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
wzpei9
Paddle
提交
899827f2
P
Paddle
项目概览
wzpei9
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
列表
看板
标记
里程碑
合并请求
0
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
Issue
1
列表
看板
标记
里程碑
合并请求
0
合并请求
0
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
899827f2
编写于
4月 02, 2018
作者:
F
fengjiayi
提交者:
GitHub
4月 02, 2018
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #9535 from reyoung/feature/fix_double_buffer
Add local cache of double buffer reader
上级
3fd92662
b94f24d4
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
72 addition
and
53 deletion
+72
-53
paddle/fluid/operators/reader/create_double_buffer_reader_op.cc
.../fluid/operators/reader/create_double_buffer_reader_op.cc
+72
-53
未找到文件。
paddle/fluid/operators/reader/create_double_buffer_reader_op.cc
浏览文件 @
899827f2
...
...
@@ -20,12 +20,29 @@ namespace paddle {
namespace
operators
{
namespace
reader
{
static
constexpr
size_t
kDoubleBufferSize
=
2
;
// 'Double buffer' means we shall maintain two batches of input data at the same
// time. So the kCacheSize shoul be at least 2.
static
constexpr
size_t
kCacheSize
=
2
;
// There will be two bacthes out of the channel during training:
// 1. the one waiting to be sent to the channel
// 2. the one just be received from the channel, which is also being used by
// subsequent operators.
// So the channel size should be kChacheSize - 2
static
constexpr
size_t
kChannelSize
=
0
;
// kCacheSize - 2
class
DoubleBufferReader
:
public
framework
::
DecoratedReader
{
public:
struct
Item
{
Item
()
:
ctx_
(
nullptr
)
{}
Item
(
Item
&&
b
)
{
payloads_
=
std
::
move
(
b
.
payloads_
);
ctx_
=
std
::
move
(
b
.
ctx_
);
}
Item
&
operator
=
(
Item
&&
b
)
{
payloads_
=
std
::
move
(
b
.
payloads_
);
ctx_
=
std
::
move
(
b
.
ctx_
);
return
*
this
;
}
std
::
vector
<
framework
::
LoDTensor
>
payloads_
;
platform
::
DeviceContext
*
ctx_
;
...
...
@@ -34,42 +51,44 @@ class DoubleBufferReader : public framework::DecoratedReader {
explicit
DoubleBufferReader
(
ReaderBase
*
reader
,
platform
::
Place
target_place
=
platform
::
CPUPlace
())
:
DecoratedReader
(
reader
),
place_
(
target_place
)
{
for
(
size_t
i
=
0
;
i
<
kDoubleBufferSize
;
++
i
)
{
if
(
platform
::
is_gpu_place
(
place_
))
{
#ifdef PADDLE_WITH_CUDA
for
(
size_t
i
=
0
;
i
<
kCacheSize
;
++
i
)
{
if
(
platform
::
is_gpu_place
(
place_
))
{
ctxs_
.
emplace_back
(
new
platform
::
CUDADeviceContext
(
boost
::
get
<
platform
::
CUDAPlace
>
(
place_
)));
#endif
}
}
start_thread
();
}
void
start_thread
()
{
buffer_
=
framework
::
MakeChannel
<
Item
>
(
kDoubleBufferSize
);
prefetcher_
=
std
::
thread
([
this
]
{
PrefetchThreadFunc
();
});
#endif
StartPrefetcher
();
}
bool
HasNext
()
const
override
;
void
ReadNext
(
std
::
vector
<
framework
::
LoDTensor
>*
out
)
override
;
void
ReInit
()
override
;
~
DoubleBufferReader
()
{
buffer_
->
Close
();
prefetcher_
.
join
();
delete
buffer_
;
~
DoubleBufferReader
()
{
EndPrefetcher
();
}
private:
void
StartPrefetcher
()
{
channel_
=
framework
::
MakeChannel
<
Item
>
(
kChannelSize
);
prefetcher_
=
std
::
thread
([
this
]
{
PrefetchThreadFunc
();
});
}
bool
HasNext
()
const
override
;
void
EndPrefetcher
()
{
channel_
->
Close
();
if
(
prefetcher_
.
joinable
())
{
prefetcher_
.
join
();
}
delete
channel_
;
channel_
=
nullptr
;
}
private:
void
PrefetchThreadFunc
();
std
::
thread
prefetcher_
;
framework
::
Channel
<
Item
>*
buffer
_
;
framework
::
Channel
<
Item
>*
channel
_
;
platform
::
Place
place_
;
std
::
vector
<
std
::
unique_ptr
<
platform
::
DeviceContext
>>
ctxs_
;
mutable
Item
local_buffer_
;
};
class
CreateDoubleBufferReaderOp
:
public
framework
::
OperatorBase
{
...
...
@@ -123,70 +142,70 @@ class CreateDoubleBufferReaderOpMaker : public DecoratedReaderMakerBase {
}
};
bool
DoubleBufferReader
::
HasNext
()
const
{
while
(
!
channel_
->
IsClosed
()
&&
!
channel_
->
CanReceive
())
{
}
return
channel_
->
CanReceive
();
}
void
DoubleBufferReader
::
ReadNext
(
std
::
vector
<
framework
::
LoDTensor
>*
out
)
{
if
(
!
HasNext
())
{
PADDLE_THROW
(
"There is no next data!"
);
}
if
(
local_buffer_
.
payloads_
.
empty
())
{
buffer_
->
Receive
(
&
local_buffer_
);
}
*
out
=
local_buffer_
.
payloads_
;
local_buffer_
.
payloads_
.
clear
();
if
(
local_buffer_
.
ctx_
)
{
local_buffer_
.
ctx_
->
Wait
();
Item
batch
;
channel_
->
Receive
(
&
batch
);
*
out
=
batch
.
payloads_
;
if
(
batch
.
ctx_
)
{
batch
.
ctx_
->
Wait
();
}
}
void
DoubleBufferReader
::
ReInit
()
{
reader_
->
ReInit
();
buffer_
->
Close
();
prefetcher_
.
join
();
delete
buffer_
;
start_thread
();
EndPrefetcher
();
StartPrefetcher
();
}
void
DoubleBufferReader
::
PrefetchThreadFunc
()
{
VLOG
(
5
)
<<
"A new prefetch thread starts."
;
size_t
gpu_ctx_offset
=
0
;
std
::
vector
<
std
::
vector
<
framework
::
LoDTensor
>>
cpu_tensor_cache
(
kCacheSize
);
std
::
vector
<
std
::
vector
<
framework
::
LoDTensor
>>
gpu_tensor_cache
(
kCacheSize
);
size_t
cached_tensor_id
=
0
;
while
(
reader_
->
HasNext
())
{
Item
batch
;
reader_
->
ReadNext
(
&
batch
.
payloads_
);
auto
&
cpu_batch
=
cpu_tensor_cache
[
cached_tensor_id
];
reader_
->
ReadNext
(
&
cpu_batch
);
if
(
platform
::
is_gpu_place
(
place_
))
{
std
::
vector
<
framework
::
LoDTensor
>
gpu_batch
;
auto
&
gpu_ctx
=
this
->
ctxs_
[
gpu_ctx_offset
++
];
gpu_ctx_offset
%=
this
->
ctxs_
.
size
();
gpu_batch
.
resize
(
batch
.
payloads_
.
size
());
for
(
size_t
i
=
0
;
i
<
batch
.
payloads_
.
size
();
++
i
)
{
framework
::
TensorCopy
(
batch
.
payloads_
[
i
],
place_
,
*
gpu_ctx
,
&
gpu_batch
[
i
]);
gpu_batch
[
i
].
set_lod
(
batch
.
payloads_
[
i
].
lod
());
auto
&
gpu_batch
=
gpu_tensor_cache
[
cached_tensor_id
];
auto
*
gpu_ctx
=
ctxs_
[
cached_tensor_id
].
get
();
gpu_batch
.
resize
(
cpu_batch
.
size
());
for
(
size_t
i
=
0
;
i
<
cpu_batch
.
size
();
++
i
)
{
framework
::
TensorCopy
(
cpu_batch
[
i
],
place_
,
*
gpu_ctx
,
&
gpu_batch
[
i
]);
gpu_batch
[
i
].
set_lod
(
cpu_batch
[
i
].
lod
());
}
batch
.
ctx_
=
gpu_ctx
.
get
();
std
::
swap
(
gpu_batch
,
batch
.
payloads_
);
batch
.
payloads_
=
gpu_batch
;
batch
.
ctx_
=
gpu_ctx
;
}
else
{
// CPUPlace
batch
.
payloads_
=
cpu_batch
;
}
++
cached_tensor_id
;
cached_tensor_id
%=
kCacheSize
;
try
{
buffer
_
->
Send
(
&
batch
);
channel
_
->
Send
(
&
batch
);
}
catch
(
paddle
::
platform
::
EnforceNotMet
e
)
{
VLOG
(
5
)
<<
"WARNING: The double buffer channel has been closed. The "
"prefetch thread will terminate."
;
break
;
}
}
buffer
_
->
Close
();
channel
_
->
Close
();
VLOG
(
5
)
<<
"Prefetch thread terminates."
;
}
bool
DoubleBufferReader
::
HasNext
()
const
{
if
(
local_buffer_
.
payloads_
.
empty
())
{
bool
ok
=
buffer_
->
Receive
(
&
local_buffer_
);
return
ok
;
}
else
{
return
true
;
}
}
}
// namespace reader
}
// namespace operators
}
// namespace paddle
...
...
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