1. 20 Jan, 2020 1 commit
    • Chao Liu's avatar
      Added bwd data v3r1 v4r1, tweaking v1 (#10) · c5da0377
      Chao Liu authored
      * Added bwd data v3r1: breaking down compute into a series of load balanced GEMM, and launch in a single kernel
      * Added bwd data v4r1: like v3r1, but launch GEMMs in multiple kernels
      * Tweaked v1r1  and v1r2 (atomic) on AMD GPU
      c5da0377
  2. 03 Dec, 2019 1 commit
    • Chao Liu's avatar
      backward data (#7) · 8f5f6496
      Chao Liu authored
      * enabled atomic add in tensor copy
      * added gridwise GEMM
      * added backward data conv using GEMM + atomic
      * added backward data conv using GEMM, no atomic
      8f5f6496
  3. 10 Sep, 2019 1 commit
  4. 09 Sep, 2019 1 commit
  5. 05 Sep, 2019 1 commit
  6. 20 Jun, 2019 1 commit
  7. 19 Jun, 2019 2 commits
  8. 18 Jun, 2019 2 commits
  9. 17 Jun, 2019 2 commits
  10. 13 Jun, 2019 1 commit
  11. 12 Jun, 2019 1 commit
  12. 11 Jun, 2019 2 commits
  13. 07 Jun, 2019 1 commit
  14. 06 Jun, 2019 1 commit
  15. 05 Jun, 2019 1 commit
  16. 03 Jun, 2019 1 commit
  17. 30 May, 2019 1 commit
  18. 23 May, 2019 1 commit
  19. 16 May, 2019 1 commit
  20. 02 May, 2019 1 commit
  21. 23 Apr, 2019 1 commit
  22. 18 Apr, 2019 1 commit
  23. 06 Apr, 2019 2 commits
  24. 03 Apr, 2019 2 commits
  25. 01 Apr, 2019 1 commit
  26. 29 Mar, 2019 1 commit
  27. 24 Mar, 2019 1 commit
  28. 22 Mar, 2019 1 commit
  29. 18 Mar, 2019 2 commits
  30. 17 Mar, 2019 1 commit
  31. 12 Mar, 2019 1 commit
  32. 04 Mar, 2019 1 commit
  33. 17 Feb, 2019 1 commit