GitHub-Proxy/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-08-12 11:49:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

Made most of the packet math primitives usable within CUDA kernel when compiling with clang

Browse Source
This commit is contained in:
Benoit Steiner 2017-02-28 17:05:28 -08:00
parent c92406d613
commit 7b61944669
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Eigen/src/Core/arch/CUDA/PacketMath.h
View File

@ -167,10 +167,10 @@ template<> EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE double2 ploadu<double2>(const d
return make_double2(from[0], from[1]);
}
template<> EIGEN_STRONG_INLINE float4 ploaddup<float4>(const float* from) {
template<> EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE float4 ploaddup<float4>(const float* from) {
return make_float4(from[0], from[0], from[1], from[1]);
}
template<> EIGEN_STRONG_INLINE double2 ploaddup<double2>(const double* from) {
template<> EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE double2 ploaddup<double2>(const double* from) {
return make_double2(from[0], from[0]);
}

4
Eigen/src/Core/util/Macros.h
View File

@ -542,8 +542,8 @@
// - static is not very good because it prevents definitions from different object files to be merged.
// So static causes the resulting linked executable to be bloated with multiple copies of the same function.
// - inline is not perfect either as it unwantedly hints the compiler toward inlining the function.
#define EIGEN_DECLARE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS
#define EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS inline
#define EIGEN_DECLARE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_DEVICE_FUNC
#define EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_DEVICE_FUNC inline
#ifdef NDEBUG
# ifndef EIGEN_NO_DEBUG