[Beowulf] bandwidth: who needs it?
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.
Jim Lux james.p.lux at jpl.nasa.govThu Oct 21 11:53:17 PDT 2004
- Previous message: [Beowulf] bandwidth: who needs it?
- Next message: [Beowulf] bandwidth: who needs it?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Bandwidth is also important if you have any sort of "store and forward" process in the comm link (say, in a switch), because, typically, you have to wait for the entire message to arrive (so you can check the CRCC) before you can send it on it's way to the next destination. I'm sure that there are high performance switches around that only wait 'til enough of the header arrives to make the routing decision, but then, the switch has to passively pass the data through without error checking. ----- Original Message ----- From: "Greg Lindahl" <lindahl at pathscale.com> To: "Mark Hahn" <hahn at physics.mcmaster.ca> Cc: <Beowulf at beowulf.org> Sent: Thursday, October 21, 2004 10:58 AM Subject: Re: [Beowulf] bandwidth: who needs it? > > do you have applications that are pushing the limits of MPI bandwidth? > > for instance, code that actually comes close to using the 8-900 MB/s > > that current high-end interconnect provides? > > Bandwidth is important not only for huge messages that hit 900 MB/s, > but also for medium sized messages. A naive formula for how long it > takes to send a message is: <snip>
- Previous message: [Beowulf] bandwidth: who needs it?
- Next message: [Beowulf] bandwidth: who needs it?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
