Creating nightly hwloc snapshot SVN tarball was a success.
Snapshot: hwloc 1.1a1r2166
Start time: Fri May 28 21:01:05 EDT 2010
End time: Fri May 28 21:03:03 EDT 2010
Your friendly daemon,
Cyrador
To that point, where exactly in the openib BTL init / query sequence is it
returning an error for you, Sylvain? Is it just a matter of tidying something
up properly before returning the error?
On May 28, 2010, at 2:21 PM, George Bosilca wrote:
> On May 28, 2010, at 10:03 , Sylvain Jeaugey
On May 28, 2010, at 10:03 , Sylvain Jeaugey wrote:
> On Fri, 28 May 2010, Jeff Squyres wrote:
>
>> On May 28, 2010, at 9:32 AM, Jeff Squyres wrote:
>>
>>> Understood, and I agreed that the bug should be fixed. Patches would be
>>> welcome. :-)
> I sent a patch on the bml layer in my first
bgog...@osl.iu.edu, le Fri 28 May 2010 11:27:47 -0400, a écrit :
> Add a backend info string, except in XML since we may not want to override
> the one that we got from the XML file
>
> + add_object_info(topology->levels[0][0], strdup("Backend=AIX"));
Mmm, this will probably need to be
Posted:
http://www.open-mpi.org/software/hwloc/v1.0/
(I was assuming we'd need at least an rc2, so I went ahead and did this before
bringing over the NEWS bullets)
--
Jeff Squyres
jsquy...@cisco.com
For corporate legal information go to:
Le 28/05/2010 17:17, Jeff Squyres a écrit :
Please look over the points I just drafted for v1.0.1; add / edit / delete as
necessary.
Looks good.
I like citing users who have been helpful in the NEWS file; it's a (small) way of
saying "thank you!".
Me too.
Brice
Please look over the points I just drafted for v1.0.1; add / edit / delete as
necessary. I like citing users who have been helpful in the NEWS file; it's a
(small) way of saying "thank you!".
When we're done, we can copy the finished points to the v1.0 branch NEWS file.
Thanks!
Begin
On Fri, 28 May 2010, Jeff Squyres wrote:
On May 28, 2010, at 9:32 AM, Jeff Squyres wrote:
Understood, and I agreed that the bug should be fixed. Patches would
be welcome. :-)
I sent a patch on the bml layer in my first e-mail. We will apply it on
our tree, but as always we're trying to
On May 28, 2010, at 7:19 AM, Sylvain Jeaugey wrote:
> So please, fix the bug first, then if you want that "automatic failover to
> TCP" feature, develop it. Put a parameter for an eventual notification, or
> abort, or whatever you want. But it doesn't exist today. It just doesn't
> work, with any
Jeff Squyres, le Fri 28 May 2010 09:03:30 -0400, a écrit :
> On May 28, 2010, at 9:01 AM, Samuel Thibault wrote:
>
> > > ...actually, I'm not seeing where we use epstopdf in our build process...?
> >
> > I believe it's hidden somewhere in pdflatex or such call.
>
> Is it our responsibility to
On May 28, 2010, at 9:01 AM, Samuel Thibault wrote:
> > ...actually, I'm not seeing where we use epstopdf in our build process...?
>
> I believe it's hidden somewhere in pdflatex or such call.
Is it our responsibility to check for it, then?
--
Jeff Squyres
jsquy...@cisco.com
For corporate
On May 28, 2010, at 7:27 AM, Brice Goglin wrote:
> I am not sure where/how to do #1 so I'll be happy if you do it :)
...actually, I'm not seeing where we use epstopdf in our build process...?
Is it invoked indirectly by some other tool? It doesn't seem to be invoked at
all on my Mac.
--
I am not sure where/how to do #1 so I'll be happy if you do it :)
Brice
Le 28/05/2010 12:24, Jeff Squyres (jsquyres) a écrit :
Both sound fine to me.
Do you want to do #1 or do you want me to do it?
-jms
Sent from my PDA. No type good.
- Original Message -
From:
On Fri, 28 May 2010, Jeff Squyres wrote:
Herein lies the quandary: we don't/can't know the user or sysadmin
intent. They may not care if the IB is borked -- they might just want
the job to fall over to TCP and continue. But they may care a lot if IB
is borked -- they might want the job to
Good call; thanks for the reminder. Thankfully, hwloc doesn't suffer from such
issues (I just sanity checked the trunk and v1.0 to be sure).
IIRC, the main issues in OMPI surrounded the use of its wrapper compilers
(i.e., trying to exec something with "gcc -m32" wouldn't work -- you have to
Anything else we want to put into 1.0.1? Or should I make an rc?
There were a few minor changes (I'm afk and can't check the svn log atm) but I
think the 2 big ones were the windows fix and the 32 bit fix.
-jms
Sent from my PDA. No type good.
Hi,
sorry to chime in so late. Jeff you may remember that I reported a
similar problem to open-mpi some years ago. But I didn't use
CFLAGS=-m32 but CC="gcc -m32" and CXX="g++ -m32", which is still in my
eyes the correct way to pass this flag to all compile commands. The
problem in open-mpi back
Both sound fine to me.
Do you want to do #1 or do you want me to do it?
-jms
Sent from my PDA. No type good.
- Original Message -
From: hwloc-devel-boun...@open-mpi.org
To: hwloc-de...@openmpi.org
Sent: Fri May 28 01:05:04
On May 28, 2010, at 6:04 AM, Sylvain Jeaugey wrote:
> Having errors on add_procs stop the application seems a good thing in all
> cases, so why not do it ? That would solve my original problem which lead
> to this discussion.
>
> Yes, the openib BTL may be suboptimal (stopping the application
On Thu, 27 May 2010, Jeff Squyres wrote:
On May 27, 2010, at 10:32 AM, Sylvain Jeaugey wrote:
That's pretty much my first proposition : abort when an error arises,
because if we don't, we'll crash soon afterwards. That's my original
concern and this should really be fixed.
Now, if you want
13th, 14th question are as follows:
(13) Some messages are not shown even though --mca snapc_base_verbose parameter
is used.
Framework : snapc
Component : full
The source file : orte/mca/snapc/base/snapc_base_open.c
The function name : orte_snapc_base_open
I think that the
Hi,Josh
>https://svn.open-mpi.org/trac/ompi/ticket/2397
Thank you very much for filing my questions to ticket system.
Now I have 3 new questions and I will post them.
Regards,
Takayuki Seki
12th question is as follows:
(12) Checkpointing of an MPI job which uses two (or more?) openib btl
A couple random questions:
* After installing my new laptop, it took me quite some time to figure
out that building hwloc from SVN failed because epstopdf was missing.
Could we check for it at configure or build time ? (we already check for
things like fig2dev)
* Updating the test topology
23 matches
Mail list logo