ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-05 06:01:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix for beta!=0 in reduce (#1440)

Browse Source 
* fix for beta!=0 in reduce

* add reviewers suggestions
This commit is contained in:
jakpiase
2024-08-06 18:10:39 +02:00
committed by GitHub
parent 4ec5c52a0c
commit b74d4d4d54
3 changed files with 16 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/ck/tensor_operation/gpu/grid/gridwise_2d_multiple_reduction_multiblock.hpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -258,7 +258,7 @@ struct GridwiseMultipleReduction_mk_to_m_multiblock
if(thread_k_cluster_id == 0)
{
if(block_group_size == 0 && !float_equal_zero{}(beta_values[iR]))
if(!float_equal_zero{}(beta_values[iR]))
{
StaticBuffer<AddressSpaceEnum::Vgpr, OutDataType, MThreadSliceSize, true>
priorDstValueBuf;

4
include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -244,7 +244,7 @@ struct GridwiseReduction_mk_to_m_multiblock
if(thread_k_cluster_id == 0)
{
if(block_group_size == 0 && !float_equal_zero{}(beta))
if(!float_equal_zero{}(beta))
{
StaticBuffer<AddressSpaceEnum::Vgpr, OutDataType, MThreadSliceSize, true>
priorDstValueBuf;