GEMM 参考资料

论文:

  1. GEMMFIP: Unifying GEMM in BLIS 2302.08417.pdf (arxiv.org)
  2. BLISlab: A Sandbox for Optimizing GEMM 1609.00076.pdf (arxiv.org)
  3. LAFF-On Programming for High Performance: ulaff.net
  4. Anatomy of High-Performance Matrix Multiplication gotoPaper.pdf (utexas.edu)
  5. Anatomy of High-Performance Many-Threaded Matrix Multiplication; blis3_ipdps14.pdf (utexas.edu)
  6. PfHP Blocking for the L1, L2, and L3 caches

     7. Publications Related to the FLAME Project (utexas.edu)

书、博客:

  1. 两分钟速览矩阵乘法库openblas核心: gemm
  2. OpenBLAS gemm 从零入门
  3. GEMM caching
  4. Blocking-for-L1-L3
  5. OPENBLAS矩阵乘法源码结构分析
  6. BLISlab tutoril阅读
  7. 多线程矩阵乘法优化
  8. 斯坦福CS217(三)GEMM计算加速

Github Repo库:

  1. how-to-optimize-gemm
  2. Optimizing-DGEMM-on-Intel-CPUs-with-AVX512F
  3. GEMM_AVX512

你可能感兴趣的:(c++,性能优化)