Journal of Parallel and Distributed Computing ( IF 3.4 ) Pub Date : 2021-01-12 , DOI: 10.1016/j.jpdc.2021.01.004 Nuntipat Phisutthangkoon , Jeeraporn Werapun
Hypercube (HC) networks (N2) provide efficient communication for parallel-and-distributed computing (PDC) but the HC-based multi-processor (MP) system is costly and not scalable, while hierarchical hypercube (HHC) networks (N2, n2+m) are less expensive and more scalable. However, the traditional HHC-routing easily conflicts, especially when executing multiple tasks (k > 2 nodes-per-task). In the past, the node-disjoint-path routing could be used to avoid the conflict but that reliable (S, D) routing limited S(source)0. Later, the parallel N2N (node-to-node) disjoint-path was proposed for reliable routing but limited (m+1)/2 pairs-of-nodes. Therefore, this study proposes the generalized N2N shortest-path (SP) routing (with arbitrary S) and the parallel N2N SP-routing, based on our hypothesis “the shortest-path routing and the proper HHC-partitioning can avoid the HHC-conflict directly”. Next, our innovation and contribution are 1. the GCD (grouping of cross dual-cube) partitioning to solve the HHC-conflict for nodes-per-task, and 2. the SP-ATAPE (all-to-all personalized exchange) embedding on the HHC-MPs. The correctness of the SP-routing was proven and the ATAPE communication was experimented to validate our conflict solution. The ATAPE results confirmed that in any group the GCD mapping could make all tasks (k 2 nodes-per-task), synchronized with the same control, working without the conflict.
中文翻译:
最短路径路由,可在分层超立方体网络上实现最佳的全部到全部个性化交换嵌入
超立方体(HC)网络(N2)可为并行和分布式计算(PDC)提供有效的通信,但是基于HC的多处理器(MP)系统成本高昂且无法扩展,而分层超立方体(HHC)网络(N2,n2+ m)价格便宜,可扩展性更高。但是,传统的HHC路由很容易发生冲突,尤其是在执行多个任务时(k > 2每个任务节点数)。过去,可以使用节点不相交路径路由来避免冲突,但是可靠的(S,D)路由会限制S(源)0.随后,提出了并行的N 2 N(节点到节点)不相交路径以实现可靠的路由,但限制了(m +1)/ 2个节点对。因此,本研究提出了广义N 2 N最短路径(SP)路由(具有任意S)和并行N 2 N SP路由,基于我们的假设“最短路径路由和适当的HHC分区可以避免直接与HHC冲突”。接下来,我们的创新和贡献是1.解决GHC(交叉双多维数据集的分组)分区,以解决HHC冲突。每个任务节点,以及2.嵌入在HHC-MP上的SP-ATAPE(所有对所有个性化交换)。验证了SP路由的正确性,并通过ATAPE通信进行了实验以验证我们的冲突解决方案。ATAPE结果证实,在任何组中,GCD映射都可以完成所有任务(k 2 每个任务的节点数),与同一个控件同步,工作无冲突。