[Beowulf] more news on the Cell
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.
Karsten Petersen Karsten.Petersen at megware.deFri Jul 1 00:55:40 PDT 2005
- Previous message: [Beowulf] WRF model on linux cluster: Mpi problem
- Next message: [Beowulf] [gorelsky@stanford.edu: CCL:dual-core Opteron 275 performance]
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Hi Eugen Leitl wrote: > http://www-128.ibm.com/developerworks/power/library/pa-cell/?ca=dgr-pow03SpufsCell > > also, see http://www.research.scea.com/research/html/CellGDC05/index.html Regarding the cell: I think it was pretty demonstrative by IBM to show the cell chip at Linuxtag2005 but not at ISC2005 (although IBM was the main sponsor and even had a BlueGene box there). Asked about this, the IBM guys conceded that they do not really see the cell chip within the HPC market. Some participants at ISC also discussed if it will be possible to port e.g. blas/lapack to the cell architecture and in what amount it will be able to do double precision float operations. (It seems to be optimized for single precision!) BTW: When it comes to raw numbercrunching power, the ClearSpeed coprocessor card looks promising, too. Best wishes Karsten -- HPC System Engineer MEGWARE Computer GmbH http://www.megware.com
- Previous message: [Beowulf] WRF model on linux cluster: Mpi problem
- Next message: [Beowulf] [gorelsky@stanford.edu: CCL:dual-core Opteron 275 performance]
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
