Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
Paddle
提交
e90afec4
P
Paddle
项目概览
PaddlePaddle
/
Paddle
12 个月 前同步成功
通知
2292
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
e90afec4
编写于
11月 23, 2018
作者:
T
Tao Luo
提交者:
GitHub
11月 23, 2018
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #14543 from luotao1/threads
add thread related inference api
上级
64ca3d17
116979a4
变更
11
隐藏空白更改
内联
并排
Showing
11 changed file
with
44 addition
and
18 deletion
+44
-18
paddle/fluid/inference/api/analysis_config.cc
paddle/fluid/inference/api/analysis_config.cc
+2
-0
paddle/fluid/inference/api/analysis_predictor.cc
paddle/fluid/inference/api/analysis_predictor.cc
+9
-2
paddle/fluid/inference/api/analysis_predictor.h
paddle/fluid/inference/api/analysis_predictor.h
+2
-0
paddle/fluid/inference/api/api_impl.cc
paddle/fluid/inference/api/api_impl.cc
+1
-2
paddle/fluid/inference/api/paddle_analysis_config.h
paddle/fluid/inference/api/paddle_analysis_config.h
+1
-1
paddle/fluid/inference/api/paddle_api.h
paddle/fluid/inference/api/paddle_api.h
+13
-0
paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
+1
-0
paddle/fluid/inference/tests/api/config_printer.h
paddle/fluid/inference/tests/api/config_printer.h
+2
-0
paddle/fluid/inference/tests/api/tester_helper.h
paddle/fluid/inference/tests/api/tester_helper.h
+11
-9
paddle/fluid/operators/math/fc_compute.h
paddle/fluid/operators/math/fc_compute.h
+1
-3
paddle/fluid/platform/cpu_helper.cc
paddle/fluid/platform/cpu_helper.cc
+1
-1
未找到文件。
paddle/fluid/inference/api/analysis_config.cc
浏览文件 @
e90afec4
...
...
@@ -46,6 +46,7 @@ contrib::AnalysisConfig::AnalysisConfig(const contrib::AnalysisConfig &other) {
prog_file
=
other
.
prog_file
;
param_file
=
other
.
param_file
;
specify_input_name
=
other
.
specify_input_name
;
cpu_math_library_num_threads_
=
other
.
cpu_math_library_num_threads_
;
// fields from this.
enable_ir_optim
=
other
.
enable_ir_optim
;
use_feed_fetch_ops
=
other
.
use_feed_fetch_ops
;
...
...
@@ -72,6 +73,7 @@ contrib::AnalysisConfig::AnalysisConfig(contrib::AnalysisConfig &&other) {
prog_file
=
other
.
prog_file
;
param_file
=
other
.
param_file
;
specify_input_name
=
other
.
specify_input_name
;
cpu_math_library_num_threads_
=
other
.
cpu_math_library_num_threads_
;
// fields from this.
enable_ir_optim
=
other
.
enable_ir_optim
;
use_feed_fetch_ops
=
other
.
use_feed_fetch_ops
;
...
...
paddle/fluid/inference/api/analysis_predictor.cc
浏览文件 @
e90afec4
...
...
@@ -35,7 +35,6 @@
#include "paddle/fluid/platform/profiler.h"
DECLARE_bool
(
profile
);
DECLARE_int32
(
paddle_num_threads
);
namespace
paddle
{
...
...
@@ -67,7 +66,7 @@ bool AnalysisPredictor::Init(
#endif
// no matter with or without MKLDNN
paddle
::
platform
::
SetNumThreads
(
FLAGS_paddle_num_threads
);
paddle
::
platform
::
SetNumThreads
(
config_
.
cpu_math_library_num_threads
()
);
if
(
!
PrepareScope
(
parent_scope
))
{
return
false
;
...
...
@@ -160,6 +159,14 @@ bool AnalysisPredictor::PrepareExecutor() {
return
true
;
}
void
AnalysisPredictor
::
SetMkldnnThreadID
(
int
tid
)
{
#ifdef PADDLE_WITH_MKLDNN
platform
::
set_cur_thread_id
(
tid
);
#else
LOG
(
ERROR
)
<<
"Please compile with MKLDNN first to use MKLDNN"
;
#endif
}
bool
AnalysisPredictor
::
Run
(
const
std
::
vector
<
PaddleTensor
>
&
inputs
,
std
::
vector
<
PaddleTensor
>
*
output_data
,
int
batch_size
)
{
...
...
paddle/fluid/inference/api/analysis_predictor.h
浏览文件 @
e90afec4
...
...
@@ -69,6 +69,8 @@ class AnalysisPredictor : public PaddlePredictor {
framework
::
Scope
*
scope
()
{
return
scope_
.
get
();
}
framework
::
ProgramDesc
&
program
()
{
return
*
inference_program_
;
}
void
SetMkldnnThreadID
(
int
tid
);
protected:
bool
PrepareProgram
(
const
std
::
shared_ptr
<
framework
::
ProgramDesc
>
&
program
);
bool
PrepareScope
(
const
std
::
shared_ptr
<
framework
::
Scope
>
&
parent_scope
);
...
...
paddle/fluid/inference/api/api_impl.cc
浏览文件 @
e90afec4
...
...
@@ -28,7 +28,6 @@ limitations under the License. */
#include "paddle/fluid/platform/profiler.h"
DEFINE_bool
(
profile
,
false
,
"Turn on profiler for fluid"
);
DECLARE_int32
(
paddle_num_threads
);
namespace
paddle
{
namespace
{
...
...
@@ -76,7 +75,7 @@ bool NativePaddlePredictor::Init(
#endif
// no matter with or without MKLDNN
paddle
::
platform
::
SetNumThreads
(
FLAGS_paddle_num_threads
);
paddle
::
platform
::
SetNumThreads
(
config_
.
cpu_math_library_num_threads
()
);
if
(
config_
.
use_gpu
)
{
place_
=
paddle
::
platform
::
CUDAPlace
(
config_
.
device
);
...
...
paddle/fluid/inference/api/paddle_analysis_config.h
浏览文件 @
e90afec4
...
...
@@ -51,9 +51,9 @@ struct AnalysisConfig : public NativeConfig {
int
max_batch_size
=
1
);
bool
use_tensorrt
()
const
{
return
use_tensorrt_
;
}
void
EnableMKLDNN
();
// NOTE this is just for internal development, please not use it.
// NOT stable yet.
void
EnableMKLDNN
();
bool
use_mkldnn
()
const
{
return
use_mkldnn_
;
}
friend
class
::
paddle
::
AnalysisPredictor
;
...
...
paddle/fluid/inference/api/paddle_api.h
浏览文件 @
e90afec4
...
...
@@ -186,6 +186,19 @@ struct NativeConfig : public PaddlePredictor::Config {
// Specify the variable's name of each input if input tensors don't follow the
// `feeds` and `fetches` of the phase `save_inference_model`.
bool
specify_input_name
{
false
};
// Set and get the number of cpu math library threads.
void
SetCpuMathLibraryNumThreads
(
int
cpu_math_library_num_threads
)
{
cpu_math_library_num_threads_
=
cpu_math_library_num_threads
;
}
int
cpu_math_library_num_threads
()
const
{
return
cpu_math_library_num_threads_
;
}
protected:
// number of cpu math library (such as MKL, OpenBlas) threads for each
// instance.
int
cpu_math_library_num_threads_
{
1
};
};
// A factory to help create different predictors.
...
...
paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
浏览文件 @
e90afec4
...
...
@@ -27,6 +27,7 @@ void SetConfig(AnalysisConfig *cfg) {
cfg
->
device
=
0
;
cfg
->
enable_ir_optim
=
true
;
cfg
->
specify_input_name
=
true
;
cfg
->
SetCpuMathLibraryNumThreads
(
FLAGS_paddle_num_threads
);
}
void
SetInput
(
std
::
vector
<
std
::
vector
<
PaddleTensor
>>
*
inputs
)
{
...
...
paddle/fluid/inference/tests/api/config_printer.h
浏览文件 @
e90afec4
...
...
@@ -53,6 +53,8 @@ std::ostream &operator<<(std::ostream &os, const NativeConfig &config) {
os
<<
GenSpaces
(
num_spaces
)
<<
"param_file: "
<<
config
.
param_file
<<
"
\n
"
;
os
<<
GenSpaces
(
num_spaces
)
<<
"specify_input_name: "
<<
config
.
specify_input_name
<<
"
\n
"
;
os
<<
GenSpaces
(
num_spaces
)
<<
"cpu_num_threads: "
<<
config
.
cpu_math_library_num_threads
()
<<
"
\n
"
;
num_spaces
--
;
os
<<
GenSpaces
(
num_spaces
)
<<
"}
\n
"
;
return
os
;
...
...
paddle/fluid/inference/tests/api/tester_helper.h
浏览文件 @
e90afec4
...
...
@@ -42,6 +42,7 @@ DEFINE_bool(use_analysis, true,
"Running the inference program in analysis mode."
);
DECLARE_bool
(
profile
);
DECLARE_int32
(
paddle_num_threads
);
namespace
paddle
{
namespace
inference
{
...
...
@@ -206,22 +207,23 @@ void TestMultiThreadPrediction(
int
batch_size
=
FLAGS_batch_size
;
int
num_times
=
FLAGS_repeat
;
std
::
vector
<
std
::
thread
>
threads
;
std
::
vector
<
std
::
unique_ptr
<
PaddlePredictor
>>
predictors
;
predictors
.
emplace_back
(
CreateTestPredictor
(
config
,
use_analysis
));
for
(
int
tid
=
1
;
tid
<
num_threads
;
++
tid
)
{
predictors
.
emplace_back
(
predictors
.
front
()
->
Clone
());
}
auto
main_predictor
=
CreateTestPredictor
(
config
,
use_analysis
);
size_t
total_time
{
0
};
for
(
int
tid
=
0
;
tid
<
num_threads
;
++
tid
)
{
threads
.
emplace_back
([
&
,
tid
]()
{
#ifdef PADDLE_WITH_MKLDNN
platform
::
set_cur_thread_id
(
static_cast
<
int
>
(
tid
)
+
1
);
#endif
// Each thread should have local inputs and outputs.
// The inputs of each thread are all the same.
std
::
vector
<
PaddleTensor
>
outputs_tid
;
auto
&
predictor
=
predictors
[
tid
];
// To ensure the thread binding correctly,
// please clone inside the threadpool.
auto
predictor
=
main_predictor
->
Clone
();
#ifdef PADDLE_WITH_MKLDNN
if
(
use_analysis
)
{
static_cast
<
AnalysisPredictor
*>
(
predictor
.
get
())
->
SetMkldnnThreadID
(
static_cast
<
int
>
(
tid
)
+
1
);
}
#endif
// warmup run
LOG
(
INFO
)
<<
"Running thread "
<<
tid
<<
", warm up run..."
;
...
...
paddle/fluid/operators/math/fc_compute.h
浏览文件 @
e90afec4
...
...
@@ -17,8 +17,6 @@ limitations under the License. */
#include "paddle/fluid/operators/math/blas.h"
#include "paddle/fluid/operators/math/jit_kernel.h"
DECLARE_int32
(
paddle_num_threads
);
namespace
paddle
{
namespace
operators
{
namespace
math
{
...
...
@@ -43,7 +41,7 @@ inline void FCCompute(const BlasT<DeviceContext, T>& blas, const int M,
.
template
Get
<
jitkernel
::
VAddKernel
<
T
>
>
(
N
);
#ifdef PADDLE_WITH_MKLML
#pragma omp parallel for
if (FLAGS_paddle_num_threads > 1)
#pragma omp parallel for
#endif
for
(
int
i
=
0
;
i
<
M
;
i
++
)
{
T
*
dst
=
Y
+
i
*
N
;
...
...
paddle/fluid/platform/cpu_helper.cc
浏览文件 @
e90afec4
...
...
@@ -41,7 +41,7 @@ void SetNumThreads(int num_threads) {
#elif defined(PADDLE_WITH_MKLML)
int
real_num_threads
=
num_threads
>
1
?
num_threads
:
1
;
platform
::
dynload
::
MKL_Set_Num_Threads
(
real_num_threads
);
omp_set_num_threads
(
num_threads
);
omp_set_num_threads
(
real_
num_threads
);
#else
PADDLE_ENFORCE
(
false
,
"To be implemented."
);
#endif
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录