企业官网建设流程全解析

Sample Usage Guide

【免费下载链接】geGE（Graph Engine）是面向昇腾的图编译器和执行器，提供了计算图优化、多流并行、内存复用和模型下沉等技术手段，加速模型执行效率，减少模型内存占用。 GE 提供对 PyTorch、TensorFlow 前端的友好接入能力，并同时支持 onnx、pb 等主流模型格式的解析与编译。项目地址: https://gitcode.com/cann/ge

1. Function Description

This sample demonstrates graph construction using Relu operator normal input, aimed at helping graph developers quickly understand normal input definition and usage of this type of operators in graph construction.

2. Directory Structure

cpp/ ├── src/ | └── CMakeLists.txt // CMake build file | └── es_showcase.h // Header file | └── make_relu_add_graph.cpp // sample file ├── CMakeLists.txt // CMake build file ├── main.cpp // Program main entry ├── README.md // README file ├── run_sample.sh // Execution script ├── utils.h // Utility file

3. Usage Instructions

3.1. Prepare CANN Package

• Installtoolkitandopspackages correctly following Environment Preparation
• Set environment variables (assuming package is installed at /usr/local/Ascend/)

source /usr/local/Ascend/cann/set_env.sh

3.2. Build and Execute

3.2.1 Generate ES Interfaces and Build Graph for DUMP

Simply run the following command to clean, generate interfaces, construct graph and DUMP graph:

bash run_sample.sh

Current run_sample.sh behavior: automatically clean old build, build sample and default execute sample dump. When you see the following message, it indicates successful execution:

[Success] sample execution successful, pbtxt dump generated in current directory. The file starts with ge_onnx_ and can be opened in netron for display

3.2.2 Output File Description

After successful execution, the following files will be generated in current directory:

ge_onnx_*.pbtxt - protobuf text format of graph structure, can be viewed with netron

3.2.3 Build Graph and Execute

Besides basic graph construction and dump functionality, esb_sample supports building graph and actually executing computation.

bash run_sample.sh -t sample_and_run

This command will:

1. Automatically generate ES interfaces
2. Compile sample program
3. Generate dump graph, run graph and output computation results

After successful execution, you will see:

[Success] sample_and_run execution successful, pbtxt and data output dump generated in current directory

You can view computation results through data file

3.3. Log Printing

If you need log printing to assist debugging during executable program execution, you can set the following environment variables beforebash run_sample.shto print logs to screen:

export ASCEND_SLOG_PRINT_TO_STDOUT=1 # Print logs to screen export ASCEND_GLOBAL_LOG_LEVEL=0 # Log level set to debug level

3.4. DUMP Graph During Graph Compilation

If you need to DUMP graph to assist debugging graph compilation process during executable program execution, you can set the following environment variables beforebash run_sample.sh -t sample_and_runto DUMP graph to execution path:

export DUMP_GE_GRAPH=2

4. Core Concepts Introduction

4.1. Graph Construction Steps

• Create graph builder (provides context, workspace and construction-related methods needed for graph construction)
• Add starting nodes (starting nodes refer to nodes without input dependencies, usually including graph inputs (like Data nodes) and weight constants (like Const nodes))
• Add intermediate nodes (intermediate nodes are computation nodes with input dependencies, usually generated by user graph construction logic, and connected using existing nodes as inputs)
• Set graph output (explicitly specify graph output nodes as computation result endpoints)

4.2. Normal Input

Concept Explanation:Normal input refers to operator input that is mandatory input with fixed input count.

Graph Construction API Features:

• Input type must match type constraint declared during operator registration, ES API will perform type checking during graph construction

For example, Relu operator prototype is shown below, ES graph construction generated API is Relu(), supporting use in C and C++

REG_OP(Relu) .INPUT(x, TensorType({DT_FLOAT, DT_FLOAT16, DT_DOUBLE, DT_INT8, DT_INT32, DT_INT16, DT_INT64, DT_UINT8, DT_UINT16, DT_QINT8, DT_BF16})) .OUTPUT(y, TensorType({DT_FLOAT, DT_FLOAT16, DT_DOUBLE, DT_INT8, DT_INT32, DT_INT16, DT_INT64, DT_UINT8, DT_UINT16, DT_QINT8, DT_BF16})) .OP_END_FACTORY_REG(Relu)

Its corresponding function prototype is:

• Function name: Relu(C++) or EsRelu(C)
• Parameters: 1 in total, which is x
• Return value: output y

C API:

EsCTensorHolder *EsRelu(EsCTensorHolder *x);

C++ API:

EsTensorHolder Relu(const EsTensorLike &x);

Note: Use TensorLike type to express input, to support case where actual parameter can directly pass numeric values

【免费下载链接】geGE（Graph Engine）是面向昇腾的图编译器和执行器，提供了计算图优化、多流并行、内存复用和模型下沉等技术手段，加速模型执行效率，减少模型内存占用。 GE 提供对 PyTorch、TensorFlow 前端的友好接入能力，并同时支持 onnx、pb 等主流模型格式的解析与编译。项目地址: https://gitcode.com/cann/ge