/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.

   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/operators/mul_op.h"

namespace paddle {
namespace operators {

class MulOp : public framework::OperatorWithKernel {
 protected:
  void InferShape(const framework::InferShapeContext &ctx) const override {
    PADDLE_ENFORCE(ctx.InputSize() == 2, "The mul op must take two inputs");
    auto dim0 = ctx.Input<Tensor>(0)->dims();
    auto dim1 = ctx.Input<Tensor>(1)->dims();
    PADDLE_ENFORCE_EQ(dim0.size(), 2,
                      "input X(%s) should be a tensor with 2 dims, a matrix",
                      ctx.op_.Input("X"));
    PADDLE_ENFORCE_EQ(dim1.size(), 2,
                      "input Y(%s) should be a tensor with 2 dims, a matrix",
                      ctx.op_.Input("Y"));
    PADDLE_ENFORCE_EQ(
        dim0[1], dim1[0],
        "First matrix's width must be equal with second matrix's height.");
    PADDLE_ENFORCE_EQ(ctx.OutputSize(), 1, "The mul op takes only one output");
    ctx.Output<Tensor>(0)->Resize({dim0[0], dim1[1]});
  }
};

class MulOpMaker : public framework::OpProtoAndCheckerMaker {
 public:
  MulOpMaker(framework::OpProto *proto, framework::OpAttrChecker *op_checker)
      : OpProtoAndCheckerMaker(proto, op_checker) {
    AddInput("X", "The first input of mul op");
    AddInput("Y", "The second input of mul op");
    AddOutput("Out", "The output of mul op");
    AddComment(R"DOC(
Two Element Mul Operator.

The equation is: Out = X * Y
)DOC");
  }
};

class MulOpGrad : public framework::OperatorWithKernel {
 protected:
  void InferShape(const framework::InferShapeContext &ctx) const override {
    PADDLE_ENFORCE_EQ(ctx.InputSize(), 3UL,
                      "Input of MulOpGrad should be 3, X, Y, Out@GRAD");
    PADDLE_ENFORCE_EQ(ctx.OutputSize(), 2UL,
                      "Output of MulOpGrad should be 2, X@GRAD, Y@GRAD");
    PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("X"), "Input(X) should not be null");
    PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("Y"), "Input(Y) should not be null");
    PADDLE_ENFORCE_NOT_NULL(ctx.InputVar(framework::GradVarName("Out")),
                            "Input(Out@GRAD) should not be null");
    auto *x_grad = ctx.Output<framework::Tensor>(framework::GradVarName("X"));
    auto *y_grad = ctx.Output<framework::Tensor>(framework::GradVarName("Y"));
    auto dim0 = ctx.Input<Tensor>(0)->dims();
    auto dim1 = ctx.Input<Tensor>(1)->dims();
    auto out_dims = ctx.Input<Tensor>(2)->dims();
    PADDLE_ENFORCE(dim0[0] * dim1[0] == out_dims[0],
                   "Out@GRAD[0] must equal to X[0] * Y[0]");
    PADDLE_ENFORCE(dim0[1] * dim1[1] == out_dims[1],
                   "Out@GRAD shape must equal to X[1] * Y[1]");

    x_grad->Resize(dim1);
    y_grad->Resize(dim0);
  }
};

}  // namespace operators
}  // namespace paddle

namespace ops = paddle::operators;
REGISTER_OP(mul, ops::MulOp, ops::MulOpMaker);
REGISTER_GRADIENT_OP(mul, mul_grad, ops::MulOpGrad);

REGISTER_OP_CPU_KERNEL(mul, ops::MulKernel<paddle::platform::CPUPlace, float>);
REGISTER_OP_CPU_KERNEL(mul_grad,
                       ops::MulGradKernel<paddle::platform::CPUPlace, float>);