diff options
author | Deven Desai <deven.desai.amd@gmail.com> | 2018-06-14 10:21:54 -0400 |
---|---|---|
committer | Deven Desai <deven.desai.amd@gmail.com> | 2018-06-14 10:21:54 -0400 |
commit | b6cc0961b17f6204038158c445eddf411c97a3e2 (patch) | |
tree | da2aa8be40f0711de87067fb037a8aae603b1c2a /unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h | |
parent | ba972fb6b40c1ea4ac991b0fb5fa6908bccfdaa6 (diff) |
updates based on PR feedback
There are two major changes (and a few minor ones which are not listed here...see PR discussion for details)
1. Eigen::half implementations for HIP and CUDA have been merged.
This means that
- `CUDA/Half.h` and `HIP/hcc/Half.h` got merged to a new file `GPU/Half.h`
- `CUDA/PacketMathHalf.h` and `HIP/hcc/PacketMathHalf.h` got merged to a new file `GPU/PacketMathHalf.h`
- `CUDA/TypeCasting.h` and `HIP/hcc/TypeCasting.h` got merged to a new file `GPU/TypeCasting.h`
After this change the `HIP/hcc` directory only contains one file `math_constants.h`. That will go away too once that file becomes a part of the HIP install.
2. new macros EIGEN_GPUCC, EIGEN_GPU_COMPILE_PHASE and EIGEN_HAS_GPU_FP16 have been added and the code has been updated to use them where appropriate.
- `EIGEN_GPUCC` is the same as `(EIGEN_CUDACC || EIGEN_HIPCC)`
- `EIGEN_GPU_DEVICE_COMPILE` is the same as `(EIGEN_CUDA_ARCH || EIGEN_HIP_DEVICE_COMPILE)`
- `EIGEN_HAS_GPU_FP16` is the same as `(EIGEN_HAS_CUDA_FP16 or EIGEN_HAS_HIP_FP16)`
Diffstat (limited to 'unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h')
-rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h b/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h index 24a57970a..8bbe449cc 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h @@ -201,7 +201,7 @@ class TensorExecutor<Expression, GpuDevice, Vectorizable> { }; -#if defined(EIGEN_CUDACC) || defined(EIGEN_HIPCC) +#if defined(EIGEN_GPUCC) template <typename Evaluator, typename Index, bool Vectorizable> struct EigenMetaKernelEval { static __device__ EIGEN_ALWAYS_INLINE @@ -276,7 +276,7 @@ inline void TensorExecutor<Expression, GpuDevice, Vectorizable>::run( evaluator.cleanup(); } -#endif // EIGEN_CUDACC || EIGEN_HIPCC +#endif // EIGEN_GPUCC #endif // EIGEN_USE_GPU // SYCL Executor policy |