[Quant][Inductor][X86] add fusion pass for linear_dynamic_fp16 with relu #141556
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/141556
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit 974bb79 with merge base 795f28a ( FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Xia-Weiwen
added
intel
jgong5
approved these changes
Nov 27, 2024
jerryzh168
approved these changes
Dec 3, 2024
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
AmdSampsa
pushed a commit
to AmdSampsa/pytorch
that referenced
this pull request
Dec 9, 2024
…elu (pytorch#141556) **Description** Fuse and prepack weight for `linear_dynamic_fp16` with post op relu. In Inductor, the pattern we see is ``` fp32 activation | (reshape) | mm/addmm <- t <- to_fp32 <- tp_fp16 <- weight | (reshape) <- relu ``` Or ``` fp32 activation | expand | bmm <- expand <- t <- to_fp32 <- tp_fp16 <- weight | (add) <- relu ``` The second pattern is for x.ndim > 2 and x is not contiguous. The first pattern is for other cases. Fuse the pattern with weight prepack, and we get ``` fp32 activation | onednn.linear_relu_dynamic_fp16 <- onednn.linear_prepack_fp16 <- weight ``` After freezing, the prepack op is gone. **Test plan** ``` python test/inductor/test_mkldnn_pattern_matcher.py -k test_linear_relu_dynamic_fp16 ``` Pull Request resolved: pytorch#141556 Approved by: https://github.com/jgong5, https://github.com/jerryzh168 ghstack dependencies: pytorch#141549
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Stack from ghstack (oldest at bottom):
Description
Fuse and prepack weight for
linear_dynamic_fp16with post op relu. In Inductor, the pattern we see isOr
The second pattern is for x.ndim > 2 and x is not contiguous. The first pattern is for other cases.
Fuse the pattern with weight prepack, and we get
After freezing, the prepack op is gone.
Test plan
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10 @voznesenskym @penguinwu @EikanWang @Guobing-Chen @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @chauhang @aakhundov