init_parallel_env¶

paddle.distributed. init_parallel_env ( ) [source]

Initialize parallel training environment in dynamic graph mode.

Note

Now initialize both NCCL and GLOO contexts for communication.

Parameters

backend (string) – A string represents the backend used by DataParallel, should be one of ‘gloo’(for cpu), ‘nccl’(for cuda), ‘bkcl’(for xpu), ‘auto’(auto detect). The auto detection prefer ‘nccl’, ‘bkcl’ than ‘gloo’.

Returns

None

Examples

# required: gpu
import paddle
import paddle.nn as nn
import paddle.optimizer as opt
import paddle.distributed as dist

class LinearNet(nn.Layer):
    def __init__(self):
        super().__init__()
        self._linear1 = nn.Linear(10, 10)
        self._linear2 = nn.Linear(10, 1)

    def forward(self, x):
        return self._linear2(self._linear1(x))

def train():
    # 1. initialize parallel environment
    dist.init_parallel_env()

    # 2. create data parallel layer & optimizer
    layer = LinearNet()
    dp_layer = paddle.DataParallel(layer)

    loss_fn = nn.MSELoss()
    adam = opt.Adam(
        learning_rate=0.001, parameters=dp_layer.parameters())

    # 3. run layer
    inputs = paddle.randn([10, 10], 'float32')
    outputs = dp_layer(inputs)
    labels = paddle.randn([10, 1], 'float32')
    loss = loss_fn(outputs, labels)

    loss.backward()

    adam.step()
    adam.clear_grad()

if __name__ == '__main__':
    dist.spawn(train)