[Beowulf] Correct networking solution for 16-core nodes
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.
Scott Atchley atchley at myri.comThu Aug 3 14:00:06 PDT 2006
- Previous message: [Beowulf] Correct networking solution for 16-core nodes
- Next message: [Beowulf] Correct networking solution for 16-core nodes
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
>> Only quadrics is clear about its switch latency (probably >> competitors have a worse one). It's 50 us for 1 card. > > We have clearly stated that the Mellanox switch is around 200 usec per > hop. Myricom's number is also well known. Greg, Don't you mean 200 nanosec? Which is about the same for the Myrinet cross-bar. Scott -- Scott Atchley Myricom Inc. http://www.myri.com
- Previous message: [Beowulf] Correct networking solution for 16-core nodes
- Next message: [Beowulf] Correct networking solution for 16-core nodes
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list