You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

ge_profiling.h 1.2 kB

1234567891011121314151617181920212223242526272829
  1. /**
  2. * Copyright (c) Huawei Technologies Co., Ltd. 2021. All rights reserved.
  3. *
  4. * Licensed under the Apache License, Version 2.0 (the "License");
  5. * you may not use this file except in compliance with the License.
  6. * You may obtain a copy of the License at
  7. *
  8. * http://www.apache.org/licenses/LICENSE-2.0
  9. *
  10. * Unless required by applicable law or agreed to in writing, software
  11. * distributed under the License is distributed on an "AS IS" BASIS,
  12. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  13. * See the License for the specific language governing permissions and
  14. * limitations under the License.
  15. */
  16. #ifndef INC_FRAMEWORK_COMMON_GE_PROFILING_H_
  17. #define INC_FRAMEWORK_COMMON_GE_PROFILING_H_
  18. #include "external/ge/ge_api_error_codes.h"
  19. #include "runtime/base.h"
  20. /// @brief Output the profiling data of single operator in Pytorch, and does not support multithreading
  21. /// @return Status result
  22. GE_FUNC_VISIBILITY ge::Status ProfSetStepInfo(const uint64_t index_id, const uint16_t tag_id, rtStream_t const stream);
  23. GE_FUNC_VISIBILITY ge::Status ProfGetDeviceFormGraphId(const uint32_t graph_id, uint32_t &device_id);
  24. #endif // INC_FRAMEWORK_COMMON_GE_PROFILING_H_

图引擎模块(GE)是MindSpore的一个子模块,其代码由C++实现,位于前端模块ME和底层硬件之间,起到承接作用。图引擎模块以ME下发的图作为输入,然后进行一系列的深度图优化操作,最后输出一张可以在底层硬件上高效运行的图。GE针对昇腾AI处理器的硬件结构特点,做了特定的优化工作,以此来充分发挥出昇腾AI处理器的强大算力。在进行模型训练/推理时,GE会被自动调用而用户并不感知。GE主要由GE API和GE Core两部分组成,详细的架构图如下所示