high_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_high_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extmul_high_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extmul_high_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extmul_high_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extadd_pairwise_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extadd_pairwise_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.add_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.add_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.sub_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.sub_sat_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.q15mulr_sat_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.min_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.min_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.max_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.max_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.avgr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shl (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shr_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.shr_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.and (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.or (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.xor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.not (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.andnot (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.bitselect (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.popcnt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.popcnt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.eq (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.ne (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.lt_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.lt_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.lt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.lt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.le_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.le_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.le (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.le (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load8_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load16_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load32_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.load64_splat (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) v128.store (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.neg (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.abs (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.min (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.min (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.max (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.max (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.add (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.sub (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.div (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.div (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.mul (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.sqrt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.sqrt (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.ceil (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.ceil (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.floor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.floor (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.trunc (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.trunc (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.nearest (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.nearest (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.convert_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f32x4.convert_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.convert_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) f64x2.convert_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.trunc_sat_f32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.trunc_sat_f32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.narrow_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i8x16.narrow_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.narrow_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_low_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_high_i8x16_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_low_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i16x8.extend_high_i8x16_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_low_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_high_i16x8_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_low_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i32x4.extend_high_i16x8_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_low_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_high_i32x4_s (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_low_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) i64x2.extend_high_i32x4_u (wasm-32-wasmrt-wasm_sat_float_to_int-wasm_simd128) Success! ======================================== ======================================== correctness_simd_op_check_x86.exe host is: target(x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-f16c-fma-sse41) simd_op_check test seed: 1680899878 paddsb (x86-32-linux) paddsb (x86-32-linux) psubsb (x86-32-linux) paddusb (x86-32-linux) psubusb (x86-32-linux) paddsw (x86-32-linux) psubsw (x86-32-linux) paddusw (x86-32-linux) psubusw (x86-32-linux) psubusb (x86-32-linux) psubusw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) addps (x86-32-linux) subps (x86-32-linux) mulps (x86-32-linux) rsqrtps (x86-32-linux) rcpps (x86-32-linux) sqrtps (x86-32-linux) maxps (x86-32-linux) minps (x86-32-linux) pavgb (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pmaxsw (x86-32-linux) pminsw (x86-32-linux) pmaxub (x86-32-linux) pminub (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) cmpeqps (x86-32-linux) cmpltps (x86-32-linux) paddb (x86-32-linux) psubb (x86-32-linux) paddw (x86-32-linux) psubw (x86-32-linux) pmullw (x86-32-linux) paddd (x86-32-linux) psubd (x86-32-linux) paddsb (x86-32-linux) paddsb (x86-32-linux) psubsb (x86-32-linux) paddusb (x86-32-linux) psubusb (x86-32-linux) paddsw (x86-32-linux) psubsw (x86-32-linux) paddusw (x86-32-linux) psubusw (x86-32-linux) psubusb (x86-32-linux) psubusw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) pcmp*b (x86-32-linux) pcmp*b (x86-32-linux) pcmp*w (x86-32-linux) pcmp*w (x86-32-linux) pcmp*d (x86-32-linux) pcmp*d (x86-32-linux) addps (x86-32-linux) subps (x86-32-linux) mulps (x86-32-linux) rsqrtps (x86-32-linux) rcpps (x86-32-linux) sqrtps (x86-32-linux) maxps (x86-32-linux) minps (x86-32-linux) pavgb (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pmaxsw (x86-32-linux) pminsw (x86-32-linux) pmaxub (x86-32-linux) pminub (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) cmpeqps (x86-32-linux) cmpltps (x86-32-linux) paddb (x86-32-linux) psubb (x86-32-linux) paddw (x86-32-linux) psubw (x86-32-linux) pmullw (x86-32-linux) paddd (x86-32-linux) psubd (x86-32-linux) paddsb (x86-32-linux) paddsb (x86-32-linux) psubsb (x86-32-linux) paddusb (x86-32-linux) psubusb (x86-32-linux) paddsw (x86-32-linux) psubsw (x86-32-linux) paddusw (x86-32-linux) psubusw (x86-32-linux) psubusb (x86-32-linux) psubusw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) pcmp*b (x86-32-linux) pcmp*b (x86-32-linux) pcmp*w (x86-32-linux) pcmp*w (x86-32-linux) pcmp*d (x86-32-linux) pcmp*d (x86-32-linux) addps (x86-32-linux) subps (x86-32-linux) mulps (x86-32-linux) rsqrtps (x86-32-linux) rcpps (x86-32-linux) sqrtps (x86-32-linux) maxps (x86-32-linux) minps (x86-32-linux) pavgb (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pmaxsw (x86-32-linux) pminsw (x86-32-linux) pmaxub (x86-32-linux) pminub (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) cmpeqps (x86-32-linux) cmpltps (x86-32-linux) paddb (x86-32-linux) psubb (x86-32-linux) paddw (x86-32-linux) psubw (x86-32-linux) pmullw (x86-32-linux) paddd (x86-32-linux) psubd (x86-32-linux) paddsb (x86-32-linux) paddsb (x86-32-linux) psubsb (x86-32-linux) paddusb (x86-32-linux) psubusb (x86-32-linux) paddsw (x86-32-linux) psubsw (x86-32-linux) paddusw (x86-32-linux) psubusw (x86-32-linux) psubusb (x86-32-linux) psubusw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhw (x86-32-linux) pmulhuw (x86-32-linux) pcmp*b (x86-32-linux) pcmp*b (x86-32-linux) pcmp*w (x86-32-linux) pcmp*w (x86-32-linux) pcmp*d (x86-32-linux) pcmp*d (x86-32-linux) addps (x86-32-linux) subps (x86-32-linux) mulps (x86-32-linux) rsqrtps (x86-32-linux) rcpps (x86-32-linux) sqrtps (x86-32-linux) maxps (x86-32-linux) minps (x86-32-linux) pavgb (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pavgb (x86-32-linux) pavgw (x86-32-linux) pmaxsw (x86-32-linux) pminsw (x86-32-linux) pmaxub (x86-32-linux) pminub (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) pmulhuw (x86-32-linux) cmpeqps (x86-32-linux) cmpltps (x86-32-linux) orps (x86-32-linux) xorps (x86-32-linux) andps (x86-32-linux) shufps (x86-32-linux) addpd (x86-32-linux) subpd (x86-32-linux) mulpd (x86-32-linux) divpd (x86-32-linux) sqrtpd (x86-32-linux) maxpd (x86-32-linux) minpd (x86-32-linux) cmpeqpd (x86-32-linux) cmpltpd (x86-32-linux) paddq (x86-32-linux) psubq (x86-32-linux) pmuludq (x86-32-linux) packssdw (x86-32-linux) packsswb (x86-32-linux) packuswb (x86-32-linux) packssdw (x86-32-linux) packssdw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) addpd (x86-32-linux) subpd (x86-32-linux) mulpd (x86-32-linux) divpd (x86-32-linux) sqrtpd (x86-32-linux) maxpd (x86-32-linux) minpd (x86-32-linux) cmpeqpd (x86-32-linux) cmpltpd (x86-32-linux) paddq (x86-32-linux) psubq (x86-32-linux) pmuludq (x86-32-linux) packssdw (x86-32-linux) packsswb (x86-32-linux) packuswb (x86-32-linux) packssdw (x86-32-linux) packssdw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) psadbw (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) pmaddwd (x86-32-linux) paddsb (x86-32-linux-sse41) paddsb (x86-32-linux-sse41) psubsb (x86-32-linux-sse41) paddusb (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) paddsw (x86-32-linux-sse41) psubsw (x86-32-linux-sse41) paddusw (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) addps (x86-32-linux-sse41) subps (x86-32-linux-sse41) mulps (x86-32-linux-sse41) rsqrtps (x86-32-linux-sse41) rcpps (x86-32-linux-sse41) sqrtps (x86-32-linux-sse41) maxps (x86-32-linux-sse41) minps (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pmaxsw (x86-32-linux-sse41) pminsw (x86-32-linux-sse41) pmaxub (x86-32-linux-sse41) pminub (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) cmpeqps (x86-32-linux-sse41) cmpltps (x86-32-linux-sse41) paddb (x86-32-linux-sse41) psubb (x86-32-linux-sse41) paddw (x86-32-linux-sse41) psubw (x86-32-linux-sse41) pmullw (x86-32-linux-sse41) paddd (x86-32-linux-sse41) psubd (x86-32-linux-sse41) paddsb (x86-32-linux-sse41) paddsb (x86-32-linux-sse41) psubsb (x86-32-linux-sse41) paddusb (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) paddsw (x86-32-linux-sse41) psubsw (x86-32-linux-sse41) paddusw (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pcmp*b (x86-32-linux-sse41) pcmp*b (x86-32-linux-sse41) pcmp*w (x86-32-linux-sse41) pcmp*w (x86-32-linux-sse41) pcmp*d (x86-32-linux-sse41) pcmp*d (x86-32-linux-sse41) addps (x86-32-linux-sse41) subps (x86-32-linux-sse41) mulps (x86-32-linux-sse41) rsqrtps (x86-32-linux-sse41) rcpps (x86-32-linux-sse41) sqrtps (x86-32-linux-sse41) maxps (x86-32-linux-sse41) minps (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pmaxsw (x86-32-linux-sse41) pminsw (x86-32-linux-sse41) pmaxub (x86-32-linux-sse41) pminub (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) cmpeqps (x86-32-linux-sse41) cmpltps (x86-32-linux-sse41) paddb (x86-32-linux-sse41) psubb (x86-32-linux-sse41) paddw (x86-32-linux-sse41) psubw (x86-32-linux-sse41) pmullw (x86-32-linux-sse41) paddd (x86-32-linux-sse41) psubd (x86-32-linux-sse41) paddsb (x86-32-linux-sse41) paddsb (x86-32-linux-sse41) psubsb (x86-32-linux-sse41) paddusb (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) paddsw (x86-32-linux-sse41) psubsw (x86-32-linux-sse41) paddusw (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pcmp*b (x86-32-linux-sse41) pcmp*b (x86-32-linux-sse41) pcmp*w (x86-32-linux-sse41) pcmp*w (x86-32-linux-sse41) pcmp*d (x86-32-linux-sse41) pcmp*d (x86-32-linux-sse41) addps (x86-32-linux-sse41) subps (x86-32-linux-sse41) mulps (x86-32-linux-sse41) rsqrtps (x86-32-linux-sse41) rcpps (x86-32-linux-sse41) sqrtps (x86-32-linux-sse41) maxps (x86-32-linux-sse41) minps (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pmaxsw (x86-32-linux-sse41) pminsw (x86-32-linux-sse41) pmaxub (x86-32-linux-sse41) pminub (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) cmpeqps (x86-32-linux-sse41) cmpltps (x86-32-linux-sse41) paddb (x86-32-linux-sse41) psubb (x86-32-linux-sse41) paddw (x86-32-linux-sse41) psubw (x86-32-linux-sse41) pmullw (x86-32-linux-sse41) paddd (x86-32-linux-sse41) psubd (x86-32-linux-sse41) paddsb (x86-32-linux-sse41) paddsb (x86-32-linux-sse41) psubsb (x86-32-linux-sse41) paddusb (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) paddsw (x86-32-linux-sse41) psubsw (x86-32-linux-sse41) paddusw (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) psubusb (x86-32-linux-sse41) psubusw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pcmp*b (x86-32-linux-sse41) pcmp*b (x86-32-linux-sse41) pcmp*w (x86-32-linux-sse41) pcmp*w (x86-32-linux-sse41) pcmp*d (x86-32-linux-sse41) pcmp*d (x86-32-linux-sse41) addps (x86-32-linux-sse41) subps (x86-32-linux-sse41) mulps (x86-32-linux-sse41) rsqrtps (x86-32-linux-sse41) rcpps (x86-32-linux-sse41) sqrtps (x86-32-linux-sse41) maxps (x86-32-linux-sse41) minps (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pavgb (x86-32-linux-sse41) pavgw (x86-32-linux-sse41) pmaxsw (x86-32-linux-sse41) pminsw (x86-32-linux-sse41) pmaxub (x86-32-linux-sse41) pminub (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) pmulhuw (x86-32-linux-sse41) cmpeqps (x86-32-linux-sse41) cmpltps (x86-32-linux-sse41) orps (x86-32-linux-sse41) xorps (x86-32-linux-sse41) andps (x86-32-linux-sse41) shufps (x86-32-linux-sse41) addpd (x86-32-linux-sse41) subpd (x86-32-linux-sse41) mulpd (x86-32-linux-sse41) divpd (x86-32-linux-sse41) sqrtpd (x86-32-linux-sse41) maxpd (x86-32-linux-sse41) minpd (x86-32-linux-sse41) cmpeqpd (x86-32-linux-sse41) cmpltpd (x86-32-linux-sse41) paddq (x86-32-linux-sse41) psubq (x86-32-linux-sse41) pmuludq (x86-32-linux-sse41) packssdw (x86-32-linux-sse41) packsswb (x86-32-linux-sse41) packuswb (x86-32-linux-sse41) packssdw (x86-32-linux-sse41) packssdw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) addpd (x86-32-linux-sse41) subpd (x86-32-linux-sse41) mulpd (x86-32-linux-sse41) divpd (x86-32-linux-sse41) sqrtpd (x86-32-linux-sse41) maxpd (x86-32-linux-sse41) minpd (x86-32-linux-sse41) cmpeqpd (x86-32-linux-sse41) cmpltpd (x86-32-linux-sse41) paddq (x86-32-linux-sse41) psubq (x86-32-linux-sse41) pmuludq (x86-32-linux-sse41) packssdw (x86-32-linux-sse41) packsswb (x86-32-linux-sse41) packuswb (x86-32-linux-sse41) packssdw (x86-32-linux-sse41) packssdw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) psadbw (x86-32-linux-sse41) pmulhrsw (x86-32-linux-sse41) pmulhrsw (x86-32-linux-sse41) pabsb (x86-32-linux-sse41) pabsw (x86-32-linux-sse41) pabsd (x86-32-linux-sse41) pmulhrsw (x86-32-linux-sse41) pmulhrsw (x86-32-linux-sse41) pabsb (x86-32-linux-sse41) pabsw (x86-32-linux-sse41) pabsd (x86-32-linux-sse41) pmulhrsw (x86-32-linux-sse41) pmulhrsw (x86-32-linux-sse41) pabsb (x86-32-linux-sse41) pabsw (x86-32-linux-sse41) pabsd (x86-32-linux-sse41) movshdup (x86-32-linux-sse41) movshdup (x86-32-linux-sse41) movshdup (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) phminposuw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddubsw (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmaddwd (x86-32-linux-sse41) pmuludq (x86-32-linux-sse41) pmulld (x86-32-linux-sse41) blend*ps (x86-32-linux-sse41) blend*pd (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pmaxsb (x86-32-linux-sse41) pminsb (x86-32-linux-sse41) pmaxuw (x86-32-linux-sse41) pminuw (x86-32-linux-sse41) pmaxud (x86-32-linux-sse41) pminud (x86-32-linux-sse41) pmaxsd (x86-32-linux-sse41) pminsd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) pcmpeqq (x86-32-linux-sse41) packusdw (x86-32-linux-sse41) pmuludq (x86-32-linux-sse41) pmulld (x86-32-linux-sse41) blend*ps (x86-32-linux-sse41) blend*pd (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pmaxsb (x86-32-linux-sse41) pminsb (x86-32-linux-sse41) pmaxuw (x86-32-linux-sse41) pminuw (x86-32-linux-sse41) pmaxud (x86-32-linux-sse41) pminud (x86-32-linux-sse41) pmaxsd (x86-32-linux-sse41) pminsd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) pcmpeqq (x86-32-linux-sse41) packusdw (x86-32-linux-sse41) pmuludq (x86-32-linux-sse41) pmulld (x86-32-linux-sse41) blend*ps (x86-32-linux-sse41) blend*pd (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pblend*b (x86-32-linux-sse41) pmaxsb (x86-32-linux-sse41) pminsb (x86-32-linux-sse41) pmaxuw (x86-32-linux-sse41) pminuw (x86-32-linux-sse41) pmaxud (x86-32-linux-sse41) pminud (x86-32-linux-sse41) pmaxsd (x86-32-linux-sse41) pminsd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) roundps (x86-32-linux-sse41) roundpd (x86-32-linux-sse41) pcmpeqq (x86-32-linux-sse41) packusdw (x86-32-linux-sse41) paddsb (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-sse41) psubsb (x86-64-linux-avx-sse41) paddusb (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) paddsw (x86-64-linux-avx-sse41) psubsw (x86-64-linux-avx-sse41) paddusw (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) addps (x86-64-linux-avx-sse41) subps (x86-64-linux-avx-sse41) mulps (x86-64-linux-avx-sse41) rsqrtps (x86-64-linux-avx-sse41) rcpps (x86-64-linux-avx-sse41) sqrtps (x86-64-linux-avx-sse41) maxps (x86-64-linux-avx-sse41) minps (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pmaxsw (x86-64-linux-avx-sse41) pminsw (x86-64-linux-avx-sse41) pmaxub (x86-64-linux-avx-sse41) pminub (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) cmpeqps (x86-64-linux-avx-sse41) cmpltps (x86-64-linux-avx-sse41) paddb (x86-64-linux-avx-sse41) psubb (x86-64-linux-avx-sse41) paddw (x86-64-linux-avx-sse41) psubw (x86-64-linux-avx-sse41) pmullw (x86-64-linux-avx-sse41) paddd (x86-64-linux-avx-sse41) psubd (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-sse41) psubsb (x86-64-linux-avx-sse41) paddusb (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) paddsw (x86-64-linux-avx-sse41) psubsw (x86-64-linux-avx-sse41) paddusw (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pcmp*b (x86-64-linux-avx-sse41) pcmp*b (x86-64-linux-avx-sse41) pcmp*w (x86-64-linux-avx-sse41) pcmp*w (x86-64-linux-avx-sse41) pcmp*d (x86-64-linux-avx-sse41) pcmp*d (x86-64-linux-avx-sse41) addps (x86-64-linux-avx-sse41) subps (x86-64-linux-avx-sse41) mulps (x86-64-linux-avx-sse41) rsqrtps (x86-64-linux-avx-sse41) rcpps (x86-64-linux-avx-sse41) sqrtps (x86-64-linux-avx-sse41) maxps (x86-64-linux-avx-sse41) minps (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pmaxsw (x86-64-linux-avx-sse41) pminsw (x86-64-linux-avx-sse41) pmaxub (x86-64-linux-avx-sse41) pminub (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) cmpeqps (x86-64-linux-avx-sse41) cmpltps (x86-64-linux-avx-sse41) paddb (x86-64-linux-avx-sse41) psubb (x86-64-linux-avx-sse41) paddw (x86-64-linux-avx-sse41) psubw (x86-64-linux-avx-sse41) pmullw (x86-64-linux-avx-sse41) paddd (x86-64-linux-avx-sse41) psubd (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-sse41) psubsb (x86-64-linux-avx-sse41) paddusb (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) paddsw (x86-64-linux-avx-sse41) psubsw (x86-64-linux-avx-sse41) paddusw (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pcmp*b (x86-64-linux-avx-sse41) pcmp*b (x86-64-linux-avx-sse41) pcmp*w (x86-64-linux-avx-sse41) pcmp*w (x86-64-linux-avx-sse41) pcmp*d (x86-64-linux-avx-sse41) pcmp*d (x86-64-linux-avx-sse41) addps (x86-64-linux-avx-sse41) subps (x86-64-linux-avx-sse41) mulps (x86-64-linux-avx-sse41) rsqrtps (x86-64-linux-avx-sse41) rcpps (x86-64-linux-avx-sse41) sqrtps (x86-64-linux-avx-sse41) maxps (x86-64-linux-avx-sse41) minps (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pmaxsw (x86-64-linux-avx-sse41) pminsw (x86-64-linux-avx-sse41) pmaxub (x86-64-linux-avx-sse41) pminub (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) cmpeqps (x86-64-linux-avx-sse41) cmpltps (x86-64-linux-avx-sse41) paddb (x86-64-linux-avx-sse41) psubb (x86-64-linux-avx-sse41) paddw (x86-64-linux-avx-sse41) psubw (x86-64-linux-avx-sse41) pmullw (x86-64-linux-avx-sse41) paddd (x86-64-linux-avx-sse41) psubd (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-sse41) psubsb (x86-64-linux-avx-sse41) paddusb (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) paddsw (x86-64-linux-avx-sse41) psubsw (x86-64-linux-avx-sse41) paddusw (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) psubusb (x86-64-linux-avx-sse41) psubusw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pcmp*b (x86-64-linux-avx-sse41) pcmp*b (x86-64-linux-avx-sse41) pcmp*w (x86-64-linux-avx-sse41) pcmp*w (x86-64-linux-avx-sse41) pcmp*d (x86-64-linux-avx-sse41) pcmp*d (x86-64-linux-avx-sse41) addps (x86-64-linux-avx-sse41) subps (x86-64-linux-avx-sse41) mulps (x86-64-linux-avx-sse41) rsqrtps (x86-64-linux-avx-sse41) rcpps (x86-64-linux-avx-sse41) sqrtps (x86-64-linux-avx-sse41) maxps (x86-64-linux-avx-sse41) minps (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pavgb (x86-64-linux-avx-sse41) pavgw (x86-64-linux-avx-sse41) pmaxsw (x86-64-linux-avx-sse41) pminsw (x86-64-linux-avx-sse41) pmaxub (x86-64-linux-avx-sse41) pminub (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) pmulhuw (x86-64-linux-avx-sse41) cmpeqps (x86-64-linux-avx-sse41) cmpltps (x86-64-linux-avx-sse41) orps (x86-64-linux-avx-sse41) xorps (x86-64-linux-avx-sse41) andps (x86-64-linux-avx-sse41) shufps (x86-64-linux-avx-sse41) addpd (x86-64-linux-avx-sse41) subpd (x86-64-linux-avx-sse41) mulpd (x86-64-linux-avx-sse41) divpd (x86-64-linux-avx-sse41) sqrtpd (x86-64-linux-avx-sse41) maxpd (x86-64-linux-avx-sse41) minpd (x86-64-linux-avx-sse41) cmpeqpd (x86-64-linux-avx-sse41) cmpltpd (x86-64-linux-avx-sse41) paddq (x86-64-linux-avx-sse41) psubq (x86-64-linux-avx-sse41) pmuludq (x86-64-linux-avx-sse41) packssdw (x86-64-linux-avx-sse41) packsswb (x86-64-linux-avx-sse41) packuswb (x86-64-linux-avx-sse41) packssdw (x86-64-linux-avx-sse41) packssdw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) addpd (x86-64-linux-avx-sse41) subpd (x86-64-linux-avx-sse41) mulpd (x86-64-linux-avx-sse41) divpd (x86-64-linux-avx-sse41) sqrtpd (x86-64-linux-avx-sse41) maxpd (x86-64-linux-avx-sse41) minpd (x86-64-linux-avx-sse41) cmpeqpd (x86-64-linux-avx-sse41) cmpltpd (x86-64-linux-avx-sse41) paddq (x86-64-linux-avx-sse41) psubq (x86-64-linux-avx-sse41) pmuludq (x86-64-linux-avx-sse41) packssdw (x86-64-linux-avx-sse41) packsswb (x86-64-linux-avx-sse41) packuswb (x86-64-linux-avx-sse41) packssdw (x86-64-linux-avx-sse41) packssdw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) psadbw (x86-64-linux-avx-sse41) pmulhrsw (x86-64-linux-avx-sse41) pmulhrsw (x86-64-linux-avx-sse41) pabsb (x86-64-linux-avx-sse41) pabsw (x86-64-linux-avx-sse41) pabsd (x86-64-linux-avx-sse41) pmulhrsw (x86-64-linux-avx-sse41) pmulhrsw (x86-64-linux-avx-sse41) pabsb (x86-64-linux-avx-sse41) pabsw (x86-64-linux-avx-sse41) pabsd (x86-64-linux-avx-sse41) pmulhrsw (x86-64-linux-avx-sse41) pmulhrsw (x86-64-linux-avx-sse41) pabsb (x86-64-linux-avx-sse41) pabsw (x86-64-linux-avx-sse41) pabsd (x86-64-linux-avx-sse41) movshdup (x86-64-linux-avx-sse41) movshdup (x86-64-linux-avx-sse41) movshdup (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) phminposuw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddubsw (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmaddwd (x86-64-linux-avx-sse41) pmuludq (x86-64-linux-avx-sse41) pmulld (x86-64-linux-avx-sse41) blend*ps (x86-64-linux-avx-sse41) blend*pd (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pmaxsb (x86-64-linux-avx-sse41) pminsb (x86-64-linux-avx-sse41) pmaxuw (x86-64-linux-avx-sse41) pminuw (x86-64-linux-avx-sse41) pmaxud (x86-64-linux-avx-sse41) pminud (x86-64-linux-avx-sse41) pmaxsd (x86-64-linux-avx-sse41) pminsd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) pcmpeqq (x86-64-linux-avx-sse41) packusdw (x86-64-linux-avx-sse41) pmuludq (x86-64-linux-avx-sse41) pmulld (x86-64-linux-avx-sse41) blend*ps (x86-64-linux-avx-sse41) blend*pd (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pmaxsb (x86-64-linux-avx-sse41) pminsb (x86-64-linux-avx-sse41) pmaxuw (x86-64-linux-avx-sse41) pminuw (x86-64-linux-avx-sse41) pmaxud (x86-64-linux-avx-sse41) pminud (x86-64-linux-avx-sse41) pmaxsd (x86-64-linux-avx-sse41) pminsd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) pcmpeqq (x86-64-linux-avx-sse41) packusdw (x86-64-linux-avx-sse41) pmuludq (x86-64-linux-avx-sse41) pmulld (x86-64-linux-avx-sse41) blend*ps (x86-64-linux-avx-sse41) blend*pd (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pblend*b (x86-64-linux-avx-sse41) pmaxsb (x86-64-linux-avx-sse41) pminsb (x86-64-linux-avx-sse41) pmaxuw (x86-64-linux-avx-sse41) pminuw (x86-64-linux-avx-sse41) pmaxud (x86-64-linux-avx-sse41) pminud (x86-64-linux-avx-sse41) pmaxsd (x86-64-linux-avx-sse41) pminsd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) roundps (x86-64-linux-avx-sse41) roundpd (x86-64-linux-avx-sse41) pcmpeqq (x86-64-linux-avx-sse41) packusdw (x86-64-linux-avx-sse41) pcmpgtq (x86-64-linux-avx-sse41) vsqrtps*ymm (x86-64-linux-avx-sse41) vsqrtpd*ymm (x86-64-linux-avx-sse41) vrsqrtps*ymm (x86-64-linux-avx-sse41) vrcpps*ymm (x86-64-linux-avx-sse41) vaddps*ymm (x86-64-linux-avx-sse41) vaddpd*ymm (x86-64-linux-avx-sse41) vmulps*ymm (x86-64-linux-avx-sse41) vmulpd*ymm (x86-64-linux-avx-sse41) vsubps*ymm (x86-64-linux-avx-sse41) vsubpd*ymm (x86-64-linux-avx-sse41) vminps*ymm (x86-64-linux-avx-sse41) vminpd*ymm (x86-64-linux-avx-sse41) vmaxps*ymm (x86-64-linux-avx-sse41) vmaxpd*ymm (x86-64-linux-avx-sse41) vroundps*ymm (x86-64-linux-avx-sse41) vroundpd*ymm (x86-64-linux-avx-sse41) vcmpeqpd*ymm (x86-64-linux-avx-sse41) vcmpltpd*ymm (x86-64-linux-avx-sse41) vcmpeqps*ymm (x86-64-linux-avx-sse41) vcmpltps*ymm (x86-64-linux-avx-sse41) vblend*ps*ymm (x86-64-linux-avx-sse41) vblend*pd*ymm (x86-64-linux-avx-sse41) vcvttps2dq*ymm (x86-64-linux-avx-sse41) vcvtdq2ps*ymm (x86-64-linux-avx-sse41) vcvttpd2dq*xmm (x86-64-linux-avx-sse41) vcvtdq2pd*ymm (x86-64-linux-avx-sse41) vcvtps2pd*ymm (x86-64-linux-avx-sse41) vcvtpd2ps*xmm (x86-64-linux-avx-sse41) paddsb (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-sse41) psubsb (x86-64-linux-avx-avx2-sse41) paddusb (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) paddsw (x86-64-linux-avx-avx2-sse41) psubsw (x86-64-linux-avx-avx2-sse41) paddusw (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) addps (x86-64-linux-avx-avx2-sse41) subps (x86-64-linux-avx-avx2-sse41) mulps (x86-64-linux-avx-avx2-sse41) rsqrtps (x86-64-linux-avx-avx2-sse41) rcpps (x86-64-linux-avx-avx2-sse41) sqrtps (x86-64-linux-avx-avx2-sse41) maxps (x86-64-linux-avx-avx2-sse41) minps (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pmaxsw (x86-64-linux-avx-avx2-sse41) pminsw (x86-64-linux-avx-avx2-sse41) pmaxub (x86-64-linux-avx-avx2-sse41) pminub (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) cmpeqps (x86-64-linux-avx-avx2-sse41) cmpltps (x86-64-linux-avx-avx2-sse41) paddb (x86-64-linux-avx-avx2-sse41) psubb (x86-64-linux-avx-avx2-sse41) paddw (x86-64-linux-avx-avx2-sse41) psubw (x86-64-linux-avx-avx2-sse41) pmullw (x86-64-linux-avx-avx2-sse41) paddd (x86-64-linux-avx-avx2-sse41) psubd (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-sse41) psubsb (x86-64-linux-avx-avx2-sse41) paddusb (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) paddsw (x86-64-linux-avx-avx2-sse41) psubsw (x86-64-linux-avx-avx2-sse41) paddusw (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pcmp*b (x86-64-linux-avx-avx2-sse41) pcmp*b (x86-64-linux-avx-avx2-sse41) pcmp*w (x86-64-linux-avx-avx2-sse41) pcmp*w (x86-64-linux-avx-avx2-sse41) pcmp*d (x86-64-linux-avx-avx2-sse41) pcmp*d (x86-64-linux-avx-avx2-sse41) addps (x86-64-linux-avx-avx2-sse41) subps (x86-64-linux-avx-avx2-sse41) mulps (x86-64-linux-avx-avx2-sse41) rsqrtps (x86-64-linux-avx-avx2-sse41) rcpps (x86-64-linux-avx-avx2-sse41) sqrtps (x86-64-linux-avx-avx2-sse41) maxps (x86-64-linux-avx-avx2-sse41) minps (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pmaxsw (x86-64-linux-avx-avx2-sse41) pminsw (x86-64-linux-avx-avx2-sse41) pmaxub (x86-64-linux-avx-avx2-sse41) pminub (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) cmpeqps (x86-64-linux-avx-avx2-sse41) cmpltps (x86-64-linux-avx-avx2-sse41) paddb (x86-64-linux-avx-avx2-sse41) psubb (x86-64-linux-avx-avx2-sse41) paddw (x86-64-linux-avx-avx2-sse41) psubw (x86-64-linux-avx-avx2-sse41) pmullw (x86-64-linux-avx-avx2-sse41) paddd (x86-64-linux-avx-avx2-sse41) psubd (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-sse41) psubsb (x86-64-linux-avx-avx2-sse41) paddusb (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) paddsw (x86-64-linux-avx-avx2-sse41) psubsw (x86-64-linux-avx-avx2-sse41) paddusw (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pcmp*b (x86-64-linux-avx-avx2-sse41) pcmp*b (x86-64-linux-avx-avx2-sse41) pcmp*w (x86-64-linux-avx-avx2-sse41) pcmp*w (x86-64-linux-avx-avx2-sse41) pcmp*d (x86-64-linux-avx-avx2-sse41) pcmp*d (x86-64-linux-avx-avx2-sse41) addps (x86-64-linux-avx-avx2-sse41) subps (x86-64-linux-avx-avx2-sse41) mulps (x86-64-linux-avx-avx2-sse41) rsqrtps (x86-64-linux-avx-avx2-sse41) rcpps (x86-64-linux-avx-avx2-sse41) sqrtps (x86-64-linux-avx-avx2-sse41) maxps (x86-64-linux-avx-avx2-sse41) minps (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pmaxsw (x86-64-linux-avx-avx2-sse41) pminsw (x86-64-linux-avx-avx2-sse41) pmaxub (x86-64-linux-avx-avx2-sse41) pminub (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) cmpeqps (x86-64-linux-avx-avx2-sse41) cmpltps (x86-64-linux-avx-avx2-sse41) paddb (x86-64-linux-avx-avx2-sse41) psubb (x86-64-linux-avx-avx2-sse41) paddw (x86-64-linux-avx-avx2-sse41) psubw (x86-64-linux-avx-avx2-sse41) pmullw (x86-64-linux-avx-avx2-sse41) paddd (x86-64-linux-avx-avx2-sse41) psubd (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-sse41) psubsb (x86-64-linux-avx-avx2-sse41) paddusb (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) paddsw (x86-64-linux-avx-avx2-sse41) psubsw (x86-64-linux-avx-avx2-sse41) paddusw (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) psubusb (x86-64-linux-avx-avx2-sse41) psubusw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pmulhw (x86-64-linux-avx-avx2-sse41) pmulhuw (x86-64-linux-avx-avx2-sse41) pcmp*b (x86-64-linux-avx-avx2-sse41) pcmp*b (x86-64-linux-avx-avx2-sse41) pcmp*w (x86-64-linux-avx-avx2-sse41) pcmp*w (x86-64-linux-avx-avx2-sse41) pcmp*d (x86-64-linux-avx-avx2-sse41) pcmp*d (x86-64-linux-avx-avx2-sse41) addps (x86-64-linux-avx-avx2-sse41) subps (x86-64-linux-avx-avx2-sse41) mulps (x86-64-linux-avx-avx2-sse41) rsqrtps (x86-64-linux-avx-avx2-sse41) rcpps (x86-64-linux-avx-avx2-sse41) sqrtps (x86-64-linux-avx-avx2-sse41) maxps (x86-64-linux-avx-avx2-sse41) minps (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pavgb (x86-64-linux-avx-avx2-sse41) pavgw (x86-64-linux-avx-avx2-sse41) pmaxsw (x86-64-linux-avx-avx2-sse41) pminsw (x86-64-linux-avx-avx2-sse41) pmaxub (x86-64-linux-avx-avx2-sse41) pminub (x86-64-linux-avx-avx2-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-sse41) cmpeqps (x86-64-linux-avx-avx2-sse41) cmpltps (x86-64-linux-avx-avx2-sse41) orps (x86-64-linux-avx-avx2-sse41) xorps (x86-64-linux-avx-avx2-sse41) andps (x86-64-linux-avx-avx2-sse41) shufps (x86-64-linux-avx-avx2-sse41) addpd (x86-64-linux-avx-avx2-sse41) subpd (x86-64-linux-avx-avx2-sse41) mulpd (x86-64-linux-avx-avx2-sse41) divpd (x86-64-linux-avx-avx2-sse41) sqrtpd (x86-64-linux-avx-avx2-sse41) maxpd (x86-64-linux-avx-avx2-sse41) minpd (x86-64-linux-avx-avx2-sse41) cmpeqpd (x86-64-linux-avx-avx2-sse41) cmpltpd (x86-64-linux-avx-avx2-sse41) paddq (x86-64-linux-avx-avx2-sse41) psubq (x86-64-linux-avx-avx2-sse41) pmuludq (x86-64-linux-avx-avx2-sse41) packssdw (x86-64-linux-avx-avx2-sse41) packsswb (x86-64-linux-avx-avx2-sse41) packuswb (x86-64-linux-avx-avx2-sse41) packssdw (x86-64-linux-avx-avx2-sse41) packssdw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) addpd (x86-64-linux-avx-avx2-sse41) subpd (x86-64-linux-avx-avx2-sse41) mulpd (x86-64-linux-avx-avx2-sse41) divpd (x86-64-linux-avx-avx2-sse41) sqrtpd (x86-64-linux-avx-avx2-sse41) maxpd (x86-64-linux-avx-avx2-sse41) minpd (x86-64-linux-avx-avx2-sse41) cmpeqpd (x86-64-linux-avx-avx2-sse41) cmpltpd (x86-64-linux-avx-avx2-sse41) paddq (x86-64-linux-avx-avx2-sse41) psubq (x86-64-linux-avx-avx2-sse41) pmuludq (x86-64-linux-avx-avx2-sse41) packssdw*ymm (x86-64-linux-avx-avx2-sse41) packsswb*ymm (x86-64-linux-avx-avx2-sse41) packuswb*ymm (x86-64-linux-avx-avx2-sse41) packssdw*ymm (x86-64-linux-avx-avx2-sse41) packssdw*ymm (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) psadbw (x86-64-linux-avx-avx2-sse41) pmulhrsw (x86-64-linux-avx-avx2-sse41) pmulhrsw (x86-64-linux-avx-avx2-sse41) pabsb (x86-64-linux-avx-avx2-sse41) pabsw (x86-64-linux-avx-avx2-sse41) pabsd (x86-64-linux-avx-avx2-sse41) pmulhrsw (x86-64-linux-avx-avx2-sse41) pmulhrsw (x86-64-linux-avx-avx2-sse41) pabsb (x86-64-linux-avx-avx2-sse41) pabsw (x86-64-linux-avx-avx2-sse41) pabsd (x86-64-linux-avx-avx2-sse41) pmulhrsw (x86-64-linux-avx-avx2-sse41) pmulhrsw (x86-64-linux-avx-avx2-sse41) pabsb (x86-64-linux-avx-avx2-sse41) pabsw (x86-64-linux-avx-avx2-sse41) pabsd (x86-64-linux-avx-avx2-sse41) movshdup (x86-64-linux-avx-avx2-sse41) movshdup (x86-64-linux-avx-avx2-sse41) movshdup (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) phminposuw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) vpmaddubsw (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) pmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) vpmaddwd (x86-64-linux-avx-avx2-sse41) pmuludq (x86-64-linux-avx-avx2-sse41) pmulld (x86-64-linux-avx-avx2-sse41) blend*ps (x86-64-linux-avx-avx2-sse41) blend*pd (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pmaxsb (x86-64-linux-avx-avx2-sse41) pminsb (x86-64-linux-avx-avx2-sse41) pmaxuw (x86-64-linux-avx-avx2-sse41) pminuw (x86-64-linux-avx-avx2-sse41) pmaxud (x86-64-linux-avx-avx2-sse41) pminud (x86-64-linux-avx-avx2-sse41) pmaxsd (x86-64-linux-avx-avx2-sse41) pminsd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) pcmpeqq (x86-64-linux-avx-avx2-sse41) packusdw (x86-64-linux-avx-avx2-sse41) pmuludq (x86-64-linux-avx-avx2-sse41) pmulld (x86-64-linux-avx-avx2-sse41) blend*ps (x86-64-linux-avx-avx2-sse41) blend*pd (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pmaxsb (x86-64-linux-avx-avx2-sse41) pminsb (x86-64-linux-avx-avx2-sse41) pmaxuw (x86-64-linux-avx-avx2-sse41) pminuw (x86-64-linux-avx-avx2-sse41) pmaxud (x86-64-linux-avx-avx2-sse41) pminud (x86-64-linux-avx-avx2-sse41) pmaxsd (x86-64-linux-avx-avx2-sse41) pminsd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) pcmpeqq (x86-64-linux-avx-avx2-sse41) packusdw (x86-64-linux-avx-avx2-sse41) pmuludq (x86-64-linux-avx-avx2-sse41) pmulld (x86-64-linux-avx-avx2-sse41) blend*ps (x86-64-linux-avx-avx2-sse41) blend*pd (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pblend*b (x86-64-linux-avx-avx2-sse41) pmaxsb (x86-64-linux-avx-avx2-sse41) pminsb (x86-64-linux-avx-avx2-sse41) pmaxuw (x86-64-linux-avx-avx2-sse41) pminuw (x86-64-linux-avx-avx2-sse41) pmaxud (x86-64-linux-avx-avx2-sse41) pminud (x86-64-linux-avx-avx2-sse41) pmaxsd (x86-64-linux-avx-avx2-sse41) pminsd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) roundps (x86-64-linux-avx-avx2-sse41) roundpd (x86-64-linux-avx-avx2-sse41) pcmpeqq (x86-64-linux-avx-avx2-sse41) packusdw (x86-64-linux-avx-avx2-sse41) pcmpgtq (x86-64-linux-avx-avx2-sse41) vsqrtps*ymm (x86-64-linux-avx-avx2-sse41) vsqrtpd*ymm (x86-64-linux-avx-avx2-sse41) vrsqrtps*ymm (x86-64-linux-avx-avx2-sse41) vrcpps*ymm (x86-64-linux-avx-avx2-sse41) vaddps*ymm (x86-64-linux-avx-avx2-sse41) vaddpd*ymm (x86-64-linux-avx-avx2-sse41) vmulps*ymm (x86-64-linux-avx-avx2-sse41) vmulpd*ymm (x86-64-linux-avx-avx2-sse41) vsubps*ymm (x86-64-linux-avx-avx2-sse41) vsubpd*ymm (x86-64-linux-avx-avx2-sse41) vminps*ymm (x86-64-linux-avx-avx2-sse41) vminpd*ymm (x86-64-linux-avx-avx2-sse41) vmaxps*ymm (x86-64-linux-avx-avx2-sse41) vmaxpd*ymm (x86-64-linux-avx-avx2-sse41) vroundps*ymm (x86-64-linux-avx-avx2-sse41) vroundpd*ymm (x86-64-linux-avx-avx2-sse41) vcmpeqpd*ymm (x86-64-linux-avx-avx2-sse41) vcmpltpd*ymm (x86-64-linux-avx-avx2-sse41) vcmpeqps*ymm (x86-64-linux-avx-avx2-sse41) vcmpltps*ymm (x86-64-linux-avx-avx2-sse41) vblend*ps*ymm (x86-64-linux-avx-avx2-sse41) vblend*pd*ymm (x86-64-linux-avx-avx2-sse41) vcvttps2dq*ymm (x86-64-linux-avx-avx2-sse41) vcvtdq2ps*ymm (x86-64-linux-avx-avx2-sse41) vcvttpd2dq*xmm (x86-64-linux-avx-avx2-sse41) vcvtdq2pd*ymm (x86-64-linux-avx-avx2-sse41) vcvtps2pd*ymm (x86-64-linux-avx-avx2-sse41) vcvtpd2ps*xmm (x86-64-linux-avx-avx2-sse41) vpaddb*ymm (x86-64-linux-avx-avx2-sse41) vpsubb*ymm (x86-64-linux-avx-avx2-sse41) vpaddsb*ymm (x86-64-linux-avx-avx2-sse41) vpsubsb*ymm (x86-64-linux-avx-avx2-sse41) vpaddusb*ymm (x86-64-linux-avx-avx2-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-sse41) vpaddw*ymm (x86-64-linux-avx-avx2-sse41) vpsubw*ymm (x86-64-linux-avx-avx2-sse41) vpaddsw*ymm (x86-64-linux-avx-avx2-sse41) vpsubsw*ymm (x86-64-linux-avx-avx2-sse41) vpaddusw*ymm (x86-64-linux-avx-avx2-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-sse41) vpaddd*ymm (x86-64-linux-avx-avx2-sse41) vpsubd*ymm (x86-64-linux-avx-avx2-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-sse41) vpmullw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-sse41) vpavgb*ymm (x86-64-linux-avx-avx2-sse41) vpavgw*ymm (x86-64-linux-avx-avx2-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-sse41) vpminsw*ymm (x86-64-linux-avx-avx2-sse41) vpmaxub*ymm (x86-64-linux-avx-avx2-sse41) vpminub*ymm (x86-64-linux-avx-avx2-sse41) vpabsb*ymm (x86-64-linux-avx-avx2-sse41) vpabsw*ymm (x86-64-linux-avx-avx2-sse41) vpabsd*ymm (x86-64-linux-avx-avx2-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-sse41) vpaddq*ymm (x86-64-linux-avx-avx2-sse41) vpsubq*ymm (x86-64-linux-avx-avx2-sse41) vpmuludq*ymm (x86-64-linux-avx-avx2-sse41) vpmuludq*ymm (x86-64-linux-avx-avx2-sse41) vpmulld*ymm (x86-64-linux-avx-avx2-sse41) vpblend*b*ymm (x86-64-linux-avx-avx2-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-sse41) vpminsb*ymm (x86-64-linux-avx-avx2-sse41) vpmaxuw*ymm (x86-64-linux-avx-avx2-sse41) vpminuw*ymm (x86-64-linux-avx-avx2-sse41) vpmaxud*ymm (x86-64-linux-avx-avx2-sse41) vpminud*ymm (x86-64-linux-avx-avx2-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-sse41) vpminsd*ymm (x86-64-linux-avx-avx2-sse41) vpcmpeqq*ymm (x86-64-linux-avx-avx2-sse41) vpackusdw*ymm (x86-64-linux-avx-avx2-sse41) vpcmpgtq*ymm (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) vpsadbw (x86-64-linux-avx-avx2-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) korw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) kxorw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) shufps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) addpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) subpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) mulpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) divpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) sqrtpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) maxpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) minpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpeqpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpltpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packsswb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packuswb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) addpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) subpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) mulpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) divpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) sqrtpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) maxpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) minpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpeqpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) cmpltpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psubq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packsswb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packuswb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) pcmpgtq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vsqrtps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vsqrtpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vaddps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vaddpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vmulps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vmulpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vsubps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vsubpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vminps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vminpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vmaxps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vmaxpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vroundps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vroundpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcmpeqpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcmpltpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcmpeqps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcmpltps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcvttps2dq*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcvtdq2ps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcvttpd2dq*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcvtdq2pd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcvtps2pd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vcvtpd2ps*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmullw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpavgb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpavgw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxub*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminub*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpabsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpabsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpabsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmullw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhrsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulhrsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*b*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*b*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*w*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*w*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*d*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmp*d*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpavgb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpavgw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxub*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminub*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpabsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpabsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpabsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpaddq*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsubq*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmulld*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxuw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminuw*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxud*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminud*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxud*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminud*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmpeqq*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpackusdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpcmpgtq*ymm (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpabsq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxuq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminuq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpmaxsq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) vpminsq (x86-64-linux-avx-avx2-avx512-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) korw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) kxorw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) shufps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) addpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) subpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) mulpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) divpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) sqrtpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) maxpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) minpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpeqpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpltpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packsswb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packuswb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) addpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) subpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) mulpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) divpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) sqrtpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) maxpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) minpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpeqpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) cmpltpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psubq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packsswb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packuswb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) pcmpgtq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vsqrtps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vsqrtpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vaddps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vaddpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vmulps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vmulpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vsubps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vsubpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vminps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vminpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vmaxps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vmaxpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vroundps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vroundpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcmpeqpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcmpltpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcmpeqps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcmpltps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcvttps2dq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcvtdq2ps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcvttpd2dq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcvtdq2pd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcvtps2pd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vcvtpd2ps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmullw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpavgb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpavgw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxub*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminub*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpabsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpabsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpabsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmullw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhrsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulhrsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*b*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*b*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*w*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*w*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*d*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmp*d*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpavgb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpavgw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxub*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminub*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpabsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpabsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpabsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpaddq*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsubq*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmulld*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxuw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminuw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxud*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminud*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxud*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminud*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmpeqq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpackusdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpcmpgtq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpabsq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxuq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminuq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpmaxsq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) vpminsq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmullw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubusw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*b (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*w (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmp*d (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) addps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) subps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) mulps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) sqrtps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) maxps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) minps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pavgw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminub (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpeqps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpltps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) korw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) kxorw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) shufps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) addpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) subpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) mulpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) divpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) sqrtpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) maxpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) minpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpeqpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpltpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packsswb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packuswb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packssdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) addpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) subpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) mulpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) divpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) sqrtpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) maxpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) minpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpeqpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) cmpltpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) paddq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psubq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packsswb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packuswb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packssdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) psadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulhrsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pabsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) movshdup (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) phminposuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddubsw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaddwd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmulld (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsb (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminuw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminud (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pmaxsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pminsd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) roundpd (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmpeqq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) packusdw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) pcmpgtq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vsqrtps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vsqrtpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrsqrt*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vrcp*ps (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vaddps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vaddpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vmulps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vmulpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vsubps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vsubpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vminps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vminpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vmaxps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vmaxpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vroundps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vroundpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcmpeqpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcmpltpd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcmpeqps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcmpltps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcvttps2dq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcvtdq2ps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcvttpd2dq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcvtdq2pd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcvtps2pd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vcvtpd2ps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmullw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhrsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*b*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*w*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*d*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpavgb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpavgw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxub*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminub*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpabsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpabsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpabsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmullw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhrsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulhrsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*b*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*b*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*w*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*w*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*d*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmp*d*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpavgb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpavgw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxub*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminub*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpabsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpabsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpabsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubusw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpaddq*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsubq*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmullq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmulld*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vmov*%k (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminsb*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxuw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminuw*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxud*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminud*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminsd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminsb*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminuw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxud*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminud*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminsd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmpeqq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpackusdw*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpcmpgtq*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpsadbw (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpabsq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxuq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminuq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpmaxsq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpminsq (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) Warning: In function test_op_vdpbf16ps_zmm_608, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. vdpbf16ps*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) Warning: In function test_op_vdpbf16ps_ymm_609, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. vdpbf16ps*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) Warning: In function test_op_vdpbf16ps_xmm_610, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. vdpbf16ps*xmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpwssd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpwssd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpwssd*xmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusd*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusd*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusd*xmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusd*xmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpwssds*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpwssds*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpwssds*xmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusds*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusds*zmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusds*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusds*ymm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusds*xmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) vpdpbusds*xmm (x86-64-linux-avx-avx2-avx512-avx512_cannonlake-avx512_sapphirerapids-avx512_skylake-sse41) Success! ======================================== ======================================== correctness_simplified_away_embedded_image.exe Success! ======================================== ======================================== correctness_simplify.exe Success! ======================================== ======================================== correctness_skip_stages.exe Success! ======================================== ======================================== correctness_skip_stages_external_array_functions.exe Success! ======================================== ======================================== correctness_skip_stages_memoize.exe Running single_memoize_test Running tuple_memoize_test Running non_trivial_allocate_predicate_test Running double_memoize_test Success! ======================================== ======================================== correctness_sliding_backwards.exe Success! ======================================== ======================================== correctness_sliding_over_guard_with_if.exe Success! ======================================== ======================================== correctness_sliding_reduction.exe Success! ======================================== ======================================== correctness_sliding_window.exe Success! ======================================== ======================================== correctness_sort_exprs.exe 9 -0.958924 -0.756802 -0.279415 0.000000 0.141120 0.656987 0.841471 0.909297 0.989358 Success! ======================================== ======================================== correctness_specialize.exe Success! ======================================== ======================================== correctness_specialize_to_gpu.exe ======================================== ======================================== correctness_split_by_non_factor.exe Success! ======================================== ======================================== correctness_split_fuse_rvar.exe Success! ======================================== ======================================== correctness_split_reuse_inner_name_bug.exe Success! ======================================== ======================================== correctness_split_store_compute.exe Defining function... Success! ======================================== ======================================== correctness_stack_allocations.exe Success! ======================================== ======================================== correctness_stage_strided_loads.exe Success! ======================================== ======================================== correctness_stencil_chain_in_update_definitions.exe Success! ======================================== ======================================== correctness_stmt_to_html.exe Success! ======================================== ======================================== correctness_storage_folding.exe Expected err: The fold factor (4) of dimension v16 of f97 is too small to store the required region accessed by loop f99.s0.v16.v16 (8). Expected err: Cannot fold dimension 1 of f106 because an extern stage accesses [0, 3], which is outside the range currently valid: [3, 6]. Expected err: The fold factor (4) of dimension v26 of f115 is too small to store the required region accessed by loop f117.s0.v26.v26 (86). Expected err: Cannot fold dimension 1 of f125 because an extern stage accesses [3, 6], which wraps around the boundary of the fold, which occurs at multiples of 4. Success! ======================================== ======================================== correctness_store_in.exe Success! ======================================== ======================================== correctness_stream_compaction.exe Success! ======================================== ======================================== correctness_strict_float.exe Running on random data: Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333357.9688 residual: -123.53125 simple_float_vec_4: 333463.9062 residual: -17.59375 simple_float_vec_8: 333475.5625 residual: -5.9375 kahan: 333357.9688 residual: -123.53125 kahan_vec_4: 333463.9062 residual: -17.59375 kahan_vec_8: 333475.5625 residual: -5.9375 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333357.9375 residual: -123.5625 simple_float_vec_4: 333463.9375 residual: -17.5625 simple_float_vec_8: 333475.5625 residual: -5.9375 kahan: 333481.5 residual: 0 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333357.9375 residual: -123.5625 simple_float_vec_4: 333463.9375 residual: -17.5625 simple_float_vec_8: 333475.5625 residual: -5.9375 kahan: 333357.9375 residual: -123.5625 kahan_vec_4: 333463.9375 residual: -17.5625 kahan_vec_8: 333475.5625 residual: -5.9375 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333357.9375 residual: -123.5625 simple_float_vec_4: 333463.9375 residual: -17.5625 simple_float_vec_8: 333475.5625 residual: -5.9375 kahan: 333481.5 residual: 0 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Running on random transposed data: Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333361.5 residual: -120 simple_float_vec_4: 333464.4688 residual: -17.03125 simple_float_vec_8: 333474.6875 residual: -6.8125 kahan: 333361.5 residual: -120 kahan_vec_4: 333464.4688 residual: -17.03125 kahan_vec_8: 333474.6875 residual: -6.8125 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333361.5 residual: -120 simple_float_vec_4: 333464.4375 residual: -17.0625 simple_float_vec_8: 333474.6562 residual: -6.84375 kahan: 333481.5312 residual: 0.03125 kahan_vec_4: 333481.5312 residual: 0.03125 kahan_vec_8: 333481.5 residual: 0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333361.5 residual: -120 simple_float_vec_4: 333464.4375 residual: -17.0625 simple_float_vec_8: 333474.6562 residual: -6.84375 kahan: 333361.5 residual: -120 kahan_vec_4: 333464.4375 residual: -17.0625 kahan_vec_8: 333474.6562 residual: -6.84375 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333361.5 residual: -120 simple_float_vec_4: 333464.4375 residual: -17.0625 simple_float_vec_8: 333474.6562 residual: -6.84375 kahan: 333481.5312 residual: 0.03125 kahan_vec_4: 333481.5312 residual: 0.03125 kahan_vec_8: 333481.5 residual: 0 Running on sorted ascending data: Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333495.0312 residual: 13.53125 simple_float_vec_4: 333482.8125 residual: 1.3125 simple_float_vec_8: 333481.7188 residual: 0.21875 kahan: 333495.0312 residual: 13.53125 kahan_vec_4: 333482.8125 residual: 1.3125 kahan_vec_8: 333481.7188 residual: 0.21875 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333495.0312 residual: 13.53125 simple_float_vec_4: 333482.8125 residual: 1.3125 simple_float_vec_8: 333481.7188 residual: 0.21875 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333495.0312 residual: 13.53125 simple_float_vec_4: 333482.8125 residual: 1.3125 simple_float_vec_8: 333481.7188 residual: 0.21875 kahan: 333495.0312 residual: 13.53125 kahan_vec_4: 333482.8125 residual: 1.3125 kahan_vec_8: 333481.7188 residual: 0.21875 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333495.0312 residual: 13.53125 simple_float_vec_4: 333482.8125 residual: 1.3125 simple_float_vec_8: 333481.7188 residual: 0.21875 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Running on sorted ascending transposed data: Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333724.9375 residual: 243.4375 simple_float_vec_4: 333480.5625 residual: -0.9375 simple_float_vec_8: 333482.6875 residual: 1.1875 kahan: 333724.9375 residual: 243.4375 kahan_vec_4: 333480.5625 residual: -0.9375 kahan_vec_8: 333482.6875 residual: 1.1875 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333724.9375 residual: 243.4375 simple_float_vec_4: 333480.5938 residual: -0.90625 simple_float_vec_8: 333482.6875 residual: 1.1875 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333724.9375 residual: 243.4375 simple_float_vec_4: 333480.5938 residual: -0.90625 simple_float_vec_8: 333482.6875 residual: 1.1875 kahan: 333724.9375 residual: 243.4375 kahan_vec_4: 333480.5938 residual: -0.90625 kahan_vec_8: 333482.6875 residual: 1.1875 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333724.9375 residual: 243.4375 simple_float_vec_4: 333480.5938 residual: -0.90625 simple_float_vec_8: 333482.6875 residual: 1.1875 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Running on sorted descending data: Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333093.7812 residual: -387.71875 simple_float_vec_4: 333438.5625 residual: -42.9375 simple_float_vec_8: 333466.5938 residual: -14.90625 kahan: 333093.7812 residual: -387.71875 kahan_vec_4: 333438.5625 residual: -42.9375 kahan_vec_8: 333466.5938 residual: -14.90625 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333093.75 residual: -387.75 simple_float_vec_4: 333438.5625 residual: -42.9375 simple_float_vec_8: 333466.5625 residual: -14.9375 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333093.75 residual: -387.75 simple_float_vec_4: 333438.5625 residual: -42.9375 simple_float_vec_8: 333466.5625 residual: -14.9375 kahan: 333093.75 residual: -387.75 kahan_vec_4: 333438.5625 residual: -42.9375 kahan_vec_8: 333466.5625 residual: -14.9375 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333093.75 residual: -387.75 simple_float_vec_4: 333438.5625 residual: -42.9375 simple_float_vec_8: 333466.5625 residual: -14.9375 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.5 residual: 0 kahan_vec_8: 333481.5 residual: 0 Running on sorted descending transposed data: Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333116.25 residual: -365.25 simple_float_vec_4: 333468.7188 residual: -12.78125 simple_float_vec_8: 333480.0312 residual: -1.46875 kahan: 333116.25 residual: -365.25 kahan_vec_4: 333468.7188 residual: -12.78125 kahan_vec_8: 333480.0312 residual: -1.46875 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: default simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333116.2188 residual: -365.28125 simple_float_vec_4: 333468.7188 residual: -12.78125 simple_float_vec_8: 333480.0625 residual: -1.4375 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.4688 residual: -0.03125 kahan_vec_8: 333481.5 residual: 0 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41 Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333116.2188 residual: -365.28125 simple_float_vec_4: 333468.7188 residual: -12.78125 simple_float_vec_8: 333480.0625 residual: -1.4375 kahan: 333116.2188 residual: -365.28125 kahan_vec_4: 333468.7188 residual: -12.78125 kahan_vec_8: 333480.0625 residual: -1.4375 Target: x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41-strict_float Strictness: strict_float simple_double: 333481.5 simple_double_vec_4: 333481.5 residual: 0 simple_double_vec_8: 333481.5 residual: 0 simple_float: 333116.2188 residual: -365.28125 simple_float_vec_4: 333468.7188 residual: -12.78125 simple_float_vec_8: 333480.0625 residual: -1.4375 kahan: 333481.4688 residual: -0.03125 kahan_vec_4: 333481.4688 residual: -0.03125 kahan_vec_8: 333481.5 residual: 0 Success! ======================================== ======================================== correctness_strict_float_bounds.exe Success! ======================================== ======================================== correctness_strided_load.exe Success! ======================================== ======================================== correctness_target.exe Success! ======================================== ======================================== correctness_thread_safety.exe Success! ======================================== ======================================== correctness_tiled_matmul.exe [SKIP] No AMX target enabled ======================================== ======================================== correctness_tracing.exe Success! ======================================== ======================================== correctness_tracing_bounds.exe Success! ======================================== ======================================== correctness_tracing_broadcast.exe Success! ======================================== ======================================== correctness_tracing_stack.exe [SKIP] Test requires UNIX signal handling ======================================== ======================================== correctness_transitive_bounds.exe Success! ======================================== ======================================== correctness_trim_no_ops.exe ======================================== ======================================== correctness_truncated_pyramid.exe Success! ======================================== ======================================== correctness_tuple_partial_update.exe Warning: In update definition 1 of Func "f": Update definition completely hides earlier definitions, because all the arguments are pure, it contains no self-references, and no reduction domain. This may be an accidental re-definition of an already-defined function. Success! ======================================== ======================================== correctness_tuple_reduction.exe ======================================== ======================================== correctness_tuple_select.exe Success! ======================================== ======================================== correctness_tuple_undef.exe Test 1... Test 2... Test 3... Test 4... Success! ======================================== ======================================== correctness_tuple_update_ops.exe Success! ======================================== ======================================== correctness_tuple_vector_reduce.exe Success! ======================================== ======================================== correctness_two_vector_args.exe Success! ======================================== ======================================== correctness_typed_func.exe Success! ======================================== ======================================== correctness_undef.exe ======================================== ======================================== correctness_uninitialized_read.exe Success! ======================================== ======================================== correctness_unique_func_image.exe Success! ======================================== ======================================== correctness_unrolled_reduction.exe Success! ======================================== ======================================== correctness_unroll_dynamic_loop.exe Success! ======================================== ======================================== correctness_unroll_huge_mux.exe Success! ======================================== ======================================== correctness_unsafe_dedup_lets.exe Success! ======================================== ======================================== correctness_unsafe_promises.exe Success! ======================================== ======================================== correctness_unused_func.exe Success! ======================================== ======================================== correctness_update_chunk.exe Success! ======================================== ======================================== correctness_vectorized_gpu_allocation.exe ======================================== ======================================== correctness_vectorized_initialization.exe Success! ======================================== ======================================== correctness_vectorized_load_from_vectorized_allocation.exe Success! ======================================== ======================================== correctness_vectorized_reduction_bug.exe Success! ======================================== ======================================== correctness_vectorize_guard_with_if.exe Success! ======================================== ======================================== correctness_vectorize_mixed_widths.exe Success! ======================================== ======================================== correctness_vectorize_nested.exe Success! ======================================== ======================================== correctness_vectorize_varying_allocation_size.exe Success! ======================================== ======================================== correctness_vector_bounds_inference.exe Success! ======================================== ======================================== correctness_vector_cast.exe [SKIP] float-to-int conversions don't work with older LLVMs on Windows ======================================== ======================================== correctness_vector_extern.exe Defining function... Success! ======================================== ======================================== correctness_vector_math.exe vector_math test seed: 1680900175 Testing floatx4 Testing floatx8 Testing doublex2 Testing uint8_tx16 Testing int8_tx16 Testing uint16_tx8 Testing int16_tx8 Testing uint32_tx4 Testing int32_tx4 Testing bfloat16_tx8 Warning: In function f844, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f847, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f850, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f853, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f856, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f859, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f865, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f868, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f871, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f874, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f877, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f880, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f883, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f886, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f889, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f892, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f895, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f898, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f901, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f904, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f907, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f910, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f913, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f925, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f928, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f931, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Testing bfloat16_tx16 Warning: In function f934, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f937, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f940, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f943, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f946, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f949, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f955, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f958, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f961, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f964, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f967, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f970, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f973, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f976, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f980, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f983, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f986, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f989, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f992, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f995, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f998, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1001, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1004, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1016, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1019, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1022, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Testing float16_tx8 Warning: In function f1025, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1028, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1031, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1034, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1037, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1040, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1046, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1049, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1052, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1055, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1058, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1061, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1064, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1067, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1070, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1073, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1076, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1079, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1082, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1085, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1088, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1091, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1094, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1106, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1109, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1112, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Testing float16_tx16 Warning: In function f1115, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1118, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1121, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1124, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1127, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1130, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1136, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1139, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1142, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1145, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1148, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1151, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1154, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1157, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1160, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1163, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1166, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1169, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1172, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1175, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1178, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1181, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1184, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1196, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1199, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function f1202, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Success! ======================================== ======================================== correctness_vector_print_bug.exe 0 1 2 3 4 5 6 7 Success! ======================================== ======================================== correctness_vector_reductions.exe vector_reductions: Testing with target(x86-64-windows-avx-avx2-avx512-avx512_cannonlake-avx512_skylake-d3d12compute-f16c-fma-jit-sse41) Warning: In function err_86, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_87, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_88, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_89, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_90, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_91, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_92, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_93, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_94, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_95, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_96, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_97, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_98, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_202, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_203, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_204, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_205, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_206, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_207, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_311, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_312, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_313, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_314, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_315, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_316, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_420, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_421, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_422, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_423, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_424, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_425, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_426, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_427, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_428, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_429, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_430, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_431, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_432, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_536, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_537, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_538, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_539, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_540, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_541, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_645, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_646, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_647, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_648, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_649, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_650, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. vector_reductions: Testing with target(x86-64-windows-avx2) Warning: In function err_754, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_755, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_756, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_757, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_758, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_759, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_760, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_761, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_762, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_763, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_764, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_765, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_766, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_870, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_871, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_872, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_873, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_874, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_875, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_979, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_980, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_981, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_982, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_983, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_984, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1088, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1089, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1090, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1091, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1092, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1093, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1094, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1095, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1096, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1097, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1098, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1099, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1100, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1206, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1207, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1208, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1209, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1210, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1211, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1315, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1316, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1317, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1318, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1319, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1320, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. vector_reductions: Testing with target(x86-64-windows-avx) Warning: In function err_1424, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1425, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1426, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1427, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1428, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1429, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1430, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1431, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1432, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1433, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1434, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1435, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1436, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1540, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1541, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1542, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1543, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1544, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1545, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1649, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1650, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1651, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1652, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1653, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1654, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1758, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1759, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1760, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1761, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1762, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1763, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1764, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1765, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1766, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1767, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1768, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1769, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1770, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1874, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1875, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1876, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1877, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1878, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1879, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1983, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1984, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1985, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1986, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1987, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_1988, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. vector_reductions: Testing with target(x86-64-windows-sse41) Warning: In function err_2092, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2093, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2094, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2095, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2096, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2097, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2098, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2099, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2100, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2101, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2102, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2103, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2104, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2208, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2209, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2210, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2211, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2212, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2213, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2317, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2318, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2319, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2320, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2321, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2322, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2426, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2427, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2428, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2429, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2430, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2431, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2432, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2433, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2434, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2435, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2436, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2437, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2438, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2542, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2543, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2544, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2545, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2546, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2547, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2651, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2652, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2653, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2654, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2655, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2656, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. vector_reductions: Testing with target(x86-64-windows) Warning: In function err_2760, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2761, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2762, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2763, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2764, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2765, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2766, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2767, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2768, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2769, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2770, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2771, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2772, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2876, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2877, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2878, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2879, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2880, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2881, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2985, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2986, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2987, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2988, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2989, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_2990, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3094, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3095, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3096, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3097, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3098, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3099, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3100, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3101, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3102, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3103, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3104, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3105, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3106, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3210, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3211, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3212, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3213, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3214, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3215, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3319, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3320, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3321, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3322, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3323, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Warning: In function err_3324, (b)float16 type operation is emulated, which is likely to slow down the performance. If your target supports native (b)float16 operations, it could be improved by adding Target feature to enable it. Success! ======================================== ======================================== correctness_vector_tile.exe Success! ======================================== ======================================== correctness_widening_lerp.exe Lerp test seed: 1680900334 Success! ======================================== ======================================== correctness_widening_reduction.exe ========================================