{
  "annotation_id": "b38ddc27-736a-4f07-bc8a-7ce818b4d343",
  "date_created": "2026-02-17T05:53:20.056000Z",
  "date_modified": "2026-02-17T05:53:20.056000Z",
  "file_hash": "ee15c63617465325611f50a21df9f40a25fc3026911d31409b2d8d8acaabdf4d",
  "private": false,
  "record": {
    "abstract": "The GEneral Matrix Multiplication (GEMM) is one of the essential algorithms in scientific computing. Single-thread GEMM implementations are well-optimised with techniques like blocking and autotuning. However, due to the complexity of modern multi-core shared memory systems, it is challenging to determine the number of threads that minimises the multi-thread GEMM runtime. We present a proof-of-concept approach to building an Architecture and Data-Structure Aware Linear Algebra (ADSALA) software library that uses machine learning to optimise the runtime performance of BLAS routines. More specifically, our method uses a machine learning model on-the-fly to automatically select the optimal number of threads for a given GEMM task based on the collected training data. Test results on two different HPC node architectures, one based on a two-socket Intel Cascade Lake and the other on a two-socket AMD Zen 3, revealed a 25 to 40 per cent speedup compared to traditional GEMM implementations in BLAS when using GEMM of memory usage within 100 MB.",
    "arxiv_id": "2601.09114",
    "authors": [
      "Yufan Xia",
      "Marco De La Pierre",
      "Amanda S. Barnard",
      "Giuseppe Maria Junior Barca"
    ],
    "categories": [
      "cs.DC",
      "cs.LG"
    ],
    "doi": "10.1109/IPDPS54959.2023.00059",
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "A Machine Learning Approach Towards Runtime Optimisation of Matrix Multiplication",
    "url": "https://arxiv.org/abs/2601.09114",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "f85ec772-e05b-465a-8641-4eb04b7ba451",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}