Title :
Designing next generation clusters with InfiniBand and 10GE/iWARP: Opportunities and challenges
Author :
Panda, Dhabaleswar K DK
Author_Institution :
Ohio State Univ., Columbus, OH
fDate :
Sept. 29 2008-Oct. 1 2008
Abstract :
Clusters with commodity multi-core processors and commodity networking technologies are providing cost-effective solutions for building next generation high-end systems including HPC clusters, servers, parallel file systems and multi-tier data-centers. The talk focus on two emerging networking technologies (InfiniBand and 10 GE/iWARP) and their associated protocols for designing such systems. In this talk, we critically examine the current and future trends of these technologies and their applicability for designing next generation petascale clusters. The talk start with the motivations behind these technologies and then focus on their architectural aspects and applicability to SAN, LAN and WAN-based clusters. Designing next generation clusters with high performance, scalability and RAS (reliability, availability and serviceability) capabilities by using these technologies will be examined. Current and future trends of InfiniBand and iWARP products was highlighted. The emerging OpenFabrics software stack, focusing both these technologies in an integrated manner, was presented. Finally, a set of case studies in designing various clusters with these networking technologies was presented to outline the associated opportunities and challenges.
Keywords :
local area networks; protocols; storage area networks; wide area networks; 10 GE/iWARP; HPC clusters; InfiniBand; LAN-based clusters; OpenFabrics software stack; SAN-based clusters; WAN-based clusters; commodity multicore processors; commodity networking technologies; multitier data-centers; parallel file systems; petascale clusters; protocols; servers; Buildings; File servers; File systems; Local area networks; Multicore processing; Network servers; Next generation networking; Protocols; Scalability; Storage area networks;
Conference_Titel :
Cluster Computing, 2008 IEEE International Conference on
Conference_Location :
Tsukuba
Print_ISBN :
978-1-4244-2639-3
Electronic_ISBN :
1552-5244
DOI :
10.1109/CLUSTR.2008.4663772