aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/core/kernels/dense_update_functor.h
blob: 61b57312502c89ba6aafb1d14de7ca1f4369df18 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
/* Copyright 2015 The TensorFlow 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.
==============================================================================*/

#ifndef TENSORFLOW_CORE_KERNELS_DENSE_UPDATE_FUNCTOR_H_
#define TENSORFLOW_CORE_KERNELS_DENSE_UPDATE_FUNCTOR_H_

#define EIGEN_USE_THREADS

#include "third_party/eigen3/unsupported/Eigen/CXX11/Tensor"
#include "tensorflow/core/framework/op_kernel.h"
#include "tensorflow/core/framework/tensor_types.h"

namespace tensorflow {

typedef Eigen::ThreadPoolDevice CPUDevice;
typedef Eigen::GpuDevice GPUDevice;

#ifdef TENSORFLOW_USE_SYCL
typedef Eigen::SyclDevice SYCLDevice;
#endif  // TENSORFLOW_USE_SYCL

enum DenseUpdateType { ADD, SUB, ASSIGN };

namespace functor {

template <typename Device, typename T, DenseUpdateType OP>
struct DenseUpdate {
  void operator()(const Device& d, typename TTypes<T>::Flat params,
                  typename TTypes<T>::ConstFlat update);
};

template <typename T>
struct DenseUpdate<CPUDevice, T, ADD> {
  void operator()(const CPUDevice& d, typename TTypes<T>::Flat params,
                  typename TTypes<T>::ConstFlat update) {
    params.device(d) += update;
  }
};

template <typename T>
struct DenseUpdate<CPUDevice, T, SUB> {
  void operator()(const CPUDevice& d, typename TTypes<T>::Flat params,
                  typename TTypes<T>::ConstFlat update) {
    params.device(d) -= update;
  }
};

template <typename T>
struct DenseUpdate<CPUDevice, T, ASSIGN> {
  void operator()(const CPUDevice& d, typename TTypes<T>::Flat params,
                  typename TTypes<T>::ConstFlat update) {
    params.device(d) = update;
  }
};

#ifdef TENSORFLOW_USE_SYCL
template <typename T>
struct DenseUpdate<SYCLDevice, T, ADD> {
  void operator()(const SYCLDevice& d, typename TTypes<T>::Flat params,
                  typename TTypes<T>::ConstFlat update) {
    params.device(d) += update;
  }
};

template <typename T>
struct DenseUpdate<SYCLDevice, T, SUB> {
  void operator()(const SYCLDevice& d, typename TTypes<T>::Flat params,
                  typename TTypes<T>::ConstFlat update) {
    params.device(d) -= update;
  }
};

template <typename T>
struct DenseUpdate<SYCLDevice, T, ASSIGN> {
  void operator()(const SYCLDevice& d, typename TTypes<T>::Flat params,
                  typename TTypes<T>::ConstFlat update) {
    params.device(d) = update;
  }
};
#endif  // TENSORFLOW_USE_SYCL

}  // end namespace functor

template <typename Device>
Status VariantCopyFn(OpKernelContext* context, const Tensor& from, Tensor* to);

template <>
Status VariantCopyFn<CPUDevice>(OpKernelContext* context, const Tensor& from,
                                Tensor* to);
template <>
Status VariantCopyFn<GPUDevice>(OpKernelContext* context, const Tensor& from,
                                Tensor* to);

}  // end namespace tensorflow

#endif  // TENSORFLOW_CORE_KERNELS_DENSE_UPDATE_FUNCTOR_H_