Add support for s8s8 dynamic quant #313
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
This will be used in PyTorch for accelerating dynamic quantization by using s8s8 matmul accelerated by ACL (see uxlfoundation/oneDNN#1885). This can go in without oneDNN 3.5, but will only offer performance benefits after it does.
jgong5
approved these changes
May 30, 2024
There was a problem hiding this comment.
The change LGTM. I'm not sure about the copyright though. cc @jingxu10 and @Guobing-Chen
|
I'm happy to get this in without the copyright notices, and work it out later. What's the process for getting this merged? |
|
Do you include this change in PyTorch CI? If so, I can merge directly. |
LGTM |
pytorch-bot bot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
Aug 23, 2024
oneDNN+ACL has optimized kernels for s8s8 matmul, so input is signed. This change leaves behaviour on all other platforms the same. This change requires intel/ideep#313 to go in, and oneDNN 3.5 for the optimized kernels. This change speeds up dynamic quantized linear by ~10x. Signed-off-by: Jonathan Deakin <jonathan.deakin@arm.com>
pytorchmergebot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
Aug 24, 2024
oneDNN+ACL has optimized kernels for s8s8 matmul, so input is signed. This change leaves behaviour on all other platforms the same. This change requires intel/ideep#313 to go in, and oneDNN 3.5 for the optimized kernels. This change speeds up dynamic quantized linear by ~10x. Also, do you have a policy on copyright headers? Arm's usual policy when contributing to open source projects is to include a copyright header on any file which is modified. Would this be acceptable? If not, is there somewhere else suitable to note copyright? Pull Request resolved: #126687 Approved by: https://github.com/jgong5, https://github.com/malfet, https://github.com/snadampal Co-authored-by: Nikita Shulga <2453524+malfet@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
This will be used in PyTorch for accelerating dynamic quantization by using s8s8 matmul accelerated by ACL (see
uxlfoundation/oneDNN#1885). This can go in without oneDNN 3.5, but will only offer performance benefits after it does.
Also, do you have a policy on copyright headers? I noticed that on this branch at least, most of the copyright headers were removed a few years ago. However, Arm's usual policy when contributing to open source projects is to include a copyright header on any file which is modified. Would this be acceptable? If not, is there somewhere else suitable to note copyright?