leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

CUTLASS 3.1 (#915)

Browse Source 
Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
This commit is contained in:
ANIKET SHIVAM
2023-04-14 20:19:34 -07:00
committed by GitHub
parent 9b8166e3f0
commit d572cc1aab
482 changed files with 37184 additions and 16419 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/cutlass/device_kernel.h
View File

@@ -99,7 +99,11 @@ void Kernel2(typename Operator::Params params) {
/// Generic CUTLASS kernel template.
template <typename Operator>
__global__ __launch_bounds__(Operator::MaxThreadsPerBlock, Operator::MinBlocksPerMultiprocessor)
__global__
#ifdef __CUDACC__
// Enclosing this in __CUDACC__ suppresses MSVC warnings.
__launch_bounds__(Operator::MaxThreadsPerBlock, Operator::MinBlocksPerMultiprocessor)
#endif // __CUDACC__
void device_kernel(CUTLASS_GRID_CONSTANT typename Operator::Params const params)
{
// Dynamic shared memory base pointer