diff options
| author |  Deven Desai <deven.desai.amd@gmail.com> | 2018-07-11 10:39:54 -0400 |
|---|---|---|
| committer | Deven Desai <deven.desai.amd@gmail.com> | 2018-07-11 10:39:54 -0400 |
| commit | 876f392c396318f33454168db36ed54308e54e0d (patch) | |
| tree | a727bc91873b5c0aeec05312176a0f39e2cb64d5 /unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h | |
| parent | 1fe0b749042320501c59378f2860d9322b0c6e19 (diff) | |
Updates corresponding to the latest round of PR feedback
The major changes are
1. Moving CUDA/PacketMath.h to GPU/PacketMath.h
2. Moving CUDA/MathFunctions.h to GPU/MathFunction.h
3. Moving CUDA/CudaSpecialFunctions.h to GPU/GpuSpecialFunctions.h
The above three changes effectively enable the Eigen "Packet" layer for the HIP platform
4. Merging the "hip_basic" and "cuda_basic" unit tests into one ("gpu_basic")
5. Updating the "EIGEN_DEVICE_FUNC" marking in some places
The change has been tested on the HIP and CUDA platforms.
Diffstat (limited to 'unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h')
| -rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h b/unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h index f009ae855..9966955f7 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorGpuHipCudaDefines.h @@ -32,8 +32,7 @@ #define gpuGetDeviceCount hipGetDeviceCount #define gpuGetErrorString hipGetErrorString #define gpuGetDeviceProperties hipGetDeviceProperties -// FIXME : use hipStreamDefault instead of 0x00 -#define gpuStreamDefault 0x00 +#define gpuStreamDefault hipStreamDefault #define gpuGetDevice hipGetDevice #define gpuSetDevice hipSetDevice #define gpuMalloc hipMalloc @@ -47,6 +46,7 @@ #define gpuSharedMemConfig hipSharedMemConfig #define gpuDeviceSetSharedMemConfig hipDeviceSetSharedMemConfig #define gpuStreamSynchronize hipStreamSynchronize +#define gpuDeviceSynchronize hipDeviceSynchronize #define gpuMemcpy hipMemcpy #else @@ -73,6 +73,7 @@ #define gpuSharedMemConfig cudaSharedMemConfig #define gpuDeviceSetSharedMemConfig cudaDeviceSetSharedMemConfig #define gpuStreamSynchronize cudaStreamSynchronize +#define gpuDeviceSynchronize cudaDeviceSynchronize #define gpuMemcpy cudaMemcpy #endif |