arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.22262cs.AR
收藏

面向大规模多小芯片加速器的人工智能工作负载通信特征分析

Communication Characterization of AI Workloads for Large-scale Multi-chiplet Accelerators

Mariam Musavi, Emmanuel Irabor, Abhijit Das, Eduard Alarcon, Sergi Abadal

AI总结:

针对下一代AI工作负载的数据密集型特征带来的可扩展性挑战,本文分析多小芯片加速器架构上AI工作负载的通信特征,发现多播流量易成性能瓶颈,建议设计小芯片级灵活互连方案以提升加速器性能与可扩展性。

摘要:

下一代人工智能(AI)工作负载因其固有的、不断发展的数据密集型特征,在执行时间方面带来了可扩展性和鲁棒性挑战。本文旨在分析由多小芯片组成的横向扩展加速器架构上,AI工作负载的数据移动特征所导致的潜在瓶颈。我们的方法捕获一组AI工作负载的单播和多播通信流量,并评估通信耗时、多播消息数量随所用小芯片数量变化等方面。研究表明,部分AI工作负载易受通信(尤其是多播流量)主导效应的影响,这可能成为性能瓶颈并限制其可扩展性。工作负载分析洞察建议,在小芯片层面设计灵活的互连解决方案,以提升下一代AI加速器的性能、效率和可扩展性。

英文摘要:

Next-generation artificial intelligence (AI) workloads are posing challenges of scalability and robustness in terms of execution time due to their intrinsic evolving data-intensive characteristics. In this paper, we aim to analyse the potential bottlenecks caused due to data movement characteristics of AI workloads on scale-out accelerator architectures composed of multiple chiplets. Our methodology captures the unicast and multicast communication traffic of a set of AI workloads and assesses aspects such as the time spent in such communications and the amount of multicast messages as a function of the number of employed chiplets. Our studies reveal that some AI workloads are potentially vulnerable to the dominant effects of communication, especially multicast traffic, which can become a performance bottleneck and limit their scalability. Workload profiling insights suggest to architect a flexible interconnect solution at chiplet level in order to improve the performance, efficiency and scalability of next-generation AI accelerators.

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。

↑