-import torch.multiprocessing as mp
+import torch_xla.core.xla_model as xm
+import torch_xla.distributed.parallel_loader as pl
+import torch_xla.distributed.xla_multiprocessing as xmp

 def _mp_fn(index):
   ...

+  # Move the model paramters to your XLA device
+  model.to(xm.xla_device())
+
+  # MpDeviceLoader preloads data to the XLA device
+  xla_train_loader = pl.MpDeviceLoader(train_loader, xm.xla_device())

-  for inputs, labels in train_loader:
+  for inputs, labels in xla_train_loader:
     optimizer.zero_grad()
     outputs = model(inputs)
     loss = loss_fn(outputs, labels)
     loss.backward()
-    optimizer.step()
+
+    # `xm.optimizer_step` combines gradients across replicas
+    xm.optimizer_step()

 if __name__ == '__main__':
-  mp.spawn(_mp_fn, args=(), nprocs=world_size)
+  # xmp.spawn automatically selects the correct world size
+  xmp.spawn(_mp_fn, args=())

 import torch.distributed as dist
-import torch.multiprocessing as mp
+import torch_xla.core.xla_model as xm
+import torch_xla.distributed.parallel_loader as pl
+import torch_xla.distributed.xla_multiprocessing as xmp
+import torch_xla.distributed.xla_backend

 def _mp_fn(rank):
   ...

-  os.environ['MASTER_ADDR'] = 'localhost'
-  os.environ['MASTER_PORT'] = '12355'
-  dist.init_process_group("gloo", rank=rank, world_size=world_size)
+  # Rank and world size are inferred from the XLA device runtime
+  dist.init_process_group("xla", init_method='xla://')
+
+  model.to(xm.xla_device())
+  # `gradient_as_bucket_view=True` required for XLA
+  ddp_model = DDP(model, gradient_as_bucket_view=True)

-  model = model.to(rank)
-  ddp_model = DDP(model, device_ids=[rank])
+  xla_train_loader = pl.MpDeviceLoader(train_loader, xm.xla_device())

-  for inputs, labels in train_loader:
+  for inputs, labels in xla_train_loader:
     optimizer.zero_grad()
     outputs = ddp_model(inputs)
     loss = loss_fn(outputs, labels)
     loss.backward()
     optimizer.step()

 if __name__ == '__main__':
-  mp.spawn(_mp_fn, args=(), nprocs=world_size)
+  xmp.spawn(_mp_fn, args=())