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

2 files changed, 4 insertions, 4 deletions

diff --git a/Eigen/src/Core/arch/CUDA/PacketMath.h b/Eigen/src/Core/arch/CUDA/PacketMath.h
index 4dda63188..8c46af09b 100644
--- a/Eigen/src/Core/arch/CUDA/PacketMath.h
+++ b/Eigen/src/Core/arch/CUDA/PacketMath.h
@@ -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]);
 }
 
diff --git a/Eigen/src/Core/util/Macros.h b/Eigen/src/Core/util/Macros.h
index 29c796647..14ec87da8 100644
--- a/Eigen/src/Core/util/Macros.h
+++ b/Eigen/src/Core/util/Macros.h
@@ -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