hummingbird
/
graphengine
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
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.
2162 Commits
28 Branches
21 MB
0 Download
 
 
 
 
 
 
Tree: e8fcd806f6
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'e8fcd806f6'
${ noResults }
graphengine/ge/hybrid/executor
zhou_lili 279eb010c1 ge code of fuzz build 3 years ago
..
worker modif dump content 3 years ago
hybrid_execution_context.cc modify geloge and add err report 3 years ago
hybrid_execution_context.h fix file num 3 years ago
hybrid_model_async_executor.cc modif dump content 3 years ago
hybrid_model_async_executor.h modif dump content 3 years ago
hybrid_model_executor.cc ge code of fuzz build 3 years ago
hybrid_model_executor.h dts:support ir build online dynamic model 3 years ago
hybrid_model_pipeline_executor.cc Optimize dependencies for const inputs 3 years ago
hybrid_model_pipeline_executor.h fixed sc warning 3 years ago
hybrid_profiler.cc modify geloge and add err report 3 years ago
hybrid_profiler.h inference supports dynamic shape 3 years ago
node_done_manager.cc modify code to add report errmsg 3 years ago
node_done_manager.h update cmake 4 years ago
node_state.cc modify geloge and add err report 3 years ago
node_state.h dts:support ir build online dynamic model 3 years ago
rt_callback_manager.cc modify geloge and add err report 3 years ago
rt_callback_manager.h dynamic shape support pipeline 3 years ago
subgraph_context.cc modify geloge and add err report 3 years ago
subgraph_context.h update 3 years ago
subgraph_executor.cc modify geloge and add err report 3 years ago
subgraph_executor.h dynamic shape support pipeline 3 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

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

C++ Text Makefile Shell CMake other