Updates for 3.4 release. (#1305)

This commit is contained in:
ANIKET SHIVAM
2024-01-16 10:42:51 -08:00
committed by GitHub
parent acba5beee5
commit 2f589ffa76
166 changed files with 5996 additions and 4702 deletions

View File

@@ -60,7 +60,7 @@ namespace cutlass {
/// Generic CUTLASS kernel template.
template <typename Operator>
__global__
CUTLASS_GLOBAL
void Kernel(typename Operator::Params params) {
// Dynamic shared memory base pointer
extern __shared__ int SharedStorageBase[];
@@ -76,7 +76,7 @@ void Kernel(typename Operator::Params params) {
/// Generic CUTLASS kernel template.
template <typename Operator>
__global__
CUTLASS_GLOBAL
void Kernel2(typename Operator::Params params) {
// Dynamic shared memory base pointer
extern __shared__ int SharedStorageBase[];
@@ -96,7 +96,7 @@ void Kernel2(typename Operator::Params params) {
/// Generic CUTLASS kernel template.
template <typename Operator>
__global__
CUTLASS_GLOBAL
#ifdef __CUDACC__
// Enclosing this in __CUDACC__ suppresses MSVC warnings.
__launch_bounds__(Operator::MaxThreadsPerBlock, Operator::MinBlocksPerMultiprocessor)