# coding=utf-8
# Copyright (c) 2021, NVIDIA CORPORATION.  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.
from typing import List, Sequence

import torch

from apex.transformer.utils import divide


def split_tensor_along_last_dim(
    tensor: torch.Tensor,
    num_partitions: int,
    contiguous_split_chunks: bool = False,
) -> List[torch.Tensor]:
    """Split a tensor along its last dimension.
    Arguments:
        tensor: input tensor.
        num_partitions: number of partitions to split the tensor
        contiguous_split_chunks: If True, make each chunk contiguous
                                 in memory.
    """
    # Get the size and dimension.
    last_dim = tensor.dim() - 1
    last_dim_size = divide(tensor.size()[last_dim], num_partitions)
    # Split.
    tensor_list = torch.split(tensor, last_dim_size, dim=last_dim)
    # Note: torch.split does not create contiguous tensors by default.
    if contiguous_split_chunks:
        return tuple(chunk.contiguous() for chunk in tensor_list)

    return tensor_list


class VocabUtility:
    """Split the vocabulary into `world_size` chunks and return the
    first and last index of the vocabulary belonging to the `rank`
    partition: Note that indices in [fist, last)"""

    @staticmethod
    def vocab_range_from_per_partition_vocab_size(
        per_partition_vocab_size: int, rank, world_size: int
    ) -> Sequence[int]:
        index_f = rank * per_partition_vocab_size
        index_l = index_f + per_partition_vocab_size
        return index_f, index_l

    @staticmethod
    def vocab_range_from_global_vocab_size(global_vocab_size: int, rank: int, world_size: int) -> Sequence[int]:
        per_partition_vocab_size = divide(global_vocab_size, world_size)
        return VocabUtility.vocab_range_from_per_partition_vocab_size(
            per_partition_vocab_size, rank, world_size
        )