Files
openmlsys-zh/chapter_accelerator/index.md
Corleone 039787dc8d sync overleaf for acceleerator (#420)
Co-authored-by: Corleone <liuchao195@huawei.com>
Co-authored-by: Jiarong Han <jiaronghan@outlook.com>
2023-02-17 10:16:44 +08:00

25 lines
979 B
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# 硬件加速器
上一章节详细讨论了后端的计算图优化、算子选择以及内存分配。当前主流深度学习模型大多基于神经网络实现无论是训练还是推理都会产生海量的计算任务尤其是涉及矩阵乘法这种高计算任务的算子。然而通用处理器芯片如CPU在执行这类算子时通常耗时较大难以满足训练和推理任务的需求。因此工业界和学术界都将目光投向特定领域的加速器芯片设计希望以此来解决算力资源不足的问题。
本章将会着重介绍加速器的基本组成原理,并且以矩阵乘法为例,介绍在加速器上的编程方式及优化方法。
本章的学习目标包括:
- 掌握加速器的基本组成
- 掌握矩阵乘法的常见优化手段
- 理解编程API的设计理念
```toc
:maxdepth: 2
accelerator_introduction
accelerator_architecture
accelerator_programming
accelerator_practise
summary
```