An Ultrahigh Performance MPI Implementation on SGI® ccNUMA Altix® Systems
Karl Feind, Kim McMahon · Computational Methods in Science and Technology · 2006
The SGI ® Message Passing Toolkit (MPT) software has implemented algorithms that provide extremely high-performance message passing on SGI Altix ® systems based on the SGI NUMAlink™ interconnect technology.Using Linux ® OS infrastructure and SGI XPMEM cross-host memory-mapping software, SGI MPI delivers extremely high MPI performance on shared-memory single host/SMP Altix systems as well as multihost superclusters.This paper outlines the Altix hardware features, OS features, and library software algorithms that have been developed to provide the low-latency and high-bandwidth capabilities.We present high-performance features like direct copy send/receive, collectives, and the ultralow-latency SHMEM™ data transfer library.We include MPI benchmark results, including an MPI ping pong latency that ranges from 1.2 to 2.3 microseconds on a 512-CPU Altix system with 1.5 GHz Intel ® Itanium ® 2 Processors.