ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-01 04:07:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

A workaround for the case that get_slice_tile() doesn't work.

Browse Source
This commit is contained in:
Jiming Ruan
2025-06-19 04:17:20 +00:00
parent c8b247c55c
commit 5c07cd0e15
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
include/ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v2.hpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -61,11 +61,11 @@ struct BlockGemmARegBSmemCRegV2
constexpr auto c_block_outer_dstr_encoding = tile_distribution_encoding<
sequence<>,
tuple<sequence<MIterPerWarp, MWarp>, sequence<NIterPerWarp, NWarp>>,
tuple<sequence<MIterPerWarp, MWarp>, sequence<NWarp, NIterPerWarp>>,
tuple<sequence<1, 2>>,
tuple<sequence<1, 1>>,
tuple<sequence<1, 0>>,
sequence<1, 2>,
sequence<0, 0>>{};
sequence<0, 1>>{};
constexpr auto c_block_dstr_encode = detail::make_embed_tile_distribution_encoding(
c_block_outer_dstr_encoding, typename WG::CWarpDstrEncoding{});
@@ -214,11 +214,11 @@ struct BlockGemmARegBSmemCRegV2
constexpr auto c_block_outer_dstr_encoding = tile_distribution_encoding<
sequence<>,
tuple<sequence<MIterPerWarp, MWarp>, sequence<NIterPerWarp, NWarp>>,
tuple<sequence<MIterPerWarp, MWarp>, sequence<NWarp, NIterPerWarp>>,
tuple<sequence<1, 2>>,
tuple<sequence<1, 1>>,
tuple<sequence<1, 0>>,
sequence<1, 2>,
sequence<0, 0>>{};
sequence<0, 1>>{};
constexpr auto c_block_dstr_encode = detail::make_embed_tile_distribution_encoding(
c_block_outer_dstr_encoding, typename WG::CWarpDstrEncoding{});