Add arrwDB — Rust HNSW with AVX-512 intrinsics#626
Open
bledden wants to merge 1 commit into
Open
Conversation
arrwDB is a vector database with a Rust HNSW core using explicit SIMD intrinsics (AVX-512 on Ice Lake, AVX2/FMA fallback). On r6i.16xlarge (same hardware as ann-benchmarks): - SIFT-1M: 1,793 QPS at 0.999 recall, 17,746 QPS at 0.786 - Deep-1M: 2,038 QPS at 0.998 recall, 20,082 QPS at 0.785 - GloVe-1.2M: 252 QPS at 0.953 recall Key implementation details: - Lock-free bulk build with diversity-aware neighbor selection - AVX-512 L2 distance kernel (4x 512-bit accumulators) - Thread-local visited lists with generation counter - Prefetch 3-ahead for memory latency hiding Repository: https://github.com/bledden/arrwDB
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Benchmark Results (r6i.16xlarge, single-threaded)
SIFT-1M (128d, euclidean):
Deep-1M (96d, angular):
GloVe-1.2M (200d, angular):
Files
ann_benchmarks/algorithms/arrwdb/module.py— BaseANN adapter wrappingRustFastHNSWIndexann_benchmarks/algorithms/arrwdb/Dockerfile— Installs Rust, builds arrwDB from source withtarget-cpu=nativeann_benchmarks/algorithms/arrwdb/config.yml— M=16/24/32/48 configurationsann_benchmarks/algorithms/arrwdb/__init__.pyTest plan
python install.py --algorithm arrwdbpython run.py --algorithm arrwdb --dataset sift-128-euclideanpython plot.py --dataset sift-128-euclidean🤖 Generated with Claude Code