ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Shuffle fix for gfx950 (#3491)

Browse Source 
* solve compiler issue

* solve the gfx950 mfma shuffle regression

* refactor jenkinsfile to handle arch name better

* [CK TILE] set divisor to count of thread along k dimension

* fix the compiler error

* solve degradation

* Finish the multiplies fix

* fix the scales

* solve compilation error

* solve the composes

* solve the error of tile sweeper

* fix the test and example

* fix for gfx950

---------

Co-authored-by: Max Podkorytov <4273004+tenpercent@users.noreply.github.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
Co-authored-by: Cong Ma <congma13@amd.com>
This commit is contained in:
Thomas Ning
2026-01-14 01:21:29 +08:00
committed by GitHub
parent 9908a87c31
commit 00c46785a8
33 changed files with 161 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/ck_tile/ops/fused_moe/kernel/fused_moegemm_shape.hpp
View File

@@ -56,10 +56,10 @@ struct FusedMoeGemmShape
using WarpTile_1 = remove_cvref_t<WarpTile_1_>;
static constexpr index_t NumWarps =
reduce_on_sequence(WarpPerBlock_0{}, multiplies{}, number<1>{});
reduce_on_sequence(WarpPerBlock_0{}, multiplies<>{}, number<1>{});
// TODO: we don't support half warps aound to 1 warp here
static_assert(NumWarps == reduce_on_sequence(WarpPerBlock_1{}, multiplies{}, number<1>{}));
static_assert(NumWarps == reduce_on_sequence(WarpPerBlock_1{}, multiplies<>{}, number<1>{}));
static constexpr index_t Block_M0 = BlockTile_0::at(number<0>{});
static constexpr index_t Block_N0 = BlockTile_0::at(number<1>{});