Merge pull request #677 from yxsamliu/fix-launch-decay

Fix hipLaunchKernelGGL for hip-clang

[ROCm/clr commit: dd0373dc02]

projects/clr/hipamd/include/hip/hcc_detail/hip_runtime.h

@@ -334,13 +334,13 @@ extern void ihipPostLaunchKernel(const char* kernelName, hipStream_t stream, gri
 typedef int hipLaunchParm;
 
 template <typename... Args, typename F = void (*)(Args...)>
-inline void hipLaunchKernelGGL(F kernelName, const dim3& numblocks, const dim3& numthreads,
+inline void hipLaunchKernelGGL(F&& kernelName, const dim3& numblocks, const dim3& numthreads,
                                unsigned memperblock, hipStream_t streamId, Args... args) {
   kernelName<<<numblocks, numthreads, memperblock, streamId>>>(args...);
 }
 
 template <typename... Args, typename F = void (*)(hipLaunchParm, Args...)>
-inline void hipLaunchKernel(F kernel, const dim3& numBlocks, const dim3& dimBlocks,
+inline void hipLaunchKernel(F&& kernel, const dim3& numBlocks, const dim3& dimBlocks,
                             std::uint32_t groupMemBytes, hipStream_t stream, Args... args) {
     hipLaunchKernelGGL(kernel, numBlocks, dimBlocks, groupMemBytes, stream, hipLaunchParm{},
                        std::move(args)...);