RaBitQ fastscan avx512 lut quant#5397
Draft
lyang24 wants to merge 2 commits into
Draft
Conversation
lyang24
changed the title
lyang24
changed the title
lyang24
force-pushed
the
rabitq-fastscan-avx512-lut-quant-experiment
branch
from
bc91d0b to
8443357
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
stacked on #5396
should wait until 5396 merged
Add AVX512 dynamic-dispatch kernels for RaBitQ fastscan LUT/query quantization:
- vectorized 16-entry LUT min/max
- vectorized LUT uint8 quantization
- vectorized query min/max and query-byte quantization
- vector accumulators for query correction sums, reducing horizontally only once per query
704 qps vs stack 1 546 qps