ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-02 04:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix transform and instances for grouped conv bwd data (#848)

Browse Source 
* Fix transform and instances for grouped conv bwd data

* Add instances for small K and small C

* Remove workaround after fix

* Fix interface tests
This commit is contained in:
Bartłomiej Kocot
2023-08-22 18:25:41 +02:00
committed by GitHub
parent eac50708d9
commit 595d23be14
8 changed files with 203 additions and 160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
View File

@@ -129,6 +129,9 @@ struct ThreadwiseTensorSliceTransfer_v3r1
constexpr auto src_access_lengths = SliceLengths{} / src_scalar_per_access;
static_assert(SliceLengths::At(SrcVectorDim) % SrcScalarPerVector == 0,
"SliceLengths[SrcVectorDim] must be divisible by SrcScalarPerVector");
constexpr auto src_dim_access_order = SrcDimAccessOrder{};
constexpr auto ordered_src_access_lengths =