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/src/SpecialFunctions | |
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/src/SpecialFunctions')
-rw-r--r-- | unsupported/Eigen/src/SpecialFunctions/SpecialFunctionsImpl.h | 4 | ||||
-rw-r--r-- | unsupported/Eigen/src/SpecialFunctions/arch/CUDA/CudaSpecialFunctions.h | 2 |
2 files changed, 3 insertions, 3 deletions
diff --git a/unsupported/Eigen/src/SpecialFunctions/SpecialFunctionsImpl.h b/unsupported/Eigen/src/SpecialFunctions/SpecialFunctionsImpl.h index 9a719e3c0..fbbc87661 100644 --- a/unsupported/Eigen/src/SpecialFunctions/SpecialFunctionsImpl.h +++ b/unsupported/Eigen/src/SpecialFunctions/SpecialFunctionsImpl.h @@ -190,7 +190,7 @@ template <> struct lgamma_impl<float> { EIGEN_DEVICE_FUNC static EIGEN_STRONG_INLINE float run(float x) { -#if !defined(EIGEN_CUDA_ARCH) && (defined(_BSD_SOURCE) || defined(_SVID_SOURCE)) && !defined(__APPLE__) && !defined(EIGEN_HIP_DEVICE_COMPILE) +#if !defined(EIGEN_GPU_COMPILE_PHASE) && (defined(_BSD_SOURCE) || defined(_SVID_SOURCE)) && !defined(__APPLE__) int dummy; return ::lgammaf_r(x, &dummy); #else @@ -203,7 +203,7 @@ template <> struct lgamma_impl<double> { EIGEN_DEVICE_FUNC static EIGEN_STRONG_INLINE double run(double x) { -#if !defined(EIGEN_CUDA_ARCH) && (defined(_BSD_SOURCE) || defined(_SVID_SOURCE)) && !defined(__APPLE__) && !defined(EIGEN_HIP_DEVICE_COMPILE) +#if !defined(EIGEN_GPU_COMPILE_PHASE) && (defined(_BSD_SOURCE) || defined(_SVID_SOURCE)) && !defined(__APPLE__) int dummy; return ::lgamma_r(x, &dummy); #else diff --git a/unsupported/Eigen/src/SpecialFunctions/arch/CUDA/CudaSpecialFunctions.h b/unsupported/Eigen/src/SpecialFunctions/arch/CUDA/CudaSpecialFunctions.h index 020ac1b62..ad011e305 100644 --- a/unsupported/Eigen/src/SpecialFunctions/arch/CUDA/CudaSpecialFunctions.h +++ b/unsupported/Eigen/src/SpecialFunctions/arch/CUDA/CudaSpecialFunctions.h @@ -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 plgamma<float4>(const float4& a) |