As promised during the last week phone-call I will go over all pending
ticket on the 1.3.4 release and ask their owner about the status of
the ticket. There are few tickets without an owner, so the RMs will
make the decision regarding their status. However, just in case one of
you is intere
Retrying w/ fewer CQ entires as Jeff describes is a good idea to help
ensure that EINVAL actually does signify that the count exceeds the max
instead of just assuming this is so). If it actually was signifying
some other error case, then one would probably not want to continue.
-Paul
Jeff Sq
Thanks for the analysis!
We've argued about btl_r2_add_btls() before -- IIRC, the consensus is
that we want it to be able to continue even if a BTL fails. So I
*think* that your #1 answer is better.
However, we might want to try a little harder if EINVAL is returned --
perhaps try decrea
- "Jeff Squyres" wrote:
> WHAT: Change OMPI's verbose build output to use
> Automake's new "silent" rules output (see below)
Not that I'm a developer, but as someone who regularly
builds OMPI I'd be very happy with this change.
cheers!
Chris
--
Christopher Samuel - (03) 9925 4751 - System
On Oct 21, 2009, at 5:43 PM, Lisandro Dalcin wrote:
Currently (trunk, just svn update'd), the following call fails
(because of the ranks=NULL pointer)
MPI_Group_{incl|excl}(group, 0, NULL, &newgroup)
Agreed; bug. I think there's a little wiggle room in the spec wording
that it may or may
On Mon, 2009-10-26 at 13:56 -0700, Paul H. Hargrove wrote:
> IANAL, but...
>
> Ashley,
> There is no copyright message or other identifying comment in this
> script. So I must ask: what is the origin of this script and may one
> legally redistribute it? If I like it enough I might want to p
IANAL, but...
Ashley,
There is no copyright message or other identifying comment in this
script. So I must ask: what is the origin of this script and may one
legally redistribute it? If I like it enough I might want to package
it with one of the projects I work on.
-Paul
Ashley Pittman
On Mon, 2009-10-26 at 10:42 -0400, Jeff Squyres wrote:
> WHY: Tidy up the output from "make all"; a nice side effect is that it
> becomes significantly easier to see compiler warnings
> Thoughts / comments?
Somewhat tangential but I find the attached script helpful in this
regard, it'll forwar
Jeff,
You are exactly right. I had a typo in the declaration of one of the
arguments, and I had neglected to use "Implicit None". I should know
better than to leave out "Implicit None".
Thanks for the diagnosis.
Larry Baker
US Geological Survey
650-329-5608
ba...@usgs.gov
On Oct 26, 200
On Oct 15, 2009, at 9:28 PM, Larry Baker wrote:
../src/run_nnlsqs_mpi.f(39): error #6285: There is no matching
specific subroutine for this generic subroutine call.
[MPI_CART_SHIFT]
Call MPI_CART_SHIFT( mpi_comm_grid, direction, amount,
-^
Sorry for the delay in reply
On Oct 26, 2009, at 11:14 AM, George Bosilca wrote:
While these emails might have crossed on the wire, the patches
regarding the revamping of the configure framework have been pushed
into the trunk before the RFC ... And this is what Rainer is
referring too.
Understood. Please see my e
While these emails might have crossed on the wire, the patches
regarding the revamping of the configure framework have been pushed
into the trunk before the RFC ... And this is what Rainer is referring
too.
george.
On Oct 26, 2009, at 10:23 , Jeff Squyres wrote:
It looks like Rainer's
WHAT: Change OMPI's verbose build output to use Automake's new
"silent" rules output (see below)
WHEN: For the 1.5 series (no particular release targeted)
WHY: Tidy up the output from "make all"; a nice side effect is that it
becomes significantly easier to see compiler warnings
WHERE: con
It looks like Rainer's an my emails crossed in the ether:
http://www.open-mpi.org/community/lists/devel/2009/10/7022.php
On Oct 26, 2009, at 9:27 AM, Rainer Keller wrote:
Dear all,
the patches to split the configure-magic into sub-project related
config-
directories is certainly of the t
Dear all,
the patches to split the configure-magic into sub-project related config-
directories is certainly of the type "Doing the Right Thing" and as discussed
in a private conversation I appreciate the effort.
However, in the light of last weeks breakage and considering the criticism
others h
WHAT: Split configury across the opal, orte, and ompi trees as relevant.
WHERE: mostly configure.ac, config/, opal/config/, orte/config/, and
ompi/config/, and various component configure.m4 scripts
WHY: To fix autogen's -no-ompi feature, fix the opalc++ and ortec++
wrapper compilers, and i
16 matches
Mail list logo
