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.
2023-09-26 17:24:26 -04:00
parent e0aaa3c3b3
commit 90d3b0fb18
428 changed files with 22252 additions and 21761 deletions
@@ -128,6 +128,7 @@ namespace detail {

 // Get just the Swizzle part of a composed layout.
 template <int B, int M, int S, class Offset, class LayoutB>
+CUTE_HOST_DEVICE constexpr
 auto
 get_swizzle_portion(ComposedLayout<Swizzle<B,M,S>,Offset,LayoutB>)
 {
@@ -136,6 +137,7 @@ get_swizzle_portion(ComposedLayout<Swizzle<B,M,S>,Offset,LayoutB>)

 // A non-swizzled layout's "Swizzle part" is the identity swizzle.
 template <class Shape, class Stride>
+CUTE_HOST_DEVICE constexpr
 auto
 get_swizzle_portion(Layout<Shape,Stride>)
 {