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
机器未来
Paddle
提交
4ef6b845
P
Paddle
项目概览
机器未来
/
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
未验证
提交
4ef6b845
编写于
5年前
作者:
Y
Yi Liu
提交者:
GitHub
5年前
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
adapte fleet api for localsgd and support nccl comm configuration in executor (#19443)
test=develop
上级
65c73684
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_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
inplace_addto
make_flag_adding_easier
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/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
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
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
84 addition
and
7 deletion
+84
-7
python/paddle/fluid/incubate/fleet/collective/__init__.py
python/paddle/fluid/incubate/fleet/collective/__init__.py
+15
-3
python/paddle/fluid/tests/unittests/test_dist_base.py
python/paddle/fluid/tests/unittests/test_dist_base.py
+12
-0
python/paddle/fluid/tests/unittests/test_dist_mnist_with_program.py
...dle/fluid/tests/unittests/test_dist_mnist_with_program.py
+51
-0
python/paddle/fluid/transpiler/collective.py
python/paddle/fluid/transpiler/collective.py
+4
-2
python/paddle/fluid/transpiler/distribute_transpiler.py
python/paddle/fluid/transpiler/distribute_transpiler.py
+2
-2
未找到文件。
python/paddle/fluid/incubate/fleet/collective/__init__.py
浏览文件 @
4ef6b845
...
...
@@ -25,6 +25,7 @@ from paddle.fluid import compiler
import
os
import
sys
import
six
class
LambConfig
(
object
):
...
...
@@ -99,7 +100,6 @@ class DistributedStrategy(fluid.BuildStrategy):
self
.
use_local_sgd
=
False
self
.
use_dist_fc
=
False
self
.
local_sgd_config
=
None
# LocalSGDConfig
self
.
dist_fc_config
=
None
# DistFCConfig
self
.
mode
=
"nccl2"
# or collective
self
.
collective_mode
=
None
# local_sgd or grad_allreduce
...
...
@@ -107,6 +107,9 @@ class DistributedStrategy(fluid.BuildStrategy):
self
.
exec_strategy
=
fluid
.
ExecutionStrategy
()
# configurations below are used for unit test
self
.
_ut4grad_allreduce
=
False
class
CollectiveOpBasedOptimizer
(
DistributedOptimizer
):
"""
...
...
@@ -161,7 +164,7 @@ class CollectiveOptimizer(DistributedOptimizer):
return
self
.
_optimizer
.
apply_gradients
(
params_grads
)
def
_check_condition
(
self
,
name
,
**
kwargs
):
for
k
,
v
in
kwargs
.
iterms
(
):
for
k
,
v
in
six
.
iteritems
(
kwargs
):
if
v
is
True
:
assert
False
,
"you can't use %s and %s together"
%
(
name
,
k
)
...
...
@@ -170,12 +173,13 @@ class CollectiveOptimizer(DistributedOptimizer):
Check the conflict condtions.
"""
if
strategy
.
use_local_sgd
:
strategy
.
mode
=
"collective"
strategy
.
collective_mode
=
"local_sgd"
self
.
_check_condition
(
"use_local_sgd"
,
use_dgc
=
main_program
.
_enable_dgc
,
use_dist_fc
=
strategy
.
use_dist_fc
,
use_lamb
=
main_program
.
_use_lamb
)
assert
strategy
.
local_sgd_config
is
not
None
,
"DistributedStrategy.local_sgd_config should be set"
if
strategy
.
use_dist_fc
:
self
.
_check_condition
(
...
...
@@ -185,6 +189,14 @@ class CollectiveOptimizer(DistributedOptimizer):
use_lamb
=
main_program
.
_use_lamb
)
assert
strategy
.
dist_fc_config
is
not
None
,
"DistributedStrategy.dist_fc_config should be set"
if
strategy
.
_ut4grad_allreduce
:
strategy
.
mode
=
"collective"
strategy
.
collective_mode
=
"grad_allreduce"
self
.
_check_condition
(
"_ut4grad_allreduce"
,
use_dgc
=
main_program
.
_enable_dgc
,
use_lamb
=
main_program
.
_use_lamb
)
if
self
.
_strategy
.
collective_mode
==
"local_sgd"
\
or
self
.
_strategy
.
collective_mode
==
"grad_allreduce"
:
assert
self
.
_strategy
.
mode
==
"collective"
,
\
...
...
This diff is collapsed.
Click to expand it.
python/paddle/fluid/tests/unittests/test_dist_base.py
浏览文件 @
4ef6b845
...
...
@@ -122,6 +122,10 @@ class TestDistRunnerBase(object):
dist_strategy
.
exec_strategy
=
exec_strategy
dist_strategy
.
fuse_memory_size
=
1
#MB
dist_strategy
.
fuse_laryer_size
=
1
if
args
.
use_local_sgd
:
dist_strategy
.
use_local_sgd
=
True
if
args
.
ut4grad_allreduce
:
dist_strategy
.
_ut4grad_allreduce
=
True
role
=
role_maker
.
PaddleCloudRoleMaker
(
is_collective
=
True
)
fleet
.
init
(
role
)
...
...
@@ -396,6 +400,8 @@ def runtime_main(test_class):
parser
.
add_argument
(
'--enable_backward_deps'
,
action
=
'store_true'
)
parser
.
add_argument
(
'--use_hallreduce'
,
action
=
'store_true'
)
parser
.
add_argument
(
'--gpu_fleet_api'
,
action
=
'store_true'
)
parser
.
add_argument
(
'--use_local_sgd'
,
action
=
'store_true'
)
parser
.
add_argument
(
'--ut4grad_allreduce'
,
action
=
'store_true'
)
parser
.
add_argument
(
'--hallreduce_inter_nranks'
,
type
=
int
,
required
=
False
,
default
=
2
)
parser
.
add_argument
(
...
...
@@ -478,6 +484,8 @@ class TestDistBase(unittest.TestCase):
self
.
_nccl_comm_num
=
1
self
.
_enable_backward_deps
=
False
self
.
_gpu_fleet_api
=
False
self
.
_use_local_sgd
=
False
self
.
_ut4grad_allreduce
=
False
self
.
_use_hallreduce
=
False
self
.
_setup_config
()
self
.
_after_setup_config
()
...
...
@@ -731,6 +739,10 @@ class TestDistBase(unittest.TestCase):
if
self
.
_gpu_fleet_api
:
tr_cmd
+=
" --gpu_fleet_api"
if
self
.
_use_local_sgd
:
tr_cmd
+=
" --use_local_sgd"
if
self
.
_ut4grad_allreduce
:
tr_cmd
+=
" --ut4grad_allreduce"
if
os
.
getenv
(
'WITH_COVERAGE'
,
'OFF'
)
==
'ON'
:
env
[
'COVERAGE_FILE'
]
=
os
.
getenv
(
'COVERAGE_FILE'
,
''
)
...
...
This diff is collapsed.
Click to expand it.
python/paddle/fluid/tests/unittests/test_dist_mnist_with_program.py
0 → 100644
浏览文件 @
4ef6b845
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from
__future__
import
print_function
import
unittest
from
test_dist_base
import
TestDistBase
class
TestDistMnistLocalSGDFleetApi
(
TestDistBase
):
def
_setup_config
(
self
):
self
.
_sync_mode
=
True
self
.
_use_reduce
=
False
self
.
_use_reader_alloc
=
False
self
.
_nccl2_mode
=
True
self
.
_gpu_fleet_api
=
True
self
.
_use_local_sgd
=
True
def
test_dist_train
(
self
):
import
paddle.fluid
as
fluid
if
fluid
.
core
.
is_compiled_with_cuda
():
self
.
check_with_place
(
"dist_mnist.py"
,
delta
=
1e-5
)
class
TestDistMnistGradAllReduceFleetApi
(
TestDistBase
):
def
_setup_config
(
self
):
self
.
_sync_mode
=
True
self
.
_use_reduce
=
False
self
.
_use_reader_alloc
=
False
self
.
_nccl2_mode
=
True
self
.
_gpu_fleet_api
=
True
self
.
_ut4grad_allreduce
=
True
def
test_dist_train
(
self
):
import
paddle.fluid
as
fluid
if
fluid
.
core
.
is_compiled_with_cuda
():
self
.
check_with_place
(
"dist_mnist.py"
,
delta
=
1e-5
)
if
__name__
==
"__main__"
:
unittest
.
main
()
This diff is collapsed.
Click to expand it.
python/paddle/fluid/transpiler/collective.py
浏览文件 @
4ef6b845
...
...
@@ -278,10 +278,12 @@ class LocalSGD(Collective):
Collective
.
_transpile_startup_program
(
self
)
block
=
self
.
startup_program
.
global_block
()
non_dist_params
=
[]
for
param
in
block
.
iter_parameters
():
if
param
.
is_distributed
:
continue
if
not
param
.
is_distributed
:
non_dist_params
.
append
(
param
)
for
param
in
non_dist_params
:
snapshot
=
block
.
create_var
(
name
=
self
.
snapshot_name
(
param
.
name
),
shape
=
param
.
shape
,
...
...
This diff is collapsed.
Click to expand it.
python/paddle/fluid/transpiler/distribute_transpiler.py
浏览文件 @
4ef6b845
...
...
@@ -334,9 +334,9 @@ class DistributeTranspiler(object):
transpiler
=
None
if
collective_mode
==
'grad_allreduce'
:
transpiler
=
collective
.
GradAllReduce
()
transpiler
=
collective
.
GradAllReduce
(
self
.
config
.
nccl_comm_num
)
elif
collective_mode
==
'local_sgd'
:
transpiler
=
collective
.
LocalSGD
()
transpiler
=
collective
.
LocalSGD
(
self
.
config
.
nccl_comm_num
)
else
:
raise
ValueError
(
'invalid collective_mode: %s'
%
collective_mode
)
...
...
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