{
  "id": "2203.02505",
  "version": "v1",
  "published": "2022-03-03T06:19:51.000Z",
  "updated": "2022-03-03T06:19:51.000Z",
  "title": "ARM 4-BIT PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM",
  "authors": [
    "Yusuke Matsui",
    "Yoshiki Imaizumi",
    "Naoya Miyamoto",
    "Naoki Yoshifuji"
  ],
  "comment": "ICASSP 2022",
  "categories": [
    "cs.LG",
    "cs.CV",
    "cs.IR"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-03-03T06:19:51.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "approximate nearest neighbor search",
      "simd-based acceleration",
      "arm architecture",
      "x64-specific simd register",
      "arm-specific neon instruction"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}