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 /Eigen/src/Core/arch/GPU | |
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 'Eigen/src/Core/arch/GPU')
-rw-r--r-- | Eigen/src/Core/arch/GPU/MathFunctions.h | 8 | ||||
-rw-r--r-- | Eigen/src/Core/arch/GPU/PacketMath.h | 8 |
2 files changed, 8 insertions, 8 deletions
diff --git a/Eigen/src/Core/arch/GPU/MathFunctions.h b/Eigen/src/Core/arch/GPU/MathFunctions.h index ff6256ce0..d2b3a2568 100644 --- a/Eigen/src/Core/arch/GPU/MathFunctions.h +++ b/Eigen/src/Core/arch/GPU/MathFunctions.h @@ -7,8 +7,8 @@ // Public License v. 2.0. If a copy of the MPL was not distributed // with this file, You can obtain one at http://mozilla.org/MPL/2.0/. -#ifndef EIGEN_MATH_FUNCTIONS_CUDA_H -#define EIGEN_MATH_FUNCTIONS_CUDA_H +#ifndef EIGEN_MATH_FUNCTIONS_GPU_H +#define EIGEN_MATH_FUNCTIONS_GPU_H namespace Eigen { @@ -17,7 +17,7 @@ namespace internal { // Make sure this is only available when targeting a GPU: we don't want to // introduce conflicts between these packet_traits definitions and the ones // we'll use on the host side (SSE, AVX, ...) -#if defined(EIGEN_CUDACC) && defined(EIGEN_USE_GPU) +#if defined(EIGEN_GPUCC) && defined(EIGEN_USE_GPU) template<> EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE float4 plog<float4>(const float4& a) { @@ -100,4 +100,4 @@ double2 prsqrt<double2>(const double2& a) } // end namespace Eigen -#endif // EIGEN_MATH_FUNCTIONS_CUDA_H +#endif // EIGEN_MATH_FUNCTIONS_GPU_H diff --git a/Eigen/src/Core/arch/GPU/PacketMath.h b/Eigen/src/Core/arch/GPU/PacketMath.h index ab8e477f4..ddf37b9c1 100644 --- a/Eigen/src/Core/arch/GPU/PacketMath.h +++ b/Eigen/src/Core/arch/GPU/PacketMath.h @@ -7,8 +7,8 @@ // Public License v. 2.0. If a copy of the MPL was not distributed // with this file, You can obtain one at http://mozilla.org/MPL/2.0/. -#ifndef EIGEN_PACKET_MATH_CUDA_H -#define EIGEN_PACKET_MATH_CUDA_H +#ifndef EIGEN_PACKET_MATH_GPU_H +#define EIGEN_PACKET_MATH_GPU_H namespace Eigen { @@ -17,7 +17,7 @@ namespace internal { // Make sure this is only available when targeting a GPU: we don't want to // introduce conflicts between these packet_traits definitions and the ones // we'll use on the host side (SSE, AVX, ...) -#if defined(EIGEN_CUDACC) && defined(EIGEN_USE_GPU) +#if defined(EIGEN_GPUCC) && defined(EIGEN_USE_GPU) template<> struct is_arithmetic<float4> { enum { value = true }; }; template<> struct is_arithmetic<double2> { enum { value = true }; }; @@ -338,4 +338,4 @@ ptranspose(PacketBlock<double2,2>& kernel) { } // end namespace Eigen -#endif // EIGEN_PACKET_MATH_CUDA_H +#endif // EIGEN_PACKET_MATH_GPU_H |