Hi,
Please check shmem.h for exposed API for hw atomics, and memory put/get
operations.
OMPI has plugin system, where every transport can expose what operations
are supported and OMPI will pick one which does for user-called API
requiring it.
For hw which does not support hw atomics or remote memo
Hi Gillies,
Thanks for info, will take a look.
We upgraded recently the jenkins server and it seems that default behave
was changed and ws/cov_build/ folder now contains info for latest in-flight
PR only :(
Will check your advice as well.
Thanks
On Mon, May 25, 2015 at 9:02 AM, Gilles Gouail
Hello,
Please check updated OMPI wiki page for detailed information for Jenkins
testing of OMPI repositories.
https://github.com/open-mpi/ompi/wiki/PRJenkins
Comments and suggestions are welcome.
--
Kind Regards,
M.
Paul,
judging by:
libibverbs: Warning: couldn't open config directory '/etc/libibverbs.d'.
libibverbs: Warning: no userspace device-specific driver found for
/sys/class/infiniband_verbs/uverbs0
it seems that ofed userspace libraries version does not match loaded ofer
kernel driver version.
On
ing that the functionality you describe may become a different
> bot...? I'm not sure.
> >
> >
> >> On Feb 5, 2015, at 9:56 AM, Mike Dubman
> wrote:
> >>
> >> yep, exactly.
> >>
> >>
> >> On Thu, Feb 5, 2015 at 2:35 PM, J
yep, exactly.
On Thu, Feb 5, 2015 at 2:35 PM, Jeff Squyres (jsquyres)
wrote:
> On Feb 5, 2015, at 7:20 AM, Mike Dubman wrote:
> >
> > sounds cool and useful.
>
> K, thanks.
>
> > Also, does it make sense to have "rebase" knob to cause "try rebase
sounds cool and useful.
Also, does it make sense to have "rebase" knob to cause "try rebase if no
conflicts" with upstream?
On Thu, Feb 5, 2015 at 2:04 PM, Jeff Squyres (jsquyres)
wrote:
> Gilles came up with a cool idea for the OMPIBot (see below). We can do
> this idea, but I want to make su
rhel6.4
we can provide ssh access to interested parties.
On Tue, Nov 11, 2014 at 2:01 PM, Gilles Gouaillardet <
gilles.gouaillar...@gmail.com> wrote:
> Thanks Mike,
>
> BTW what is the distro running on your test cluster ?
>
> Mike Dubman wrote:
> ok, I disabled vad
itive, but also remove an important piece of
> information :
> there is something wrong with the master.
>
> would you mind discussion this on the weekly call ?
>
> Cheers,
>
> Gilles
>
>
> On 2014/11/11 17:38, Mike Dubman wrote:
>
> how about if I will disable the fai
how about if I will disable the failing test(s) and make jenkins to pass?
It will help us to make sure we don`t break something that did work before?
On Tue, Nov 11, 2014 at 7:02 AM, Gilles Gouaillardet <
gilles.gouaillar...@iferc.org> wrote:
> Mike,
>
> Jenkins runs automated tests on each pull
btw, do you plan to add atomics API to MTL layer as well?
On Thu, Nov 6, 2014 at 5:23 PM, Nathan Hjelm wrote:
> At the moment I select the lowest latency BTL that can reach all of the
> ranks in the communicator used to create the window. I can add code to
> round-robin windows over the availab
-thread-multiple made it
> work...?
>
> On Nov 5, 2014, at 11:37 AM, Mike Dubman wrote:
>
> > the problem is that now the behavior is changed.
> > Before: user provided single flag and could use MT support.
> > Now same method will not work starting from v1.8.4 which
fix
it to keep old behave by enabling both flags if one of them is ON?
Thanks
On Wed, Nov 5, 2014 at 5:41 PM, Jeff Squyres (jsquyres)
wrote:
> On Nov 5, 2014, at 9:42 AM, Mike Dubman wrote:
>
> > Hey Jeff,
> >
> > now we use only this "--enable-mpi-thread-multipl
Hey Jeff,
now we use only this "--enable-mpi-thread-multiple" and it worked.
does it mean that now we need to pass "--enable-mpi-thread-multiple
--enable-opal-multi-threads"
to get it working again?
Maybe if one of the params used it should enable another one as well?
Thanks
On Wed, Nov 5, 2014
gt; i fixed it in https://github.com/open-mpi/ompi-release/pull/49
>
> please note a similar warning is fixed in
> https://github.com/open-mpi/ompi-release/pull/48
>
> Cheers,
>
> Gilles
>
> On 2
pen-mpi/ompi-release/pull/49
>
> please note a similar warning is fixed in
> https://github.com/open-mpi/ompi-release/pull/48
>
> Cheers,
>
> Gilles
>
> On 2014/10/23 17:14, Mike Dubman wrote:
>
> *05:12:10* more information, such as the ld(1) and ld.so(8) manual pages.
*05:12:10* more information, such as the ld(1) and ld.so(8) manual pages.
*05:12:10*
--
*05:12:10* make[3]: Leaving directory
`/scrap/jenkins/workspace/hpc-ompi-shmem/label/r-vmb-centos5-u7-x86-64/ompi/mca/btl/vader'
*05:12:10*
gt; Those revisions listed above that are new to this repository have
> >> not appeared on any other notification email; so we list those
> >> revisions in full, below.
> >>
> >> - Log -----
> >>
(commit)
>> >
>> > Those revisions listed above that are new to this repository have
>> > not appeared on any other notification email; so we list those
>> > revisions in full, below.
>> >
>> > - Log ---
maybe we should have another MCA parameter to specify desired policy?
LAST,CONCAT,FIRST and let user select it?
basically, it is to mimic "setenv(var,val,overwrite)" behavior which is
easy to explain and good to have.
On Tue, Sep 9, 2014 at 7:31 PM, Ralph Castain wrote:
> WHAT: Generate an
r32484
On Sat, Aug 9, 2014 at 5:09 PM, Ralph Castain wrote:
> Hmmmwell, I showed you how to fix them, so please feel free to do so
> :-)
>
> I have no way to build that component.
>
>
> On Aug 8, 2014, at 10:32 PM, Mike Dubman wrote:
>
> still, th
yep, missed "green" report.
Thanks
On Sat, Aug 9, 2014 at 1:24 PM, Jeff Squyres (jsquyres)
wrote:
> Fixed with Ralph's commit last night (r32480).
>
>
> On Aug 9, 2014, at 1:33 AM, Mike Dubman wrote:
>
> > 02:36:30
> > CC base/odls_bas
*02:36:30* CC base/odls_base_default_fns.lo*02:36:30*
base/odls_base_default_fns.c: In function
'odls_base_default_wait_local_proc':*02:36:30*
base/odls_base_default_fns.c:2001: warning: implicit declaration of
function 'ORTE_FLAG_SET'*02:36:30* base/odls_base_default_fns.c:2001:
error: 'OR
at 7:12 PM, Ralph Castain wrote:
> Fixed in r32462
>
> On Aug 8, 2014, at 8:13 AM, Mike Dubman wrote:
>
>
> *Josh,Devendar - could you please take a look?*
>
> *Thanks*
>
>
> *15:45:00* Making install in mca/coll/fca*15:45:00* make[2]: Entering
> directory
&
*Josh,Devendar - could you please take a look?*
*Thanks*
*15:45:00* Making install in mca/coll/fca*15:45:00* make[2]: Entering
directory
`/scrap/jenkins/scrap/workspace/hpc-ompi-shmem/label/hpc-test-node/ompi/mca/coll/fca'*15:45:00*
CC coll_fca_module.lo*15:45:00* coll_fca_module.c: In
Also, latest commit into openib (origin/v1.8
https://svn.open-mpi.org/trac/ompi/changeset/32391) broke something:
*11:45:01* + timeout -s SIGSEGV 3m
/scrap/jenkins/workspace/OMPI-vendor/label/hpctest/ompi_install1/bin/mpirun
-np 8 -mca pml ob1 -mca btl self,openib
/scrap/jenkins/workspace/OMPI-ven
Making all in mca/common/ofacm
make[2]: Entering directory
`/hpc/local/benchmarks/hpc-stack-gcc/src/install/ompi-master/opal/mca/common/ofacm'
CC libmca_common_ofacm_la-common_ofacm_base.lo
CC libmca_common_ofacm_la-common_ofacm_oob.lo
CC libmca_common_ofacm_la-common_ofacm_
OSHMEM memheap implementation relies on the "_end" symbol provided by linux
linker. The _end symbol indicates the beginning of the program dynamic
allocation area.
This is needed to allow programmatic access to the process global/static
variables.
On Thu, Jul 24, 2014 at 9:22 PM, Marco Atzeri
uts of the OMPI tree.
> >
> > It does not seem to happen on RHEL 6.5, but does happen on RHEL 7 and
> SLES 12 (beta).
> >
> > What's the difference?
> >
> >
> > On Jul 24, 2014, at 6:12 AM, Mike Dubman
> wrote:
> >
> >> this is a comm
m=/opt/knem-1.1.1.90mlnx
--with-platform=contrib/platform/mellanox/optimized ' --define
'use_default_rpm_opt_flags 1' openmpi-1.8.2rc2-1.src.rpm
On Thu, Jul 24, 2014 at 11:58 AM, Bert Wesarg
wrote:
> On 07/24/2014 10:15 AM, Mike Dubman wrote:
>
>> the problem occurs
the problem occurs when build is started from src.rpm (and probably from
tarball as well):
try make distcheck and use src tree from tarball.
On Thu, Jul 24, 2014 at 10:57 AM, Bert Wesarg
wrote:
> On 07/24/2014 09:32 AM, Mike Dubman wrote:
>
>> yes, sure - it fails on sles12, rhel
"git clean", or something?
>
>
> On Jul 23, 2014, at 10:02 AM, Mike Dubman
> wrote:
>
> > nope, we use git.
> > it passed on rhel 6.x, failed on ubuntu/debian/fedora and rhel 7.x
> >
> >
> > On Wed, Jul 23, 2014 at 4:03 PM, Jeff Squyres (jsquyr
http://www.open-mpi.org/community/lists/devel/2014/07/15211.php
>
>
> On Jul 23, 2014, at 9:01 AM, Mike Dubman wrote:
>
> >
> > CC libvt_mpi_la-vt_iowrap_helper.lo
> > CC libvt_mpi_la-vt_libwrap.lo
> > CC libvt_mpi_la-vt_mallocwrap.lo
>
CC libvt_mpi_la-vt_iowrap_helper.lo
CC libvt_mpi_la-vt_libwrap.lo
CC libvt_mpi_la-vt_mallocwrap.lo
CC libvt_mpi_la-vt_mpifile.lo
make[6]: Entering directory
'/var/tmp/OFED_topdir/BUILD/openmpi-1.8.2rc2/ompi/contrib/vt/vt/tools/vtunify/mpi'
ln -s
/var/tmp/OFED_topdir/
we have a strong use-case for list of env variables passed as mca params.(it
was presented and discussed in the past).
we can rename opal_base_envlist as "-mca x var=val" for consistency.
also, "-x" param now is just an alias for "-mca opal_base_envlist var=val"
- so, we can keep it (w/o deprecati
these are two separate issues:
1. -x var=val (or -mca opal_base_envlist var=val) will work in the same way
opal_base_envlist does the same as "-x" and can be used in the very same
fashion as -x
2. When list of vars is passed with help of opal_base_envlist, the escaping
is possible but escaped cha
,
> and I don't think common/pmi calls the slurm .m4 check - at least, it
> probably shouldn't
>
> On Jul 11, 2014, at 11:57 AM, Mike Dubman
> wrote:
>
> I think the problem related to new version of SLURM which was upgraded on
> our machines.
> we had 2.6.6 now it is 1
ohh... sorry about that.
will be more careful next time.
On Sat, Jul 12, 2014 at 8:43 PM, Ralph Castain wrote:
> Congrats - your Makefile.am change broke it :-)
>
> I reverted it so the repo can build again
>
> On Jul 12, 2014, at 10:23 AM, Mike Dubman
> wrote:
>
> Fro
>From repo
On Jul 12, 2014 7:59 PM, "Ralph Castain" wrote:
> Just checked out the tarball and it builds fine for me - did you build
> this from the tarball, or from the repo?
>
>
> On Jul 12, 2014, at 9:29 AM, Mike Dubman wrote:
>
> make[8]: Entering directory
make[8]: Entering directory
`/hpc/newhome/hpcuser/workspace/hpc-internal-tools.git/build/dist-ompi-mellanox-v1.8-1.8/master/ompi/contrib/vt/vt/extlib/otf/tools/otfinfo'
make[8]: Leaving directory
`/hpc/newhome/hpcuser/workspace/hpc-internal-tools.git/build/dist-ompi-mellanox-v1.8-1.8/master/ompi/c
ersion is still at 1.13.x)
>
>
>
> On Jul 12, 2014, at 8:38 AM, svn-commit-mai...@open-mpi.org wrote:
>
> > Author: miked (Mike Dubman)
> > Date: 2014-07-12 08:38:15 EDT (Sat, 12 Jul 2014)
> > New Revision: 32225
> > URL: https://svn.open-mpi.org/trac/om
Nope
Are they on list?
On Jul 12, 2014 6:36 PM, "Jeff Squyres (jsquyres)"
wrote:
> Mike --
>
> Did you contact the VT folks before making this change?
>
>
>
> On Jul 12, 2014, at 8:38 AM, <
> svn-commit-mai...@open-mpi.org> wrote:
>
> > Author:
De: "Jeff Squyres (jsquyres)"
> > À: "Open MPI Developers List"
> > Envoyé: Jeudi 10 Juillet 2014 22:27:12
> > Objet: Re: [OMPI devel] openmpi.spec
> >
> > Mike and I talked in IM. The results of our chat was Mike's commit:
> >
> >
ook at this. Have a look at other components
> that use
> > hwloc and copy their header file setup and make file.am setup.
> >
> > Sent from my phone. No type good.
> > On Jul 10, 2014, at 8:22 AM, "Mike Dubman" <
> mi...@dev.mellanox.co.i
Hi,
The following commit https://svn.open-mpi.org/trac/ompi/changeset/32147
does some harm:
the line 202 in the change causes openmpi.src.rpm to contain arch in the
rpm name, i.e. openmpi-1.8.2a1-1.el6.src.rpm
The src.rpm should be arch agnostic.
what do you think?
Thanks
confirmed.
Thanks
On Thu, Jul 10, 2014 at 3:31 PM, Jeff Squyres (jsquyres) wrote:
> Bert: good catch, thanks
>
> Mellanox: can you confirm that this change was required?
>
> Sent from my phone. No type good.
>
> > On Jul 9, 2014, at 4:59 PM, "Ralph Castain" wrote:
> >
> > Ouch - yes, we defini
Hi guys,
jenkins node failing on this.
is hwloc-devel now required to be available as part of distro?
Thanks
M
*15:14:11* make[3]: Leaving directory
`/scrap/jenkins/scrap/workspace/hpc-ompi-shmem/label/hpc-test-node/opal'*15:14:11*
make[2]: Leaving directory
`/scrap/jenkins/scrap/workspace/hpc-o
mponent?
>
> On Jul 8, 2014, at 9:20 AM, Mike Dubman wrote:
>
> >
> >
> > $/usr/mpi/gcc/openmpi-1.8.2a1/bin/ompi_info -a -l 9|less
> > Caught signal 13 (Broken pipe)
> > backtrace
> > 2 0x00054cac mxm_handle_error()
> /var/tmp
Hi,
The latest svn/trunks fails to install on centos 5.7,5.8,5.9 but works fine
on others.
after:
./configure --with-platform=contrib/platform/mellanox/optimized
--with-knem=/opt/knem-0.9.7mlnx1 --with-fca=/opt/mellanox/fca
--with-ompi-param-check --enable-picky
--prefix=/scrap/jenkins/workspace/
$/usr/mpi/gcc/openmpi-1.8.2a1/bin/ompi_info -a -l 9|less
Caught signal 13 (Broken pipe)
backtrace
2 0x00054cac mxm_handle_error()
/var/tmp/OFED_topdir/BUILD/mxm-3.2.2883/src/mxm/util/debug/debug.c:653
3 0x00054e74 mxm_error_signal_handler()
/var/tmp/OFED_topdir/BUILD/m
GV)
>
> Cheers,
>
> Gilles
>
> On 2014/06/25 14:22, Mike Dubman wrote:
> > Hi,
> > The following commit broke trunk in jenkins:
> >
> >>>> Per the OMPI developer conference, remove the last vestiges of
> > OMPI_USE_PROGRESS_THREADS
> >
>
the timeout sending a SIGSEGV)
>
> Cheers,
>
> Gilles
>
> On 2014/06/25 14:22, Mike Dubman wrote:
> > Hi,
> > The following commit broke trunk in jenkins:
> >
> >>>> Per the OMPI developer conference, remove the last vestiges of
> > OMPI_USE_PROGRESS
Hi,
The following commit broke trunk in jenkins:
>>>Per the OMPI developer conference, remove the last vestiges of
OMPI_USE_PROGRESS_THREADS
*22:15:09* +
LD_LIBRARY_PATH=/scrap/jenkins/scrap/workspace/hpc-ompi-shmem/label/hpc-test-node/oshm_install2/lib*22:15:09*
+ OMPI_MCA_scoll_fca_enable=1*22
.org] On Behalf Of Mike Dubman [
> mi...@dev.mellanox.co.il]
> Sent: Thursday, June 19, 2014 4:20 PM
> To: Open MPI Developers
> Subject: Re: [OMPI devel] Compile OpenMPI with MXM support
>
> Hi,
> it seems that you extracted mxm.bin.rpm into $HOME and use it in configure.
>
Hi,
it seems that you extracted mxm.bin.rpm into $HOME and use it in configure.
It may have an issues during "configure" phase as libmxm.so may contain
rpath to /opt/mellanox/mxm and you probably need LD_LIBRARY_PATH set to the
real mxm location to make it working and also adjust .la files in mxm d
with this fix - no failure.
Thanks!
On Mon, Jun 2, 2014 at 8:52 PM, Ralph Castain wrote:
> Yep, that's the one. Should have fixed that problem
>
>
> On Jun 2, 2014, at 10:30 AM, Mike Dubman wrote:
>
> This one? "Fix typo that would cause a segfault if orte_startu
This one? "Fix typo that would cause a segfault if orte_startup_timeout was
set"
If so, it is still running.
On Mon, Jun 2, 2014 at 8:16 PM, Ralph Castain wrote:
> You're still missing a commit that fixed this problem
>
> On Jun 2, 2014, at 9:44 AM, Mike Dubman wrot
these failures. Otherwise, it is impossible to replicate
> the problem.
>
>
> On Jun 2, 2014, at 6:49 AM, Ralph Castain wrote:
>
> Hi guys
>
> I'm awake now and will take a look at this - thanks
> Ralph
>
> On Jun 2, 2014, at 6:34 AM, Mike Dubman wrote:
>
&
> then i can only review the code and hope i can find the root cause of the
> error i am unable to reproduce in my environment
>
> Cheers,
>
> Gilles
>
>
>
>
> On Mon, Jun 2, 2014 at 9:03 PM, Mike Dubman
> wrote:
>
>> Hi,
>> The jenkins took y
s/devices/system/cpu/cpu0/cpufreq/scaling_governor
> (pseudo) file on your system ?
>
> if this still does not work for you, then this might be a different issue
> i was unable to reproduce.
> in this case, could you run mpirun under gdb and send a gdb stack trace ?
>
>
> Cheers,
>
&g
, 2014 at 2:24 PM, Mike Dubman
wrote:
> Hi,
> This fix "orte_rtc_base_select: skip a RTC module if it has a zero
> priority" did not help and jenkins stilll fails as before.
> The ompi was configured:
> --with-platform=contrib/platform/mellanox/optimized
> --with-omp
Hi,
This fix "orte_rtc_base_select: skip a RTC module if it has a zero
priority" did not help and jenkins stilll fails as before.
The ompi was configured:
--with-platform=contrib/platform/mellanox/optimized --with-ompi-param-check
--enable-picky --with-knem --with-mxm --with-fca
The run was on sin
Hi,
The trunk hangs after following commits, seems 3-5,7 can be the ones.
Changes
1. Java-oshmem: update examples
2. Java: update javadoc's install locations
3. Replace the PML barrier with an RTE barrier for now until we can come
up with a better solution for connectionless BTLs.
4
applied here: https://svn.open-mpi.org/trac/ompi/changeset/31909
On Sun, Jun 1, 2014 at 9:15 AM, Artem Polyakov wrote:
> Hi, all.
>
> Ralph commited the code that was developed for this RFC (r31908). This
> commit will brake PMI1 support. In case of hurry - apply attached patch.
> Ralph will ap
here it goes, https://svn.open-mpi.org/trac/ompi/changeset/31751
On Wed, May 14, 2014 at 9:19 AM, Bert Wesarg wrote:
> Dear all,
>
> the Score-P community is currently in the process to support the OpenSHMEM
> API in its performance measurement infrastructure Score-P [1]. And we are
> near a re
should be fixed.
thanks
On Tue, May 13, 2014 at 2:53 AM, Joshua Ladd wrote:
> Yes. Will look into it.
>
> Josh
>
>
> On Mon, May 12, 2014 at 6:01 PM, Jeff Squyres (jsquyres) <
> jsquy...@cisco.com> wrote:
>
>> Ah; I guess the tags aren't getting pulled over.
>>
>> Mellanox -- can you check into
thanks for patch, we will review it next week.
Also, you can select different shmem collectives at runtime:
-mca scoll_mpi_enable 1 (to select MPI collectives for shmem)
On Sat, May 10, 2014 at 7:08 PM, Bert Wesarg wrote:
> On 05/10/2014 02:46 PM, Bert Wesarg wrote:
>
>> Hi,
>>
>> I get a dea
thanks
fixed in r31562
On Wed, Apr 30, 2014 at 3:50 AM, Ralph Castain wrote:
> ? oshmem/shmem/fortran/profile/pshmem_pe_accessible_f.c
> ? oshmem/shmem/fortran/profile/pshmem_iget128_f.c
> ? oshmem/shmem/fortran/profile/pshmem_int4_add_f.c
> ? oshmem/shmem/fortran/profi
hit send too soon.
this commit:
Follow the lead set by Jeff: no need to run AC_CONFIG_HEADERS on
orte_config.h. However, unlike the MPI layer, we don't run that macro on
another file in orte/include, so ensure we add that -I path back!
On Tue, Apr 29, 2014 at 8:40 AM, Mike Dubman
seems like started from this commit:
On Tue, Apr 29, 2014 at 8:39 AM, Mike Dubman wrote:
>
> contrib/dist/make_dist_tarball -highok -distdir
> /scrap/jenkins/scrap/workspace/hpc-ompi-shmem/label/hpc-test-node/tarball
>
>
>
> *03:36:26* make[3]: warning: -jN forced
contrib/dist/make_dist_tarball -highok -distdir
/scrap/jenkins/scrap/workspace/hpc-ompi-shmem/label/hpc-test-node/tarball
*03:36:26* make[3]: warning: -jN forced in submake: disabling
jobserver mode.*03:36:26* CC orte-info.o*03:36:26* CC
output.o*03:36:26* CC param.o*03:36:26*
>>> I didn't see a reply to my question about the primary use case for this
being for scripts, and therefore a slightly-more-than-trivial regexp...
The primary use-case:
collect system related info w/ help of ompi_info and validate cluster setup
is according to site/vendor rules.
Can be done manu
itten for them,
> that the admins use or will be handed to them. Either way would be a
> great addition for
> system/build/runtime verification of the installed libraries.
>
> Best
> Steve...
>
>
> On 4/25/14, 7:13 AM, Jeff Squyres (jsquyres) wrote:
>
> On Apr 25,
, Apr 25, 2014 at 1:32 PM, Jeff Squyres (jsquyres) wrote:
> On Apr 24, 2014, at 1:38 AM, Mike Dubman wrote:
>
> > ** prefix each well-known MCA param with "print_":
>
> I like the overall idea of this RFC, but I'm not wild about this specific
> word "pr
Also, the reason for rfc is this:
https://svn.open-mpi.org/trac/ompi/ticket/4556#comment:5
On Fri, Apr 25, 2014 at 7:41 AM, Mike Dubman wrote:
> not a requirement of course, but warm recommendation. Like you mentioned:
> "component developers who choose to expose such information
ing anyone even a passing
> thought that we do so.
>
>
>
> On Apr 23, 2014, at 10:38 PM, Mike Dubman
> wrote:
>
>
> WHAT:
> * Formalize well-known MCA parameters that can be used by any component to
> represent external dependencies for this component.
>
> *
WHAT:
* Formalize well-known MCA parameters that can be used by any component to
represent external dependencies for this component.
* Component can set that well-known MCA r/o parameters to expose to the
end-users different setup related traits of the OMPI installation.
Example:
ompi_info can p
git
On Wed, Apr 16, 2014 at 1:32 PM, Jeff Squyres (jsquyres) wrote:
> What source code repository technology(ies) do you use for Open MPI
> development? (indicate all that apply)
>
> - SVN
> - Mercurial
> - Git
>
> I ask this question because there's serious discussions afoot to switch
> OMPI's
fixed in r31392
sorry about that.
On Tue, Apr 15, 2014 at 8:11 AM, Ralph Castain wrote:
> Hi Gilles
>
> There really isn't any need to open tickets when things like this happen.
> A simple note to devel is usually considered adequate. The problem will
> either be repaired by the responsible org
availability can be tested with
autotools macros.
On Mon, Apr 14, 2014 at 10:43 PM, Jeff Squyres (jsquyres) <
jsquy...@cisco.com> wrote:
> On Apr 14, 2014, at 3:27 PM, Mike Dubman wrote:
>
> > this was true if all external libraries were maintaining ABI
> compatibility in
hmm... very smart. thanks. seems it can work. will think about it more.
On Mon, Apr 14, 2014 at 10:13 PM, Jeff Squyres (jsquyres) <
jsquy...@cisco.com> wrote:
> On Apr 14, 2014, at 2:57 PM, Mike Dubman wrote:
>
> > I think (+know) that many production environments and
it'll only use capability 13 with X.Y.Z but will use
> both 13 and 27 with A.B.C.
>
>
>
>
> On Apr 14, 2014, at 2:48 PM, "Jeff Squyres (jsquyres)"
> wrote:
>
> > On Apr 14, 2014, at 10:59 AM, Mike Dubman
> wrote:
> >
> >> Ther
it'll only use capability 13 with X.Y.Z but will use
> both 13 and 27 with A.B.C.
>
>
>
>
> On Apr 14, 2014, at 2:48 PM, "Jeff Squyres (jsquyres)"
> wrote:
>
> > On Apr 14, 2014, at 10:59 AM, Mike Dubman
> wrote:
> >
> >> Ther
it'll only use capability 13 with X.Y.Z but will use
> both 13 and 27 with A.B.C.
>
>
>
>
> On Apr 14, 2014, at 2:48 PM, "Jeff Squyres (jsquyres)"
> wrote:
>
> > On Apr 14, 2014, at 10:59 AM, Mike Dubman
> wrote:
> >
> >> Ther
ster the component, ompi_info has to
> *load* it first. So any library incompatibility may well have already
> caused a problem.
>
>
> On Apr 14, 2014, at 7:59 AM, Mike Dubman wrote:
>
> There is no correlation between built_with and running_with versions of
> external libr
sysadmin/user-experience.
On Mon, Apr 14, 2014 at 5:47 PM, Ralph Castain wrote:
>
> On Apr 14, 2014, at 7:34 AM, Mike Dubman wrote:
>
> it is unrelated:
>
> 1. The OMPI can support and built with many different (or all) versions of
> external library (for example: libmxm or
in your configure logic, and
> are trying to find a bandaid. Perhaps a better solution (that wouldn't
> cause us to change every component in the code base) would be to just add
> appropriate tests to your configure logic so you don't incorrectly build
> against an unsupported
+devel mailing list (for web mail archive)
On Sat, Apr 12, 2014 at 9:04 PM, Mike Dubman wrote:
>
> Hi,
>
> Could you please suggest if following is addressed in MCA architecture or
> maybe it is something we should add:
>
> Current MCA API:
> The new MCA component s
thanks
fixed here: r31334
On Tue, Apr 8, 2014 at 6:03 AM, Ralph Castain wrote:
> On Linux, with oshmem enabled:
>
> pinit_f.c:26:2: warning: #ident is a GCC extension
> pshmem_init.c:31: warning: no previous prototype for 'pstart_pes'
> pshmem_align.c:25: warning: no previous prototype for 'psh
profiling interface for
> SHMEM API functions (like MPI does)?
>
>
> On Mar 31, 2014, at 7:21 PM, Mike Dubman wrote:
>
> > thanks, we will fix that.
> >
> >
> > On Mon, Mar 31, 2014 at 5:04 PM, Ralph Castain wrote:
> > Hmmm...I'll ask the Mellanox folks
ily add that capability
> to the mca params file.. This would seem far preferable to creating a
> completely new, parallel way of setting envars.
>
> Why not do it that way?
>
>
>
> On Tue, Apr 1, 2014 at 4:34 PM, Mike Dubman wrote:
>
>> The "-x var=v
The "-x var=val" cannot be placed into mca params file.
On Wed, Apr 2, 2014 at 2:34 AM, Mike Dubman wrote:
> yes, it is expected that the "string" value should be quoted. will clarify
> it in the help message and man page. Thanks for spotting.
>
> The underlying
are these
> not just MCA params to begin with, in which case we don't need another
> duplicate mechanism for setting them?
>
> We should only be setting envars that have nothing to do with OMPI, not
> setting OMPI-related envars - anything OMPI related is supposed to be an
> MCA p
;
>
>
> On Tue, Apr 1, 2014 at 2:14 PM, wrote:
>
>> Author: miked (Mike Dubman)
>> Date: 2014-04-01 17:14:31 EDT (Tue, 01 Apr 2014)
>> New Revision: 31302
>> URL: https://svn.open-mpi.org/trac/ompi/changeset/31302
>>
>> Log:
>> opal: add mca param
thanks, we will fix that.
On Mon, Mar 31, 2014 at 5:04 PM, Ralph Castain wrote:
> Hmmm...I'll ask the Mellanox folks to fix that, but it will have to be for
> 1.8.1 as we have to release 1.8.0 today for the upstream packagers. I
> expect 1.8.1 will go out in the next 1-2 months based on prior e
Hi Jeff,
We are working on "mxm" btl and plan to use some "common" verbs APIs from
it.
Regards
On Tue, Mar 25, 2014 at 5:01 PM, Jeff Squyres (jsquyres) wrote:
> Mike / Vasily / Alina --
>
> Are you guys using ompi_common_verbs_find_ports() somewhere? I don't see
> it being used anyhere othe
ill be able to
run,otherwise no fallback to other provider will be available for user at
runtime.
On Wed, Mar 12, 2014 at 12:08 AM, Jeff Squyres (jsquyres) <
jsquy...@cisco.com> wrote:
> On Mar 6, 2014, at 12:00 PM, Mike Dubman wrote:
>
> > but AF_IB is always declared, rega
but AF_IB is always declared, regardless of actual presence in the kernel.
On Thu, Mar 6, 2014 at 5:56 PM, Ralph Castain wrote:
> Let me see if I can help translate. I think the problem here is Jeff's
> comment about a "run time check", which wasn't actually what he is
> proposing here.
>
> If
Hi,
coll/hcoll is Mellanox driven collective package.
coll/ml is managed/supported/developed by ORNL folks.
On Tue, Mar 4, 2014 at 1:06 PM, Ralph Castain wrote:
> Ummm...the "ml" stands for Mellanox. This is a component you folks
> contributed at some time. IIRC, the hcoll and/or bcol are mean
yep, now it fine.
thx
On Thu, Feb 27, 2014 at 4:43 PM, Ralph Castain wrote:
> you need to update your repo
>
> On Feb 26, 2014, at 9:55 PM, Mike Dubman wrote:
>
> *07:32:17* make[2]: Entering directory
> `/scrap/jenkins/workspace/ompi-vendor-gerrit/label/hpc/or
1 - 100 of 174 matches
Mail list logo
