Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
composable_kernel
Commits
fd9e80c5
Commit
fd9e80c5
authored
Jun 25, 2023
by
aska-0096
Browse files
fix gemm
parent
8053bca3
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
7 additions
and
7 deletions
+7
-7
include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
...ation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
+3
-3
include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
+4
-4
No files found.
include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
View file @
fd9e80c5
...
@@ -349,10 +349,10 @@ struct GridwiseGemmMultipleD_Wmma
...
@@ -349,10 +349,10 @@ struct GridwiseGemmMultipleD_Wmma
using
GridwiseGemmPipe
=
using
GridwiseGemmPipe
=
remove_cvref_t
<
decltype
(
GridwiseGemmPipeline_Selector
<
PipelineVer
,
remove_cvref_t
<
decltype
(
GridwiseGemmPipeline_Selector
<
PipelineVer
,
AEnableLds
,
BEnableLds
,
NumGemmKPrefetchStage
,
NumGemmKPrefetchStage
,
LoopSched
>
())
>
;
LoopSched
,
AEnableLds
,
BEnableLds
>
())
>
;
// Describe how data store to (LDS/VGPR) buffer from Global memory
// Describe how data store to (LDS/VGPR) buffer from Global memory
__host__
__device__
static
constexpr
auto
MakeABlockDescriptor
()
__host__
__device__
static
constexpr
auto
MakeABlockDescriptor
()
...
...
include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
View file @
fd9e80c5
...
@@ -141,11 +141,11 @@ struct GridwiseGemm_Wmma
...
@@ -141,11 +141,11 @@ struct GridwiseGemm_Wmma
using
ThisThreadBlock
=
ThisThreadBlock
<
BlockSize
>
;
using
ThisThreadBlock
=
ThisThreadBlock
<
BlockSize
>
;
using
GridwiseGemmPipe
=
using
GridwiseGemmPipe
=
remove_cvref_t
<
decltype
(
GridwiseGemmPipeline_Selector
<
PipelineVer
,
remove_cvref_t
<
decltype
(
GridwiseGemmPipeline_Selector
<
PipelineVer
,,
AEnableLds
,
BEnableLds
,
NumGemmKPrefetchStage
,
NumGemmKPrefetchStage
,
LoopSched
>
())
>
;
LoopSched
,
AEnableLds
,
BEnableLds
>
())
>
;
// Describe how data store to (LDS/VGPR) buffer from Global memory
// Describe how data store to (LDS/VGPR) buffer from Global memory
__host__
__device__
static
constexpr
auto
MakeABlockDescriptor
()
__host__
__device__
static
constexpr
auto
MakeABlockDescriptor
()
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment