1/* Copyright 2015 The TensorFlow Authors. All Rights Reserved.
2
3Licensed under the Apache License, Version 2.0 (the "License");
4you may not use this file except in compliance with the License.
5You may obtain a copy of the License at
6
7 http://www.apache.org/licenses/LICENSE-2.0
8
9Unless required by applicable law or agreed to in writing, software
10distributed under the License is distributed on an "AS IS" BASIS,
11WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12See the License for the specific language governing permissions and
13limitations under the License.
14==============================================================================*/
15
16#ifndef TENSORFLOW_CORE_KERNELS_TILE_FUNCTOR_H_
17#define TENSORFLOW_CORE_KERNELS_TILE_FUNCTOR_H_
18
19#include "third_party/eigen3/unsupported/Eigen/CXX11/Tensor"
20
21#include "tensorflow/core/framework/tensor.h"
22#include "tensorflow/core/framework/tensor_types.h"
23#include "tensorflow/core/platform/types.h"
24
25namespace tensorflow {
26
27namespace internal {
28
29// Device-specific naive implementation for Tile.
30
31template <typename T>
32void TileSimple(const Eigen::ThreadPoolDevice& d, Tensor* out,
33 const Tensor& in);
34
35#if GOOGLE_CUDA || TENSORFLOW_USE_ROCM
36template <typename T>
37void TileSimple(const Eigen::GpuDevice& d, Tensor* out, const Tensor& in);
38#endif // GOOGLE_CUDA || TENSORFLOW_USE_ROCM
39
40template <typename Device, typename T, typename Tmultiples, int NDIM>
41void TileUsingEigen(const Device& d, Tensor* out, const Tensor& in,
42 const gtl::ArraySlice<Tmultiples> broadcast_array) {
43 Eigen::array<Tmultiples, NDIM> b;
44 for (int i = 0; i < NDIM; ++i) b[i] = broadcast_array[i];
45 MaybeWith32BitIndexing<Device>(
46 [&](auto out32, auto in32) { out32.device(d) = in32.broadcast(b); },
47 out->tensor<T, NDIM>(), in.tensor<T, NDIM>());
48}
49
50template <typename Device, typename T, typename Tmultiples>
51void TileUsingEigen(const Device& d, Tensor* out, const Tensor& in,
52 const gtl::ArraySlice<Tmultiples>) {
53 auto x = in.tensor<T, 0>();
54 auto y = out->tensor<T, 0>();
55 // In the scalar case we simply copy the input.
56 y.device(d) = x;
57}
58
59} // end namespace internal
60
61namespace functor {
62
63template <typename Device, typename T, typename Tmultiples>
64struct Tile {
65 void operator()(const Device& d, Tensor* out, const Tensor& in,
66 const gtl::ArraySlice<Tmultiples> broadcast_array) const {
67 switch (in.dims()) {
68 case 0:
69 internal::TileUsingEigen<Device, T, Tmultiples>(d, out, in,
70 broadcast_array);
71 break;
72 case 1:
73 internal::TileUsingEigen<Device, T, Tmultiples, 1>(d, out, in,
74 broadcast_array);
75 break;
76 case 2:
77 internal::TileUsingEigen<Device, T, Tmultiples, 2>(d, out, in,
78 broadcast_array);
79 break;
80 case 3:
81 internal::TileUsingEigen<Device, T, Tmultiples, 3>(d, out, in,
82 broadcast_array);
83 break;
84 case 4:
85 internal::TileUsingEigen<Device, T, Tmultiples, 4>(d, out, in,
86 broadcast_array);
87 break;
88 case 5:
89 internal::TileUsingEigen<Device, T, Tmultiples, 5>(d, out, in,
90 broadcast_array);
91 break;
92 case 6:
93 internal::TileUsingEigen<Device, T, Tmultiples, 6>(d, out, in,
94 broadcast_array);
95 break;
96 case 7:
97 internal::TileUsingEigen<Device, T, Tmultiples, 7>(d, out, in,
98 broadcast_array);
99 break;
100 default:
101 internal::TileSimple<T>(d, out, in);
102 break;
103 }
104 }
105};
106
107} // end namespace functor
108} // end namespace tensorflow
109
110#endif // TENSORFLOW_CORE_KERNELS_TILE_FUNCTOR_H_
111