Skip to content

GitLab

"docs/vscode:/vscode.git/clone" did not exist on "c85b80c2b64d0f420aaca59679e5f38f71a8a53e"
Switch branch/tag
  1. 13 Oct, 2021 1 commit
  3. 12 Oct, 2021 2 commits
  5. 10 Oct, 2021 2 commits
  7. 08 Oct, 2021 4 commits
  9. 07 Oct, 2021 1 commit
  11. 06 Oct, 2021 1 commit
    • Chao Liu's avatar
      Tweak GEMM kernel (#38) · b3e8d57d
      Chao Liu authored 
      * add parameters

* tweak gemm

* tweak

* update conv

* update script

* adding bwd 1x1

* update script

* adding 1x1 bwd

* debugging bwd 1x1 failure

* update script

* update script

* test

* test v100

* clean up
      b3e8d57d
  13. 04 Oct, 2021 2 commits
  15. 02 Oct, 2021 4 commits
  17. 01 Oct, 2021 1 commit
  19. 30 Sep, 2021 1 commit
  21. 29 Sep, 2021 1 commit
  23. 15 Sep, 2021 4 commits
  25. 14 Sep, 2021 2 commits
  27. 13 Sep, 2021 3 commits
  29. 12 Sep, 2021 2 commits
  31. 11 Sep, 2021 3 commits
  33. 10 Sep, 2021 1 commit
  35. 09 Sep, 2021 2 commits
  37. 08 Sep, 2021 1 commit
  39. 05 Sep, 2021 1 commit
    • Chao Liu's avatar
      GEMM driver and kernel (#29) · 19613902
      Chao Liu authored 
      * add gemm driver

* tweak

* add gemm kernel: mk_kn_mn and km_kn_mn

* tweak

* add GEMM km_nk_mn

* fix comment
      19613902
  41. 31 Aug, 2021 1 commit
    • ltqin's avatar
      Backward weight v4r4r2 with xdlops (#18) · 627d8ef3
      ltqin authored 
      

* start

* modify transformat

* modify device convolutiion

* modify host

* added host conv bwd and wrw

* remove bwd, seperate wrw

* clean

* hacall k to zero

* out log

* fixed

* fixed

* change to (out in wei)

* input hack

* hack to out

* format

* fix by comments

* change wei hacks(wei transform has not merge)

* fix program once issue

* fix review comment

* fix vector load issue

* tweak
Co-authored-by: default avatarltqin <letaoqin@amd.com>
Co-authored-by: default avatarJing Zhang <jizhan@amd.com>
Co-authored-by: default avatarChao Liu <chao.liu2@amd.com>
      627d8ef3