On Fri, Jun 14, 2013 at 10:53:24PM +0000, Jeff Squyres (jsquyres) wrote:
> On Jun 12, 2013, at 5:47 PM, Jason Gunthorpe 
> <[email protected]> wrote:
> 
> > Someone has to finish the ummunotify rewrite Roland
> > started. Realistically MPI is going to be the only user, can someone
> > from the MPI world do this?
> 
> 1. I tried to ask what needed to be done at the beginning of this
> thread and didn't get much of an answer.

AFAIK, only Roland knows the state of his rewrite, hopefully he will
comment.. I told you everything I know about what happened with the
last attempt :|

> 2. We've (all) been asking for this functionality *for years*; I
> even helped with the first implementation.  Can't the verbs
> community finish it?  :-) MPI is probably your biggest customer,
> after all...

There isn't much of a verbs community, to be honest. Unless you can
get a vendor to commit resources to the project, I wouldn't expect
much.

> I have no doubt that ODP solves problems for someone.  It just
> doesn't seem to solve the very-long-standing MPI issues with verbs
> and registration caches.

As we've discussed it helps write a registration cache.

The 'All of address space' varient that Haggai mentioned should also
be very interesting.

But this is all future stuff.

FWIW, I agree with you that ummunot is something MPI really needs to
function.

Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to