This repository was archived by the owner on Nov 17, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 6.8k
[FEATURE] Add quantized version of reshape with DNNL reorder primitive. #20835
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Hey @agrabows , Thanks for submitting the PR
CI supported jobs: [miscellaneous, centos-gpu, clang, centos-cpu, unix-gpu, website, windows-cpu, windows-gpu, unix-cpu, edge, sanity] Note: |
8e9315a
to
a3870eb
Compare
a3870eb
to
62e638d
Compare
RafLit
reviewed
Jan 31, 2022
dd01051
to
8164c6b
Compare
8e531be
to
6d2b7ee
Compare
@mxnet-bot run ci [centos-gpu] |
Jenkins CI successfully triggered : [centos-gpu] |
RafLit
approved these changes
Feb 14, 2022
bartekkuncer
approved these changes
Feb 15, 2022
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM.
bgawrych
approved these changes
Feb 16, 2022
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Reshape operators from both NDArray and NumPy modules of MXNet had no quantized version so if it appeared between two quantized operators data would have to be dequantized and quantized again after reshape (as shown on picture below with version after change as well). Goal was to create quantized reshape operator.



Previous version:
New version:
Speedup:
Checklist
Essentials
Changes