1. 24 12月, 2018 1 次提交
  2. 21 12月, 2018 1 次提交
  3. 20 12月, 2018 1 次提交
  4. 19 12月, 2018 2 次提交
  5. 18 12月, 2018 5 次提交
  6. 17 12月, 2018 2 次提交
  7. 14 12月, 2018 2 次提交
  8. 13 12月, 2018 4 次提交
  9. 11 12月, 2018 1 次提交
  10. 10 12月, 2018 1 次提交
  11. 05 12月, 2018 1 次提交
  12. 04 12月, 2018 1 次提交
  13. 03 12月, 2018 1 次提交
  14. 01 12月, 2018 3 次提交
  15. 29 11月, 2018 2 次提交
  16. 28 11月, 2018 1 次提交
  17. 27 11月, 2018 2 次提交
  18. 26 11月, 2018 4 次提交
  19. 24 11月, 2018 1 次提交
  20. 23 11月, 2018 2 次提交
    • P
      add the bigobj option to NVCC compile · 445fff24
      peizhilin 提交于
      fix code style
      445fff24
    • S
      Fix cmake for AMDGPU platform (#13801) · 61c5f13f
      sabreshao 提交于
      * HIP cmake.
      Enable whole archieve build for pybind library.
      
      Disable two warning.
      
      Rollback to C++11.
      
      Link RCCL to WA gpu kernel loading issue.
      
      Update eigen to fix build failure.
      
      Add more include directories.
      
      Fix O3 build failure.
      
      Update eigen.
      
      fix tensor_util_test segment fault issue
      
      add more macro check in hip.cmake.
      we may consider refine hip.cmake to inherit all add_definitions() in parrent scope, in the future.
      
      Fix rocRAND load.
      
      Update eigen to fix gru_unit_op and reduce_op.
      
      Add HIP support to testing.
      
      Update eigen to support int16 and int8 in arg min and arg max.
      
      * add rocprim as cub library used by nv implementation
      
      * Reduce build time in rocprim.
      
      * Add rocprim introduction, remove useless cmake code.
      
      * Remove useless flags and format cmake file.
      61c5f13f
  21. 22 11月, 2018 2 次提交