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.

assert_pass.h 1.4 kB

5 years ago
5 years ago
5 years ago
5 years ago
4 years ago
5 years ago
5 years ago
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748
  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_ASSERT_PASS_H_
  17. #define GE_GRAPH_PASSES_ASSERT_PASS_H_
  18. #include <vector>
  19. #include "graph/passes/base_pass.h"
  20. namespace ge {
  21. class AssertPass : public BaseNodePass {
  22. public:
  23. Status Run(NodePtr& node) override;
  24. private:
  25. ///
  26. /// collect assert and other unused ops
  27. /// @param assert_node assert node
  28. /// @param nodes_unused nodes to be deleted
  29. /// @return void
  30. ///
  31. void CollectUnusedNode(const NodePtr &assert_node, std::vector<ge::NodePtr>& nodes_unused);
  32. ///
  33. /// remove unused nodes from graph
  34. /// @param graph
  35. /// @param nodes_unused nodes to be deleted
  36. /// @return Status
  37. ///
  38. Status RemoveUnusedNode(std::vector<NodePtr>& nodes_unused);
  39. };
  40. } // namespace ge
  41. #endif // GE_GRAPH_PASSES_ASSERT_PASS_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