[Beowulf] IB in the real world
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.
Steffen Persvold sp at scali.comSun May 15 20:35:53 PDT 2005
- Previous message: [Beowulf] IB in the real world
- Next message: [Beowulf] IB in the real world
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Thu, 2005-05-12 at 16:58 -0700, Josh England wrote: > On Thu, 2005-05-12 at 14:32 -0700, Bill Broadley wrote: [] > > > > 2. How good is the OpenIB+MPI stack(s)? Any reliable enough for large > > month long jobs? > > No MPI has been ported to the OpenIB stack yet. The verbs > implementation was just completed a couple months ago. I believe a few > efforts are currently underway. If you want MPI, you're stuck with a > vendor's IB stack for a little while yet. Not entirely true. The Scali MPI use uDAPL and AFAIK OpenIB provides a uDAPL interface. I don't know how good the uDAPL implementation is though since I haven't tested it. So basically, when the OpenIB stack matures, there are MPI solutions that is ready to use it already... -- Steffen
- Previous message: [Beowulf] IB in the real world
- Next message: [Beowulf] IB in the real world
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
