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

v4.1 release

Browse Source
This commit is contained in:
Junkai-Wu
2025-07-03 20:07:53 +08:00
committed by GitHub
parent b995f93317
commit a1aaf2300a
155 changed files with 18407 additions and 6068 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
include/cute/algorithm/copy.hpp
View File

@@ -260,13 +260,10 @@ copy(AutoVectorizingCopyWithAssumedAlignment<MaxVecBits> const&,
{
// If more than one element vectorizes to 8bits or more, then recast and copy
using VecType = uint_bit_t<vec_bits>;
// Preserve volatility
using SrcVecType = conditional_t<is_volatile_v<typename SrcEngine::element_type>, VecType const volatile, VecType const>;
using DstVecType = conditional_t<is_volatile_v<typename DstEngine::element_type>, VecType volatile, VecType >;
// Recast
Tensor src_v = recast<SrcVecType>(src);
Tensor dst_v = recast<DstVecType>(dst);
Tensor src_v = recast<VecType>(src);
Tensor dst_v = recast<VecType>(dst);
return copy_if(constant_fn<true_type>{}, src_v, dst_v);
} else {
return copy_if(constant_fn<true_type>{}, src, dst);