pytorch使用horovod多gpu训练的实现

import torch
import horovod.torch as hvd

# Initialize Horovod 初始化horovod
hvd.init()

# Pin GPU to be used to process local rank (one GPU per process) 分配到每个gpu上
torch.cuda.set_device(hvd.local_rank())

# Define dataset... 定义dataset
train_dataset = ...

# Partition dataset among workers using DistributedSampler 对dataset的采样器进行调整，使用torch.utils.data.distributed.DistributedSampler
train_sampler = torch.utils.data.distributed.DistributedSampler(
  train_dataset, num_replicas=hvd.size(), rank=hvd.rank())

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=..., sampler=train_sampler)

# Build model...
model = ...
model.cuda()

optimizer = optim.SGD(model.parameters())

# Add Horovod Distributed Optimizer 使用Horovod的分布式优化器函数包裹在原先optimizer上
optimizer = hvd.DistributedOptimizer(optimizer, named_parameters=model.named_parameters())

# Broadcast parameters from rank 0 to all other processes. 参数广播到每个gpu上
hvd.broadcast_parameters(model.state_dict(), root_rank=0)

for epoch in range(100):
  for batch_idx, (data, target) in enumerate(train_loader):
    optimizer.zero_grad()
    output = model(data)
    loss = F.nll_loss(output, target)
    loss.backward()
    optimizer.step()
    if batch_idx % args.log_interval == 0:
      print('Train Epoch: {} [{}/{}]tLoss: {}'.format(
        epoch, batch_idx * len(data), len(train_sampler), loss.item()))