An Efficient All-to-all Communication Algorithm for Mesh/Torus Networks
An Efficient All-to-all Communication Algorithm for Mesh/Torus Networks
复制标题
DOI：
10.1109/ispa.2012.44
复制
发表时间：
2012-07
期刊：
影响因子：
--
通讯作者：
S. Yazaki;Haruyuki Takaue;Yuichiro Ajima;T. Shimizu;H. Ishihata
中科院分区：
文献类型：
--
作者：
S. Yazaki;Haruyuki Takaue;Yuichiro Ajima;T. Shimizu;H. Ishihata
提出了一种适用于环形网和网状网的全对全通信算法A2 AT。A2 AT利用节点的并发消息传输功能，对消息发送顺序进行调度，使所有链路都得到充分利用。通过使用A2 AT，消息的跳数等于在所有消息传输的路由中共享链路的最大消息数。因此，A2 AT可以保持同步，而不需要相位操作，如MPI屏障。当使用作为A2 AT的理想配置的VOQ时，通过A2 AT获得的mesh/torus网络的通信时间平均比理想时间高大约1.20和1.09倍。当网络中虚拟信道数最少且缓冲区较小时，在实际网络中，A2 AT算法与传统算法相比，通信时间分别减少了12.5%和36.0%。在15×15×15（= 3，375个节点）mesh和torus网络上，当使用两个控制器时，A2 AT比A2 AND分别减少了28.2%和55.7%的通信时间（平均减少18.6%和44.8%）。在相同的mesh网络和torus网络上，当使用6个控制器时，A2 AT与A2 AND相比，通信时间分别减少了15.1%和41.9%，平均减少了14.4%和37.5%。
An efficient all-to-all communication algorithm for torus and mesh networks, A2AT, was proposed. A2AT schedules message sending sequence so that all links are fully used by exploiting function of concurrent message transfer in the node. By using A2AT, the hop count of messages equals the maximum number of messages sharing a link in their routes for all message transfers. A2AT can therefore maintain synchronization without the need for phasing operation such as an MPI barrier. When the VOQ which is an ideal configuration for A2AT was used, communication times for mesh/torus network obtained by A2AT were roughly 1.20 and 1.09 times higher, on average, than those of the ideal times. When the networks had the minimum number of virtual channels and a small buffer, assuming a practical network, A2AT was able to reduce communication times by 12.5% and 36.0% compared with those of the conventional algorithm. When two controllers are used, A2AT reduced 28.2% and 55.7% communication time with those by A2AND on 15×15×15 (=3,375 nodes) mesh and torus networks respectively (18.6% and 44.8% in average). A2AT also reduced 15.1% and 41.9% of communication time with those by A2AND on the same mesh and torus networks respectively (14.4% and 37.5% in average) when six controllers are used.