CUTLASS 3.2.1 (#1113)

* Updates for 3.2.1 release.

* Minor fix in gemm op profiler for raster order.

* Add scheduler mapping for raster order in the kernels.
This commit is contained in:
ANIKET SHIVAM
2023-09-26 17:24:26 -04:00
committed by GitHub
parent e0aaa3c3b3
commit 90d3b0fb18
428 changed files with 22252 additions and 21761 deletions
@@ -434,14 +434,6 @@ class gen_device:
" if (result != cudaSuccess) {\n" + \
" return Status::kErrorInternal;\n" + \
" }\n" + \
"\n" + \
" result = cudaFuncSetAttribute(\n" + \
" Kernel<B2bGemmKernel>,\n" + \
" cudaFuncAttributePreferredSharedMemoryCarveout, 100);\n" + \
"\n" + \
" if (result != cudaSuccess) {\n" + \
" return Status::kErrorInternal;\n" + \
" }\n" + \
" }\n" + \
" cutlass::Kernel<B2bGemmKernel><<<grid, block, smem_size, stream>>>(params_);\n" + \
" result = cudaGetLastError();\n" + \