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_ROCM
Commits
09852d3b
Commit
09852d3b
authored
Oct 21, 2024
by
chenjun
Browse files
uncomment
parent
7fb0b322
Changes
2
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
151 additions
and
151 deletions
+151
-151
profiler/include/profiler/profile_gemm_multiply_multiply_impl.hpp
.../include/profiler/profile_gemm_multiply_multiply_impl.hpp
+7
-7
profiler/src/CMakeLists.txt
profiler/src/CMakeLists.txt
+144
-144
No files found.
profiler/include/profiler/profile_gemm_multiply_multiply_impl.hpp
View file @
09852d3b
...
@@ -84,12 +84,12 @@ bool profile_gemm_multiply_multiply_impl(int do_verification,
...
@@ -84,12 +84,12 @@ bool profile_gemm_multiply_multiply_impl(int do_verification,
std
::
min
(
n_iter
,
std
::
min
(
n_iter
,
static_cast
<
int
>
(
std
::
ceil
(
static_cast
<
double
>
(
rotating
)
/
total_gemm_needed
))));
static_cast
<
int
>
(
std
::
ceil
(
static_cast
<
double
>
(
rotating
)
/
total_gemm_needed
))));
//
std::cout << "a_m_k: " << a_m_k.mDesc << std::endl;
std
::
cout
<<
"a_m_k: "
<<
a_m_k
.
mDesc
<<
std
::
endl
;
//
std::cout << "b_k_n: " << b_k_n.mDesc << std::endl;
std
::
cout
<<
"b_k_n: "
<<
b_k_n
.
mDesc
<<
std
::
endl
;
//
std::cout << "d0_m_n: " << d0_m_n.mDesc << std::endl;
std
::
cout
<<
"d0_m_n: "
<<
d0_m_n
.
mDesc
<<
std
::
endl
;
//
std::cout << "d1_m_n: " << d1_m_n.mDesc << std::endl;
std
::
cout
<<
"d1_m_n: "
<<
d1_m_n
.
mDesc
<<
std
::
endl
;
//
std::cout << "e_m_n: " << e_m_n_device_result.mDesc << std::endl;
std
::
cout
<<
"e_m_n: "
<<
e_m_n_device_result
.
mDesc
<<
std
::
endl
;
//
std::cout << "rotating count: " << rotating_count << std::endl;
std
::
cout
<<
"rotating count: "
<<
rotating_count
<<
std
::
endl
;
switch
(
init_method
)
switch
(
init_method
)
{
{
...
@@ -146,7 +146,7 @@ bool profile_gemm_multiply_multiply_impl(int do_verification,
...
@@ -146,7 +146,7 @@ bool profile_gemm_multiply_multiply_impl(int do_verification,
const
auto
op_ptrs
=
ck
::
tensor_operation
::
device
::
instance
::
DeviceOperationInstanceFactory
<
const
auto
op_ptrs
=
ck
::
tensor_operation
::
device
::
instance
::
DeviceOperationInstanceFactory
<
DeviceOp
>::
GetInstances
();
DeviceOp
>::
GetInstances
();
//
std::cout << "found " << op_ptrs.size() << " instances" << std::endl;
std
::
cout
<<
"found "
<<
op_ptrs
.
size
()
<<
" instances"
<<
std
::
endl
;
// Run reference GEMM
// Run reference GEMM
if
(
do_verification
)
if
(
do_verification
)
...
...
profiler/src/CMakeLists.txt
View file @
09852d3b
This diff is collapsed.
Click to expand it.
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