Add a FAISS_OPT_LEVEL=avx512_spr build mode. #2404
Merged
Conversation
This file contains 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
- avx512_spr enables advanced avx512 instructions available since Intel(R) Sapphire Rapids. Signed-off-by: Mulugeta Mammo <[email protected]>
Signed-off-by: Assane Diop <[email protected]>
mulugetam
requested review from
heemin32,
navneet1v,
VijayanB,
vamshin,
jmazanec15,
naveentatikonda,
junqiu-lei,
martin-gaievski,
ryanbogan,
luyuncheng,
shatejas and
0ctopus13prime
as code owners
DEVELOPER_GUIDE.md
Outdated
| # else if (system_supports_avx512) generate_avx512_binaries() | ||
| # else if (system_supports_ avx2) generate_avx2_binaries() | ||
| # else() generate_generic_binaries() | ||
| ./gradlew build -Davx2.enabled=true |
There was a problem hiding this comment.
I think we can remove this line
There was a problem hiding this comment.
You mean lines 294-298?
|
@mulugetam Thanks for making these changes. Can you fix the failing CI and add CHANGELOG |
naveentatikonda
added
backport 2.x
Features
|
@naveentatikonda Looks like the CI is using gcc 10.5.0 (we need 12.1+). Will proceed with fixing the other issues (which are mainly formatting). |
Co-authored-by: Naveen Tatikonda <[email protected]> Signed-off-by: mulugetam <[email protected]>
Co-authored-by: Naveen Tatikonda <[email protected]> Signed-off-by: mulugetam <[email protected]>
Signed-off-by: Mulugeta Mammo <[email protected]>
Signed-off-by: Mulugeta Mammo <[email protected]>
|
@mulugetam also pls fix the failing unit test related to avx512_spr. Thanks! |
Signed-off-by: Mulugeta Mammo <[email protected]>
Signed-off-by: Mulugeta Mammo <[email protected]>
|
Thanks! Could you re-run CI? |
Signed-off-by: Naveen Tatikonda <[email protected]>
|
I tried to cherry-pick these changes and built them on Peter's custom image with GCC 12.4 without any compile-time or runtime issues when tested with some sample curl commands. |
naveentatikonda
approved these changes
Jan 22, 2025
|
BWC framework is flaky and the failing BWC tests not related to these changes |
|
Pending opensearch-project/opensearch-build#5241 to be merged and images to be pushed before new tests would take effect. |
|
@mulugetam can you pls share some performance benchmarking results when tested from opensearch comparing avx512_spr results with avx512 and avx2 atleast for a couple of datasets ? |
|
@naveentatikonda We're currently working on that and will share it when its ready. For a quick check, you may run hamming bench with |
4 tasks
|
New image is online we can retry the test on this PR. Thanks. |
navneet1v
approved these changes
Jan 24, 2025
naveentatikonda
merged commit 90fdad4
into
opensearch-project:main
33 of 34 checks passed
opensearch-trigger-bot bot
pushed a commit
that referenced
this pull request
Jan 24, 2025
* Add avx512_spr option to FAISS_OPT_LEVEL. - avx512_spr enables advanced avx512 instructions available since Intel(R) Sapphire Rapids. Signed-off-by: Mulugeta Mammo <[email protected]> * Fix documentation. Signed-off-by: Assane Diop <[email protected]> * Update scripts/build.sh Co-authored-by: Naveen Tatikonda <[email protected]> Signed-off-by: mulugetam <[email protected]> * Update scripts/build.sh Co-authored-by: Naveen Tatikonda <[email protected]> Signed-off-by: mulugetam <[email protected]> * Fix formatting issues. Signed-off-by: Mulugeta Mammo <[email protected]> * Update CHANGELOG.md for avx512_spr build mode. Signed-off-by: Mulugeta Mammo <[email protected]> * Fix bugs in build options and avx512_spr flag testing. Signed-off-by: Mulugeta Mammo <[email protected]> * Upgrade gcc version to 12.4. Signed-off-by: Mulugeta Mammo <[email protected]> --------- Signed-off-by: Mulugeta Mammo <[email protected]> Signed-off-by: Assane Diop <[email protected]> Signed-off-by: mulugetam <[email protected]> Signed-off-by: Naveen Tatikonda <[email protected]> Co-authored-by: Assane Diop <[email protected]> Co-authored-by: Naveen Tatikonda <[email protected]> (cherry picked from commit 90fdad4)
naveentatikonda
added a commit
that referenced
this pull request
Jan 27, 2025
* Add a FAISS_OPT_LEVEL=avx512_spr build mode. (#2404) * Add avx512_spr option to FAISS_OPT_LEVEL. - avx512_spr enables advanced avx512 instructions available since Intel(R) Sapphire Rapids. Signed-off-by: Mulugeta Mammo <[email protected]> * Fix documentation. Signed-off-by: Assane Diop <[email protected]> * Update scripts/build.sh Co-authored-by: Naveen Tatikonda <[email protected]> Signed-off-by: mulugetam <[email protected]> * Update scripts/build.sh Co-authored-by: Naveen Tatikonda <[email protected]> Signed-off-by: mulugetam <[email protected]> * Fix formatting issues. Signed-off-by: Mulugeta Mammo <[email protected]> * Update CHANGELOG.md for avx512_spr build mode. Signed-off-by: Mulugeta Mammo <[email protected]> * Fix bugs in build options and avx512_spr flag testing. Signed-off-by: Mulugeta Mammo <[email protected]> * Upgrade gcc version to 12.4. Signed-off-by: Mulugeta Mammo <[email protected]> --------- Signed-off-by: Mulugeta Mammo <[email protected]> Signed-off-by: Assane Diop <[email protected]> Signed-off-by: mulugetam <[email protected]> Signed-off-by: Naveen Tatikonda <[email protected]> Co-authored-by: Assane Diop <[email protected]> Co-authored-by: Naveen Tatikonda <[email protected]> (cherry picked from commit 90fdad4) * Fix failing rolling upgrade workflow Signed-off-by: Naveen Tatikonda <[email protected]> * Update init-faiss.cmake Signed-off-by: Naveen Tatikonda <[email protected]> --------- Signed-off-by: Naveen Tatikonda <[email protected]> Co-authored-by: mulugetam <[email protected]> Co-authored-by: Naveen Tatikonda <[email protected]>
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.
Description
FAISS recently added a new build mode,
avx512_spr, which enables the use of advanced AVX512 instructions available since Intel® Sapphire Rapids. These instructions includeavx512_fp16,avx512_bf16,avx512_vpopcntdq, and many others. Some optimizations leveraging these instructions, such as speeding up Hamming distance evaluation for binary vectors, have already been implemented and merged. Additional optimizations are also in the pipeline. This PR enables K-NN to utilize this newavx512_sprbuild mode.The code changes are implemented such that, by default, if the underlying system is an Intel® Sapphire Rapids or a newer-generation processor,
avx512_sprbinaries are generated. Otherwise, depending on the features available in the system and consistent with the existing implementation,avx512,avx2, orgenericbinaries may be generated.Check List
--signoff.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.