全网格网络中不使用虚拟通道的无死锁路由
Deadlock-free routing for Full-mesh networks without using Virtual Channels
AI总结:
针对全网格网络,提出TERA路由算法,利用嵌入物理子网络实现无死锁非最短路径,无需虚拟通道,在对抗性流量下性能提升80%,缓冲区需求减少50%。
摘要:
高基数、低直径网络(如HyperX和Dragonfly)使用全网格核心,并依赖多个虚拟通道(VC)来避免自适应路由中的数据包死锁。然而,虚拟通道在面积、功耗和设计复杂度方面给交换机带来了显著开销,限制了交换机的可扩展性。本文首先重新审视了在全网格网络中通过链路排序方案实现的无虚拟通道路由,这些方案实现简单,但在对抗性流量下会出现性能下降。因此,为克服这些挑战,我们提出了TERA(拓扑嵌入路由算法),一种新颖的路由算法,它利用嵌入的物理子网络提供无死锁的非最短路径,而无需使用虚拟通道。在全网格网络中,处理对抗性流量时,TERA比链路排序路由算法性能提升80%,在应用内核中提升高达100%。此外,与其他基于虚拟通道的方法相比,它在保持相当延迟和吞吐量的同时,将缓冲区需求减少了50%。最后,2D-HyperX评估的初步结果显示,TERA优于使用相同数量虚拟通道的最先进算法,性能提升高达32%。
英文摘要:
High-radix, low-diameter networks like HyperX and Dragonfly use a Full-mesh core, and rely on multiple virtual channels (VCs) to avoid packet deadlocks in adaptive routing. However, VCs introduce significant overhead in the switch in terms of area, power, and design complexity, limiting the switch scalability. This paper starts by revisiting VC-less routing through link ordering schemes in Full-mesh networks, which offer implementation simplicity but suffer from performance degradation under adversarial traffic. Thus, to overcome these challenges, we propose TERA (Topology-Embedded Routing Algorithm), a novel routing algorithm which employs an embedded physical subnetwork to provide deadlock-free non-minimal paths without using VCs. In a Full-mesh network, TERA outperforms link ordering routing algorithms by 80% when dealing with adversarial traffic, and up to 100% in application kernels. Furthermore, compared to other VC-based approaches, it reduces buffer requirements by 50%, while maintaining comparable latency and throughput. Lastly, early results from a 2D-HyperX evaluation show that TERA outperforms state-of-the-art algorithms that use the same number of VCs, achieving performance improvements of up to 32%.
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。