import pickle

import torch
import torch.distributed as dist


def get_world_size():
    if not dist.is_available():
        return 1
    if not dist.is_initialized():
        return 1
    return dist.get_world_size()


def get_rank():
    if not dist.is_available():
        return 0
    if not dist.is_initialized():
        return 0
    return dist.get_rank()


def is_main_process():
    return get_rank() == 0


def synchronize():
    """
       Helper function to synchronize (barrier) among all processes when
       using distributed training
    """
    if not dist.is_available():
        return
    if not dist.is_initialized():
        return
    world_size = dist.get_world_size()
    if world_size == 1:
        return
    dist.barrier()


def _encode(encoded_data, data):
    # gets a byte representation for the data
    encoded_bytes = pickle.dumps(data)
    # convert this byte string into a byte tensor
    storage = torch.ByteStorage.from_buffer(encoded_bytes)
    tensor = torch.ByteTensor(storage).to("cuda")
    # encoding: first byte is the size and then rest is the data
    s = tensor.numel()
    assert s <= 255, "Can't encode data greater than 255 bytes"
    # put the encoded data in encoded_data
    encoded_data[0] = s
    encoded_data[1: (s + 1)] = tensor


def all_gather(data):
    """
    Run all_gather on arbitrary picklable data (not necessarily tensors)
    Args:
        data: any picklable object
    Returns:
        list[data]: list of data gathered from each rank
    """
    world_size = get_world_size()
    if world_size == 1:
        return [data]

    # serialized to a Tensor
    buffer = pickle.dumps(data)
    storage = torch.ByteStorage.from_buffer(buffer)
    tensor = torch.ByteTensor(storage).to("cuda")

    # obtain Tensor size of each rank
    local_size = torch.LongTensor([tensor.numel()]).to("cuda")
    size_list = [torch.LongTensor([0]).to("cuda") for _ in range(world_size)]
    dist.all_gather(size_list, local_size)
    size_list = [int(size.item()) for size in size_list]
    max_size = max(size_list)

    # receiving Tensor from all ranks
    # we pad the tensor because torch all_gather does not support
    # gathering tensors of different shapes
    tensor_list = []
    for _ in size_list:
        tensor_list.append(torch.ByteTensor(size=(max_size,)).to("cuda"))
    if local_size != max_size:
        padding = torch.ByteTensor(size=(max_size - local_size,)).to("cuda")
        tensor = torch.cat((tensor, padding), dim=0)
    dist.all_gather(tensor_list, tensor)

    data_list = []
    for size, tensor in zip(size_list, tensor_list):
        buffer = tensor.cpu().numpy().tobytes()[:size]
        data_list.append(pickle.loads(buffer))

    return data_list