aboutsummaryrefslogtreecommitdiffhomepage
path: root/unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h
diff options
context:
space:
mode:
authorGravatar Deven Desai <deven.desai.amd@gmail.com>2018-06-14 10:21:54 -0400
committerGravatar Deven Desai <deven.desai.amd@gmail.com>2018-06-14 10:21:54 -0400
commitb6cc0961b17f6204038158c445eddf411c97a3e2 (patch)
treeda2aa8be40f0711de87067fb037a8aae603b1c2a /unsupported/Eigen/CXX11/src/Tensor/TensorExecutor.h
parentba972fb6b40c1ea4ac991b0fb5fa6908bccfdaa6 (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.h4
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