// Copyright (c) 2019 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 "lite/kernels/fpga/reshape_compute.h"
#include <vector>
#include "lite/operators/reshape_op.h"

namespace paddle {
namespace lite {
namespace kernels {
namespace fpga {

using float16 = zynqmp::float16;

void ReshapeCompute::Run() {
  auto& param = Param<operators::ReshapeParam>();
  param.output->mutable_data<float16>();
  auto x = param.x;
  // auto actual_shape = param.actual_shape;
  Tensor* actual_shape = nullptr;  // TODO(chonwhite) change it.
  auto output = param.output;
  bool inplace = param.inplace;
  auto x_dims = x->dims();
  auto output_dims = output->dims();
  if (actual_shape) {
    auto actual_shape_dims = actual_shape->dims();
    auto* actual_shape_data = actual_shape->data<int>();
    auto shape = std::vector<int>(
        actual_shape_data, actual_shape_data + actual_shape_dims.production());
    output_dims = lite::operators::ValidateShape(shape, x_dims);
    output->Resize(output_dims);
  }
  if (inplace) {
    output->ShareDataWith(*x);
  } else {
    output->CopyDataFrom(*x);
  }

  param.x->ZynqTensor()->saveToFile("reshape_in", true);
  output->ZynqTensor()->saveToFile("reshape_out", true);

  output->Resize(output_dims);
}

}  // namespace fpga
}  // namespace kernels
}  // namespace lite
}  // namespace paddle

REGISTER_LITE_KERNEL(reshape,
                     kFPGA,
                     kFP16,
                     kNHWC,
                     paddle::lite::kernels::fpga::ReshapeCompute,
                     def)
    .BindInput("X",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindInput("Shape",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindOutput("Out",
                {LiteType::GetTensorTy(TARGET(kFPGA),
                                       PRECISION(kFP16),
                                       DATALAYOUT(kNHWC))})
    .Finalize();

REGISTER_LITE_KERNEL(reshape2,
                     kFPGA,
                     kFP16,
                     kNHWC,
                     paddle::lite::kernels::fpga::ReshapeCompute,
                     def)
    .BindInput("X",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindInput("Shape",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindOutput("Out",
                {LiteType::GetTensorTy(TARGET(kFPGA),
                                       PRECISION(kFP16),
                                       DATALAYOUT(kNHWC))})
    .BindOutput("XShape",
                {LiteType::GetTensorTy(TARGET(kFPGA),
                                       PRECISION(kFP16),
                                       DATALAYOUT(kNHWC))})
    .Finalize();

REGISTER_LITE_KERNEL(flatten,
                     kFPGA,
                     kFP16,
                     kNHWC,
                     paddle::lite::kernels::fpga::ReshapeCompute,
                     def)
    .BindInput("X",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindInput("Shape",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindOutput("Out",
                {LiteType::GetTensorTy(TARGET(kFPGA),
                                       PRECISION(kFP16),
                                       DATALAYOUT(kNHWC))})
    .Finalize();

REGISTER_LITE_KERNEL(flatten2,
                     kFPGA,
                     kFP16,
                     kNHWC,
                     paddle::lite::kernels::fpga::ReshapeCompute,
                     def)
    .BindInput("X",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindInput("Shape",
               {LiteType::GetTensorTy(TARGET(kFPGA),
                                      PRECISION(kFP16),
                                      DATALAYOUT(kNHWC))})
    .BindOutput("Out",
                {LiteType::GetTensorTy(TARGET(kFPGA),
                                       PRECISION(kFP16),
                                       DATALAYOUT(kNHWC))})
    .BindOutput("XShape",
                {LiteType::GetTensorTy(TARGET(kFPGA),
                                       PRECISION(kFP16),
                                       DATALAYOUT(kNHWC))})
    .Finalize();