Pathscale InfiniPath: a first look
暂无分享,去创建一个
Clusters are now a dominant model for high-capacity, scalable computing based on a commodity cost structure. This paper describes the first generation PathScale/spl trade/ InfiniPath/spl trade/ adapter - a single chip ASIC directly connecting HyperTransport/spl trade/ attached processors, such as the AMD Opteron/spl trade/, to the InfiniBand/spl trade/ network fabric. In addition to providing ultra-low communications latency, the PathScale InfiniPath adapter achieves high bandwidth from very small to large message sizes. Its performance also scales on multi-core processor nodes. Use of the InfiniBand switching fabric permits high bandwidth to be realized at a commodity fabric price point.
[1] G.E. Moore,et al. Cramming More Components Onto Integrated Circuits , 1998, Proceedings of the IEEE.
[2] David A. Patterson,et al. Latency Lags Bandwidth , 2005, ICCD.
[3] William Gropp,et al. Users guide for mpich, a portable implementation of MPI , 1996 .
[4] David A. Patterson,et al. Latency lags bandwith , 2004, CACM.