• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright 2020 Huawei Technologies Co., Ltd
2#
3# Licensed under the Apache License, Version 2.0 (the "License");
4# you may not use this file except in compliance with the License.
5# You may obtain a copy of the License at
6#
7# http://www.apache.org/licenses/LICENSE-2.0
8#
9# Unless required by applicable law or agreed to in writing, software
10# distributed under the License is distributed on an "AS IS" BASIS,
11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12# See the License for the specific language governing permissions and
13# limitations under the License.
14
15import numpy as np
16
17import mindspore as ms
18from mindspore import context, Tensor, Parameter
19from mindspore.common.api import _cell_graph_executor
20from mindspore.nn import Cell, TrainOneStepCell, Momentum
21from mindspore.ops import operations as P
22
23
24class Net(Cell):
25    def __init__(self, matmul_weight, strategy1=None):
26        super().__init__()
27        self.gatherv2 = P.Gather().shard(strategy1)
28        self.reshape = P.Reshape().add_prim_attr("skip_redistribution", True)
29        self.matmul = P.MatMul(transpose_b=False)
30        self.index = Tensor(np.ones([64, 64]), dtype=ms.int32)
31        self.matmul_weight = Parameter(matmul_weight, "w1")
32        self.axis = 0
33
34    def construct(self, x, b):
35        out = self.gatherv2(x, self.index, self.axis)
36        out = self.reshape(out, (64, -1))
37        out = self.matmul(out, self.matmul_weight)
38        return out
39
40
41_w1 = Tensor(np.ones([4096, 32]), dtype=ms.float32)
42_x = Tensor(np.ones([64, 64]), dtype=ms.float32)
43_b = Tensor(np.ones([128, 64, 32]), dtype=ms.float32)
44
45def compile_net(net):
46    optimizer = Momentum(net.trainable_params(), learning_rate=0.1, momentum=0.9)
47    train_net = TrainOneStepCell(net, optimizer)
48    train_net.set_auto_parallel()
49    train_net.set_train()
50    _cell_graph_executor.compile(train_net, _x, _b)
51    context.reset_auto_parallel_context()
52
53
54def test_reshape_skip_redistribution():
55    context.set_auto_parallel_context(parallel_mode="semi_auto_parallel", device_num=8, global_rank=0)
56    strategy1 = ((1, 8), (1, 1))
57    net = Net(_w1, strategy1)
58    compile_net(net)
59