// Copyright (c) 2022 PaddlePaddle Authors. 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.

#include "paddle/phi/kernels/unpool_grad_kernel.h"

#include <algorithm>
#include <string>
#include <vector>

#include "paddle/phi/backends/cpu/cpu_context.h"
#include "paddle/phi/core/kernel_registry.h"
#include "paddle/phi/kernels/funcs/math_function.h"

namespace phi {

template <typename T, typename IndT, typename Context>
void UnpoolGrad(const Context& dev_ctx,
                const DenseTensor& x,
                const DenseTensor& indices,
                const DenseTensor& out,
                const DenseTensor& out_grad,
                DenseTensor* x_grad) {
  T* input_grad_data = dev_ctx.template Alloc<T>(x_grad);
  const T* output_grad_data = out_grad.data<T>();
  funcs::SetConstant<Context, T> zero;
  zero(dev_ctx, x_grad, static_cast<T>(0));
  const int batch_size = static_cast<int>(x.dims()[0]);
  const int input_height = static_cast<int>(x.dims()[2]);
  const int input_width = static_cast<int>(x.dims()[3]);
  const int output_channels = static_cast<int>(out.dims()[1]);
  const int output_height = static_cast<int>(out.dims()[2]);
  const int output_width = static_cast<int>(out.dims()[3]);
  int64_t input_feasize = static_cast<int64_t>(input_height) * input_width;
  int64_t output_feasize = static_cast<int64_t>(output_height) * output_width;
  const IndT* indices_data = indices.data<IndT>();

  for (int b = 0; b < batch_size; ++b) {
    for (int c = 0; c < output_channels; ++c) {
      for (int i = 0; i < input_feasize; ++i) {
        IndT index = indices_data[i];
        PADDLE_ENFORCE_LT(
            index,
            output_feasize,
            common::errors::InvalidArgument(
                "index should less than output tensor height * output tensor "
                "width. Expected %ld < %ld, but got "
                "%ld >= %ld. Please check input value.",
                index,
                output_feasize,
                index,
                output_feasize));
        input_grad_data[i] = output_grad_data[index];
      }
      input_grad_data += input_feasize;
      indices_data += input_feasize;
      output_grad_data += output_feasize;
    }
  }
}

template <typename T, typename Context>
void UnpoolGradKernel(const Context& dev_ctx,
                      const DenseTensor& x,
                      const DenseTensor& indices,
                      const DenseTensor& out,
                      const DenseTensor& out_grad,
                      const std::vector<int>& ksize UNUSED,
                      const std::vector<int>& strides UNUSED,
                      const std::vector<int>& paddings UNUSED,
                      const IntArray& output_size UNUSED,
                      const std::string& data_format UNUSED,
                      DenseTensor* x_grad) {
  if (x_grad && x_grad->numel() == 0) {
    dev_ctx.template Alloc<T>(x_grad);
    return;
  }
  const auto& indices_type = indices.dtype();
  if (indices_type == DataType::INT32) {
    UnpoolGrad<T, int, Context>(dev_ctx, x, indices, out, out_grad, x_grad);
  } else {
    UnpoolGrad<T, int64_t, Context>(dev_ctx, x, indices, out, out_grad, x_grad);
  }
}

template <typename T, typename IndT, typename Context>
void Unpool3dGrad(const Context& dev_ctx,
                  const DenseTensor& x,
                  const DenseTensor& indices,
                  const DenseTensor& out,
                  const DenseTensor& out_grad,
                  DenseTensor* x_grad) {
  T* input_grad_data = dev_ctx.template Alloc<T>(x_grad);
  const T* output_grad_data = out_grad.data<T>();
  funcs::SetConstant<Context, T> zero;
  zero(dev_ctx, x_grad, static_cast<T>(0));

  const int batch_size = static_cast<int>(x.dims()[0]);
  const int input_depth = static_cast<int>(x.dims()[2]);
  const int input_height = static_cast<int>(x.dims()[3]);
  const int input_width = static_cast<int>(x.dims()[4]);
  const int output_channels = static_cast<int>(out.dims()[1]);
  const int output_depth = static_cast<int>(out.dims()[2]);
  const int output_height = static_cast<int>(out.dims()[3]);
  const int output_width = static_cast<int>(out.dims()[4]);
  int64_t input_feasize =
      static_cast<int64_t>(input_depth) * input_height * input_width;
  int64_t output_feasize =
      static_cast<int64_t>(output_depth) * output_height * output_width;
  const IndT* indices_data = indices.data<IndT>();

  for (int b = 0; b < batch_size; ++b) {
    for (int c = 0; c < output_channels; ++c) {
      for (int i = 0; i < input_feasize; ++i) {
        IndT index = indices_data[i];
        PADDLE_ENFORCE_LT(
            index,
            output_feasize,
            common::errors::InvalidArgument(
                "index should less than output tensor depth * output tensor "
                "height "
                "* output tensor width. Expected %ld < %ld, but got "
                "%ld >= %ld. Please check input value.",
                index,
                output_feasize,
                index,
                output_feasize));
        input_grad_data[i] = output_grad_data[index];
      }
      input_grad_data += input_feasize;
      indices_data += input_feasize;
      output_grad_data += output_feasize;
    }
  }
}

template <typename T, typename Context>
void Unpool3dGradKernel(const Context& dev_ctx,
                        const DenseTensor& x,
                        const DenseTensor& indices,
                        const DenseTensor& out,
                        const DenseTensor& out_grad,
                        const std::vector<int>& ksize UNUSED,
                        const std::vector<int>& strides,
                        const std::vector<int>& paddings UNUSED,
                        const std::vector<int>& output_size UNUSED,
                        const std::string& data_format UNUSED,
                        DenseTensor* x_grad) {
  if (x_grad && x_grad->numel() == 0) {
    dev_ctx.template Alloc<T>(x_grad);
    return;
  }
  const auto& indices_type = indices.dtype();
  if (indices_type == DataType::INT32) {
    Unpool3dGrad<T, int, Context>(dev_ctx, x, indices, out, out_grad, x_grad);
  } else {
    Unpool3dGrad<T, int64_t, Context>(
        dev_ctx, x, indices, out, out_grad, x_grad);
  }
}

}  // namespace phi

PD_REGISTER_KERNEL(unpool_grad,
                   CPU,
                   ALL_LAYOUT,
                   phi::UnpoolGradKernel,
                   float,
                   double,
                   int64_t) {}

PD_REGISTER_KERNEL(unpool3d_grad,
                   CPU,
                   ALL_LAYOUT,
                   phi::Unpool3dGradKernel,
                   float,
                   double,
                   int64_t) {}