ARM 4-BIT PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM
This work provides a domain-specific optimization for efficient similarity search on ARM devices, though it is incremental as it adapts existing PQ methods to a new architecture.
The paper tackles the problem of accelerating 4-bit product quantization for nearest neighbor search on ARM architectures, where performance lags behind x64 systems due to SIMD limitations, and achieves a 10x speedup over naive PQ while maintaining accuracy.
We accelerate the 4-bit product quantization (PQ) on the ARM architecture. Notably, the drastic performance of the conventional 4-bit PQ strongly relies on x64-specific SIMD register, such as AVX2; hence, we cannot yet achieve such good performance on ARM. To fill this gap, we first bundle two 128-bit registers as one 256-bit component. We then apply shuffle operations for each using the ARM-specific NEON instruction. By making this simple but critical modification, we achieve a dramatic speedup for the 4-bit PQ on an ARM architecture. Experiments show that the proposed method consistently achieves a 10x improvement over the naive PQ with the same accuracy.