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
98c12b1a
P
Paddle
项目概览
PaddlePaddle
/
Paddle
1 年多 前同步成功
通知
2302
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
提交
98c12b1a
编写于
4月 19, 2018
作者:
X
Xin Pan
提交者:
Yang Yang(Tony)
4月 18, 2018
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Clean up C++ codes. (#10022)
* Privatize OpHandleBase * Clean up a few private members
上级
777cb55c
变更
14
隐藏空白更改
内联
并排
Showing
14 changed file
with
85 addition
and
54 deletion
+85
-54
paddle/fluid/framework/details/broadcast_op_handle.h
paddle/fluid/framework/details/broadcast_op_handle.h
+5
-3
paddle/fluid/framework/details/broadcast_op_handle_test.cc
paddle/fluid/framework/details/broadcast_op_handle_test.cc
+1
-1
paddle/fluid/framework/details/computation_op_handle.cc
paddle/fluid/framework/details/computation_op_handle.cc
+2
-2
paddle/fluid/framework/details/computation_op_handle.h
paddle/fluid/framework/details/computation_op_handle.h
+9
-4
paddle/fluid/framework/details/fetch_op_handle.h
paddle/fluid/framework/details/fetch_op_handle.h
+10
-5
paddle/fluid/framework/details/gather_op_handle.h
paddle/fluid/framework/details/gather_op_handle.h
+5
-3
paddle/fluid/framework/details/gather_op_handle_test.cc
paddle/fluid/framework/details/gather_op_handle_test.cc
+1
-1
paddle/fluid/framework/details/multi_devices_graph_builder.cc
...le/fluid/framework/details/multi_devices_graph_builder.cc
+2
-1
paddle/fluid/framework/details/nccl_all_reduce_op_handle.h
paddle/fluid/framework/details/nccl_all_reduce_op_handle.h
+5
-4
paddle/fluid/framework/details/op_handle_base.h
paddle/fluid/framework/details/op_handle_base.h
+26
-15
paddle/fluid/framework/details/scale_loss_grad_op_handle.h
paddle/fluid/framework/details/scale_loss_grad_op_handle.h
+7
-4
paddle/fluid/framework/details/send_op_handle.h
paddle/fluid/framework/details/send_op_handle.h
+5
-4
paddle/fluid/framework/details/ssa_graph_builder.cc
paddle/fluid/framework/details/ssa_graph_builder.cc
+3
-3
paddle/fluid/framework/details/threaded_ssa_graph_executor.cc
...le/fluid/framework/details/threaded_ssa_graph_executor.cc
+4
-4
未找到文件。
paddle/fluid/framework/details/broadcast_op_handle.h
浏览文件 @
98c12b1a
...
...
@@ -29,9 +29,7 @@ namespace framework {
namespace
details
{
struct
BroadcastOpHandle
:
public
OpHandleBase
{
const
std
::
vector
<
Scope
*>
&
local_scopes_
;
const
std
::
vector
<
platform
::
Place
>
&
places_
;
public:
BroadcastOpHandle
(
const
std
::
vector
<
Scope
*>
&
local_scopes
,
const
std
::
vector
<
platform
::
Place
>
&
places
);
...
...
@@ -41,6 +39,10 @@ struct BroadcastOpHandle : public OpHandleBase {
protected:
void
RunImpl
()
override
;
private:
const
std
::
vector
<
Scope
*>
&
local_scopes_
;
const
std
::
vector
<
platform
::
Place
>
&
places_
;
};
}
// namespace details
...
...
paddle/fluid/framework/details/broadcast_op_handle_test.cc
浏览文件 @
98c12b1a
...
...
@@ -90,7 +90,7 @@ struct TestBroadcastOpHandle {
op_handle_
->
AddInput
(
dummy_var_handle
);
for
(
size_t
j
=
0
;
j
<
gpu_list_
.
size
();
++
j
)
{
op_handle_
->
dev_ctxes_
[
gpu_list_
[
j
]]
=
ctxs_
[
j
].
get
(
);
op_handle_
->
SetDeviceContext
(
gpu_list_
[
j
],
ctxs_
[
j
].
get
()
);
VarHandle
*
out_var_handle
=
new
VarHandle
(
2
,
j
,
"out"
,
gpu_list_
[
j
]);
vars_
.
emplace_back
(
out_var_handle
);
op_handle_
->
AddOutput
(
out_var_handle
);
...
...
paddle/fluid/framework/details/computation_op_handle.cc
浏览文件 @
98c12b1a
...
...
@@ -28,8 +28,8 @@ ComputationOpHandle::ComputationOpHandle(const OpDesc &op_desc, Scope *scope,
void
ComputationOpHandle
::
RunImpl
()
{
auto
*
cur_ctx
=
dev_ctxes_
[
place_
];
for
(
auto
*
in
:
inputs_
)
{
bool
need_wait
=
in
->
generated_op_
&&
in
->
generated_op_
->
dev_ctxes_
[
place_
]
!=
cur_ctx
;
bool
need_wait
=
in
->
generated_op_
&&
in
->
generated_op_
->
DeviceContext
(
place_
)
!=
cur_ctx
;
if
(
need_wait
)
{
in
->
generated_op_
->
Wait
(
cur_ctx
);
}
...
...
paddle/fluid/framework/details/computation_op_handle.h
浏览文件 @
98c12b1a
...
...
@@ -14,6 +14,9 @@
#pragma once
#include <string>
#include <vector>
#include "paddle/fluid/framework/details/op_handle_base.h"
#include "paddle/fluid/framework/op_registry.h"
#include "paddle/fluid/framework/operator.h"
...
...
@@ -24,10 +27,7 @@ namespace paddle {
namespace
framework
{
namespace
details
{
struct
ComputationOpHandle
:
public
OpHandleBase
{
std
::
unique_ptr
<
OperatorBase
>
op_
;
Scope
*
scope_
;
platform
::
Place
place_
;
public:
ComputationOpHandle
(
const
OpDesc
&
op_desc
,
Scope
*
scope
,
platform
::
Place
place
);
...
...
@@ -35,6 +35,11 @@ struct ComputationOpHandle : public OpHandleBase {
protected:
void
RunImpl
()
override
;
private:
std
::
unique_ptr
<
OperatorBase
>
op_
;
Scope
*
scope_
;
platform
::
Place
place_
;
};
}
// namespace details
}
// namespace framework
...
...
paddle/fluid/framework/details/fetch_op_handle.h
浏览文件 @
98c12b1a
...
...
@@ -14,6 +14,9 @@
#pragma once
#include <string>
#include <vector>
#include "paddle/fluid/framework/details/op_handle_base.h"
#include "paddle/fluid/framework/feed_fetch_type.h"
#include "paddle/fluid/framework/scope.h"
...
...
@@ -24,11 +27,7 @@ namespace framework {
namespace
details
{
struct
FetchOpHandle
:
public
OpHandleBase
{
FeedFetchList
*
data_
;
size_t
offset_
;
std
::
vector
<
Scope
*>
*
local_scopes_
;
std
::
vector
<
LoDTensor
>
tensors_
;
public:
FetchOpHandle
(
FeedFetchList
*
data
,
size_t
offset
,
std
::
vector
<
Scope
*>
*
local_scopes
);
...
...
@@ -42,6 +41,12 @@ struct FetchOpHandle : public OpHandleBase {
protected:
void
RunImpl
()
override
;
private:
FeedFetchList
*
data_
;
size_t
offset_
;
std
::
vector
<
Scope
*>
*
local_scopes_
;
std
::
vector
<
LoDTensor
>
tensors_
;
};
}
// namespace details
...
...
paddle/fluid/framework/details/gather_op_handle.h
浏览文件 @
98c12b1a
...
...
@@ -29,9 +29,7 @@ namespace framework {
namespace
details
{
struct
GatherOpHandle
:
public
OpHandleBase
{
const
std
::
vector
<
Scope
*>
&
local_scopes_
;
const
std
::
vector
<
platform
::
Place
>
&
places_
;
public:
GatherOpHandle
(
const
std
::
vector
<
Scope
*>
&
local_scopes
,
const
std
::
vector
<
platform
::
Place
>
&
places
);
...
...
@@ -41,6 +39,10 @@ struct GatherOpHandle : public OpHandleBase {
protected:
void
RunImpl
()
override
;
private:
const
std
::
vector
<
Scope
*>
&
local_scopes_
;
const
std
::
vector
<
platform
::
Place
>
&
places_
;
};
}
// namespace details
...
...
paddle/fluid/framework/details/gather_op_handle_test.cc
浏览文件 @
98c12b1a
...
...
@@ -78,7 +78,7 @@ struct TestGatherOpHandle {
op_handle_
.
reset
(
new
GatherOpHandle
(
local_scopes_
,
gpu_list_
));
// add input
for
(
size_t
j
=
0
;
j
<
gpu_list_
.
size
();
++
j
)
{
op_handle_
->
dev_ctxes_
[
gpu_list_
[
j
]]
=
ctxs_
[
j
].
get
(
);
op_handle_
->
SetDeviceContext
(
gpu_list_
[
j
],
ctxs_
[
j
].
get
()
);
auto
*
in_var_handle
=
new
VarHandle
(
1
,
j
,
"input"
,
gpu_list_
[
j
]);
vars_
.
emplace_back
(
in_var_handle
);
op_handle_
->
AddInput
(
in_var_handle
);
...
...
paddle/fluid/framework/details/multi_devices_graph_builder.cc
浏览文件 @
98c12b1a
...
...
@@ -60,7 +60,8 @@ void MultiDevSSAGraphBuilder::CreateOpHandleIOs(SSAGraph *result,
const
platform
::
Place
&
p
,
const
size_t
&
i
)
const
{
auto
*
op_handle
=
result
->
ops_
.
back
().
get
();
op_handle
->
dev_ctxes_
[
p
]
=
platform
::
DeviceContextPool
::
Instance
().
Get
(
p
);
op_handle
->
SetDeviceContext
(
p
,
platform
::
DeviceContextPool
::
Instance
().
Get
(
p
));
auto
var_names
=
op
.
InputArgumentNames
();
...
...
paddle/fluid/framework/details/nccl_all_reduce_op_handle.h
浏览文件 @
98c12b1a
...
...
@@ -27,10 +27,6 @@ namespace framework {
namespace
details
{
struct
NCCLAllReduceOpHandle
:
public
OpHandleBase
{
const
std
::
vector
<
Scope
*>
&
local_scopes_
;
const
std
::
vector
<
platform
::
Place
>
&
places_
;
const
platform
::
NCCLContextMap
&
nccl_ctxs_
;
NCCLAllReduceOpHandle
(
const
std
::
vector
<
Scope
*>
&
local_scopes
,
const
std
::
vector
<
platform
::
Place
>
&
places
,
const
platform
::
NCCLContextMap
&
ctxs
);
...
...
@@ -43,6 +39,11 @@ struct NCCLAllReduceOpHandle : public OpHandleBase {
protected:
void
RunImpl
()
override
;
private:
const
std
::
vector
<
Scope
*>
&
local_scopes_
;
const
std
::
vector
<
platform
::
Place
>
&
places_
;
const
platform
::
NCCLContextMap
&
nccl_ctxs_
;
};
}
// namespace details
...
...
paddle/fluid/framework/details/op_handle_base.h
浏览文件 @
98c12b1a
...
...
@@ -27,28 +27,15 @@ namespace details {
constexpr
char
kLocalExecScopeName
[]
=
"@LCOAL_SCOPE@"
;
class
OpHandleBase
{
private:
DISABLE_COPY_AND_ASSIGN
(
OpHandleBase
);
public:
std
::
vector
<
VarHandleBase
*>
inputs_
;
std
::
vector
<
VarHandleBase
*>
outputs_
;
std
::
unordered_map
<
platform
::
Place
,
platform
::
DeviceContext
*
,
platform
::
PlaceHash
>
dev_ctxes_
;
#ifdef PADDLE_WITH_CUDA
std
::
unordered_map
<
int
,
cudaEvent_t
>
events_
;
#endif
OpHandleBase
()
{}
virtual
~
OpHandleBase
();
std
::
string
DebugString
()
const
;
virtual
std
::
string
Name
()
const
=
0
;
virtual
~
OpHandleBase
();
void
Run
(
bool
use_event
);
virtual
void
Wait
(
platform
::
DeviceContext
*
waited_dev
);
...
...
@@ -61,6 +48,18 @@ class OpHandleBase {
// will likely block other computations.
virtual
bool
IsMultiDeviceTransfer
()
{
return
false
;
}
const
platform
::
DeviceContext
*
DeviceContext
(
platform
::
Place
place
)
{
return
dev_ctxes_
[
place
];
}
void
SetDeviceContext
(
platform
::
Place
place
,
platform
::
DeviceContext
*
ctx_
)
{
dev_ctxes_
[
place
]
=
ctx_
;
}
const
std
::
vector
<
VarHandleBase
*>
&
Inputs
()
const
{
return
inputs_
;
}
const
std
::
vector
<
VarHandleBase
*>
&
Outputs
()
const
{
return
outputs_
;
}
protected:
void
RunAndRecordEvent
(
const
std
::
function
<
void
()
>
&
callback
);
...
...
@@ -68,6 +67,18 @@ class OpHandleBase {
const
std
::
function
<
void
()
>
&
callback
);
virtual
void
RunImpl
()
=
0
;
std
::
vector
<
VarHandleBase
*>
inputs_
;
std
::
vector
<
VarHandleBase
*>
outputs_
;
std
::
unordered_map
<
platform
::
Place
,
platform
::
DeviceContext
*
,
platform
::
PlaceHash
>
dev_ctxes_
;
#ifdef PADDLE_WITH_CUDA
std
::
unordered_map
<
int
,
cudaEvent_t
>
events_
;
#endif
DISABLE_COPY_AND_ASSIGN
(
OpHandleBase
);
};
}
// namespace details
...
...
paddle/fluid/framework/details/scale_loss_grad_op_handle.h
浏览文件 @
98c12b1a
...
...
@@ -14,6 +14,8 @@
#pragma once
#include <string>
#include "paddle/fluid/framework/details/op_handle_base.h"
#include "paddle/fluid/framework/lod_tensor.h"
#include "paddle/fluid/framework/scope.h"
...
...
@@ -23,10 +25,6 @@ namespace framework {
namespace
details
{
struct
ScaleLossGradOpHandle
:
public
OpHandleBase
{
float
coeff_
;
Scope
*
scope_
;
platform
::
Place
place_
;
ScaleLossGradOpHandle
(
size_t
num_dev
,
Scope
*
scope
,
platform
::
Place
place
,
platform
::
DeviceContext
*
context
);
...
...
@@ -36,6 +34,11 @@ struct ScaleLossGradOpHandle : public OpHandleBase {
protected:
void
RunImpl
()
override
;
private:
float
coeff_
;
Scope
*
scope_
;
platform
::
Place
place_
;
};
}
// namespace details
...
...
paddle/fluid/framework/details/send_op_handle.h
浏览文件 @
98c12b1a
...
...
@@ -28,10 +28,6 @@ namespace framework {
namespace
details
{
struct
SendOpHandle
:
public
OpHandleBase
{
std
::
unique_ptr
<
OperatorBase
>
op_
;
const
Scope
*
local_scope_
;
const
platform
::
Place
&
place_
;
SendOpHandle
(
const
framework
::
OpDesc
&
op_desc
,
const
Scope
*
local_scope
,
const
platform
::
Place
&
place
);
...
...
@@ -43,6 +39,11 @@ struct SendOpHandle : public OpHandleBase {
protected:
void
RunImpl
()
override
;
private:
std
::
unique_ptr
<
OperatorBase
>
op_
;
const
Scope
*
local_scope_
;
const
platform
::
Place
&
place_
;
};
}
// namespace details
...
...
paddle/fluid/framework/details/ssa_graph_builder.cc
浏览文件 @
98c12b1a
...
...
@@ -117,12 +117,12 @@ void SSAGraphBuilder::PrintGraphviz(const SSAGraph &graph, std::ostream &sout) {
std
::
string
op_name
=
"op_"
+
std
::
to_string
(
op_id
++
);
sout
<<
op_name
<<
" [label=
\"
"
<<
op
->
Name
()
<<
"
\"
, shape=rect]"
<<
std
::
endl
;
for
(
auto
in
:
op
->
inputs_
)
{
for
(
auto
in
:
op
->
Inputs
()
)
{
std
::
string
var_name
=
"var_"
+
std
::
to_string
(
vars
[
in
]);
sout
<<
var_name
<<
" -> "
<<
op_name
<<
std
::
endl
;
}
for
(
auto
out
:
op
->
outputs_
)
{
for
(
auto
out
:
op
->
Outputs
()
)
{
std
::
string
var_name
=
"var_"
+
std
::
to_string
(
vars
[
out
]);
sout
<<
op_name
<<
" -> "
<<
var_name
<<
std
::
endl
;
}
...
...
@@ -133,7 +133,7 @@ void SSAGraphBuilder::PrintGraphviz(const SSAGraph &graph, std::ostream &sout) {
void
SSAGraphBuilder
::
AddOutputToLeafOps
(
SSAGraph
*
graph
)
{
for
(
auto
&
op
:
graph
->
ops_
)
{
if
(
!
op
->
outputs_
.
empty
())
{
if
(
!
op
->
Outputs
()
.
empty
())
{
continue
;
}
auto
*
dummy_leaf
=
new
DummyVarHandle
();
...
...
paddle/fluid/framework/details/threaded_ssa_graph_executor.cc
浏览文件 @
98c12b1a
...
...
@@ -53,7 +53,7 @@ FeedFetchList ThreadedSSAGraphExecutor::Run(
};
auto
InsertPendingOp
=
[
&
pending_ops
](
OpHandleBase
&
op_instance
)
{
pending_ops
.
insert
({
&
op_instance
,
op_instance
.
inputs_
.
size
()});
pending_ops
.
insert
({
&
op_instance
,
op_instance
.
Inputs
()
.
size
()});
};
// Transform SSAGraph to pending_ops & pending_vars
...
...
@@ -69,7 +69,7 @@ FeedFetchList ThreadedSSAGraphExecutor::Run(
}
for
(
auto
&
op
:
graph_
->
ops_
)
{
if
(
op
->
inputs_
.
empty
())
{
// Special case, Op has no input.
if
(
op
->
Inputs
()
.
empty
())
{
// Special case, Op has no input.
ready_ops
.
insert
(
op
.
get
());
}
else
{
InsertPendingOp
(
*
op
);
...
...
@@ -99,7 +99,7 @@ FeedFetchList ThreadedSSAGraphExecutor::Run(
fetch_ops
.
emplace_back
(
op
);
for
(
auto
&
p
:
places_
)
{
op
->
dev_ctxes_
[
p
]
=
fetch_ctxs_
.
Get
(
p
);
op
->
SetDeviceContext
(
p
,
fetch_ctxs_
.
Get
(
p
)
);
}
for
(
auto
*
var
:
vars
)
{
...
...
@@ -180,7 +180,7 @@ void ThreadedSSAGraphExecutor::RunOp(
op
->
Run
(
use_event_
);
VLOG
(
10
)
<<
op
<<
" "
<<
op
->
Name
()
<<
" Done "
;
running_ops_
--
;
ready_var_q
->
Extend
(
op
->
outputs_
);
ready_var_q
->
Extend
(
op
->
Outputs
()
);
VLOG
(
10
)
<<
op
<<
" "
<<
op
->
Name
()
<<
"Signal posted"
;
}
catch
(
platform
::
EnforceNotMet
ex
)
{
exception_
.
reset
(
new
platform
::
EnforceNotMet
(
ex
));
...
...
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