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 14:24:26 -07:00
committed by GitHub
parent e0aaa3c3b3
commit 90d3b0fb18
428 changed files with 22253 additions and 21762 deletions

View File

@@ -387,8 +387,7 @@ abs(ScaledBasis<T,N> const& e) {
}
// Multiplication
template <class A, int N, class T,
__CUTE_REQUIRES(cute::is_integral<A>::value)>
template <class A, int N, class T>
CUTE_HOST_DEVICE constexpr
auto
operator*(A const& a, ScaledBasis<T,N> const& e) {
@@ -396,8 +395,7 @@ operator*(A const& a, ScaledBasis<T,N> const& e) {
return ScaledBasis<decltype(r),N>{r};
}
template <int N, class T, class B,
__CUTE_REQUIRES(cute::is_integral<B>::value)>
template <int N, class T, class B>
CUTE_HOST_DEVICE constexpr
auto
operator*(ScaledBasis<T,N> const& e, B const& b) {