def __init__()

in torchbenchmark/models/tacotron2/distributed.py [0:0]

• 40 lines of code
• 18 McCabe index (conditional complexity)

    def __init__(self, module):
        super(DistributedDataParallel, self).__init__()
        #fallback for PyTorch 0.3
        if not hasattr(dist, '_backend'):
            self.warn_on_half = True
        else:
            self.warn_on_half = True if dist._backend == dist.dist_backend.GLOO else False

        self.module = module

        for p in self.module.state_dict().values():
            if not torch.is_tensor(p):
                continue
            dist.broadcast(p, 0)

        def allreduce_params():
            if(self.needs_reduction):
                self.needs_reduction = False
                buckets = {}
                for param in self.module.parameters():
                    if param.requires_grad and param.grad is not None:
                        tp = type(param.data)
                        if tp not in buckets:
                            buckets[tp] = []
                        buckets[tp].append(param)
                if self.warn_on_half:
                    if torch.cuda.HalfTensor in buckets:
                        print("WARNING: gloo dist backend for half parameters may be extremely slow." +
                              " It is recommended to use the NCCL backend in this case. This currently requires" +
                              "PyTorch built from top of tree master.")
                        self.warn_on_half = False

                for tp in buckets:
                    bucket = buckets[tp]
                    grads = [param.grad.data for param in bucket]
                    coalesced = _flatten_dense_tensors(grads)
                    dist.all_reduce(coalesced)
                    coalesced /= dist.get_world_size()
                    for buf, synced in zip(grads, _unflatten_dense_tensors(coalesced, grads)):
                        buf.copy_(synced)

        for param in list(self.module.parameters()):
            def allreduce_hook(*unused):
                param._execution_engine.queue_callback(allreduce_params)
            if param.requires_grad:
                param.register_hook(allreduce_hook)