Galen asked for a writeup of where the UD BTL support is at and what
(important) issues remain, so here it is.
Right now, to ensure MPI guaranteed delivery semantics the DR PML must
be used with UD -- the UD BTL does not implement its own reliability.
The best solution would be to implement a
Hello,
On Tuesday 19 June 2007 16:41, Brian Barrett wrote:
> >> Please raise Your hand if anybody cares.
> >
> > Sun cares very much about this for the exact reason you state (Binary
> > compatibility).
> > I'd prefer this ddt is placed at the end of the list.
>
> I think we should try to avoid bin
It's today. If there's time left on the main OMPI call, we'll do it
there. Otherwise, I'll tell everyone on today's call what the number
is for after the OMPI call.
On Jun 19, 2007, at 10:38 AM, Andrew Friedley wrote:
oops, was this yesterday? If it was today, whats the number?
Andrew
On Jun 19, 2007, at 8:35 AM, Terry D. Dontje wrote:
Rainer Keller wrote:
Hello dear all,
with the current numbering in mpif-common.h, the optional ddt
MPI_REAL2 will
break the binary compatibility of the fortran interface from v1.2 to
v1.3
(see r15133).
Now apart from MPI_REAL2 being of let's
Rainer Keller wrote:
Hello dear all,
with the current numbering in mpif-common.h, the optional ddt
MPI_REAL2 will
break the binary compatibility of the fortran interface from v1.2 to
v1.3
(see r15133).
Now apart from MPI_REAL2 being of let's say rather minor importance,
the group
may fea
oops, was this yesterday? If it was today, whats the number?
Andrew
Jeff Squyres wrote:
On Jun 13, 2007, at 3:38 PM, Andrew Friedley wrote:
I'd like to call in as some of this applies to UD as well, is that
okay?
Sounds good.
Andrew
Jeff Squyres wrote:
On Jun 13, 2007, at 2:41 PM, Gle
Hello dear all,
with the current numbering in mpif-common.h, the optional ddt MPI_REAL2 will
break the binary compatibility of the fortran interface from v1.2 to v1.3
(see r15133).
Now apart from MPI_REAL2 being of let's say rather minor importance, the group
may feal that the numbering of data
