Adapt fp32 sq8 dist functions ip cosine [MOD-13392] #882
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
- Implemented inner product and cosine distance functions for SQ8-to-SQ8 vectors in SVE, NEON, and AVX512 architectures. - Added corresponding distance function selection logic in IP_space.cpp and function headers in IP_space.h. - Created benchmarks for SQ8-to-SQ8 distance functions to evaluate performance across different architectures. - Developed unit tests to validate the correctness of the new distance functions against expected results. - Ensured compatibility with existing optimization features for various CPU architectures.
…mproving performance
… SQ8-to-SQ8 calculations
… NEON and AVX512 headers
- Implemented NEON, SVE, and AVX512F optimized functions for calculating L2 squared distance between SQ8 (scalar quantized 8-bit) vectors. - Introduced helper functions for processing vector elements using NEON and SVE intrinsics. - Updated L2_space.cpp and L2_space.h to include new distance function for SQ8-to-SQ8. - Enhanced AVX512F, NEON, and SVE function selectors to choose the appropriate implementation based on CPU features. - Added unit tests to validate the correctness of the new L2 squared distance functions. - Updated benchmark tests to include performance measurements for the new implementations.
…ocumentation accordingly
…tance assertion tolerance
…om/RedisAI/VectorSimilarity into dorer-sq8-dist-functions-l2
… using AVX512 VNNI; add benchmarks and tests for new functionality
…VE, and AVX512; add corresponding selection functions and update tests for consistency.
…update benchmarks and tests for new functionality
- Updated distance function declarations in IP_space.h to clarify that SQ8-to-SQ8 functions use precomputed sum/norm. - Removed precomputed distance function implementations for AVX512F, NEON, and SVE architectures from their respective source files. - Adjusted benchmark tests to remove references to precomputed distance functions and ensure they utilize the updated quantization methods. - Modified utility functions to support the creation of SQ8 quantized vectors with precomputed sum and norm. - Updated unit tests to reflect changes in the quantization process and removed tests specifically for precomputed distance functions.
…nsistency - Updated include paths in AVX512F_BW_VL_VNNI.cpp to reflect new naming conventions. - Modified unit tests in test_spaces.cpp to streamline vector initialization and quantization processes. - Replaced repetitive code with utility functions for populating and quantizing vectors. - Enhanced assertions in tests to ensure optimized distance functions are correctly chosen and validated. - Removed unnecessary parameters from utility functions to simplify their interfaces. - Improved test coverage for edge cases, including zero and constant vectors, ensuring accuracy across various scenarios.
- Refactor the SQ8 inner product computation to eliminate unnecessary dequantization steps, improving performance. - Introduce a new helper function `InnerProductStepSQ8` that computes the inner product directly using quantized values. - Update the main inner product function `SQ8_InnerProductSIMD_SVE_IMP` to utilize the new helper function, streamlining the computation process. - Modify the test suite to validate the new implementation, ensuring correctness against the baseline non-optimized version. - Add edge case tests for self-distance, symmetry, zero vectors, constant vectors, and extreme values to ensure robustness of the SQ8 cosine distance function. - Introduce utility functions for preprocessing and populating SQ8 queries, enhancing test clarity and maintainability.
…to dorer-fp32-sq8-dist-functions-ip-cosine
…d size calculations
…to dorer-fp32-sq8-dist-functions-ip-cosine
…to dorer-fp32-sq8-dist-functions-ip-cosine
…quantization parameters
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #882 +/- ##
=======================================
Coverage 97.13% 97.13%
=======================================
Files 129 129
Lines 7614 7615 +1
=======================================
+ Hits 7396 7397 +1
Misses 218 218 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
…tion parameters and clean up code formatting
…to dorer-fp32-sq8-dist-functions-ip-cosine
meiravgri
reviewed
Jan 8, 2026
| #include <arm_sve.h> | ||
| #include <iostream> | ||
| #include <string.h> | ||
| using sq8 = vecsim_types::sq8; |
Collaborator
There was a problem hiding this comment.
Suggested change
| using sq8 = vecsim_types::sq8; | |
| using sq8 = vecsim_types::sq8; |
tests/unit/test_spaces.cpp
Outdated
| TEST(SQ8_EdgeCases, CosineConstantVectorTest) { | ||
| auto optimization = getCpuOptimizationFeatures(); | ||
| size_t dim = 128; | ||
| std::vector<float> v_const(dim + 1, 0.5f); |
Collaborator
There was a problem hiding this comment.
Isnt the interesting case is when the quantized vector has constant values?
Comment on lines
+329
to
330
| test_utils::SQ8_NotOptimized_InnerProduct(v1_orig.data(), v2_compressed.data(), dim); | ||
|
|
Collaborator
There was a problem hiding this comment.
dont we want to test naive to SQ8_NotOptimized_InnerProduct with differnt vectors like we did for SQ8_SQ8?
meiravgri
reviewed
Jan 8, 2026
tests/unit/test_spaces.cpp
Outdated
| SQ8_InnerProduct((const void *)v1_orig.data(), (const void *)v2_compressed.data(), dim); | ||
|
|
||
| ASSERT_NEAR(dist, baseline, 0.01) << "SQ8_InnerProduct failed to match expected distance"; | ||
| // Since we're comparing identical vectors, the inner product distance should be close to 0 |
Collaborator
There was a problem hiding this comment.
i see that all other types also validate we get 0 distance for idnetical vectors
consider keeping this test here as well
Collaborator
Author
There was a problem hiding this comment.
There is one:
TEST(SQ8_EdgeCases, SelfDistanceCosine)
meiravgri
reviewed
Jan 8, 2026
tests/unit/test_spaces.cpp
Outdated
|
|
||
| dist_func_t<float> arch_opt_func; | ||
| float baseline = SQ8_Cosine(v1_orig.data(), v2_quantized.data(), dim); | ||
| float baseline = test_utils::SQ8_NotOptimized_Cosine(v1_orig.data(), v2_quantized.data(), dim); |
Collaborator
There was a problem hiding this comment.
we usually compare to the naive calculation no?
meiravgri
approved these changes
Jan 8, 2026
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.
Describe the changes in the pull request
Fix and datpat the Fp32 SQ8 functions and tests to fit the new stracutre of the query vector.
[elements][sum]
Which issues this PR fixes
Main objects this PR modified
Mark if applicable