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
fefd767f
"tests/test_models_unet_2d.py" did not exist on "98f346835ab43e642f5d7d66253b1e06065af21f"
Commit
fefd767f
authored
Sep 16, 2022
by
wangshaojie6
Browse files
merge remote develop
parents
96b0f78c
370efa6c
Changes
22
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
14 additions
and
2 deletions
+14
-2
profiler/src/profiler.cpp
profiler/src/profiler.cpp
+12
-0
script/run_full_performance_tests.sh
script/run_full_performance_tests.sh
+2
-2
No files found.
profiler/src/profiler.cpp
View file @
fefd767f
...
...
@@ -10,6 +10,8 @@ int profile_gemm_add_add_fastgelu(int, char*[]);
int
profile_gemm_reduce
(
int
,
char
*
[]);
int
profile_gemm_bias_add_reduce
(
int
,
char
*
[]);
int
profile_batched_gemm
(
int
,
char
*
[]);
int
profile_batched_gemm_gemm
(
int
,
char
*
[]);
int
profile_batched_gemm_add_relu_gemm_add
(
int
,
char
*
[]);
int
profile_batched_gemm_reduce
(
int
,
char
*
[]);
int
profile_grouped_gemm
(
int
,
char
*
[]);
int
profile_conv_fwd
(
int
,
char
*
[]);
...
...
@@ -32,6 +34,8 @@ static void print_helper_message()
" gemm_reduce: GEMM+Reduce
\n
"
" gemm_bias_add_reduce: GEMM+Bias+Add+Reduce
\n
"
" batched_gemm: Batched GEMM
\n
"
" batched_gemm_gemm: Batched+GEMM+GEMM
\n
"
" batched_gemm_add_relu_gemm_add: Batched+GEMM+bias+gelu+GEMM+bias
\n
"
" batched_gemm_reduce: Batched GEMM+Reduce
\n
"
" grouped_gemm: Grouped GEMM
\n
"
" conv_fwd: Convolution Forward
\n
"
...
...
@@ -80,6 +84,14 @@ int main(int argc, char* argv[])
{
return
profile_batched_gemm
(
argc
,
argv
);
}
else
if
(
strcmp
(
argv
[
1
],
"batched_gemm_gemm"
)
==
0
)
{
return
profile_batched_gemm_gemm
(
argc
,
argv
);
}
else
if
(
strcmp
(
argv
[
1
],
"batched_gemm_add_relu_gemm_add"
)
==
0
)
{
return
profile_batched_gemm_add_relu_gemm_add
(
argc
,
argv
);
}
else
if
(
strcmp
(
argv
[
1
],
"batched_gemm_reduce"
)
==
0
)
{
return
profile_batched_gemm_reduce
(
argc
,
argv
);
...
...
script/run_full_performance_tests.sh
View file @
fefd767f
...
...
@@ -138,5 +138,5 @@ print_log_header $splitK_gemm_log $env_type $branch $host_name
#run ONNX gemm tests
export
onnx_log
=
"perf_onnx_gemm_
${
gpu_arch
}
.log"
print_log_header
$onnx_log
$env_type
$branch
$host_name
./profile_onnx_gemm.sh gemm 0 0
$verify
2
0 1 2>&1 |
tee
-a
$onnx_log
./profile_onnx_gemm.sh gemm 1 0
$verify
2
0 1 2>&1 |
tee
-a
$onnx_log
./profile_onnx_gemm.sh gemm 0 0
$verify
1
0 1 2>&1 |
tee
-a
$onnx_log
./profile_onnx_gemm.sh gemm 1 0
$verify
1
0 1 2>&1 |
tee
-a
$onnx_log
Prev
1
2
Next
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