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
aebefeac
Commit
aebefeac
authored
Feb 01, 2023
by
Jing Zhang
Browse files
add contraction_bilinear
parent
ba40c2ce
Changes
3
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
436 additions
and
0 deletions
+436
-0
example/26_contraction/CMakeLists.txt
example/26_contraction/CMakeLists.txt
+2
-0
example/26_contraction/contraction_bilinear_xdl_fp64.cpp
example/26_contraction/contraction_bilinear_xdl_fp64.cpp
+427
-0
include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
...r_operation/gpu/element/binary_element_wise_operation.hpp
+7
-0
No files found.
example/26_contraction/CMakeLists.txt
View file @
aebefeac
add_example_executable
(
example_contraction_bilinear_xdl_fp32 contraction_bilinear_xdl_fp32.cpp
)
add_example_executable
(
example_contraction_bilinear_xdl_fp32 contraction_bilinear_xdl_fp32.cpp
)
add_example_executable
(
example_contraction_scale_xdl_fp32 contraction_scale_xdl_fp32.cpp
)
add_example_executable
(
example_contraction_scale_xdl_fp32 contraction_scale_xdl_fp32.cpp
)
add_example_executable
(
example_contraction_bilinear_xdl_fp64 contraction_bilinear_xdl_fp64.cpp
)
example/26_contraction/contraction_bilinear_xdl_fp64.cpp
0 → 100644
View file @
aebefeac
This diff is collapsed.
Click to expand it.
include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
View file @
aebefeac
...
@@ -118,6 +118,13 @@ struct Bilinear
...
@@ -118,6 +118,13 @@ struct Bilinear
template
<
typename
Y
,
typename
X0
,
typename
X1
>
template
<
typename
Y
,
typename
X0
,
typename
X1
>
__host__
__device__
constexpr
void
operator
()(
Y
&
,
const
X0
&
,
const
X1
&
)
const
;
__host__
__device__
constexpr
void
operator
()(
Y
&
,
const
X0
&
,
const
X1
&
)
const
;
template
<
>
__host__
__device__
constexpr
void
operator
()
<
double
,
double
,
double
>
(
double
&
y
,
const
double
&
x0
,
const
double
&
x1
)
const
{
y
=
alpha_
*
x0
+
beta_
*
x1
;
};
template
<
>
template
<
>
__host__
__device__
constexpr
void
__host__
__device__
constexpr
void
operator
()
<
float
,
float
,
float
>
(
float
&
y
,
const
float
&
x0
,
const
float
&
x1
)
const
operator
()
<
float
,
float
,
float
>
(
float
&
y
,
const
float
&
x0
,
const
float
&
x1
)
const
...
...
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