I-Cluster: Intense computing with untapped resources

Richard, Bruno ; Augerat, Philippe

HP Development Company

关键词: cluster;    scientific computing;    peer-to-peer;    supercomputing;   

RP-ID  :  HPL-2002-81

学科分类：计算机科学（综合）

美国|英语

来源: HP Labs

【 摘 要 】

I-Cluster is a research initiative from HP Labs Grenoble in partnership with INRIA (ID-IMAG Laboratory). It provides a distributed Peer-to-Peer framework of tools that transparently take advantage of unused network resources and federate them to crystallize into specific virtual functions. These functions are compute-intensive services, which are statically decomposed to fit the I-Cluster framework, then dynamically recomposed upon users needs. Typical I-Cluster functions are supercomputing, content rendering, content distribution. The I-Cluster experimentation platform, based on 225 typical desktop machines has been benchmarked as the 385th most powerful supercomputer in the world using Linpack, making it the first cluster based on mainstream technologies to enter the TOP500 in May 2001. This paper introduces the I-Cluster initiative and its overall architecture, and describes the prospects addressed by the research team. These include scaling conventional clustering tools to large number of machines, solving Peer-to-Peer computing security issues using OS sandboxing, self-organization and resilience to unanticipated disconnections of a large and heterogeneous community of computers, and automatic resource collection. Notes: Copyright National Technological University Press. To be published in and presented at the 4th International Conference on Massively Parallel Computing Systems, 10-12 April 2002, Ischia, Italy 7 Pages