ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] Minor splitk bugfix for gemms and conv (#3387)

Browse Source 
* fix for splitk if splitk < grid

* add different splitk implementation

* minor bugfix for streamk gemm

* Add test

---------

Co-authored-by: Bartlomiej Kocot <barkocot@amd.com>
This commit is contained in:
jakpiase
2025-12-24 00:10:13 +01:00
committed by GitHub
parent e1381d6a71
commit c0797c1671
3 changed files with 80 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
include/ck_tile/ops/grouped_convolution/kernel/grouped_convolution_backward_weight_kernel.hpp
View File

@@ -568,6 +568,15 @@ struct GroupedConvolutionBackwardWeightKernel
}
}
if(kargs.GemmK < TilePartitioner::BlockGemmShape::WarpTile::at(number<2>{}) * kargs.k_batch)
{
if(ck_tile::EnvIsEnabled(CK_TILE_ENV(CK_TILE_LOGGING)))
{
CK_TILE_ERROR("KBatch is too large, part of GPU wouldn't be utilized!");
}
return false;
}
const index_t ConvK = kargs.wei_g_k_c_xs_lengths[number<1>{}];
const index_t ConvC = kargs.wei_g_k_c_xs_lengths[number<2>{}];