# Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# MIT License
#
# Copyright (c) Meta Platforms, Inc. and affiliates.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

from typing import Iterable

import torch


def _is_distributed():
    return torch.distributed.is_initialized() and torch.distributed.get_world_size() > 1


def _is_complex_or_float(tensor):
    return torch.is_floating_point(tensor) or torch.is_complex(tensor)


def broadcast_tensors(tensors: Iterable[torch.Tensor], src: int = 0):
    """
    Broadcast the tensors from the given parameters to all workers.
    This can be used to ensure that all workers have the same model to start with.
    """
    if not _is_distributed():
        return

    tensors = [tensor for tensor in tensors if _is_complex_or_float(tensor)]
    handles = []
    for tensor in tensors:
        handle = torch.distributed.broadcast(tensor.data, src=src, async_op=True)
        handles.append(handle)
    for handle in handles:
        handle.wait()