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
yangql
composable_kernel-1
Commits
f53ede26
"docs/git@developer.sourcefind.cn:renzhc/diffusers_dcu.git" did not exist on "673eb60f1c4d971e1a577bed767053e50578b461"
Unverified
Commit
f53ede26
authored
May 02, 2023
by
zjing14
Committed by
GitHub
May 02, 2023
Browse files
fixed init range (#691)
parent
4feebedd
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
+3
-3
profiler/include/profiler/profile_gemm_splitk_impl.hpp
profiler/include/profiler/profile_gemm_splitk_impl.hpp
+3
-3
No files found.
profiler/include/profiler/profile_gemm_splitk_impl.hpp
View file @
f53ede26
...
@@ -72,8 +72,8 @@ bool profile_gemm_splitk_impl(int do_verification,
...
@@ -72,8 +72,8 @@ bool profile_gemm_splitk_impl(int do_verification,
{
{
case
0
:
break
;
case
0
:
break
;
case
1
:
case
1
:
a_m_k
.
GenerateTensorValue
(
GeneratorTensor_2
<
ADataType
>
{
0
,
1
});
a_m_k
.
GenerateTensorValue
(
GeneratorTensor_2
<
ADataType
>
{
-
1
,
2
});
b_k_n
.
GenerateTensorValue
(
GeneratorTensor_2
<
BDataType
>
{
-
1
,
1
});
b_k_n
.
GenerateTensorValue
(
GeneratorTensor_2
<
BDataType
>
{
-
1
,
2
});
break
;
break
;
default:
default:
a_m_k
.
GenerateTensorValue
(
GeneratorTensor_3
<
ADataType
>
{
0.0
,
1.0
});
a_m_k
.
GenerateTensorValue
(
GeneratorTensor_3
<
ADataType
>
{
0.0
,
1.0
});
...
@@ -94,7 +94,7 @@ bool profile_gemm_splitk_impl(int do_verification,
...
@@ -94,7 +94,7 @@ bool profile_gemm_splitk_impl(int do_verification,
a_device_buf
.
ToDevice
(
a_m_k
.
mData
.
data
());
a_device_buf
.
ToDevice
(
a_m_k
.
mData
.
data
());
b_device_buf
.
ToDevice
(
b_k_n
.
mData
.
data
());
b_device_buf
.
ToDevice
(
b_k_n
.
mData
.
data
());
c_device_buf
.
ToDevice
(
c_m_n_device_result
.
mData
.
data
()
);
c_device_buf
.
SetZero
(
);
using
DeviceOp
=
ck
::
tensor_operation
::
device
::
DeviceGemmSplitK
<
ALayout
,
using
DeviceOp
=
ck
::
tensor_operation
::
device
::
DeviceGemmSplitK
<
ALayout
,
BLayout
,
BLayout
,
...
...
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