[x86] matmulnbit x64 kernel for 8bits#24491
Merged
fajin-corp merged 44 commits intomainfrom Apr 24, 2025
Merged
Conversation
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
liqunfu
previously approved these changes
Apr 21, 2025
Contributor
liqunfu
left a comment
liqunfu
left a comment
There was a problem hiding this comment.
LGTM, it will be better if you add performance results, either mlas benchmark or even better ort-genai benchmark. ort-genai benchmark is preferred because I found mlas benchmark tends to show higher improvement that does not exist with genai.
yihonglyu
reviewed
Apr 23, 2025
Contributor
|
"For non-vnni platform, the i16 cannot fit in 4 i8. To avoid overflow extra instructions are needed. This is the major reason of non-vnni slow down." does this issue exist with 4bit non-vnni? |
liqunfu
approved these changes
Apr 24, 2025
Contributor
Author
4bit does not have this issue. it is caused by (i8 * i8) * 2. the result is put in i16. (i4 * i4) * 2 can fit in i16 |
jywu-msft
pushed a commit
that referenced
this pull request
Apr 30, 2025
### Description Cherry pick the following into [rel-1.22.0](https://github.com/microsoft/onnxruntime/tree/rel-1.22.0) - (#24487) - (#24466) - (#24493) - (#24484) - (#24494) - (#24489) - (#24504) - (#24510) - (#24456) - (#24537) - (#24501) - (#24519) - (#24513) - (#24539) - (#24514) - (#24542) - (#24585) Not added: Planning to cherry pick Cuda Matmulnbits PRs once the fix for failing cuda pipeline is ready - (#24491) - (#24509) - (#24564) --------- Co-authored-by: Adrian Lizarraga <[email protected]> Co-authored-by: minfhong-quic <[email protected]> Co-authored-by: minfhong-quic <[email protected]> Co-authored-by: Justin Chu <[email protected]> Co-authored-by: Prathik Rao <[email protected]> Co-authored-by: Edward Chen <[email protected]> Co-authored-by: Ankan Banerjee <[email protected]> Co-authored-by: Maximilian Müller <[email protected]> Co-authored-by: Gaurav Garg <[email protected]> Co-authored-by: iraut <[email protected]> Co-authored-by: Hrishikesh Manohar <[email protected]> Co-authored-by: Maximilian Müller <[email protected]> Co-authored-by: Scott McKay <[email protected]> Co-authored-by: Jiajia Qin <[email protected]> Co-authored-by: kunal-vaishnavi <[email protected]> Co-authored-by: xhcao <[email protected]>
jatinwadhwa921
pushed a commit
to intel/onnxruntime
that referenced
this pull request
Apr 30, 2025
### Description Cherry pick the following into [rel-1.22.0](https://github.com/microsoft/onnxruntime/tree/rel-1.22.0) - (microsoft#24487) - (microsoft#24466) - (microsoft#24493) - (microsoft#24484) - (microsoft#24494) - (microsoft#24489) - (microsoft#24504) - (microsoft#24510) - (microsoft#24456) - (microsoft#24537) - (microsoft#24501) - (microsoft#24519) - (microsoft#24513) - (microsoft#24539) - (microsoft#24514) - (microsoft#24542) - (microsoft#24585) Not added: Planning to cherry pick Cuda Matmulnbits PRs once the fix for failing cuda pipeline is ready - (microsoft#24491) - (microsoft#24509) - (microsoft#24564) --------- Co-authored-by: vraspar <[email protected]> Co-authored-by: Adrian Lizarraga <[email protected]> Co-authored-by: minfhong-quic <[email protected]> Co-authored-by: minfhong-quic <[email protected]> Co-authored-by: Justin Chu <[email protected]> Co-authored-by: Prathik Rao <[email protected]> Co-authored-by: Edward Chen <[email protected]> Co-authored-by: Ankan Banerjee <[email protected]> Co-authored-by: Maximilian Müller <[email protected]> Co-authored-by: Gaurav Garg <[email protected]> Co-authored-by: iraut <[email protected]> Co-authored-by: Hrishikesh Manohar <[email protected]> Co-authored-by: Maximilian Müller <[email protected]> Co-authored-by: Scott McKay <[email protected]> Co-authored-by: Jiajia Qin <[email protected]> Co-authored-by: kunal-vaishnavi <[email protected]> Co-authored-by: xhcao <[email protected]>
vraspar
pushed a commit
that referenced
this pull request
May 1, 2025
### Description Add 8bits support for matmulnbits on x86 __AVX512 VNNI__ | M | N | K | 8-bit Time (ns) | 4-bit Time (ns) | Slow down (8-bit / 4-bit) | |:-----:|:-------:|:-------:|:----------------:|:----------------:|:------------------------:| | 1 | 4096 | 4096 | 34145 | 27723 | **1.23×** | | 1 | 11008 | 4096 | 415285 | 68656 | **6.05×** | | 1 | 4096 | 11008 | 407801 | 68061 | **5.99×** | | 1 | 11008 | 11008 | 2674538 | 1003532 | **2.67×** | | 4096 | 4096 | 4096 | 80338759 | 86321713 | **0.93×** | | 4096 | 11008 | 4096 | 213421935 | 225245276 | **0.95×** | | 4096 | 4096 | 11008 | 240164365 | 228966953 | **1.05×** | | 4096 | 11008 | 11008 | 628352046 | 596738340 | **1.05×** | __AVX512__ | M | N | K | 8-bit Time (ns) | 4-bit Time (ns) | Slow down (8-bit / 4-bit) | |:-----:|:-------:|:-------:|:----------------:|:----------------:|:------------------------:| | 1 | 4096 | 4096 | 53324 | 37882 | **1.41×** | | 1 | 11008 | 4096 | 244560 | 103255 | **2.37×** | | 1 | 4096 | 11008 | 435131 | 95734 | **4.55×** | | 1 | 11008 | 11008 | 2790710 | 1075216 | **2.60×** | | 4096 | 4096 | 4096 | 200629000 | 132841540 | **1.51×** | | 4096 | 11008 | 4096 | 532141914 | 350613184 | **1.52×** | | 4096 | 4096 | 11008 | 544011977 | 351679619 | **1.55×** | | 4096 | 11008 | 11008 | 1421865147 | 925593210 | **1.54×** | Token generation is bottlenecked at memory access. 8b model's 2x size is major reason of token generation slow down. For non-vnni platform, the i16 cannot fit in 4 i8. To avoid overflow extra instructions are needed. This is the major reason of non-vnni slow down. ### Motivation and Context MatMul4Bits model has repetition issue. 6b model resolved this issue.
jywu-msft
pushed a commit
that referenced
this pull request
May 1, 2025
### Description Cherry pick the following into [rel-1.22.0](https://github.com/microsoft/onnxruntime/tree/rel-1.22.0) - (#24491) - (#24509) - (#24564) - (#24574) - (#24582) - (#24584) - (#24568) - (#24587) - (#24563) - (#24592) - (#24526) - (#24552) - (#24588) - (#24605) - (#24606) --------- Co-authored-by: Jing Fang <[email protected]> Co-authored-by: Tianlei Wu <[email protected]> Co-authored-by: Baiju Meswani <[email protected]> Co-authored-by: Scott McKay <[email protected]> Co-authored-by: Mark Schofield <[email protected]> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Edward Chen <[email protected]> Co-authored-by: Ashwath Shankarnarayan <[email protected]> Co-authored-by: saurabh <[email protected]> Co-authored-by: Adrian Lizarraga <[email protected]> Co-authored-by: Hector Li <[email protected]>
ankitm3k
pushed a commit
to intel/onnxruntime
that referenced
this pull request
May 12, 2025
### Description Add 8bits support for matmulnbits on x86 __AVX512 VNNI__ | M | N | K | 8-bit Time (ns) | 4-bit Time (ns) | Slow down (8-bit / 4-bit) | |:-----:|:-------:|:-------:|:----------------:|:----------------:|:------------------------:| | 1 | 4096 | 4096 | 34145 | 27723 | **1.23×** | | 1 | 11008 | 4096 | 415285 | 68656 | **6.05×** | | 1 | 4096 | 11008 | 407801 | 68061 | **5.99×** | | 1 | 11008 | 11008 | 2674538 | 1003532 | **2.67×** | | 4096 | 4096 | 4096 | 80338759 | 86321713 | **0.93×** | | 4096 | 11008 | 4096 | 213421935 | 225245276 | **0.95×** | | 4096 | 4096 | 11008 | 240164365 | 228966953 | **1.05×** | | 4096 | 11008 | 11008 | 628352046 | 596738340 | **1.05×** | __AVX512__ | M | N | K | 8-bit Time (ns) | 4-bit Time (ns) | Slow down (8-bit / 4-bit) | |:-----:|:-------:|:-------:|:----------------:|:----------------:|:------------------------:| | 1 | 4096 | 4096 | 53324 | 37882 | **1.41×** | | 1 | 11008 | 4096 | 244560 | 103255 | **2.37×** | | 1 | 4096 | 11008 | 435131 | 95734 | **4.55×** | | 1 | 11008 | 11008 | 2790710 | 1075216 | **2.60×** | | 4096 | 4096 | 4096 | 200629000 | 132841540 | **1.51×** | | 4096 | 11008 | 4096 | 532141914 | 350613184 | **1.52×** | | 4096 | 4096 | 11008 | 544011977 | 351679619 | **1.55×** | | 4096 | 11008 | 11008 | 1421865147 | 925593210 | **1.54×** | Token generation is bottlenecked at memory access. 8b model's 2x size is major reason of token generation slow down. For non-vnni platform, the i16 cannot fit in 4 i8. To avoid overflow extra instructions are needed. This is the major reason of non-vnni slow down. ### Motivation and Context MatMul4Bits model has repetition issue. 6b model resolved this issue.
Contributor
|
This PR has been included in the |
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
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.
Description
Add 8bits support for matmulnbits on x86
AVX512 VNNI
AVX512
Token generation is bottlenecked at memory access. 8b model's 2x size is major reason of token generation slow down.
For non-vnni platform, the i16 cannot fit in 4 i8. To avoid overflow extra instructions are needed. This is the major reason of non-vnni slow down.
Motivation and Context
MatMul4Bits model has repetition issue. 6b model resolved this issue.