1 | /* Copyright 2015 The TensorFlow Authors. All Rights Reserved. |
2 | |
3 | Licensed under the Apache License, Version 2.0 (the "License"); |
4 | you may not use this file except in compliance with the License. |
5 | You may obtain a copy of the License at |
6 | |
7 | http://www.apache.org/licenses/LICENSE-2.0 |
8 | |
9 | Unless required by applicable law or agreed to in writing, software |
10 | distributed under the License is distributed on an "AS IS" BASIS, |
11 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
12 | See the License for the specific language governing permissions and |
13 | limitations under the License. |
14 | ==============================================================================*/ |
15 | |
16 | #if GOOGLE_CUDA || TENSORFLOW_USE_ROCM |
17 | |
18 | #include "tensorflow/core/kernels/gather_functor.h" |
19 | #include "tensorflow/core/framework/register_types.h" |
20 | |
21 | namespace tensorflow { |
22 | |
23 | typedef Eigen::GpuDevice GPUDevice; |
24 | |
25 | namespace functor { |
26 | |
27 | // Forward declarations of the functor specializations for GPU. |
28 | #define DECLARE_GPU_SPECS_INDEX(T, Index) \ |
29 | template <> \ |
30 | int64_t GatherFunctor<GPUDevice, T, Index>::operator()( \ |
31 | OpKernelContext* ctx, typename TTypes<T, 3>::ConstTensor Tparams, \ |
32 | typename TTypes<Index>::ConstFlat Tindices, \ |
33 | typename TTypes<T, 3>::Tensor Tout); \ |
34 | extern template struct GatherFunctor<GPUDevice, T, Index>; |
35 | |
36 | #define DECLARE_GPU_SPECS(T) \ |
37 | DECLARE_GPU_SPECS_INDEX(T, int32); \ |
38 | DECLARE_GPU_SPECS_INDEX(T, int64_t) |
39 | |
40 | TF_CALL_int64(DECLARE_GPU_SPECS); |
41 | TF_CALL_GPU_NUMBER_TYPES(DECLARE_GPU_SPECS); |
42 | TF_CALL_COMPLEX_TYPES(DECLARE_GPU_SPECS); |
43 | |
44 | #undef DECLARE_GPU_SPECS |
45 | #undef DECLARE_GPU_SPECS_INDEX |
46 | |
47 | } // namespace functor |
48 | } // namespace tensorflow |
49 | |
50 | #else |
51 | |
52 | #include "tensorflow/core/kernels/gather_functor.h" |
53 | |
54 | #endif // GOOGLE_CUDA || TENSORFLOW_USE_ROCM |
55 | |