arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.05737cs.LGcs.PF
收藏

一种用于神经网络推理的JIT算法

A JIT Compiler for Neural Network Inference

Universität Bremen(不来梅大学)

Felix Thielke, Arne Hasselbring

摘要:

本文描述了一个C++库,它在运行时将神经网络模型编译成执行推理的机器码。这种方法通常有望实现最佳性能,因为它能够将网络的静态已知属性直接集成到代码中。在我们对NAO V6平台的实验中,它在小型网络上的性能明显优于现有的实现,而在大型网络上则表现较差。该库已经是2018年B-Human代码版本的一部分,但此后一直在扩展,现在作为独立版本提供,可以集成到任何C++14代码库中。

英文摘要:

This paper describes a C++ library that compiles neural network models at runtime into machine code that performs inference. This approach in general promises to achieve the best performance possible since it is able to integrate statically known properties of the network directly into the code. In our experiments on the NAO V6 platform, it outperforms existing implementations significantly on small networks, while being inferior on large networks. The library was already part of the B-Human code release 2018, but has been extended since and is now available as a standalone version that can be integrated into any C++14 code base.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑