CUTLASS 3.5.1 (#1623)

* CUTLASS 3.5.1

* updates, optimizations, fixes
This commit is contained in:
Vijay Thakkar
2024-07-29 08:46:24 -04:00
committed by GitHub
parent 56b46e2d13
commit be60a0b272
312 changed files with 19793 additions and 6775 deletions
+2 -2
View File
@@ -120,7 +120,7 @@ print_type(T&&...) {
CUTE_HOST_DEVICE
bool
block(int bid)
block([[maybe_unused]] int bid)
{
#if defined(__CUDA_ARCH__)
return blockIdx.x + blockIdx.y*gridDim.x + blockIdx.z*gridDim.x*gridDim.y == bid;
@@ -131,7 +131,7 @@ block(int bid)
CUTE_HOST_DEVICE
bool
thread(int tid, int bid)
thread([[maybe_unused]] int tid, [[maybe_unused]] int bid)
{
#if defined(__CUDA_ARCH__)
return (threadIdx.x + threadIdx.y*blockDim.x + threadIdx.z*blockDim.x*blockDim.y == tid) && block(bid);