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
TonyTonyFun
Paddle
提交
1b0c7d7c
P
Paddle
项目概览
TonyTonyFun
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
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
0
Issue
0
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
1b0c7d7c
编写于
12月 15, 2017
作者:
Y
Yu Yang
提交者:
GitHub
12月 15, 2017
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Simplize system_allocator and fix GPU_INFO (#6653)
上级
c13805e9
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
23 addition
and
46 deletion
+23
-46
paddle/memory/detail/system_allocator.cc
paddle/memory/detail/system_allocator.cc
+13
-37
paddle/platform/gpu_info.cc
paddle/platform/gpu_info.cc
+10
-9
未找到文件。
paddle/memory/detail/system_allocator.cc
浏览文件 @
1b0c7d7c
...
...
@@ -19,6 +19,7 @@ limitations under the License. */
#include <stdlib.h> // for malloc and free
#include <sys/mman.h> // for mlock and munlock
#include <algorithm> // for std::max
#include "gflags/gflags.h"
...
...
@@ -28,7 +29,7 @@ limitations under the License. */
// of memory available to the system for paging. So, by default, we
// should set false to use_pinned_memory.
DEFINE_bool
(
use_pinned_memory
,
true
,
"If set, allocate cpu pinned memory."
);
DECLARE_double
(
fraction_of_gpu_memory_to_use
);
namespace
paddle
{
namespace
memory
{
namespace
detail
{
...
...
@@ -77,45 +78,20 @@ void* GPUAllocator::Alloc(size_t& index, size_t size) {
// CUDA documentation doesn't explain if cudaMalloc returns nullptr
// if size is 0. We just make sure it does.
if
(
size
<=
0
)
return
nullptr
;
size_t
available
=
0
;
size_t
capacity
=
0
;
paddle
::
platform
::
GpuMemoryUsage
(
available
,
capacity
);
// Reserve memory for page tables, etc.
size_t
reserving
=
0.05
*
capacity
+
paddle
::
platform
::
GpuMinChunkSize
();
size_t
usable
=
available
>
reserving
?
available
-
reserving
:
0
;
// If remaining size no less than expected size, using general
// cudaMalloc to allocate GPU memory.
void
*
p
=
0
;
if
(
size
<=
usable
)
{
cudaError_t
result
=
cudaMalloc
(
&
p
,
size
);
if
(
result
==
cudaSuccess
)
{
index
=
0
;
gpu_alloc_size_
+=
size
;
return
p
;
}
}
// If remaining size less than expected size or cudaMalloc failed,
// cudaMallocHost will be considered as a fallback allocator.
//
// NOTE: here, we use GpuMaxAllocSize() as the maximum memory size
// of host fallback allocation. Allocates too much would reduce
// the amount of memory available to the underlying system for paging.
usable
=
paddle
::
platform
::
GpuMaxAllocSize
()
-
fallback_alloc_size_
;
if
(
size
>
usable
)
return
nullptr
;
cudaError_t
result
=
cudaMallocHost
(
&
p
,
size
);
void
*
p
;
cudaError_t
result
=
cudaMalloc
(
&
p
,
size
);
if
(
result
==
cudaSuccess
)
{
index
=
1
;
fallback
_alloc_size_
+=
size
;
index
=
0
;
gpu
_alloc_size_
+=
size
;
return
p
;
}
else
{
LOG
(
WARNING
)
<<
"Cannot malloc "
<<
size
/
1024.0
/
1024.0
<<
" MB GPU memory. Please shrink FLAGS_fraction_of_gpu_memory_to_use "
"environment variable to a lower value. Current value is "
<<
FLAGS_fraction_of_gpu_memory_to_use
;
return
nullptr
;
}
return
nullptr
;
}
void
GPUAllocator
::
Free
(
void
*
p
,
size_t
size
,
size_t
index
)
{
...
...
paddle/platform/gpu_info.cc
浏览文件 @
1b0c7d7c
...
...
@@ -73,19 +73,20 @@ size_t GpuMaxChunkSize() {
size_t
available
=
0
;
GpuMemoryUsage
(
available
,
total
);
// Reserving the rest memory for page tables, etc.
size_t
reserving
=
0.05
*
total
;
VLOG
(
10
)
<<
"GPU Usage "
<<
available
/
1024
/
1024
<<
"M/"
<<
total
/
1024
/
1024
<<
"M"
;
size_t
reserving
=
static_cast
<
size_t
>
(
0.05
*
total
);
// If available less than minimum chunk size, no usable memory exists.
available
=
std
::
max
(
std
::
max
(
available
,
GpuMinChunkSize
())
-
GpuMinChunkSize
(),
reserving
)
-
reserving
;
std
::
min
(
std
::
max
(
available
,
GpuMinChunkSize
())
-
GpuMinChunkSize
(),
total
-
reserving
);
// Reserving the rest memory for page tables, etc.
size_t
allocating
=
FLAGS_fraction_of_gpu_memory_to_use
*
total
;
size_t
allocating
=
static_cast
<
size_t
>
(
FLAGS_fraction_of_gpu_memory_to_use
*
(
total
-
reserving
));
PADDLE_ENFORCE_L
T
(
allocating
,
available
);
PADDLE_ENFORCE_L
E
(
allocating
,
available
);
return
allocating
;
}
...
...
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