leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 24 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
examples/13_two_tensor_op_fusion/threadblock/grouped_threadblock_swizzle.h
-28
View File
@@ -90,34 +90,6 @@ struct GroupedThreadblockSwizzle : detail::GroupedThreadblockSwizzleBase {
}
};
template <
typename ThreadblockShape,
typename LayoutC,
cutlass::gemm::kernel::GroupScheduleMode GroupScheduleMode_ = cutlass::gemm::kernel::GroupScheduleMode::kDeviceOnly,
int PrefetchTileCount = 128,
int ThreadCount = PrefetchTileCount>
struct GemmGroupedThreadblockSwizzle : GroupedThreadblockSwizzle<
cutlass::gemm::kernel::GemmGroupedProblemVisitor<
ThreadblockShape,
GroupScheduleMode_,
PrefetchTileCount,
ThreadCount,
platform::is_same<LayoutC, cutlass::layout::ColumnMajor>::value
>
> {
using Base = GroupedThreadblockSwizzle<cutlass::gemm::kernel::GemmGroupedProblemVisitor<
ThreadblockShape,
GroupScheduleMode_,
PrefetchTileCount,
ThreadCount,
platform::is_same<LayoutC, cutlass::layout::ColumnMajor>::value>>;
CUTLASS_HOST_DEVICE
GemmGroupedThreadblockSwizzle(typename Base::ProblemVisitor::Params& params,
typename Base::ProblemVisitor::SharedStorage& shared_storage,
int block_idx) : Base(params, shared_storage, block_idx) {}
};
template <
typename ThreadblockShape,
typename LayoutC,