Improved internode communication for tile QR decomposition for multicore cluster systems
Improved internode communication for tile QR decomposition for multicore cluster systems
复制标题
改进了多核集群系统瓦片 QR 分解的节点间通信
DOI：
10.1109/ipdpsw.2015.145
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Tomohiro Suzuki
中科院分区：
文献类型：
--
作者：
Thanyarat Jitpeera;Paphawadee Netsuwan;Tamaki Tanaka;Poom Kumam;Tomohiro Suzuki
矩阵分解的瓦片算法可以生成许多细粒度的任务。因此，他们的适用性处理与多课程体系结构引起了高度重视，从高性能计算（HPC）社区。我们实现的瓷砖QR分解的集群系统具有动态调度，OpenMP工作共享，和其他有用的功能。在本文中，我们将讨论在我们以前的实现中出现的节点间通信问题。改进后的实现具有较强和较弱的可扩展性。
Tile algorithms for matrix decomposition can generate many fine-grained tasks. Therefore, their suitability for processing with multicourse architecture has attracted much attention from the high-performance computing (HPC) community. Our implementation of tile QR decomposition for a cluster system has dynamic scheduling, OpenMP work- sharing, and other useful features. In this article, we discuss the problems in internodes communications that were present in our previous implementation. The improved implementation has both strong and weak scalability.