[Beowulf] Has anyone actually seen/used a cell system?
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Larry Stewart larry.stewart at sicortex.comThu Sep 21 07:43:31 PDT 2006
- Previous message: [Beowulf] AMD Opteron Linpack Benchmark
- Next message: [Beowulf] Your thoughts on use of NUMA-based systems in clusters?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
When I went looking for papers on the Cell Processor memory system, I eventually found this one. The Berkeley paper and this one are the most useful I have found so far. http://portal.acm.org/citation.cfm?id=1158825.1159067 Cell Multiprocessor Communication Network: Built for Speed by Kistler (IBM), Perrone (IBM) and Petrini (PNNL) It was published in IEEE MICRO, but those of you who have access to the ACM/IEEE Computer digital libraries can get it. This paper has a frothy title, but you can puzzle out real information by looking at the graphs closely. (Redundant - the UCB paper is at http://www.cs.berkeley.edu/~samw/projects/cell/CF06.pdf ) -Larry **
- Previous message: [Beowulf] AMD Opteron Linpack Benchmark
- Next message: [Beowulf] Your thoughts on use of NUMA-based systems in clusters?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
