提交 6e5635fd 编写于 作者: Y Yancey1989

update

上级 b1e51836
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 cp_2.4_fix_numpy 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_dlpack_for fix_imperative_dygraph_error fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fix_var_stop_gradient_error 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/frl_train_eval incubate/infrt incubate/lite inplace_addto layer_norm make_flag_adding_easier master matmul_double_grad 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 prv-reshape-mkldnn-ut2 pten_tensor_refactor 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 revert-47325-remove_cudnn_hardcode revert-47645-add_npu_storage_dims revert-48815-set_free_when_no_cache_hit_default_value_true revert-49654-prim_api_gen revert-49763-fix_static_composite_gen rocm_dev_0217 support-0D-sort support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_for_Filtetfiles test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.4.1 v2.4.0 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 lite-v0.1
无相关合并请求
......@@ -279,11 +279,20 @@ class DistributeTranspiler:
grad_blocks = split_dense_variable(grad_list, len(pserver_endpoints))
param_blocks = split_dense_variable(param_list, len(pserver_endpoints))
assert (len(grad_blocks) == len(param_blocks))
# step2: Create new vars for the parameters and gradients blocks and
# add ops to do the split.
grad_var_mapping = self._append_split_op(program, grad_blocks)
param_var_mapping = self._create_vars_from_blocklist(program,
param_blocks)
grad_var_mapping = self._create_vars_from_blocklist(
program, grad_blocks, add_trainer_suffix=self.trainer_num > 1)
grad_param_mapping = dict()
for g, p in zip(grad_blocks, param_blocks):
g_name, g_bid, _ = g.split(":")
p_name, p_bid, _ = p.split(":")
grad_param_mapping[grad_var_mapping[g_name][int(g_bid)]] = \
param_var_mapping[p_name][int(p_bid)]
rpc_client_var = program.global_block().create_var(
name=RPC_CLIENT_VAR_NAME,
persistable=True,
......@@ -304,15 +313,21 @@ class DistributeTranspiler:
# step 3.1: insert send op to send gradient vars to parameter servers
ps_dispatcher.reset()
for varname, send_vars in grad_var_mapping.items():
send_vars = []
for varname, splited_vars in grad_var_mapping.items():
index = find_op_by_output_arg(program.global_block(), varname)
eplist = ps_dispatcher.dispatch(send_vars)
eplist = ps_dispatcher.dispatch(splited_vars)
if len(splited_vars) > 1:
self._insert_split_op(program, varname, splited_vars)
index += 1
program.global_block().insert_op(
index=index,
index=index + 1,
type="send_vars",
inputs={"X": send_vars},
inputs={"X": splited_vars},
outputs={"RPCClient": rpc_client_var},
attrs={"epmap": eplist})
for _, var in enumerate(splited_vars):
send_vars.append(var)
if self.sync_mode:
program.global_block().append_op(
......@@ -322,21 +337,12 @@ class DistributeTranspiler:
attrs={"endpoints": pserver_endpoints})
# step 3.2: insert recv op to receive parameters from parameter server
ps_dispatcher.reset()
recv_vars = []
for b in param_blocks:
varname, block_id, _ = b.split(":")
recv_vars.append(param_var_mapping[varname][int(block_id)])
for b in grad_blocks:
varname, block_id, _ = b.split(":")
send_vars.append(grad_var_mapping[varname][int(block_id)])
for _, var in enumerate(send_vars):
recv_vars.append(grad_param_mapping[var])
ps_dispatcher.reset()
eplist = ps_dispatcher.dispatch(recv_vars)
for i, ep in enumerate(eplist):
self.param_grad_ep_mapping[ep]["params"].append(recv_vars[i])
self.param_grad_ep_mapping[ep]["grads"].append(send_vars[i])
program.global_block().append_op(
type="recv",
inputs={},
......@@ -344,6 +350,10 @@ class DistributeTranspiler:
"RPCClient": rpc_client_var},
attrs={"epmap": eplist})
for i, ep in enumerate(eplist):
self.param_grad_ep_mapping[ep]["params"].append(recv_vars[i])
self.param_grad_ep_mapping[ep]["grads"].append(send_vars[i])
# TODO(Yancey1989): check dist lookup table
if self.has_distributed_lookup_table:
self._replace_lookup_table_op_with_prefetch(program, rpc_client_var,
......@@ -848,6 +858,34 @@ class DistributeTranspiler:
lod_level=var.lod_level,
persistable=persistable)
def _insert_split_op(self, program, orig_varname, splited_vars):
orig_var = program.global_block().vars[orig_varname]
index = find_op_by_output_arg(program.global_block(), orig_varname)
if orig_var.type == core.VarDesc.VarType.SELECTED_ROWS:
height_sections = []
for v in splited_vars:
height_sections.append(v.shape[0])
program.global_block().insert_op(
index=index + 1,
type="split_selected_rows",
inputs={"X": orig_var},
outputs={"Out": splited_vars},
attrs={"height_sections": height_sections})
elif orig_var.type == core.VarDesc.VarType.LOD_TENSOR:
sections = []
for v in splited_vars:
sections.append(v.shape[0])
program.global_block().insert_op(
index=index + 1,
type="split_byref",
inputs={"X": orig_var},
outputs={"Out": splited_vars},
attrs={"sections": sections} # assume split evenly
)
else:
AssertionError("Variable type should be in set "
"[LOD_TENSOR, SELECTED_ROWS]")
def _append_split_op(self, program, gradblocks):
# Split variables that need to be split and append respective ops
add_suffix = False
......@@ -860,11 +898,13 @@ class DistributeTranspiler:
if len(splited_vars) <= 1:
continue
orig_var = program.global_block().vars[varname]
index = find_op_by_output_arg(program.global_block(), orig_var.name)
if orig_var.type == core.VarDesc.VarType.SELECTED_ROWS:
height_sections = []
for v in splited_vars:
height_sections.append(v.shape[0])
program.global_block().append_op(
program.global_block().insert_op(
index=index + 1,
type="split_selected_rows",
inputs={"X": orig_var},
outputs={"Out": splited_vars},
......@@ -873,7 +913,8 @@ class DistributeTranspiler:
sections = []
for v in splited_vars:
sections.append(v.shape[0])
program.global_block().append_op(
program.global_block().insert_op(
index=index + 1,
type="split_byref",
inputs={"X": orig_var},
outputs={"Out": splited_vars},
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部