The Columbia project at NASA Ames includes twenty 512 processor Altix systems. Four of those systems are joined together into a Numalink based globally accessible non-coherent memory Altix SuperCluster. PBSPro 7.0 and 7.1 have been used to schedule and run work on this system. In this presentation, we will go over features of PBSPro especially applicable to such systems, some problems we have encountered and how they have been addressed, and remaining, unresolved issues.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
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.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.