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
e55b67a0
Commit
e55b67a0
authored
Aug 10, 2022
by
Anthony Chang
Browse files
fix compilation warnings
parent
ed424975
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
2 additions
and
6 deletions
+2
-6
example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp
example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp
+1
-1
include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
...n/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
+1
-1
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
...operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
+0
-4
No files found.
example/31_batched_gemm_gemm/batched_gemm_gemm_xdl_fp16.cpp
View file @
e55b67a0
...
...
@@ -321,7 +321,7 @@ int main(int argc, char* argv[])
float
ave_time
=
invoker
.
Run
(
argument
,
StreamConfig
{
nullptr
,
time_kernel
});
std
::
size_t
flop
=
(
(
size_t
)
M
*
N
*
K
*
2
+
(
size_t
)
M
*
N
*
O
*
2
)
*
BatchCount
;
std
::
size_t
flop
=
(
size_t
(
M
)
*
N
*
K
*
2
+
size_t
(
M
)
*
N
*
O
*
2
)
*
BatchCount
;
std
::
size_t
num_btype
=
(
sizeof
(
ADataType
)
*
M
*
K
+
sizeof
(
B0DataType
)
*
K
*
N
+
sizeof
(
B1DataType
)
*
N
*
O
+
sizeof
(
CDataType
)
*
M
*
O
)
*
BatchCount
;
...
...
include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_gemm_xdl_cshuffle_v1.hpp
View file @
e55b67a0
...
...
@@ -571,7 +571,7 @@ struct GridwiseBatchedGemmGemm_Xdl_CShuffle
NumGemmKPrefetchStage
>
(
b1_grid_desc_bk0_n_bk1
,
make_multi_index
(
0
,
n_block_data_idx_on_grid
,
0
),
b_element_op
,
b
1
_element_op
,
b1_block_desc_bk0_n_bk1
,
make_multi_index
(
0
,
0
,
0
),
tensor_operation
::
element_wise
::
PassThrough
{});
...
...
include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
View file @
e55b67a0
...
...
@@ -1260,10 +1260,6 @@ struct ThreadwiseTensorSliceTransfer_StaticToStatic
static_assert
(
DstScalarPerVector
==
SpaceFillingCurve
::
ScalarPerVector
,
"wrong!DstScalarPerVector != SpaceFillingCurve::ScalarPerVector"
);
typename
vector_type_maker
<
DstData
,
DstScalarPerVector
>::
type
dst_vector
;
using
dst_vector_t
=
typename
vector_type_maker
<
DstData
,
DstScalarPerVector
>::
type
::
type
;
constexpr
auto
num_access
=
SpaceFillingCurve
::
GetNumOfAccess
();
static_for
<
0
,
num_access
,
1
>
{}([
&
](
auto
idx_1d
)
{
...
...
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