I've just recently joined because I, too, am working on a (possible) OpenMPI
component. The basics are: A Topology and Weight Evolving Artificial Neural
Network (TWEANN) that learns to configure point-to-point comm. on ob1
fabrics in various compute clusters given a context of existing schedules,
priorities and the cluster's working configuration at any given point in
time. The challenge is in learning to partition the (experiments)
software's tasks and data and to configure the compute fabric to run the mix
in an efficient and effective manner. The premise is that the fabric
represents a Theory of Constraints problem not currently addressed which
cannot be hardcoded or run on dr (using OS threaded schemes). This also
deals with "... When failing to load a component".
At any rate, that's the general idea.
> -----Original Message-----
> From: devel-bounces_at_[hidden]
> [mailto:devel-bounces_at_[hidden]] On Behalf Of Sylvain Jeaugey
> Sent: Monday, August 03, 2009 11:16 AM
> To: Open MPI Developers
> Subject: Re: [OMPI devel] [PATCH] Better error reporting when
> failing to load a component
> On Mon, 3 Aug 2009, Jeff Squyres wrote:
> > On Aug 3, 2009, at 8:23 AM, Arthur Huillet wrote:
> >> I have recently started working on OpenMPI, and part of my job
> >> consists in adding a new module to OpenMPI.
> > Cool. What are you adding?
> A collective component to support some Bull specific hardware.
> devel mailing list