If my git is correct
$ git rev-list --boundary v2.x...master/master | grep '^-'
-acc2c7937cd3b50de16044b673399e4c4a7456bc
-6772d32b85b836438eeca72e4a8fda026ea67a55
-ec44a25070f99b6e1d96886fe3990ad560ee63c0
$ git show ec44a25070f99b6e1d96886fe3990ad560ee63c0
commit
that patch.
-Paul
On Tue, Aug 23, 2016 at 10:16 PM, Gilles Gouaillardet
<gil...@rist.or.jp <mailto:gil...@rist.or.jp>> wrote:
Paul,
you can download a patch at
https://patch-diff.githubusercontent.com/raw/open-mpi/om
Karol,
is there any place i can download glibc 2.24 for tumbleweed ?
i'd like to have a look at what is going wrong with openmpi 1.10
Cheers,
Gilles
On 8/25/2016 10:24 AM, Karol Mroz wrote:
Greetings!
I would like to upgrade our (openSUSE Tumbleweed) version of Open MPI
from 1.10.3
Karol,
it is correct vampirtrace was removed from Open MPI 2.0.0
are you using your own (or openSUSE) .spec file ? or the one provided by
Open MPI ?
fwiw, Open MPI 1.10.4 and 2.0.1 should be released in a near future.
Cheers,
Gilles
On 8/25/2016 10:24 AM, Karol Mroz wrote:
_CRED;
}
#else
return PMIX_ERR_NOT_SUPPORTED;
#endif
I can only surmise, therefore, that Solaris doesn’t pass either of
the two #if define’d tests. Is there a Solaris alternative?
On Aug 23, 2016, at 5:55 AM, r...@open-mpi.org
<mailto:r...@open-mpi.org> wrote:
Thanks Gilles!
wrote:
> Fixed in 9210230
>
> > On Aug 22, 2016, at 8:49 PM, r...@open-mpi.org <javascript:;> wrote:
> >
> > Yeah, I started working on it earlier this evening - will look some more
> tomorrow
> >
> >> On Aug 22, 2016, at 7:57 PM, Gilles G
Thanks Paul,
at first glance, something is going wrong in the sec module under solaris.
I will keep digging tomorrow
Cheers,
Gilles
On Tuesday, August 23, 2016, Paul Hargrove wrote:
> On Solaris 11.3 on x86-64:
>
> $ mpirun -mca btl sm,self,openib -np 2 -host
Folks,
i made a trivial test
echo hello | mpirun -np 1 cat
and with v2.x and v1.10, the output is "hello" as expected
but with master, there is no output at all (!)
i was able to fix that with the dirty workaround below.
the root cause (on master) is that orte_cmd_options.stdin_target
Folks,
i was reviewing the sources of the coll/sync module, and
1) i noticed the same pattern is used in *every* sources :
if (s->in_operation) {
return s->c_coll.coll_xxx(...);
} else {
COLL_SYNC(s, s->c_coll.coll_xxx(...));
}
is there any rationale for not
app to run.
>
>
> On Aug 20, 2016, at 7:38 PM, Gilles Gouaillardet <
> gilles.gouaillar...@gmail.com
> <javascript:_e(%7B%7D,'cvml','gilles.gouaillar...@gmail.com');>> wrote:
>
> Ralph,
>
> in the meantime, and if not done already, your user can simply red
Ralph,
in the meantime, and if not done already, your user can simply redefine
MPI_Bcast in the app.
int MPI_Bcast(void *buffer, int count, MPI_Datatype type, int root,
MPI_Comm comm) {
PMPI_Barrier(comm);
return PMPI_Bcast(buffer, count, datatype, root, comm);
}
the root causes are
-
Thanks Jeff for the lengthy explanation,
and fwiw, i have no strong opinion too
Cheers,
Gilles
On 8/18/2016 8:20 PM, Jeff Squyres (jsquyres) wrote:
On Aug 18, 2016, at 12:44 AM, Gilles Gouaillardet <gil...@rist.or.jp> wrote:
when reading the dev meeting minutes, i saw MPI_Reduce
Folks,
when reading the dev meeting minutes, i saw MPI_Reduce_local was
discussed and might be moved to the coll framework,
and here are my 0.02 US$ :
the prototype of MPI_Reduce_local is
int MPI_Reduce_local(const void *inbuf, void *inoutbuf, int count,
MPI_Datatype
Franz-Joseph,
the excellent NAG compiler is a commercial product, and as such, not all
developers can afford it.
this issue should be fixed in the master (feel free to give the latest
nightly tarball a try)
a fix for v2.x is pending for review at
ce as no specialized hierarchies can be built without the RTE
information.
George.
On Wed, Aug 10, 2016 at 3:57 AM, Gilles Gouaillardet
<gil...@rist.or.jp <mailto:gil...@rist.or.jp>> wrote:
Ralph,
i noticed dist-graph/distgraph_test_4 from the ibm test suite
Ralph,
i noticed dist-graph/distgraph_test_4 from the ibm test suite fails when
using a hostfile and running no task on the host running mpirun.
n0$ mpirun --host n1:1,n2:1 -np 2 ./dist-graph/distgraph_test_4
the root cause is OPAL_PMIX_NODEID is correctly set ( 0, 1, 2) by
mpirun, but
Also, btl/vader has a higher exclusivity than btl/sm, so if you do not
manually specify any btl, vader should be used.
you can run with
--mca btl_base_verbose 10
to confirm which btl is used
Cheers,
Gilles
On 7/27/2016 9:20 AM, Nathan Hjelm wrote:
sm is deprecated in 2.0.0 and will
Hi,
can you please run again with
--mca pml ob1
if Open MPI was built with mxm support, pml/cm and mtl/mxm are used
instead of pml/ob1 and btl/openib
Cheers,
Gilles
On 7/27/2016 8:56 AM, tmish...@jcity.maeda.co.jp wrote:
Hi folks,
I saw a performance degradation of openmpi-2.0.0
of days. Let me know
if you figure it out before I get to it.
-Nathan
On Jul 25, 2016, at 8:38 PM, Gilles Gouaillardet <gil...@rist.or.jp> wrote:
Eric,
where can your test case be downloaded ? how many nodes and tasks do you need
to reproduce the bug ?
fwiw, currently there are two Op
Eric,
where can your test case be downloaded ? how many nodes and tasks do you
need to reproduce the bug ?
fwiw, currently there are two Open MPI repositories
- https://github.com/open-mpi/ompi
there is only one branch and is the 'master' branch, today, this can
be seen as Open MPI 3.0 pre
s to be replaced by "-lpthread", or similar.
-Paul
On Mon, Jul 25, 2016 at 6:03 PM, Gilles Gouaillardet
<gil...@rist.or.jp <mailto:gil...@rist.or.jp>> wrote:
Folks,
This is a followup of a thread that initially started at
http://www.open-mpi.org/community/lists/users
Folks,
This is a followup of a thread that initially started at
http://www.open-mpi.org/community/lists/users/2016/07/29635.php
The user is trying to build Open MPI with PGI compiler and
libslurm.la/libpmi.la support, and slurm was built with gcc compiler.
At first, it fails because the
Ralph,
I am not sure of what you mean by "hook"
there are basically two ways to trigger a build
- github webhook contact your Jenkins server. your server must be
publically accessible, and you need to register it's url in github. new
build start right after a pr is created
- poll from the
that tomorrow though
Cheers,
Gilles
On Thursday, July 21, 2016, Jeff Squyres (jsquyres) <jsquy...@cisco.com>
wrote:
> On Jul 21, 2016, at 3:53 AM, Gilles Gouaillardet <gil...@rist.or.jp
> <javascript:;>> wrote:
> >
> > Folks,
> >
> > Mellanox Jenkins
nmpi" directory. My guess that
> it is somehow removed during jenkins execution.
>
> I'm checking now.
>
> 2016-07-21 20:11 GMT+06:00 Jeff Squyres (jsquyres) <jsquy...@cisco.com
> <javascript:_e(%7B%7D,'cvml','jsquy...@cisco.com');>>:
>
>> On Jul
Ralph,
I noted singleton are broken on master.
git bisect points to the commit in which PMIx_tool were introduced.
if you revert to this commit, orted forked by the singleton crashes.
iirc, latest master does nit work, but orted does not crash either.
sorry for the lack of details , I am afk
Folks,
Mellanox Jenkins marks recent PR's as failed for very surprising reasons.
mpirun --mca btl sm,self ...
failed because processes could not contact each other. i was able to
reproduce this once on my workstation,
and found the root cause was a dirty build and/or install dir.
i
Howard,
did you bump both btl_tcp_rndv_eager_limit and btl_tcp_eager_limit ?
you might also need to bump btl_tcp_sndbuf, btl_tcp_rcvbuf and
btl_tcp_max_send_size to get the max performance out of your 100Gb
ethernet cards
last but not least, you might also need to bump btl_tcp_links to
<r...@open-mpi.org> wrote:
> Okay, I’ll investigate why that is happening - thanks!
>
> On Jul 16, 2016, at 7:45 AM, Gilles Gouaillardet <
> gilles.gouaillar...@gmail.com
> <javascript:_e(%7B%7D,'cvml','gilles.gouaillar...@gmail.com');>> wrote:
>
> Th
uzzles me is that no debugger_release
> message should be sent unless a debugger is attached - in which case, the
> event should be registered.
>
> So why is it being sent? Is it the child job that is receiving it? Or is
> it the parent?
>
>
> On Jul 16, 2016, at 7:19 AM, Gilles
, July 15, 2016, Ralph Castain <r...@open-mpi.org> wrote:
> Okay, I’ll take a look - thanks!
>
> On Jul 15, 2016, at 7:08 AM, Gilles Gouaillardet <
> gilles.gouaillar...@gmail.com
> <javascript:_e(%7B%7D,'cvml','gilles.gouaillar...@gmail.com');>> wrot
> On Jul 15, 2016, at 1:20 AM, Gilles Gouaillardet <gil...@rist.or.jp
> <javascript:;>> wrote:
> >
> > Ralph,
> >
> > i noticed MPI_Comm_spawn is broken on master and on RHEL7
> >
> > for some reason i cannot yet explain, it works just fine on RH
Ralph,
i noticed MPI_Comm_spawn is broken on master and on RHEL7
for some reason i cannot yet explain, it works just fine on RHEL6 (!)
mpirun -np 1 ./dynamic/intercomm_create
from the ibm test suite can be used to reproduce the issue.
i digged a bit and i found OPAL_ERR_DEBUGGER_RELEASE
OpenMPI so it avoids a CMake bug,
let's follow up at https://github.com/open-mpi/ompi/issues/1868
Cheers,
Gilles
On 7/13/2016 8:30 PM, Paul Kapinos wrote:
Hi Gilles,
On 07/13/16 01:10, Gilles Gouaillardet wrote:
Paul,
The two header files in include/mpp simply include the file
Eric,
OpenMPI 2.0.0 has been released, so the fix should land into the v2.x
branch shortly.
If i understand correctly, you script download/compile OpenMPI and then
download/compile PETSc.
In this is correct, and for the time being, feel free to patch Open MPI
v2.x before compiling it,
Paul,
The two header files in include/mpp simply include the file with the same
name in the upper directory.
A simple workaround is to replace these two files in include/mpp with
symbolic links to files with the same name in the upper directory.
Would you mind giving this a try ?
Cheers,
This is a warning that can be safely ignored.
That being said, this can be seen as a false positive (unless we fix
flex or its generated output).
Also, and generally speaking, these kind of warnings is for developers
only (e.g. end users can do nothing about that).
That raises the
note Open MPI 1.10.3 has just been released, and you should use it,
install procedure of 1.8.1 should work too.
what is exactly the issue ?
the fortran wrapper is mpifort, mpif90 is just an alias.
is there a Fortran compiler on your system ?
if not, just install one and re configure/make install
Paul,
https://github.com/open-mpi/ompi-release/pull/1178 is ready to be
merged, but the milestone was set to v2.0.1
Cheers,
Gilles
On 6/16/2016 10:40 AM, Paul Hargrove wrote:
I still see failures to build ROMIO on OpenBSD-5.9:
Paul,
NAG related stuff was added in https://github.com/open-mpi/ompi/pull/1295
Milestone was set to v2.0.1 so no PR was even issued (yet) for the v2.x
branch.
If there is a consensus to update the milestone to v2.0.0, i ll be happy
to PR
Cheers,
Gilles
On 6/16/2016 10:32 AM, Paul
Folks,
this is a follow up of a user report available at
http://www.open-mpi.org/community/lists/users/2016/06/29423.php
Basically, one node has a dual port ConnectX3 card, with one IB port and
one 10 GbE port.
When diagnosing some RDMA errors (not the point of this email), the user
was
especially for
reduction operations. It is clearly specified that if you execute
multiple times a collective between the same processes with the same
values and in the context of the same run you should get the exact
same result.
George.
On Friday, June 10, 2016, Gilles Gouaillardet <gil.
Folks,
i was thinking of using the MPI_T interface in order to try within the
same MPI test program *all* the available algo of a given collective.
That cannot currently be done because the mca parameter is registered with
{flag=0, scope=MCA_BASE_VAR_SCOPE_READONLY}
i made a proof of
my 0.02 US$
from an implementation point of view, the canonical way of using Jenkins
with Github is
1) receive/poll a new PR
2) create a "check" and mark it pending
3) run a script
4) update the "check" status (OK/Failed) based on the exit status of the
script.
that being said, it is
fwiw,
the onsided/c_fence_lock test from the ibm test suite hangs
(mpirun -np 2 ./c_fence_lock)
i ran a git bisect and it incriminates commit
b90c83840f472de3219b87cd7e1a364eec5c5a29
commit b90c83840f472de3219b87cd7e1a364eec5c5a29
Author: bosilca
List-Post:
for
Edgar or someone who cares about MPI-IO. Should we worry about this
for 1.10?
I’m inclined to not delay 1.10.3 over this one, but am open to
contrary opinions
On May 26, 2016, at 7:22 PM, Gilles Gouaillardet <gil...@rist.or.jp
<mailto:gil...@rist.or.jp>> wrote:
In my environme
Ralph,
the cxx_win_attr issue is dealt at
https://github.com/open-mpi/ompi/pull/1473
iirc, only big endian and/or sizeof(Fortran integer) > sizeof(int) is
impacted.
the second error seems a bit weirdest at a time.
once in a while, MPI_File_open fails, and when it fails, it always fails
Paul,
here it is https://github.com/open-mpi/ompi-release/pull/1192
Thanks !
Gilles
On 5/25/2016 4:42 PM, Gilles Gouaillardet wrote:
Paul,
please disregard this PR for now, i will make a new one shortly ...
Cheers,
Gilles
On 5/25/2016 4:25 PM, Paul Hargrove wrote:
Thanks Gilles
Paul,
please disregard this PR for now, i will make a new one shortly ...
Cheers,
Gilles
On 5/25/2016 4:25 PM, Paul Hargrove wrote:
Thanks Gilles.
I will retest and follow up in the PR.
-Paul
On Tue, May 24, 2016 at 11:56 PM, Gilles Gouaillardet
<gil...@rist.or.jp <mail
Paul,
this works fine on RHEL7 but not on RHEL6
here is the relevant configure output
< checking for library containing clock_gettime... -lrt
---
> checking for library containing clock_gettime... none required
the reason is clock_gettime was moved from librt into libc between RHEL6
and
Paul,
the v2.x commit message says it was cherry-picked from master.
I can pr this for v1.10 too
Cheers,
Gilles
On Saturday, May 21, 2016, Paul Hargrove wrote:
> The Solaris Studio 12.5 Fortran compiler is not being identified correctly
> by libtool.
> This is the same
Paul,
I was hoping I got some feedback from mpich folks before I commit it into
master and PR to the release branches.
I am fine to merge it and pr now if needed
Cheers,
Gilles
On Saturday, May 21, 2016, Paul Hargrove wrote:
> As before, this RC cannot build ROMIO on
Note this affects OS X only.
in opal/util/ethtool.c, ethtool_cmd_speed must not be defined if not
HAVE_STRUCT_ETHTOOL_CMD
I will not be able to push a fix until tomorrow
Cheers,
Gilles
On Friday, May 20, 2016, George Bosilca wrote:
> Travis seems to be broken due to a
, Gilles Gouaillardet wrote:
Folks,
currently, default mapping policy on master is different than v2.x.
my preliminary question is : when will the master mapping policy land
into the release branch ?
v2.0.0 ? v2.x ? v3.0.0 ?
here are some commands and their output (both n0 and n1 have 16
Samuel,
the (main) reason is none of us are lawyers and none of us know whether
all test suites can be redistributed for general public use or not.
if someone has any interest in the test suites, he/she is free to make a
request for access grant.
Cheers,
Gilles
On 5/18/2016 8:46 AM,
Folks,
currently, default mapping policy on master is different than v2.x.
my preliminary question is : when will the master mapping policy land
into the release branch ?
v2.0.0 ? v2.x ? v3.0.0 ?
here are some commands and their output (both n0 and n1 have 16 cores
each, mpirun runs on
and for non-local
peers with the reachability argument set to NULL (because the bitmask
doesn't provide any benefit when adding only 1 peer).
-Nathan
On Tue, May 17, 2016 at 12:00:38AM +0900, Gilles Gouaillardet wrote:
Jeff,
this is not what I observed
(tcp btl, 2 to 4 nodes with one task
> In short, only BTLs with the same exclusivity level will be considered
> (e.g., this is how we exclude TCP when using HPC-class networks), and then
> the BTL modules with the highest priority will be used for a given peer.
>
>
> > On May 16, 2016, at 7:19 AM, Gilles Gouaillarde
{
>> MPI_Recv(buf, 6, MPI_CHAR, 0, 99, MPI_COMM_WORLD, MPI_STATUS_IGNORE);
>> printf("%s received %s, rank %d\n", hostname, buf, world_rank);
>> }
>> else
>> {
>> strcpy(buf, "haha!");
>> MPI_Send(bu
vises you to eat right, exercise regularly
and quit ageing.
On Sun, May 15, 2016 at 10:49 AM, Gilles Gouaillardet
<gilles.gouaillar...@gmail.com
<mailto:gilles.gouaillar...@gmail.com>> wrote:
At first glance, that seems a bit odd...
are you sure you corre
rgeon general advises you to eat right, exercise regularly and quit
> ageing.
>
> On Sun, May 15, 2016 at 10:20 AM, Gilles Gouaillardet <
> gilles.gouaillar...@gmail.com
> <javascript:_e(%7B%7D,'cvml','gilles.gouaillar...@gmail.com');>> wrote:
>
>> did you check th
did you check the add_procs callbacks ?
(e.g. mca_btl_tcp_add_procs() for the tcp btl)
this is where the reachable bitmap is set, and I guess this is what you are
looking for.
keep in mind that if several btl can be used, the one with the higher
exclusivity is used
(e.g. tcp is never used if
to use ompio
mpirun --mca io ompio ...
to use romio (v2.x)
mpirun --mca io romio314 ...
to use romio (v1.10)
mpirun --mca io romio ...
Cheers,
Gilles
On Wednesday, May 11, 2016, Michael Rezny wrote:
> Hi Sreenidhi,
> you need to specify --collective as an input
Folks,
i found a bug in the mindist_test.c test (missing strdup() cause free()
to crash)
and filed https://github.com/mellanox-hpc/jenkins_scripts/pull/30 to get
it fixed.
Cheers,
Gilles
On 5/11/2016 7:10 AM, Ralph Castain wrote:
Ick - nothing I can do with that blast. I can't find
Thanks Paul,
i pushed your patch at
https://github.com/open-mpi/ompi/commit/ef3ee027b07fa8cd447e4fffec56ecfe3332548e
and will PR from now
Cheers,
Gilles
On 5/6/2016 1:13 PM, Paul Hargrove wrote:
Disclamer first:
Yes, I am testing a *beta* compiler but this is NOT about a compiler bug.
Paul,
on which distro are you running ?
are you compiling on a 64 bit distro to generate a 32 bit library ?
it seems we are currently only testing a atomic on a long (32 bits on a
32 bits arch) and
then incorrectly assume it works also on 64 bits (!)
Cheers,
Gilles
On 5/9/2016 3:59
Paul,
can you please give a try to
https://patch-diff.githubusercontent.com/raw/open-mpi/ompi/pull/1643.patch ?
Cheers,
Gilles
On 5/3/2016 2:21 PM, Paul Hargrove wrote:
This is NOT a new issue, but I wanted to mention it explicitly once
again since no progress has been made since I
Ralph,
the OMPI_ENABLE_MPI_PROFILING related warnings are fixed in
https://github.com/open-mpi/ompi-release/pull/1056
Cheers,
Gilles
On Saturday, April 30, 2016, Ralph Castain wrote:
> On CentOS-7 using gcc 4.8:
>
>
> btl_tcp.c: In function ‘mca_btl_tcp_add_procs’:
>
Thank you
> Durga
>
>
>
> The surgeon general advises you to eat right, exercise regularly and quit
> ageing.
>
> On Thu, Apr 28, 2016 at 2:34 AM, Gilles Gouaillardet <gil...@rist.or.jp
> <javascript:_e(%7B%7D,'cvml','gil...@rist.or.jp');>> wrote:
>
>
the add_procs subroutine of the btl should be called.
/* i added a printf in mca_btl_tcp_add_procs and it *is* invoked */
can you try again with --mca pml ob1 --mca pml_base_verbose 100 ?
maybe the add_procs subroutine is not invoked because openmpi uses cm
instead of ob1
Cheers,
Gilles
12:03 AM, Jeff Squyres (jsquyres) wrote:
On Apr 25, 2016, at 9:50 AM, Gilles Gouaillardet
<gilles.gouaillar...@gmail.com> wrote:
and fwiw, Jeff uses an internally mirrored repo for ompi-tests, so it Cisco
clusters should use the latest test suites.
Correct. My local git mirrors update n
ithub.com/open-mpi/ompi-tests.git
> scm_subdir = ibm
>
> Not sure Ralph meant those errors. But they only happen on ppc64 and not
> on x86_64 with a very similar mtt configuration file.
>
> Adrian
>
> On Mon, Apr 25, 2016 at 10:50:03PM +0900, Gilles Gouaillar
t; I don’t know - this isn’t on my machine, but rather in the weekend and
> nightly MTT reports. I’m assuming folks are running the latest test suite,
> but...
>
>
> On Apr 25, 2016, at 6:20 AM, Gilles Gouaillardet <
> gilles.gouaillar...@gmail.com> wrote:
>
> Ralph,
>
>
Ralph,
can you make sure the ibm test suite is up to date ?
I pushed a fix for datatypes a few days ago, and it should be fine now.
I will double check this tomorrow anyway
Cheers,
Gilles
On Monday, April 25, 2016, Ralph Castain wrote:
> I’m seeing some consistent errors
Folks,
This is a follow-up on a question initially posted on the users ML at
http://www.open-mpi.org/community/lists/users/2016/04/29018.php.
In this environment, there is no link on the Infinipath card.
However, it seems the psm mtl is trying to use it instead of
disqualifying itself at
Nadia,
by any chance, could this test suite be contributed to the ompi-tests
repository ?
Cheers,
Gilles
On Friday, April 15, 2016, DERBEY, NADIA wrote:
> Jeff,
>
> Actually, we have a functional test suite that used to pass for these
> types and it fails now with
George,
about the process binding part
On 4/13/2016 7:32 AM, George Bosilca wrote:
Also my processes, despite the fact that I asked for 1 per node, are not bound
to the first core. Shouldn’t we release the process binding when we know there
is a single process per node (as in the above case)
David,
This is declared via the MCA_BASE_FRAMEWORK_DECLARE macro
https://svn.open-mpi.org/source/xref/ompi_master/opal/mca/installdirs/base/installdirs_base_components.c#175
Cheers,
Gilles
On Sunday, April 10, 2016, David Froger wrote:
> Hello,
>
> Looking at Open
learn from history.
On Fri, Apr 8, 2016 at 12:12 AM, Gilles Gouaillardet
<gil...@rist.or.jp <mailto:gil...@rist.or.jp>> wrote:
Hi,
the hostnames (or their IPs) are only used to ssh orted.
if you use only the tcp btl :
TCP *MPI* communications (vs OOB man
Hi,
the hostnames (or their IPs) are only used to ssh orted.
if you use only the tcp btl :
TCP *MPI* communications (vs OOB management communications) are handled
by btl/tcp
by default, all usable interfaces are used, then messages are split
(iirc, by ob1 pml) and then "fragments"
are sent
an
On 03/25/2016 01:58 AM, Gilles Gouaillardet wrote:
> Sebastian,
>
> at first glance, the global lock in romio glue is not necessary.
>
> feel free to give the attached patch a try
> (it works with your example, and i made no further testing)
>
> Cheers,
>
>
Scott,
out of curiosity ...
generally speaking, and when HT is more efficient, how is it used ?
- flat MPI, with one task per thread
- Hybrid MPI+OpenMP, a task is bound to a core or socket, but never to a
thread
Cheers,
Gilles
On Thursday, March 24, 2016, Atchley, Scott
gets the first
>ids.
>
>
>If MPI_Type_contiguous would work better I am open to switching to that.
>
>
>On Tue, Mar 22, 2016 at 11:06 PM, Gilles Gouaillardet <gil...@rist.or.jp>
>wrote:
>
>Dominik,
>
>with MPI_Type_indexed, array_of_d
eger kinds?
4. What does the blocklength parameter specify exactly. I played with
this some and changing the blocklength did not seem to change anything
Thanks for the help.
-Dominic Kedelty
On Wed, Mar 16, 2016 at 12:02 AM, Gilles Gouaillardet
<gil...@rist.or.jp <mailto:gil...@rist.or
Monika,
is there ant reason why you use openmpi 1.4.5 ?
it is quite antique today, 1.10.2 is the latest stable version.
strictly speaking, openmpi does not require linux, it works fine on
Solaris, bsd variants, Cygwin and other arch.
the memory footprint is made of the library size, and the
if you did not configure with --disable-dlopen, you need to make install
from opal/mca/btl/If
if not, you need make install from your top builddir
you can
mpirun --mca btl_base_verbose 100 ...
to see if your btl was found and did not somehow disqualify itself
(for example because it's priority is
that a configuration file is needed.
all processes return:
STOP A configuration file is required
I am attaching the subroutine of the code that I believe is where the
problem is occuring.
On Mon, Mar 14, 2016 at 6:25 PM, Gilles Gouaillardet
<gilles.gouaillar...@gmail.com <mailto:gilles.gou
actually do think they work fine if you do a GNU build and use
them to
specify the Intel compilers. I also think it works fine when you
do an
Intel build and compile with gcc. So to me it just looks like
that one
include file is the problem.
Dave
Samuel,
there is clearly no hope when you use mpi.mod and mpi_f08.mod
my point was, it is not even possible to expect "legacy" mpif.h work
with different compilers.
and by the way, if the application is compiled with -i8 (fortran integer
is 8 bytes by default), then OpenMPI must have been
Larry,
currently, OpenMPI generate mpif-sizeof.h with up to 15 dimensions with
intel compilers, but up to 7 dimensions with "recent" gcc (for example
gcc 5.2 and higher)
so i guess the logic behind this is "give the compiler all it can
handle", so if intel somehow "extended" the standard to
Dave,
you should not expect anything when mixing Fortran compilers
(and to be on the safe side, you might not expect much when mixing C/C++
compilers too,
for example, if you built ompi with intel and use gcc for your app, gcc
might complain about unresolved symbols from the intel runtime)
include
> Jeff’s warning about debug builds being used for performance testing
>
+1
I’m increasingly feeling that we shouldn’t output that message every time
> someone executes a debug-based operation, even if we add a param to turn
> off the warning.
>
+1
>
> On
t more convenient for those developers who
> don’t would be nice.
>
> > On Mar 2, 2016, at 4:51 AM, Jeff Squyres (jsquyres) <jsquy...@cisco.com
> <javascript:;>> wrote:
> >
> > On Mar 2, 2016, at 6:30 AM, Mark Santcroos <mark.santcr...@rutgers.edu
> <javascrip
a
performance benchmark, then i will not get the warning i need (and yes,
i will be the only one to blame ... but isn't it something we want to
avoid here ?)
Cheers,
Gilles
On 3/2/2016 1:43 PM, George Bosilca wrote:
On Mar 1, 2016, at 22:27 , Gilles Gouaillardet <gil...@rist.or.jp> wrote:
ng opinion, and i am fine with setting a parameter (i
will likely soon forget i set that) in a config file.
Cheers,
Gilles
On 3/2/2016 1:21 PM, Jeff Squyres (jsquyres) wrote:
On Mar 1, 2016, at 10:17 PM, Gilles Gouaillardet <gil...@rist.or.jp> wrote:
In this case, should we only dis
(jsquyres) wrote:
On Mar 1, 2016, at 10:06 PM, Gilles Gouaillardet <gil...@rist.or.jp> wrote:
what about *not* issuing this warning if OpenMPI is built from git ?
that would be friendlier for OMPI developers,
and should basically *not* affect endusers, since they would rather build OMPI
Jeff,
what about *not* issuing this warning if OpenMPI is built from git ?
that would be friendlier for OMPI developers,
and should basically *not* affect endusers, since they would rather
build OMPI from a tarball.
Cheers,
Gilles
On 3/2/2016 1:00 PM, Jeff Squyres (jsquyres) wrote:
WHAT:
fwiw
in a previous thread, Jeff Hammond explained this is why mpich is
relying on C89 instead of C99,
since C89 appears to be a subset of C++11.
Cheers,
Gilles
On 3/2/2016 1:02 AM, Nathan Hjelm wrote:
I will add to how crazy this is. The C standard has been very careful
to not break
Adrian,
About bitness, it is correctly set when MPI install successes
See https://mtt.open-mpi.org/index.php?do_redir or even your successful
install on x86_64
I suspect it is queried once the installation is successful, and I ll try
to have a look at it.
Cheers,
Gilles
On Tuesday, March 1,
Ralph,
The goal here is to allow vendor to distribute binary orte frameworks
(on top of binary components they can already distribute) that can be used
by a user compiled "stock" openmpi library).
Did I get it right so far ?
I gave it some thoughts and found that could be simplified.
My
201 - 300 of 758 matches
Mail list logo