[mvapich-discuss] support for Mellanox/Voltaire FCA MPI Collective Accelerator

[Dhabaleswar Panda]

Hi Jeff,

Sure, we will do it. Thanks for your suggestion. We always incorporate new
features as runtime options so that users and system integrators will have
flexibility to enable/disable these features.

Thanks,

DK


> Dr. Panda,
>
> When you do implement, please make it a run time selectable option.
>
> Thanks,
>
> -Jeff
>
>
> /**********************************************************/
> /* Jeff Konz                          jeffrey.konz at hp.com */
> /* Solutions Architect                   HPC Benchmarking */
> /* Americas Shared Solutions Architecture (SSA)           */
> /* Hewlett-Packard Company                                */
> /* Office: 248-491-7480              Mobile: 248-345-6857 */
> /**********************************************************/
>
>
> > -----Original Message-----
> > From: Dhabaleswar Panda [mailto:panda at cse.ohio-state.edu]
> > Sent: Friday, September 02, 2011 12:05 PM
> > To: Konz, Jeffrey (SSA Solution Centers)
> > Cc: mvapich-discuss at cse.ohio-state.edu
> > Subject: Re: [mvapich-discuss] support for Mellanox/Voltaire FCA MPI
> > Collective Accelerator
> >
> > MVAPICH2 currently does not support this. However, support for native
> > collective offload and MPI non-blocking calls using Mellanox CORE-
> > Direct
> > feature will be available in upcoming MVAPICH2 releases.
> >
> > Thanks,
> >
> > DK
> >
> > > Does MVAPICH2 support the Mellanox/Voltaire FCA MPI Collective
> > Accelerator?
> > >
> > > If so, is this run time selectable?
> > >
> > > Thanks,
> > >
> > > -Jeff
> > >
> > > _______________________________________________
> > > mvapich-discuss mailing list
> > > mvapich-discuss at cse.ohio-state.edu
> > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss
> > >
>
>