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.

add_kernel.h 1.4 kB

5 years ago
5 years ago
5 years ago
5 years ago
5 years ago
5 years ago
1234567891011121314151617181920212223242526272829303132333435363738394041
  1. /**
  2. * Copyright 2020 Huawei Technologies Co., Ltd
  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 GE_GRAPH_PASSES_FOLDING_KERNEL_ADD_KERNEL_H_
  17. #define GE_GRAPH_PASSES_FOLDING_KERNEL_ADD_KERNEL_H_
  18. #include <vector>
  19. #include "inc/kernel.h"
  20. namespace ge {
  21. class AddKernel : public Kernel {
  22. public:
  23. Status Compute(const ge::OpDescPtr op_desc_ptr, const std::vector<ge::ConstGeTensorPtr> &input,
  24. std::vector<ge::GeTensorPtr> &v_output) override;
  25. private:
  26. Status AddCheck(const OpDescPtr &op_desc_ptr, const std::vector<ConstGeTensorPtr> &input);
  27. template <typename T>
  28. Status OverflowCheck(const T &x, const T &y, DataType data_type);
  29. template <typename InT>
  30. Status BCastAdd(const OpDescPtr &op_desc_ptr, const std::vector<ConstGeTensorPtr> &input,
  31. std::vector<GeTensorPtr> &v_output);
  32. };
  33. } // namespace ge
  34. #endif // GE_GRAPH_PASSES_FOLDING_KERNEL_ADD_KERNEL_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