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
279580cf
Commit
279580cf
authored
Jul 05, 2023
by
Po-Yen, Chen
Browse files
Fix format
parent
51ef7647
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
4 additions
and
4 deletions
+4
-4
include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
...k/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
+2
-2
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
...k/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
+2
-2
No files found.
include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
View file @
279580cf
...
@@ -79,9 +79,9 @@ struct GridwiseGemmPipeline_v2
...
@@ -79,9 +79,9 @@ struct GridwiseGemmPipeline_v2
do
do
{
{
#if CK_EXPERIMENTAL_PIPELINE_V2_IGLP_OPT
#if CK_EXPERIMENTAL_PIPELINE_V2_IGLP_OPT
__builtin_amdgcn_iglp_opt
(
CK_EXPERIMENTAL_PIPELINE_V2_IGLP_OPT
);
__builtin_amdgcn_iglp_opt
(
CK_EXPERIMENTAL_PIPELINE_V2_IGLP_OPT
);
#endif
#endif
block_sync_lds
();
block_sync_lds
();
...
...
include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
View file @
279580cf
...
@@ -29,7 +29,7 @@ __global__ void
...
@@ -29,7 +29,7 @@ __global__ void
__launch_bounds__
(
CK_MAX_THREAD_PER_BLOCK
,
CK_MIN_BLOCK_PER_CU
)
__launch_bounds__
(
CK_MAX_THREAD_PER_BLOCK
,
CK_MIN_BLOCK_PER_CU
)
#endif
#endif
#if CK_USE_WAVES_PER_EU
#if CK_USE_WAVES_PER_EU
__attribute__
((
amdgpu_waves_per_eu
(
CK_MIN_WAVES_PER_EU
,
CK_MAX_WAVES_PER_EU
)))
__attribute__
((
amdgpu_waves_per_eu
(
CK_MIN_WAVES_PER_EU
,
CK_MAX_WAVES_PER_EU
)))
#endif
#endif
kernel_gemm_xdlops_v2r3
(
const
FloatAB
*
__restrict__
p_a_grid
,
kernel_gemm_xdlops_v2r3
(
const
FloatAB
*
__restrict__
p_a_grid
,
const
FloatAB
*
__restrict__
p_b_grid
,
const
FloatAB
*
__restrict__
p_b_grid
,
...
@@ -65,7 +65,7 @@ __global__ void
...
@@ -65,7 +65,7 @@ __global__ void
__launch_bounds__
(
CK_MAX_THREAD_PER_BLOCK
,
CK_MIN_BLOCK_PER_CU
)
__launch_bounds__
(
CK_MAX_THREAD_PER_BLOCK
,
CK_MIN_BLOCK_PER_CU
)
#endif
#endif
#if CK_USE_WAVES_PER_EU
#if CK_USE_WAVES_PER_EU
__attribute__
((
amdgpu_waves_per_eu
(
CK_MIN_WAVES_PER_EU
,
CK_MAX_WAVES_PER_EU
)))
__attribute__
((
amdgpu_waves_per_eu
(
CK_MIN_WAVES_PER_EU
,
CK_MAX_WAVES_PER_EU
)))
#endif
#endif
kernel_gemm_xdlops_v2r3
(
const
typename
GridwiseGemm
::
Argument
karg
)
kernel_gemm_xdlops_v2r3
(
const
typename
GridwiseGemm
::
Argument
karg
)
{
{
...
...
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