leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

CUTLASS 3.2.1 (#1113)

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files
include/cute/atom/mma_atom.hpp
+1 -1
View File
@@ -155,7 +155,7 @@ struct MMA_Atom<MMA_Traits<Args...>>
if constexpr (has_dereference<FrgTypeA>::value) {
// If the intended FrgTypeA is a view (of the current tensor), forward the whole
static_assert(is_same<ValTypeA, typename remove_cvref_t<ATensor>::value_type>::value, "Expecting ValTypeA type");
static_assert(is_same<get_raw_type_t<ValTypeA>, typename remove_cvref_t<ATensor>::value_type>::value, "Expecting ValTypeA type");
return make_tensor<FrgTypeA>(std::forward<ATensor>(atensor));
} else {
// Else, the intended FrgTypeA is a value type, construct a new tensor with a fragment layout