mirror/eigen
2
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-03-07 18:27:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

Made the reduction code compile with cuda-clang

Browse Source
This commit is contained in:
Benoit Steiner 2017-03-14 14:16:53 -07:00
parent bfd7bf9c5b
commit f0f3591118
1 changed files with 17 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
unsupported/Eigen/CXX11/src/Tensor/TensorReduction.h
View File

@ -11,6 +11,17 @@
#ifndef EIGEN_CXX11_TENSOR_TENSOR_REDUCTION_H
#define EIGEN_CXX11_TENSOR_TENSOR_REDUCTION_H
// clang is incompatible with the CUDA syntax wrt making a kernel a class friend,
// so we'll use a macro to make clang happy.
#ifndef KERNEL_FRIEND
#if defined(__clang__) && defined(__CUDA__)
#define KERNEL_FRIEND friend __global__
#else
#define KERNEL_FRIEND friend
#endif
#endif
namespace Eigen {
@ -681,15 +692,15 @@ struct TensorEvaluator<const TensorReductionOp<Op, Dims, ArgType, MakePointer_>,
template <typename S, typename O, bool V> friend struct internal::FullReducerShard;
#endif
#if defined(EIGEN_USE_GPU) && defined(__CUDACC__)
template <int B, int N, typename S, typename R, typename I> friend void internal::FullReductionKernel(R, const S, I, typename S::CoeffReturnType*, unsigned int*);
template <int B, int N, typename S, typename R, typename I> KERNEL_FRIEND void internal::FullReductionKernel(R, const S, I, typename S::CoeffReturnType*, unsigned int*);
#ifdef EIGEN_HAS_CUDA_FP16
template <typename S, typename R, typename I> friend void internal::ReductionInitFullReduxKernelHalfFloat(R, const S, I, half2*);
template <int B, int N, typename S, typename R, typename I> friend void internal::FullReductionKernelHalfFloat(R, const S, I, half*, half2*);
template <int NPT, typename S, typename R, typename I> friend void internal::InnerReductionKernelHalfFloat(R, const S, I, I, half*);
template <typename S, typename R, typename I> KERNEL_FRIEND void internal::ReductionInitFullReduxKernelHalfFloat(R, const S, I, half2*);
template <int B, int N, typename S, typename R, typename I> KERNEL_FRIEND void internal::FullReductionKernelHalfFloat(R, const S, I, half*, half2*);
template <int NPT, typename S, typename R, typename I> KERNEL_FRIEND void internal::InnerReductionKernelHalfFloat(R, const S, I, I, half*);
#endif
template <int NPT, typename S, typename R, typename I> friend void internal::InnerReductionKernel(R, const S, I, I, typename S::CoeffReturnType*);
template <int NPT, typename S, typename R, typename I> KERNEL_FRIEND void internal::InnerReductionKernel(R, const S, I, I, typename S::CoeffReturnType*);
template <int NPT, typename S, typename R, typename I> friend void internal::OuterReductionKernel(R, const S, I, I, typename S::CoeffReturnType*);
template <int NPT, typename S, typename R, typename I> KERNEL_FRIEND void internal::OuterReductionKernel(R, const S, I, I, typename S::CoeffReturnType*);
#endif
#if defined(EIGEN_USE_SYCL)