xref: /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/gpu/metrics.h (revision b6fb3261f9314811a0f4371741dbb8839866f948)
1 /* Copyright 2022 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 #ifndef TENSORFLOW_COMPILER_XLA_SERVICE_GPU_METRICS_H_
17 #define TENSORFLOW_COMPILER_XLA_SERVICE_GPU_METRICS_H_
18 
19 #include <cstdint>
20 
21 namespace xla {
22 
23 // HLO passes (HLO -> HLO).
24 void RecordHloPassesDuration(uint64_t time_usecs);
25 
26 // Compiling HLO to LLVM.
27 void RecordHloToLlvmDuration(uint64_t time_usecs);
28 
29 // The entire LLVM to PTX pipeline, including both LLVM optimization (LLVM ->
30 // LLVM) and compiling LLVM -> PTX.
31 void RecordLlvmPassesAndLlvmToPtxDuration(uint64_t time_usecs);
32 
33 // LLVM passes (linking and optimization) only (LLVM -> LLVM).
34 void RecordLlvmPassesDuration(uint64_t time_usecs);
35 
36 // Compiling LLVM to PTX only.
37 void RecordLlvmToPtxDuration(uint64_t time_usecs);
38 
39 // Compiling PTX to cubin.
40 void RecordPtxToCubinDuration(uint64_t time_usecs);
41 
42 }  // namespace xla
43 
44 #endif  // TENSORFLOW_COMPILER_XLA_SERVICE_GPU_METRICS_H_
45