1. 25 2月, 2022 1 次提交
    • C
      [Phi] Support cudnn kernel moving & move softmax kernels (#39547) · 8895379a
      Chen Weihang 提交于
      * support cudnn kernel moving
      
      * polish cmake rules
      
      * add unittest for coverage
      
      * remove orig kernel
      
      * remove softmax cudnn kernel
      
      * fix softmax test failed
      
      * fix npu func error
      
      * resolve conflict
      
      * rename gpu dnn kernels
      
      * fix name rule error
      
      * fix compile error
      
      * update fp16 namespace
      8895379a
  2. 14 11月, 2018 2 次提交
  3. 09 11月, 2018 2 次提交
  4. 12 2月, 2018 1 次提交
  5. 10 2月, 2018 2 次提交
  6. 12 12月, 2017 1 次提交
    • Q
      Refine device context (#6433) · 61ec0b95
      QI JUN 提交于
      There are mainly following fixes:
      
      - take `DeviceContext` as the template parameter of math functors and OpKernel instead of `Place`
      - remove `eigen_device` interface in base class  `DeviceContext`
      - remove `GetEigenDevice` interface in `ExecutionContext` and base class `DeviceContext`
      - remove unused `platform::EigenDeviceConverter`
      - rename `REGISTER_OP_GPU_KERNEL` to `REGISTER_OP_CUDA_KERNEL`
      - rename `USE_GPU_ONLY_OP` to `USE_CUDA_ONLY_OP`
      61ec0b95
  7. 13 11月, 2017 1 次提交
  8. 28 9月, 2017 1 次提交
  9. 27 9月, 2017 1 次提交
  10. 26 9月, 2017 1 次提交
  11. 22 9月, 2017 1 次提交
  12. 13 9月, 2017 1 次提交
  13. 12 9月, 2017 1 次提交