arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05371cs.DC
收藏

Nvidia GPU单设备和多设备同步方法研究

A Study of Single and Multi-device Synchronization Methods in Nvidia GPUs

Lingqi Zhang, Mohamed Wahib, Haoyu Zhang, Satoshi Matsuoka

摘要:

GPU在通用计算中发挥着越来越重要的作用。许多算法需要在单个GPU中以不同的粒度级别进行同步。此外,密集GPU节点的出现也要求多GPU同步。Nvidia最新的CUDA提供了多种同步方法。到目前为止,还没有充分了解这些同步方法的特点。这项工作探讨了重要的未记录功能,并深入分析了Nvidia GPU最先进的同步方法的性能考虑因素和缺陷。在为运行在单GPU和/或多GPU环境上的应用程序、库和框架做出设计选择时,所提供的分析将非常有用。我们提供了一个常用的约简算子的案例研究,以说明在我们的分析中获得的知识如何有用。我们还描述了我们的微观基准和测量方法。

英文摘要:

GPUs are playing an increasingly important role in general-purpose computing. Many algorithms require synchronizations at different levels of granularity in a single GPU. Additionally, the emergence of dense GPU nodes also calls for multi-GPU synchronization. Nvidia's latest CUDA provides a variety of synchronization methods. Until now, there is no full understanding of the characteristics of those synchronization methods. This work explores important undocumented features and provides an in-depth analysis of the performance considerations and pitfalls of the state-of-art synchronization methods for Nvidia GPUs. The provided analysis would be useful when making design choices for applications, libraries, and frameworks running on single and/or multi-GPU environments. We provide a case study of the commonly used reduction operator to illustrate how the knowledge gained in our analysis can be useful. We also describe our micro-benchmarks and measurement methods.

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。

↑