xref: /aosp_15_r20/external/tensorflow/tensorflow/core/util/use_cudnn.h (revision b6fb3261f9314811a0f4371741dbb8839866f948)
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 // The utility to check Cudnn dependency and set Cudnn-related flags.
17 
18 #ifndef TENSORFLOW_CORE_UTIL_USE_CUDNN_H_
19 #define TENSORFLOW_CORE_UTIL_USE_CUDNN_H_
20 
21 #include "tensorflow/core/platform/types.h"
22 
23 namespace tensorflow {
24 
25 bool CudnnUseAutotune();
26 bool CudnnUseFrontend();
27 bool CudnnUseRuntimeFusion();
28 bool CudnnRnnUseAutotune();
29 bool CudnnDisableConv1x1Optimization();
30 bool DebugCudnnRnn();
31 bool DebugCudnnRnnUseTensorOps();
32 int64_t DebugCudnnRnnAlgo();
33 
34 // Returns true if the CuDNN depthwise convolution can be used. See cudnn
35 // release note 7.6.3.
36 // (https://docs.nvidia.com/deeplearning/sdk/cudnn-release-notes/rel_763.html)
37 bool ShouldCudnnGroupedConvolutionBeUsed(const int32_t filter_rows,
38                                          const int32_t filter_cols,
39                                          const int32_t in_depth,
40                                          const int32_t out_depth);
41 }  // namespace tensorflow
42 
43 #endif  // TENSORFLOW_CORE_UTIL_USE_CUDNN_H_
44