1. 17 Oct, 2022 1 commit
  2. 02 Sep, 2022 1 commit
  3. 10 Jul, 2022 1 commit
  4. 04 Jul, 2022 1 commit
  5. 18 Jun, 2022 4 commits
  6. 17 Jun, 2022 1 commit
  7. 16 Jun, 2022 1 commit
  8. 14 Jun, 2022 2 commits
  9. 13 Jun, 2022 2 commits
  10. 12 Jun, 2022 1 commit
  11. 11 Jun, 2022 1 commit
  12. 10 Jun, 2022 6 commits
  13. 09 Jun, 2022 3 commits
  14. 08 Jun, 2022 2 commits
  15. 01 Jun, 2022 1 commit
  16. 31 May, 2022 1 commit
  17. 30 May, 2022 2 commits
  18. 29 May, 2022 1 commit
  19. 28 May, 2022 4 commits
  20. 27 May, 2022 1 commit
  21. 26 May, 2022 2 commits
    • ltqin's avatar
      Add FP64 XDL GEMM built-in function (#199) · 3e6c2610
      ltqin authored
      
      
      * add intrin_mfma_f64_16x16x4f64
      
      * add example
      
      * gemm reference add double data type
      
      * chang init data
      
      * fix M N PerXdlops
      
      * fix ifdef
      
      * add comparsion config
      
      * add conv fwd example
      
      * format log out
      
      * change rc matrix egister layout
      
      * reorganize example
      
      * reorganize example 2
      
      * format,because merge develop
      
      * fix call impl adding acc data type
      
      * lost ;
      
      * add compiler warning
      
      * change example tunning parameters
      
      * add test for fp64
      
      * add instance
      
      * add test/gemm/gemm_fp64.cpp
      
      * fix get name issue
      
      * remove some tunning parameter
      
      * fix conflict
      
      * format
      
      * use integer value for GEMM test
      
      * add acc data type
      
      * remove typeid because fp16
      
      * fix streamconfig etc bug from merging develop
      
      * format
      
      * remove test_gemm_xdl_fp64
      
      * add AccDataType
      
      * AccDataType problem
      Co-authored-by: default avatarqinletao <letaoqin@amd.com>
      Co-authored-by: default avatarChao Liu <chao.liu2@amd.com>
      3e6c2610
    • ltqin's avatar
      fp16 tag · c5c32b4d
      ltqin authored
      c5c32b4d
  22. 25 May, 2022 1 commit