ARM 4-BIT PQ: SIMD-Based Acceleration for Approximate Nearest Neighbor Search on ARM

Yusuke Matsui; Yoshiki Imaizumi; Naoya Miyamoto; Naoki Yoshifuji

ICASSP 2022accepted0 citations

ARM 4-BIT PQ: SIMD-Based Acceleration for Approximate Nearest Neighbor Search on ARM

Yusuke Matsui, Yoshiki Imaizumi, Naoya Miyamoto, Naoki Yoshifuji

Abstract

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.

BibTeX

@inproceedings{icassp2022_arm4bitpqsimdbas,
  title = {ARM 4-BIT PQ: SIMD-Based Acceleration for Approximate Nearest Neighbor Search on ARM},
  author = {Yusuke Matsui and Yoshiki Imaizumi and Naoya Miyamoto and Naoki Yoshifuji},
  booktitle = {ICASSP 2022},
  year = {2022}
}