You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Paddle/python/paddle/fluid/tests/unittests/collective_broadcast_op.py

71 lines
2.3 KiB

supports collective communicated training (#18175) * fix prepare context redundant code problem, optimize executor by caching create_varaiables test=develop * supports collective training in executor * make fetch_list runable with variables, add more unittest for use_program_cache test=develop * fix comment test=develop * use unique name for nccl_id * supports output to stream in program_to_code * insert sync_comm_stream before regularization; add skip_op_callstack capability in program_to_code * set op role in collective training * add collective op role * remove orig file * add build optimizer by strategy * add collective strategy * refine collective strategy * add multi-process role maker * refine strategy building factory so that we can easily plugin more strategy * scale loss grad in collective sgd transpiler * add support for distributed fc * code format * revert some features for dist fc * add support for distributed fc training * fix prepare context redundant code problem, optimize executor by caching create_varaiables test=develop * supports collective training in executor * make fetch_list runable with variables, add more unittest for use_program_cache test=develop * use unique name for nccl_id * supports output to stream in program_to_code * insert sync_comm_stream before regularization; add skip_op_callstack capability in program_to_code * set op role in collective training * add collective op role * fix comment test=develop * remove orig file * add build optimizer by strategy * add collective strategy * refine collective strategy * add multi-process role maker * refine strategy building factory so that we can easily plugin more strategy * scale loss grad in collective sgd transpiler * add support for distributed fc * code format * revert some features for dist fc * add support for distributed fc training * test=develop add collective op unittest standard * test=develop remove the test_collective directory * test=develop remove the test_collective directory * remove slicegather test * code format for reducescatter * update attr of shard_index_op * Modify macro nccl_helper * remove test without distribute * macro collective_helper * marcro update * test=develop update support python3.5 * test=develop change gpu memory use to 0.1 when test * test=develop update ut equal func * test=develop set flags to 1.5 * test=develop fix pickle dumple py35 * test=develop fix divide in slice and add sync_comm_stream update atol and rtol to 1e-05 rm shard_index op and test modify read input from file to read from memory remove origin_program in framework and add i/o in c_sync_calc_stream * test=develop update unittest sync operator I/O
6 years ago
# 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 numpy as np
import argparse
import os
import sys
import signal
import time
import socket
from contextlib import closing
from six import string_types
import math
import paddle
import paddle.fluid as fluid
import paddle.fluid.profiler as profiler
import paddle.fluid.unique_name as nameGen
from paddle.fluid import core
import unittest
from multiprocessing import Process
import paddle.fluid.layers as layers
from functools import reduce
from test_collective_base import TestCollectiveRunnerBase, runtime_main
class TestCollectiveBroadcast(TestCollectiveRunnerBase):
def __init__(self):
self.global_ring_id = 0
def get_model(self, main_prog, startup_program):
ring_id = 0
rootid = 1
with fluid.program_guard(main_prog, startup_program):
tindata = layers.data(
name="tindata", shape=[10, 1000], dtype='float32')
toutdata = main_prog.current_block().create_var(
name="outofbroadcast",
dtype='float32',
type=core.VarDesc.VarType.LOD_TENSOR,
persistable=False,
stop_gradient=False)
main_prog.global_block().append_op(
type="c_broadcast",
inputs={'X': tindata},
attrs={'ring_id': ring_id,
'root': rootid},
outputs={'Out': toutdata})
main_prog.global_block().append_op(
type="c_sync_comm_stream",
inputs={'X': toutdata},
outputs={'Out': toutdata},
attrs={'ring_id': ring_id})
return toutdata
if __name__ == "__main__":
runtime_main(TestCollectiveBroadcast, "broadcast", 0)