[Beowulf] SC|05: will 10Ge beat IB?
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.
Greg Lindahl lindahl at pathscale.comMon Nov 21 20:42:41 PST 2005
- Previous message: [Beowulf] SC|05: will 10Ge beat IB?
- Next message: [Beowulf] CfP: Second IEEE Workshop on High Performance Computing in Medicine and Biology
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
> further, there was also LOTS of 10G ethernet this year, and I have > to wonder: will 10G squeeze IB out of the market? Which market? There's no question that outside the high-end of HPC, 10G ethernet will eventually win. Like the past couple of ethernet transitions we've all witnessed, Ethernet will be late and more expensive than predicted, and by the time it's really cheap, the high end will be at a higher bandwidth. And non-Ethernet will always win on latency. Then it comes down to: what fraction of the market will find 10G ethernet to be good enough? My bet (look at my employer) is that it will be about the same fraction that was happy with gigabit ethernet a couple of years ago. These things go in cycles, they don't really change. -- greg (employed by, not speaking for, PathScale.)
- Previous message: [Beowulf] SC|05: will 10Ge beat IB?
- Next message: [Beowulf] CfP: Second IEEE Workshop on High Performance Computing in Medicine and Biology
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
