xref: /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/gpu/for_thunk.h (revision b6fb3261f9314811a0f4371741dbb8839866f948)
1 /* Copyright 2017 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_FOR_THUNK_H_
17 #define TENSORFLOW_COMPILER_XLA_SERVICE_GPU_FOR_THUNK_H_
18 
19 #include <vector>
20 
21 #include "tensorflow/compiler/xla/service/gpu/buffer_allocations.h"
22 #include "tensorflow/compiler/xla/service/gpu/sequential_thunk.h"
23 #include "tensorflow/compiler/xla/service/gpu/thunk.h"
24 #include "tensorflow/compiler/xla/service/hlo_instruction.h"
25 #include "tensorflow/core/platform/stream_executor_no_cuda.h"
26 
27 namespace xla {
28 namespace gpu {
29 
30 // ForThunk executes 'loop_limit' invocations of 'body_thunk_sequence'.
31 class ForThunk : public Thunk {
32  public:
33   ForThunk(ThunkInfo thunk_info, const int64_t loop_limit,
34            std::unique_ptr<ThunkSequence> body_thunk_sequence);
35   ForThunk(const ForThunk&) = delete;
36   ForThunk& operator=(const ForThunk&) = delete;
37 
38   Status Initialize(const GpuExecutable& executable,
39                     se::StreamExecutor* executor) override;
40   Status ExecuteOnStream(const ExecuteParams& params) override;
41 
42  private:
43   const int64_t loop_limit_;
44   std::unique_ptr<SequentialThunk> body_thunk_sequence_;
45 };
46 
47 }  // namespace gpu
48 }  // namespace xla
49 
50 #endif  // TENSORFLOW_COMPILER_XLA_SERVICE_GPU_FOR_THUNK_H_
51