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
Crayon鑫
Paddle
提交
e1140f2b
P
Paddle
项目概览
Crayon鑫
/
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
提交
e1140f2b
编写于
7年前
作者:
Y
Yi Wang
提交者:
GitHub
7年前
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #2970 from gangliao/memcpy
Add CPU/GPU Memcpy in memory folder
上级
6129ab42
6cae35b5
develop
2.0.1-rocm-post
Ligoml-patch-1
OliverLPH-patch-1
OliverLPH-patch-2
PaddlePM-patch-1
PaddlePM-patch-2
ZHUI-patch-1
add_default_att
add_model_benchmark_ci
add_some_yaml_config
addfile
all_new_design_exec
ascendrc
ascendrelease
cherry_undefined_var
compile_windows
delete_2.0.1-rocm-post
delete_add_default_att
delete_all_new_design_exec
delete_ascendrc
delete_compile_windows
delete_delete_addfile
delete_disable_iterable_dataset_unittest
delete_fix_dataloader_memory_leak
delete_fix_imperative_dygraph_error
delete_fix_retry_ci
delete_fix_undefined_var
delete_improve_sccache
delete_incubate/lite
delete_paddle_tiny_install
delete_paralleltest
delete_prv-disable-more-cache
delete_revert-31068-fix_conv3d_windows
delete_revert-31562-mean
delete_revert-33630-bug-fix
delete_revert-34159-add_npu_bce_logical_dev
delete_revert-34910-spinlocks_for_allocator
delete_revert-35069-revert-34910-spinlocks_for_allocator
delete_revert-36057-dev/read_flags_in_ut
dingjiaweiww-patch-1
disable_iterable_dataset_unittest
dy2static
enable_eager_model_test
final_state_gen_python_c
final_state_intermediate
fix-numpy-issue
fix_concat_slice
fix_dataloader_memory_leak
fix_imperative_dygraph_error
fix_npu_ci
fix_op_flops
fix_retry_ci
fix_rnn_docs
fix_tensor_type
fix_undefined_var
fixiscan
fixiscan1
fixiscan2
fixiscan3
github/fork/123malin/netifaces
github/fork/123malin/tdm_abacus
github/fork/AshburnLee/dev_unique
github/fork/ForFishes/fix_memory_matmul
github/fork/ForFishes/rm_fluid
github/fork/LielinJiang/move-2.0-api
github/fork/LielinJiang/visual-dl-cb
github/fork/LiuChiachi/add-transformer-generate-square-subsequent-mask-api
github/fork/LiuChiachi/fix-example-code-for-hapi-Model
github/fork/LiuChiachi/remove-input-requirment-in-dygraph-Model
github/fork/MrChengmo/fix_ps_profiler
github/fork/MrChengmo/update_ps_heter
github/fork/PWhiddy/patch-1
github/fork/Shixiaowei02/dev/save_load_upgrade
github/fork/TCChenlong/fix_hapi
github/fork/TCChenlong/fix_inden
github/fork/Thunderbrook/xpu_slice
github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var
github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_2
github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_3
github/fork/XieYunshen/timeout_20S_ut
github/fork/ZeyuChen/remove-nltk
github/fork/arlesniak/arlesniak/selective__mkldnn_flags
github/fork/baiyfbupt/code_doc_mig
github/fork/chalsliu/set_timeout
github/fork/chen-zhiyu/develop
github/fork/chenwhql/ci/try_to_find_test_buffer_shared_memory_reuse_pass_error
github/fork/chenwhql/dygraph/remove_scale_loss_and_apply_collective_grads
github/fork/chenwhql/saveload/add_get_inference_program
github/fork/chenwhql/saveload/remove_save_load_config
github/fork/cryoco/pass-compatibility-trt
github/fork/danleifeng/isempty_api2.0
github/fork/frankwhzhang/api_transfer
github/fork/hbwx24/error_msg/cuda_kernel_error_msg
github/fork/heavengate/cherry_yolo_box
github/fork/heavengate/update_yolo_box
github/fork/iclementine/rnn_fix
github/fork/iducn/testestse
github/fork/jczaja/prv-25537-fix
github/fork/jeff41404/release/1.8
github/fork/jiweibo/api_2.0
github/fork/jiweibo/fix_lite_resnet50_test
github/fork/juncaipeng/fix_doc_1
github/fork/lfchener/sample_code
github/fork/littletomatodonkey/fix_reg_doc
github/fork/liym27/dy2stat_update_assign_to_rc20
github/fork/luotao1/profiler_ut
github/fork/mapingshuo/add_wait
github/fork/mapingshuo/doc_2.0
github/fork/mapingshuo/zero-0.5
github/fork/miraiwk/dev
github/fork/pangyoki/add-Categorical-class-branch
github/fork/pangyoki/add-multinomial-op-branch
github/fork/pangyoki/fix-test_distritbution-CI
github/fork/qjing666/doublegrad
github/fork/qjing666/fix_hdfs_download
github/fork/sandyhouse/add_gather_etc
github/fork/sandyhouse/add_send_recv_alltoall_etc
github/fork/sandyhouse/pipeline_exe_run
github/fork/seiriosPlus/feature/large_scale_kv_save_delta
github/fork/seiriosPlus/fix/paddle_errors_fix
github/fork/seiriosPlus/fix/paddle_op_errors
github/fork/shangzhizhou/fix_test_activation_op_random_bug
github/fork/smallv0221/yxp0924
github/fork/smallv0221/yxp0925
github/fork/swtkiwi/del-matplotlib
github/fork/tianshuo78520a/kunlun_test
github/fork/tianshuo78520a/update_dockerfile
github/fork/wanghaoshuang/bert_fuse
github/fork/wanghaoshuang/label_smooth
github/fork/wanghuancoder/develop_CUDASynchronize
github/fork/wanghuancoder/develop_Layer_doc
github/fork/wanghuancoder/develop_ParameterList_doc
github/fork/wanghuancoder/develop_Sequential_doc
github/fork/wanghuancoder/develop_bilinear_tensor_product
github/fork/wanghuancoder/develop_coverage_build_sh
github/fork/wanghuancoder/develop_in_dynamic_mode_doc
github/fork/wanghuancoder/develop_unique_name_doc
github/fork/wangxicoding/fleet_meta_combine
github/fork/wawltor/error_message_fix_5
github/fork/willthefrog/remove_l2_norm
github/fork/windstamp/momentum_op
github/fork/windstamp/mv_op_5
github/fork/windstamp/normal_api
github/fork/wojtuss/wojtuss/fusion_gru_quantization
github/fork/wojtuss/wojtuss/quantization-with-shift
github/fork/wzzju/fix_err_info
github/fork/wzzju/pure_fp16
github/fork/xiemoyuan/op_error_message
github/fork/xiemoyuan/optimize_error_message
github/fork/yaoxuefeng6/fix_doc
github/fork/yaoxuefeng6/mod_dataset_v2
github/fork/yongqiangma/lod
github/fork/ysh329/fix-clip-by-norm-error
github/fork/ysh329/fix-error-clip-by-value
github/fork/yukavio/error_info
github/fork/zhangting2020/conv_filter_grad
github/fork/zhangting2020/is_compile_with_cuda
github/fork/zhangting2020/place_doc
github/fork/zhangting2020/program
github/fork/zhhsplendid/fix_any
github/fork/zhhsplendid/refine_api2
github/fork/zhhsplendid/refine_api2_test
github/fork/zhhsplendid/refine_api_test_ptb_lm
github/fork/zhhsplendid/refine_api_test_resnet
github/fork/zhhsplendid/refine_api_test_simnet
github/fork/zhiqiu/dev/refine_initializer
github/fork/zhiqiu/dev/remove_inplace_argument
github/fork/zlsh80826/nvinfer_plugin_var_len_cuda11
improve_sccache
incubate/infrt
incubate/lite
inplace_addto
make_flag_adding_easier
master
move_embedding_to_phi
move_histogram_to_pten
move_sgd_to_phi
move_slice_to_pten
move_temporal_shift_to_phi
move_yolo_box_to_phi
npu_fix_alloc
numel
paddle_tiny_install
paralleltest
preln_ernie
prv-disable-more-cache
prv-md-even-more
prv-onednn-2.5
pten_tensor_refactor
release/0.11.0
release/0.12.0
release/0.13.0
release/0.14.0
release/0.15.0
release/1.0.0
release/1.1
release/1.2
release/1.3
release/1.4
release/1.5
release/1.6
release/1.7
release/1.8
release/2.0
release/2.0-alpha
release/2.0-beta
release/2.0-rc
release/2.0-rc1
release/2.1
release/2.2
release/2.3
release/2.3-fc-ernie-fix
release/2.4
release/lite-0.1
revert-24981-add_device_attr_for_regulization
revert-26856-strategy_example2
revert-27520-disable_pr
revert-31068-fix_conv3d_windows
revert-31562-mean
revert-32290-develop-hardlabel
revert-33037-forci
revert-33475-fix_cifar_label_dimension
revert-33630-bug-fix
revert-34159-add_npu_bce_logical_dev
revert-34406-add_copy_from_tensor
revert-34910-spinlocks_for_allocator
revert-35069-revert-34910-spinlocks_for_allocator
revert-36057-dev/read_flags_in_ut
revert-36201-refine_fast_threaded_ssa_graph_executor
revert-36985-add_license
revert-37318-refactor_dygraph_to_eager
revert-37926-eager_coreops_500
revert-37956-revert-37727-pylayer_support_tuple
revert-38100-mingdong
revert-38301-allocation_rearrange_pr
revert-38703-numpy_bf16_package_reupload
revert-38732-remove_useless_header_in_elementwise_mul_grad
revert-38959-Reduce_Grad
revert-39143-adjust_empty
revert-39227-move_trace_op_to_pten
revert-39268-dev/remove_concat_fluid_kernel
revert-40170-support_partial_grad
revert-41056-revert-40727-move_some_activaion_to_phi
revert-41065-revert-40993-mv_ele_floordiv_pow
revert-41068-revert-40790-phi_new
revert-41944-smaller_inference_api_test
revert-42149-do-not-reset-default-stream-for-stream-safe-cuda-allocator
revert-43155-fix_ut_tempfile
revert-43882-revert-41944-smaller_inference_api_test
revert-45808-phi/simplify_size_op
revert-46827-deform_comment
rocm_dev_0217
support_weight_transpose
test_benchmark_ci
test_feature_precision_test_c
test_model_benchmark
test_model_benchmark_ci
zhiqiu-patch-1
v2.4.0-rc0
v2.3.2
v2.3.1
v2.3.0
v2.3.0-rc0
v2.2.2
v2.2.1
v2.2.0
v2.2.0-rc0
v2.2.0-bak0
v2.1.3
v2.1.2
v2.1.1
v2.1.0
v2.1.0-rc0
v2.0.2
v2.0.1
v2.0.0
v2.0.0-rc1
v2.0.0-rc0
v2.0.0-beta0
v2.0.0-alpha0
v1.8.5
v1.8.4
v1.8.3
v1.8.2
v1.8.1
v1.8.0
v1.7.2
v1.7.1
v1.7.0
v1.6.3
v1.6.2
v1.6.1
v1.6.0
v1.6.0-rc0
v1.5.2
v1.5.1
v1.5.0
v1.4.1
v1.4.0
v1.3.2
v1.3.1
v1.3.0
v1.2.1
v1.2.0
v1.1.0
v1.0.2
v1.0.1
v1.0.0
v1.0.0-rc0
v0.15.0
v0.15.0-rc0
v0.14.0
v0.13.0
v0.12.0
v0.11.1a2
v0.11.1a1
v0.11.0
lite-v0.1
无相关合并请求
变更
5
隐藏空白更改
内联
并排
Showing
5 changed file
with
121 addition
and
25 deletion
+121
-25
paddle/memory/memory.cc
paddle/memory/memory.cc
+44
-1
paddle/memory/memory.h
paddle/memory/memory.h
+13
-3
paddle/platform/enforce.h
paddle/platform/enforce.h
+26
-19
paddle/platform/gpu_info.cc
paddle/platform/gpu_info.cc
+24
-1
paddle/platform/gpu_info.h
paddle/platform/gpu_info.h
+14
-1
未找到文件。
paddle/memory/memory.cc
浏览文件 @
e1140f2b
...
...
@@ -15,7 +15,8 @@ limitations under the License. */
#include "paddle/memory/memory.h"
#include "paddle/memory/detail/buddy_allocator.h"
#include "paddle/memory/detail/system_allocator.h"
#include "paddle/platform/assert.h"
#include <cstring> // for memcpy
namespace
paddle
{
namespace
memory
{
...
...
@@ -45,6 +46,13 @@ size_t Used<platform::CPUPlace>(platform::CPUPlace place) {
return
GetCPUBuddyAllocator
()
->
Used
();
}
template
<
>
void
Copy
<
platform
::
CPUPlace
,
platform
::
CPUPlace
>
(
platform
::
CPUPlace
,
void
*
dst
,
platform
::
CPUPlace
,
const
void
*
src
,
size_t
num
)
{
std
::
memcpy
(
dst
,
src
,
num
);
}
#ifndef PADDLE_ONLY_CPU
detail
::
BuddyAllocator
*
GetGPUBuddyAllocator
(
int
gpu_id
)
{
...
...
@@ -77,6 +85,41 @@ size_t Used<platform::GPUPlace>(platform::GPUPlace place) {
return
GetGPUBuddyAllocator
(
place
.
device
)
->
Used
();
}
template
<
>
void
Copy
<
platform
::
CPUPlace
,
platform
::
GPUPlace
>
(
platform
::
CPUPlace
dst_place
,
void
*
dst
,
platform
::
GPUPlace
src_place
,
const
void
*
src
,
size_t
num
,
cudaStream_t
stream
)
{
platform
::
SetDeviceId
(
src_place
.
device
);
platform
::
GpuMemcpyAsync
(
dst
,
src
,
num
,
cudaMemcpyDeviceToHost
,
stream
);
}
template
<
>
void
Copy
<
platform
::
GPUPlace
,
platform
::
CPUPlace
>
(
platform
::
GPUPlace
dst_place
,
void
*
dst
,
platform
::
CPUPlace
src_place
,
const
void
*
src
,
size_t
num
,
cudaStream_t
stream
)
{
platform
::
SetDeviceId
(
dst_place
.
device
);
platform
::
GpuMemcpyAsync
(
dst
,
src
,
num
,
cudaMemcpyHostToDevice
,
stream
);
}
template
<
>
void
Copy
<
platform
::
GPUPlace
,
platform
::
GPUPlace
>
(
platform
::
GPUPlace
dst_place
,
void
*
dst
,
platform
::
GPUPlace
src_place
,
const
void
*
src
,
size_t
num
,
cudaStream_t
stream
)
{
if
(
dst_place
==
src_place
)
{
platform
::
SetDeviceId
(
src_place
.
device
);
platform
::
GpuMemcpyAsync
(
dst
,
src
,
num
,
cudaMemcpyDeviceToDevice
,
stream
);
}
else
{
platform
::
GpuMemcpyPeer
(
dst
,
dst_place
.
device
,
src
,
src_place
.
device
,
num
,
stream
);
}
}
#endif // PADDLE_ONLY_CPU
}
// namespace memory
...
...
This diff is collapsed.
Click to expand it.
paddle/memory/memory.h
浏览文件 @
e1140f2b
...
...
@@ -14,20 +14,30 @@ limitations under the License. */
#pragma once
#include "paddle/platform/gpu_info.h"
#include "paddle/platform/place.h"
namespace
paddle
{
namespace
memory
{
template
<
class
Place
>
template
<
typename
Place
>
void
*
Alloc
(
Place
,
size_t
);
template
<
class
Place
>
template
<
typename
Place
>
void
Free
(
Place
,
void
*
);
template
<
class
Place
>
template
<
typename
Place
>
size_t
Used
(
Place
);
template
<
typename
DstPlace
,
typename
SrcPlace
>
void
Copy
(
DstPlace
,
void
*
dst
,
SrcPlace
,
const
void
*
src
,
size_t
num
);
#ifndef PADDLE_ONLY_CPU
template
<
typename
DstPlace
,
typename
SrcPlace
>
void
Copy
(
DstPlace
,
void
*
dst
,
SrcPlace
,
const
void
*
src
,
size_t
num
,
cudaStream_t
stream
);
#endif // PADDLE_ONLY_CPU
template
<
typename
T
,
/* must be POD types */
typename
Place
/* platform::GPUPlace or platform::CPUPlace */
,
typename
std
::
enable_if
<
std
::
is_pod
<
T
>
::
value
>::
type
*
=
nullptr
>
...
...
This diff is collapsed.
Click to expand it.
paddle/platform/enforce.h
浏览文件 @
e1140f2b
...
...
@@ -43,10 +43,26 @@ namespace platform {
// For more details, please check https://stackoverflow.com/a/43870188/724872.
#define UNLIKELY(condition) __builtin_expect(static_cast<bool>(condition), 0)
template
<
typename
T
>
inline
void
throw_on_error
(
T
e
)
{
throw_on_error
(
e
,
""
);
}
template
<
typename
...
Args
>
inline
typename
std
::
enable_if
<
sizeof
...(
Args
)
!=
0
,
void
>::
type
throw_on_error
(
int
stat
,
const
Args
&
...
args
)
{
if
(
UNLIKELY
(
!
(
stat
)))
{
throw
std
::
runtime_error
(
string
::
Sprintf
(
args
...)
+
string
::
Sprintf
(
" at [%s:%s];"
,
__FILE__
,
__LINE__
));
}
}
#ifndef PADDLE_ONLY_CPU
template
<
typename
...
Args
>
inline
void
throw_on_error
(
cudaError_t
e
,
const
Args
&
...
args
)
{
inline
typename
std
::
enable_if
<
sizeof
...(
Args
)
!=
0
,
void
>::
type
throw_on_error
(
cudaError_t
e
,
const
Args
&
...
args
)
{
if
(
UNLIKELY
(
e
))
{
// clang-format off
throw
thrust
::
system_error
(
...
...
@@ -58,7 +74,8 @@ inline void throw_on_error(cudaError_t e, const Args&... args) {
}
template
<
typename
...
Args
>
inline
void
throw_on_error
(
curandStatus_t
stat
,
const
Args
&
...
args
)
{
inline
typename
std
::
enable_if
<
sizeof
...(
Args
)
!=
0
,
void
>::
type
throw_on_error
(
curandStatus_t
stat
,
const
Args
&
...
args
)
{
if
(
stat
!=
CURAND_STATUS_SUCCESS
)
{
// clang-format off
throw
thrust
::
system_error
(
...
...
@@ -70,7 +87,8 @@ inline void throw_on_error(curandStatus_t stat, const Args&... args) {
}
template
<
typename
...
Args
>
inline
void
throw_on_error
(
cudnnStatus_t
stat
,
const
Args
&
...
args
)
{
inline
typename
std
::
enable_if
<
sizeof
...(
Args
)
!=
0
,
void
>::
type
throw_on_error
(
cudnnStatus_t
stat
,
const
Args
&
...
args
)
{
if
(
stat
==
CUDNN_STATUS_SUCCESS
)
{
return
;
}
else
{
...
...
@@ -84,7 +102,8 @@ inline void throw_on_error(cudnnStatus_t stat, const Args&... args) {
}
template
<
typename
...
Args
>
inline
void
throw_on_error
(
cublasStatus_t
stat
,
const
Args
&
...
args
)
{
inline
typename
std
::
enable_if
<
sizeof
...(
Args
)
!=
0
,
void
>::
type
throw_on_error
(
cublasStatus_t
stat
,
const
Args
&
...
args
)
{
std
::
string
err
;
if
(
stat
==
CUBLAS_STATUS_SUCCESS
)
{
return
;
...
...
@@ -113,15 +132,6 @@ inline void throw_on_error(cublasStatus_t stat, const Args&... args) {
#endif // PADDLE_ONLY_CPU
template
<
typename
...
Args
>
inline
void
throw_on_error
(
int
stat
,
const
Args
&
...
args
)
{
if
(
UNLIKELY
(
!
(
stat
)))
{
throw
std
::
runtime_error
(
string
::
Sprintf
(
args
...)
+
string
::
Sprintf
(
" at [%s:%s];"
,
__FILE__
,
__LINE__
));
}
}
#define PADDLE_THROW(...) \
do { \
throw std::runtime_error( \
...
...
@@ -129,12 +139,9 @@ inline void throw_on_error(int stat, const Args&... args) {
string::Sprintf(" at [%s:%s];", __FILE__, __LINE__)); \
} while (0)
/**
* @brief Enforce a condition, otherwise throw an EnforceNotMet
*/
#define PADDLE_ENFORCE(condition, ...) \
do { \
::paddle::platform::throw_on_error(condition, __VA_ARGS__); \
#define PADDLE_ENFORCE(...) \
do { \
::paddle::platform::throw_on_error(__VA_ARGS__); \
} while (0)
}
// namespace platform
...
...
This diff is collapsed.
Click to expand it.
paddle/platform/gpu_info.cc
浏览文件 @
e1140f2b
...
...
@@ -44,7 +44,7 @@ void SetDeviceId(int id) {
"cudaSetDevice failed in paddle::platform::SetDeviceId"
);
}
void
GpuMemoryUsage
(
size_t
&
available
,
size_t
&
total
)
{
void
GpuMemoryUsage
(
size_t
&
available
,
size_t
&
total
)
{
PADDLE_ENFORCE
(
cudaMemGetInfo
(
&
available
,
&
total
),
"cudaMemGetInfo failed in paddle::platform::GetMemoryUsage"
);
}
...
...
@@ -82,5 +82,28 @@ size_t GpuMaxChunkSize() {
return
usable
;
}
void
GpuMemcpyAsync
(
void
*
dst
,
const
void
*
src
,
size_t
count
,
enum
cudaMemcpyKind
kind
,
cudaStream_t
stream
)
{
PADDLE_ENFORCE
(
cudaMemcpyAsync
(
dst
,
src
,
count
,
kind
,
stream
),
"cudaMemcpyAsync failed in paddle::platform::GpuMemcpyAsync"
);
}
void
GpuMemcpySync
(
void
*
dst
,
const
void
*
src
,
size_t
count
,
enum
cudaMemcpyKind
kind
)
{
PADDLE_ENFORCE
(
cudaMemcpy
(
dst
,
src
,
count
,
kind
),
"cudaMemcpy failed in paddle::platform::GpuMemcpySync"
);
// note: cudaMemcpy may actually be asynchronous with respect to the caller,
// block on stream 0 to make sure the copy has completed
PADDLE_ENFORCE
(
cudaStreamSynchronize
(
0
),
"cudaStreamSynchronize failed in paddle::platform::GpuMemcpySync"
);
}
void
GpuMemcpyPeer
(
void
*
dst
,
int
dst_device
,
const
void
*
src
,
int
src_device
,
size_t
count
,
cudaStream_t
stream
)
{
PADDLE_ENFORCE
(
cudaMemcpyPeerAsync
(
dst
,
dst_device
,
src
,
src_device
,
count
,
stream
),
"cudaMemcpyPeerAsync failed in paddle::platform::GpuMemcpyPeer"
);
}
}
// namespace platform
}
// namespace paddle
This diff is collapsed.
Click to expand it.
paddle/platform/gpu_info.h
浏览文件 @
e1140f2b
...
...
@@ -16,6 +16,7 @@ limitations under the License. */
#ifndef PADDLE_ONLY_CPU
#include <cuda_runtime.h>
#include <stddef.h>
namespace
paddle
{
...
...
@@ -31,7 +32,7 @@ int GetCurrentDeviceId();
void
SetDeviceId
(
int
device_id
);
//!Get the memory usage of current GPU device.
void
GpuMemoryUsage
(
size_t
&
available
,
size_t
&
total
);
void
GpuMemoryUsage
(
size_t
&
available
,
size_t
&
total
);
//! Get the maximum allocation size of current GPU device.
size_t
GpuMaxAllocSize
();
...
...
@@ -42,6 +43,18 @@ size_t GpuMinChunkSize();
//! Get the maximum chunk size for GPU buddy allocator.
size_t
GpuMaxChunkSize
();
//! Copy memory from address src to dst asynchronously.
void
GpuMemcpyAsync
(
void
*
dst
,
const
void
*
src
,
size_t
count
,
enum
cudaMemcpyKind
kind
,
cudaStream_t
stream
);
//! Copy memory from address src to dst synchronously.
void
GpuMemcpySync
(
void
*
dst
,
const
void
*
src
,
size_t
count
,
enum
cudaMemcpyKind
kind
);
//! Copy memory from one device to another device.
void
GpuMemcpyPeer
(
void
*
dst
,
int
dst_device
,
const
void
*
src
,
int
src_device
,
size_t
count
,
cudaStream_t
stream
);
}
// namespace platform
}
// namespace paddle
...
...
This diff is collapsed.
Click to expand it.
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