Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: Re: [OMPI devel] RFC: Remove heterogeneous support
From: Jeff Squyres (jsquyres) (jsquyres_at_[hidden])
Date: 2014-04-30 16:15:22


Ok, fair enough; thanks. That's a pretty good reason to not chop it any time soon (and it's not like there's any pressure to do/not do something immediately).

Can you keep us informed -- e.g., if your requirement ever does disappear and it would be safe to delete this functionality from OMPI? (I'm not saying we *would* delete it, but if a community member changes their stance from "there's a nonzero chance we're going to need it" to "we're not going to use it", that would be a very helpful data point).

Thanks.

On Apr 30, 2014, at 12:44 PM, Joshua Ladd <jladd.mlnx_at_[hidden]> wrote:

> Hi, OMPI Community
>
> On the call yesterday, Ralph and Jeff posed the question to the Community at large and to NVIDIA in particular if they/we/us have a vested interest in heterogeneous support. Mellanox and NVIDIA are partnering on systems that, on today's roadmap, could require heterogeneous support from the underlying MPI. At the moment, it's not known if this will remain an issue. Today it appears it is, but tomorrow it may not be. So, anyhow, to answer the question: Yes, there are core OMPI developers and industrial partners for whom this support appears to be important given the current state of the art.
>
> Best regards,
>
> Josh
>
> Joshua S. Ladd, PhD
> Staff Engineer, HPC Software
> Mellanox Technologies
>
> Email: joshual_at_[hidden]
>
>
>
> On Mon, Apr 28, 2014 at 2:00 PM, Nathan Hjelm <hjelmn_at_[hidden]> wrote:
> On Mon, Apr 28, 2014 at 01:58:13PM -0400, George Bosilca wrote:
> > My concern was more about the “what" factor: what do you write on remote memory in a heterogeneous case. I imagine you can either write the converted data or you can convert remotely after writing. Anyway, on both cases you need intermediary buffers to do the conversion (especially if we are looking a size mismatch), so the interest of RMA is quickly vanishing.
> >
> > For now, I would just not support heterogeneous environments for RMA. We might want to add a check at windows creation time, so at least the users are warned.
>
> Good point. I will look at adding a warning now.
>
> -Nathan
>
> _______________________________________________
> devel mailing list
> devel_at_[hidden]
> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel
> Link to this post: http://www.open-mpi.org/community/lists/devel/2014/04/14639.php
>
> _______________________________________________
> devel mailing list
> devel_at_[hidden]
> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel
> Link to this post: http://www.open-mpi.org/community/lists/devel/2014/04/14659.php

-- 
Jeff Squyres
jsquyres_at_[hidden]
For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/