Product Introduction

• You agree to comply with national laws, regulations, and public ethics when using the Kunpeng BoostKit Homogeneous Acceleration Framework (HAF). You shall not use HAF to engage in any activities that violate the law, infringe on the rights and interests of others, interrupt social order, undermine social stability, or engage in any activities that endanger or attempt to endanger the computer system and network security.

• You agree that Huawei shall assume no liability for any indirect, incidental, special, or any form of punitive damages, or any loss of profits, revenue, data, or data use.
• You acknowledge and agree that you need to download and integrate the open source and third-party software on which the software package of HAF depends. Huawei does not assume any responsibility for the software vulnerabilities and security issues.

HAF provides user-friendly programming methods and application programming interfaces (APIs) to quickly, effectively, and securely push specified acceleration segments of your service programs to offload nodes, optimizing the offload effect. To accelerate diversified computing that is underlain by a wide range of hardware, HAF offers components such as compiler plugins and device/host runtime services to construct a directives-based programming acceleration framework. You can add Java annotations to service code and compile the code. Then the acceleration job of code execution is automatically pushed to the intelligent acceleration component to achieve a better acceleration effect.

HAF has the following features:

• Provides a set of user-friendly Java annotation capabilities and compilation plugins, allowing you to add acceleration annotations to proper positions of your service logic code. During compilation, you can invoke the HAF compilation plugin to automatically generate logic blocks of offload push execution, which use the HAF runtime library to implement offload push.
• Enables specified logical blocks of a user service to be pushed to a specified offload node.