Benchmark for big-batch IVF search #2567
Closed
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
|
This pull request was exported from Phabricator. Differential Revision: D41098338 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D41098338 |
mdouze
added a commit
to mdouze/faiss
that referenced
this pull request
Nov 11, 2022
Summary: Pull Request resolved: facebookresearch#2567 Intuitively, it should be easier to handle big-batch searches because all distance computations for a set of queries can be done locally within each inverted list. This benchmark implements this in pure python (but should be close to optimal in terms of speed), on CPU for IndexIVFFlat, IndexIVFPQ and IndexIVFScalarQuantizer. GPU is also supported. The results are not systematically better, see https://docs.google.com/document/d/1d3YuV8uN7hut6aOATCOMx8Ut-QEl_oRnJdPgDBRF1QA/edit?usp=sharing Differential Revision: D41098338 fbshipit-source-id: 02b5ae1fa89ac37972cd2bce2ced9f7dbc2dc8af
mdouze
force-pushed
the
export-D41098338
branch
from
5fa234d to
e308b13
Compare
|
This pull request was exported from Phabricator. Differential Revision: D41098338 |
mdouze
added a commit
to mdouze/faiss
that referenced
this pull request
Nov 24, 2022
Summary: Pull Request resolved: facebookresearch#2567 Intuitively, it should be easier to handle big-batch searches because all distance computations for a set of queries can be done locally within each inverted list. This benchmark implements this in pure python (but should be close to optimal in terms of speed), on CPU for IndexIVFFlat, IndexIVFPQ and IndexIVFScalarQuantizer. GPU is also supported. The results are not systematically better, see https://docs.google.com/document/d/1d3YuV8uN7hut6aOATCOMx8Ut-QEl_oRnJdPgDBRF1QA/edit?usp=sharing Differential Revision: D41098338 fbshipit-source-id: d418947b526b7b4c5ecd03b713271e88b7ef5e26
mdouze
force-pushed
the
export-D41098338
branch
from
e308b13 to
a209cec
Compare
|
This pull request was exported from Phabricator. Differential Revision: D41098338 |
mdouze
added a commit
to mdouze/faiss
that referenced
this pull request
Dec 9, 2022
…arch#2567) Summary: Pull Request resolved: facebookresearch#2567 Intuitively, it should be easier to handle big-batch searches because all distance computations for a set of queries can be done locally within each inverted list. This benchmark implements this in pure python (but should be close to optimal in terms of speed), on CPU for IndexIVFFlat, IndexIVFPQ and IndexIVFScalarQuantizer. GPU is also supported. The results are not systematically better, see https://docs.google.com/document/d/1d3YuV8uN7hut6aOATCOMx8Ut-QEl_oRnJdPgDBRF1QA/edit?usp=sharing Reviewed By: algoriddle Differential Revision: D41098338 fbshipit-source-id: be4df745b7f89521bdcba84f76f4b35829579097
mdouze
force-pushed
the
export-D41098338
branch
from
a209cec to
955128f
Compare
…arch#2567) Summary: Pull Request resolved: facebookresearch#2567 Intuitively, it should be easier to handle big-batch searches because all distance computations for a set of queries can be done locally within each inverted list. This benchmark implements this in pure python (but should be close to optimal in terms of speed), on CPU for IndexIVFFlat, IndexIVFPQ and IndexIVFScalarQuantizer. GPU is also supported. The results are not systematically better, see https://docs.google.com/document/d/1d3YuV8uN7hut6aOATCOMx8Ut-QEl_oRnJdPgDBRF1QA/edit?usp=sharing Reviewed By: algoriddle Differential Revision: D41098338 fbshipit-source-id: 4eb19710b8ab6c0f64f68d8ed862a75fb6f8fd24
mdouze
force-pushed
the
export-D41098338
branch
from
955128f to
73c8f24
Compare
|
This pull request was exported from Phabricator. Differential Revision: D41098338 |
|
This pull request has been merged in fa53e2c. |
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.
Summary:
Intuitively, it should be easier to handle big-batch searches because all distance computations for a set of queries can be done locally within each inverted list.
This benchmark implements this in pure python (but should be close to optimal in terms of speed), on CPU for IndexIVFFlat and IndexIVFPQ.
The results are not systematically better, see https://docs.google.com/document/d/1d3YuV8uN7hut6aOATCOMx8Ut-QEl_oRnJdPgDBRF1QA/edit?usp=sharing
Differential Revision: D41098338