Enable fast qlinear static/dynamic path for AArch64 through ACL directly #148583
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
fadara01
requested review from
digantdesai,
jerryzh168,
jianyuh,
kimishpatel and
salilsdesai
as code owners
pytorch-bot
bot
added
module: cpu
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/148583
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit fe602ae with merge base 6c3492b ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
fadara01
added a commit
that referenced
this pull request
Mar 5, 2025
This enables a fast path for eager mode dynamic quantization for AArch64 through Arm Compute Library (ACL) directly. Context: PR #126687 enabled an optimized implementation for qlinear_dynamic for aarch64 through ideep → oneDNN → ACL which improved performance by ~10x compared to the previous implementation. However, the current qlinear_dynamic path (ideep → oneDNN → ACL) suffers from high overhead due to the API friction between the stateless oneDNN API and the stateful ACL low-precision GEMM (lowp_gemm) API - for example, ACL's lowp_gemm objects cache information like weights reduction or weights in optimized memory format which oneDNN does not allow due to its stateless nature. Hence, ACL currently runs a (redundant) sum of columns and pre-transposition (to the gemm kerne's optimal format) for each GEMM operation. This PR addresses the sub-optimalities above by integrating ACL directly with qlinear_dynamic. This approach yields an average speedup (averaged over context_lengths of 2^3 up to 2^9) of ~ 50% for bert-base-uncased, bert-large-uncased, roberta-base, distilbert-base-uncased with 16 threads on a Neoverse-V1 (with transformers==4.48). To achieve this we introduce PackedLinearWeightsACL (as a subclasses of PackedLinearWeightsOnednn ) with an implementation of qlinear_dynamic that uses ACL directly, while qlinear still follows the oneDNN path. ghstack-source-id: 555097f Pull Request resolved: #148583
fadara01
changed the title
Collaborator
Author
|
Sorry, this PR is a mistake, I'm a ghstack newbie |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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):
This enables a fast path for eager mode dynamic quantization for AArch64 through Arm Compute Library (ACL) directly.
Context: PR #126687 enabled an optimized implementation for qlinear_dynamic for aarch64 through ideep → oneDNN → ACL which improved performance by ~10x compared to the previous implementation.
However, the current qlinear_dynamic path (ideep → oneDNN → ACL) suffers from high overhead due to the API friction between the stateless oneDNN API and the stateful ACL low-precision GEMM (lowp_gemm) API - for example, ACL's lowp_gemm objects cache information like weights reduction or weights in optimized memory format which oneDNN does not allow due to its stateless nature.
Hence, ACL currently runs a (redundant) sum of columns and pre-transposition (to the gemm kerne's optimal format) for each GEMM operation.
This PR addresses the sub-optimalities above by integrating ACL directly with qlinear_dynamic. This approach yields an average speedup (averaged over context_lengths of 2^3 up to 2^9) of ~ 50% for bert-base-uncased, bert-large-uncased, roberta-base, distilbert-base-uncased with 16 threads on a Neoverse-V1 (with transformers==4.48).
To achieve this we introduce PackedLinearWeightsACL (as a subclasses of PackedLinearWeightsOnednn ) with an implementation of qlinear_dynamic that uses ACL directly, while qlinear still follows the oneDNN path.
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10