Megafly: A Topology for Exascale Systems
Megafly: A Topology for Exascale Systems
复制标题
Megafly：百亿亿次系统的拓扑
DOI：
10.1007/978-3-319-92040-5_15
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Mike Parker
中科院分区：
文献类型：
--
作者：
Mario Flajslik;Eric Borch;Mike Parker
在本文中，我们探讨了适合未来需要支持超过五万个端点的百亿亿次系统的网络拓扑。随着以更高链路速度使用光学器件的必要性不断增加，一些更传统的拓扑（例如 Tori 和 Fat-Tree）在如此大规模的情况下变得异常昂贵。我们确定了两种具有成本效益的分层拓扑，一种是规范的 Dragonfly，另一种是 Dragonfly 拓扑的变体，我们称之为 Megafly。 Megafly 是一种间接分层拓扑，具有高路径多样性、灵活的锥形选项和丰富的可能的系统设计点。我们描述并分析了 Megafly 拓扑，以了解其与 Dragonfly 相比的主要特性和优势。此外，我们定义了 Megafly 锥形方案，可以实现系统性能与成本的良好平衡。我们的评估表明，Megafly 拓扑在各种流量模式下实现了与 Dragonfly 相同或更好的吞吐量，同时仅需要一半的虚拟通道即可实现无死锁路由。 Megafly 还提供了更好的公平性，这在同步流量模式（例如邻居交换）的评估中得到了体现。我们还在一个小型案例研究中展示了 Megafly 的设计灵活性以及成本与性能的权衡，该案例说明了构建高性能结构拓扑的挑战。
In this paper we explore network topologies suitable for future exascale systems that need to support over fifty thousand endpoints. With the increased necessity to use optics at higher link speeds, some of the more traditional topologies, such as Tori and Fat-Trees, become prohibitively expensive at such large scale. We identify two cost efficient hierarchical topologies, one a canonical Dragonfly, and one a variant of the Dragonfly topology that we call Megafly. Megafly is an indirect hierarchical topology with high path diversity, flexible tapering options and an abundance of possible system design points. We describe and analyze the Megafly topology to understand its key features and advantages, when compared to the Dragonfly. Additionally, we define a Megafly tapering scheme that enables a good balance of system performance versus cost. Our evaluation shows that the Megafly topology achieves equal or better throughput than the Dragonfly on a variety of traffic patterns, while requiring only half of the virtual channels for deadlock-free routing. Megafly also provides better fairness, which is shown in the evaluation of synchronizing traffic patterns, such as neighbor exchanges. We also showcase the design flexibility and cost vs. performance trade-offs of Megafly in a mini case study that illustrates the challenges of building a high performance fabric topology.
DOI：
10.1109/cluster.2015.57
发表时间：
2015-09
期刊：
2015 IEEE International Conference on Cluster Computing
影响因子：
--
作者：
Emily M. Hastings;David Rincon-Cruz;Marc Spehlmann;S. Meyers;Anda Xu;David P. Bunde;V. Leung
通讯作者：
Emily M. Hastings;David Rincon-Cruz;Marc Spehlmann;S. Meyers;Anda Xu;David P. Bunde;V. Leung