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
085d9d11
"vscode:/vscode.git/clone" did not exist on "8bea943714909cb39d20b126ccbd96c6e7c89bc7"
Commit
085d9d11
authored
Sep 26, 2022
by
Astha Rai
Browse files
changed NumDim into 2D
parent
5da7cd69
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
8 additions
and
3 deletions
+8
-3
include/ck/tensor_operation/gpu/device/device_elementwise_2d.hpp
.../ck/tensor_operation/gpu/device/device_elementwise_2d.hpp
+8
-3
No files found.
include/ck/tensor_operation/gpu/device/device_elementwise_2d.hpp
View file @
085d9d11
...
@@ -26,12 +26,17 @@ template <typename InDataTypeTuple,
...
@@ -26,12 +26,17 @@ template <typename InDataTypeTuple,
index_t
NPerThread
,
index_t
NPerThread
,
typename
InScalarPerVectorSeq
,
typename
InScalarPerVectorSeq
,
typename
OutScalarPerVectorSeq
>
typename
OutScalarPerVectorSeq
>
struct
DeviceElementwise
struct
DeviceElementwise
:
public
DeviceElementwiseBase
<
InDataTypeTuple
,
:
public
DeviceElementwiseBase
<
InDataTypeTuple
,
OutDataTypeTuple
,
ElementwiseOperation
,
NumDim
>
OutDataTypeTuple
,
ElementwiseOperation
,
NumDim_m
,
NumDim_n
>
{
{
static
constexpr
int
NumInput
=
InDataTypeTuple
::
Size
();
static
constexpr
int
NumInput
=
InDataTypeTuple
::
Size
();
static
constexpr
int
NumOutput
=
OutDataTypeTuple
::
Size
();
static
constexpr
int
NumOutput
=
OutDataTypeTuple
::
Size
();
const
index_t
NumDim
=
NumDim_m
+
NumDim_n
;
static_assert
(
NumInput
==
InScalarPerVectorSeq
::
Size
()
&&
static_assert
(
NumInput
==
InScalarPerVectorSeq
::
Size
()
&&
NumOutput
==
OutScalarPerVectorSeq
::
Size
(),
NumOutput
==
OutScalarPerVectorSeq
::
Size
(),
"Tuple size is inconsistent with the number of in/out!"
);
"Tuple size is inconsistent with the number of in/out!"
);
...
@@ -115,7 +120,7 @@ struct DeviceElementwise
...
@@ -115,7 +120,7 @@ struct DeviceElementwise
}
}
template
<
index_t
TupleSize
>
template
<
index_t
TupleSize
>
static
auto
GenerateInOutGrid
se_2d
.
hpp2
dDescTuple
(
Number
<
TupleSize
>
)
static
auto
GenerateInOutGrid
1
dDescTuple
(
Number
<
TupleSize
>
)
{
{
return
generate_tuple
(
return
generate_tuple
(
[
&
](
auto
)
{
[
&
](
auto
)
{
...
...
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