You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
67 lines
2.4 KiB
67 lines
2.4 KiB
/* 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. */
|
|
|
|
#pragma once
|
|
|
|
#include "paddle/operators/math/math_function.h"
|
|
|
|
#include "paddle/framework/eigen.h"
|
|
#include "paddle/framework/op_registry.h"
|
|
|
|
namespace paddle {
|
|
namespace operators {
|
|
|
|
using Tensor = framework::Tensor;
|
|
template <typename T, int MajorType = Eigen::RowMajor,
|
|
typename IndexType = Eigen::DenseIndex>
|
|
using EigenMatrix = framework::EigenMatrix<T, MajorType, IndexType>;
|
|
|
|
template <typename Place, typename T>
|
|
class MulKernel : public framework::OpKernel {
|
|
public:
|
|
void Compute(const framework::ExecutionContext& context) const override {
|
|
auto* X = context.Input<Tensor>("X");
|
|
auto* Y = context.Input<Tensor>("Y");
|
|
auto* Z = context.Output<Tensor>("Out");
|
|
Z->mutable_data<T>(context.GetPlace());
|
|
auto* device_context =
|
|
const_cast<platform::DeviceContext*>(context.device_context_);
|
|
math::matmul<Place, T>(*X, false, *Y, false, 1, Z, 0, device_context);
|
|
}
|
|
};
|
|
|
|
template <typename Place, typename T>
|
|
class MulGradKernel : public framework::OpKernel {
|
|
public:
|
|
void Compute(const framework::ExecutionContext& ctx) const override {
|
|
auto* X = ctx.Input<Tensor>("X");
|
|
auto* Y = ctx.Input<Tensor>("Y");
|
|
auto* dOut = ctx.Input<Tensor>(framework::GradVarName("Out"));
|
|
|
|
auto* dX = ctx.Output<Tensor>(framework::GradVarName("X"));
|
|
auto* dY = ctx.Output<Tensor>(framework::GradVarName("Y"));
|
|
dX->mutable_data<T>(ctx.GetPlace());
|
|
dY->mutable_data<T>(ctx.GetPlace());
|
|
auto* device_context =
|
|
const_cast<platform::DeviceContext*>(ctx.device_context_);
|
|
// dX = dOut * Y'. dX: M x K, dOut : M x N, Y : K x N
|
|
math::matmul<Place, T>(*dOut, false, *Y, true, 1, dX, 0, device_context);
|
|
// dY = X' * dOut. dY: K x N, dOut : M x N, X : M x K
|
|
math::matmul<Place, T>(*X, true, *dOut, false, 1, dY, 0, device_context);
|
|
}
|
|
};
|
|
|
|
} // namespace operators
|
|
} // namespace paddle
|