1 /* Copyright 2016 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 #include "tensorflow/core/kernels/cast_op_impl.h"
17
18 #include "tensorflow/core/util/work_sharder.h"
19
20 namespace tensorflow {
21
22 typedef Eigen::ThreadPoolDevice CPUDevice;
23 typedef Eigen::GpuDevice GPUDevice;
24
GetCpuCastFromBfloat(DataType dst_dtype)25 CastFunctorType GetCpuCastFromBfloat(DataType dst_dtype) {
26 CURRY_TYPES3(CAST_CASE, CPUDevice, bfloat16);
27 return nullptr;
28 }
29
30 #if (defined(GOOGLE_CUDA) && GOOGLE_CUDA) || \
31 (defined(TENSORFLOW_USE_ROCM) && TENSORFLOW_USE_ROCM)
GetGpuCastFromBfloat(DataType dst_dtype)32 CastFunctorType GetGpuCastFromBfloat(DataType dst_dtype) {
33 if (dst_dtype == DT_FLOAT) {
34 return [](OpKernelContext* ctx, const Tensor& inp, Tensor* out,
35 bool truncate) {
36 functor::CastFunctor<GPUDevice, float, bfloat16> func;
37 func(ctx->eigen_device<GPUDevice>(), out->flat<float>(),
38 inp.flat<bfloat16>(), truncate);
39 };
40 }
41 return nullptr;
42 }
43 #endif // GOOGLE_CUDA || TENSORFLOW_USE_ROCM
44
45 } // namespace tensorflow
46