ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-01 20:21:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK TILE] Refactor grouped conv fwd large tensor (#3144)

Browse Source
This commit is contained in:
Bartłomiej Kocot
2025-11-04 00:34:48 +01:00
committed by GitHub
parent c7ded76cc7
commit 99f38e4d9b
5 changed files with 161 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
include/ck_tile/ops/grouped_convolution/kernel/grouped_convolution_forward_kernel.hpp
View File

@@ -434,14 +434,13 @@ struct GroupedConvFwdKernelArgs
/// multiplication implementation. It is responsible for storing
/// results calculated by @ref GemmPipeline_ "GemmPipeline" to
/// the output C tensor in global memory.
template <bool EnableSplitImage_,
typename GroupedConvTraitsType_,
template <typename GroupedConvTraitsType_,
typename TilePartitioner_,
typename GemmPipeline_,
typename EpiloguePipeline_>
struct GroupedConvolutionForwardKernel
{
static constexpr bool EnableSplitImage = EnableSplitImage_;
static constexpr bool EnableSplitImage = GroupedConvTraitsType_::EnableSplitImage;
static constexpr index_t NDimSpatial = GroupedConvTraitsType_::NDimSpatial;
static constexpr ConvolutionSpecialization ConvSpecialization =
GroupedConvTraitsType_::ConvSpecialization;