Iain,
Thanks for the reply, yours sounds like a good suggestion to try to
work around this.
Steve
Iain Bason wrote:
On Apr 6, 2009, at 7:22 PM, Steve Lowder wrote:
Recently I've been running an MPI code that uses the LAPACK slamch
routine to determine machine precision parameters. This s
On Tue, Apr 07, 2009 at 02:23:45PM -0600, Ralph Castain wrote:
> It isn't in a file - unless you specify it, OMPI will set it
> automatically based on the number of procs on the node vs. what OMPI
> thinks are the number of available processors. The question is: why
> does OMPI not correctly
Does OpenMPI know about the number of CPUS per node for FreeBSD?
DM
On Tue, 7 Apr 2009, Ralph Castain wrote:
I would really suggest looking at George's note first as I think you are
chasing your tail here. It sounds like the most likely problem is that OMPI
thinks you are oversubscribed and i
It isn't in a file - unless you specify it, OMPI will set it
automatically based on the number of procs on the node vs. what OMPI
thinks are the number of available processors. The question is: why
does OMPI not correctly know the number of processors on your machine?
I don't remember now,
On Tue, Apr 07, 2009 at 01:40:13PM -0600, Ralph Castain wrote:
> I would really suggest looking at George's note first as I think you
> are chasing your tail here. It sounds like the most likely problem is
> that OMPI thinks you are oversubscribed and is setting sched_yield
> accordingly. whi
I would really suggest looking at George's note first as I think you
are chasing your tail here. It sounds like the most likely problem is
that OMPI thinks you are oversubscribed and is setting sched_yield
accordingly. which would fully account for these diffs.
Note that the methods for set
On Tue, Apr 07, 2009 at 03:18:31PM -0400, George Bosilca wrote:
> Steve,
>
> I spotted a strange value for the mpi_yield_when_idle MCA parameter. 1
> means your processor is oversubscribed, and this trigger a call to
> sched_yield after each check on the SM. Are you running the job
> oversub
On Tue, Apr 07, 2009 at 12:00:55PM -0700, Mostyn Lewis wrote:
> Steve,
>
> Did you rebuild 1.2.9? As I see you have static libraries, maybe there's
> a lurking phthread or something else that may have changed over time?
>
> DM
Yes. I downloaded 1.2.9, 1.3, and 1.3.1, all within minutes of each
Hi Steve,
I see improvements in 1.3.1 as compared to 1.2.9 in Netpipe results.
The below Open MPI installations were compiled with the same compiler,
configure options, run on the same cluster, and run with the same MCA
parameters. (Note, ClusterTools 8.2 is essentially
1.3.1r20828.)
http://www
Steve,
I spotted a strange value for the mpi_yield_when_idle MCA parameter. 1
means your processor is oversubscribed, and this trigger a call to
sched_yield after each check on the SM. Are you running the job
oversubscribed? If not it looks like somehow we don't correctly
identify that th
Steve,
Did you rebuild 1.2.9? As I see you have static libraries, maybe there's
a lurking phthread or something else that may have changed over time?
DM
On Tue, 7 Apr 2009, Steve Kargl wrote:
On Tue, Apr 07, 2009 at 09:10:21AM -0700, Eugene Loh wrote:
Steve Kargl wrote:
I can rebuild 1.2.9
[node20.cimu.org:90002] btl_sm_bandwidth=900 (default value)
[node20.cimu.org:90002] btl_sm_latency=100 (default value)
All these params do is influence the selection logic for deciding
which BTL to use to send the data. Since you directed OMPI to only use
sm, they are irrelevant.
On Apr
On Tue, Apr 07, 2009 at 09:10:21AM -0700, Eugene Loh wrote:
> Steve Kargl wrote:
>
> >I can rebuild 1.2.9 and 1.3.1. Is there any particular configure
> >options that I should enable/disable?
>
> I hope someone else will chime in here, because I'm somewhat out of
> ideas. All I'm saying is tha
On Tue, Apr 07, 2009 at 08:39:20AM -0700, Eugene Loh wrote:
> Iain Bason wrote:
>
> >But maybe Steve should try 1.3.2 instead? Does that have your
> >improvements in it?
>
> 1.3.2 has the single-queue implementation and automatic sizing of the sm
> mmap file, both intended to fix problems at
Hi Francesco
Sorry, I was out of the loop, doing some real work ... :)
Jody and Terry already gave you great advice (as they always do),
and got you moving in the right direction, which is great news!
More comments below.
I think we need to cut this message short,
for good mailing list etiquett
On Tue, Apr 07, 2009 at 08:00:39AM -0700, Eugene Loh wrote:
> Iain Bason wrote:
>
> >There are a bunch changes in the shared memory module between 1.2.9
> >and 1.3.1. One significant change is the introduction of the "sendi"
> >internal interface. I believe George Bosilca did the initial
>
On Tuesday 07 April 2009, Eugene Loh wrote:
> Iain Bason wrote:
> > But maybe Steve should try 1.3.2 instead? Does that have your
> > improvements in it?
>
> 1.3.2 has the single-queue implementation and automatic sizing of the sm
> mmap file, both intended to fix problems at large np. At np=2, y
Steve Kargl wrote:
I can rebuild 1.2.9 and 1.3.1. Is there any particular configure
options that I should enable/disable?
I hope someone else will chime in here, because I'm somewhat out of
ideas. All I'm saying is that 10-usec latencies on sm with 1.3.0 or
1.3.1 are out of line with what o
Iain Bason wrote:
But maybe Steve should try 1.3.2 instead? Does that have your
improvements in it?
1.3.2 has the single-queue implementation and automatic sizing of the sm
mmap file, both intended to fix problems at large np. At np=2, you
shouldn't expect to see much difference.
And th
On Tuesday 07 April 2009, Bernhard Knapp wrote:
> Hi
>
> I am trying to get a parallel job of the gromacs software started. MPI
> seems to boot fine but unfortunately it seems not to be able to open a
> specified file although it is definitly in the directory where the job
> is started.
Do all the
On Apr 7, 2009, at 11:00 AM, Eugene Loh wrote:
Iain Bason wrote:
There are a bunch changes in the shared memory module between
1.2.9 and 1.3.1. One significant change is the introduction of
the "sendi" internal interface. I believe George Bosilca did the
initial implementation. Thi
Iain Bason wrote:
There are a bunch changes in the shared memory module between 1.2.9
and 1.3.1. One significant change is the introduction of the "sendi"
internal interface. I believe George Bosilca did the initial
implementation. This is just a wild guess, but maybe there is
somethin
On Apr 6, 2009, at 7:22 PM, Steve Lowder wrote:
Recently I've been running an MPI code that uses the LAPACK slamch
routine to determine machine precision parameters. This software is
compiled using the latest Intel Fortran compiler and setting the -
fpe0 argument to watch for certain floa
There are a bunch changes in the shared memory module between 1.2.9
and 1.3.1. One significant change is the introduction of the "sendi"
internal interface. I believe George Bosilca did the initial
implementation. This is just a wild guess, but maybe there is
something about sendi that i
Hi Gustavo:
"I feel myself stupid enough in this circumstance."
That was the case. Adjusted as indicated by Jody, the connectivity
test passed and the hello test:
Hello, world, I am 0 of 4
1 of 4
2 of 4
3 of 4
Combine
Hi Jody:
I should only blame myself. Gustavo's indications were clear. Still, I
misunderstood them.
Since I am testing on one node (where everything is there)
mpirun -host deb64 -n 4 connectivity_c
Connectivity test on 4 processes PASSED
thanks
francesco
On Tue, Apr 7, 2009 at 12:27 PM, jody
OMPI doesn't do anything wrt your file, so it can only be a question
of (a) is your file on the remote machine, and (b) what directory it
is in relative to where your process starts.
Try just running pwd with mpirun and see what directory you are in.
The you can ssh to that node and do an "
Dear Ralph and other users
I tried both versions with the relative path and with the -wdir option
but in both cases the error is still the same. Additionally I tried to
simply start the job in my home directory but it does not help either
... any other ideas?
thx
Bernhard
[bknapp@quoVadis0
I assume you are running in a non-managed environment and so are using
ssh for your launcher? Could you tell us what version of OMPI you are
using?
The problem is that ssh drops you in your home directory, not your
current working directory. Thus, the path to any file you specify must
be
Hi
I am trying to get a parallel job of the gromacs software started. MPI
seems to boot fine but unfortunately it seems not to be able to open a
specified file although it is definitly in the directory where the job
is started. I also changed the file permissions to 777 but it does not
affect
Hi
What are the options "-deb64" and "-1" you are passing to mpirun:
> /usr/local/bin/mpirun -deb64 -1 connectivity_c 2>&1 | tee n=1.connectivity.out
I don't think these are legal options for mpirun (at least they don't
show up in `man mpirun`).
And i think you should add a "-n 4" (for 4 processo
On Tue, 2009-04-07 at 11:39 +0200, Francesco Pietra wrote:
> Hi Gus:
> I should have set clear at the beginning that on the Zyxel router
> (connected to Internet by dynamic IP afforded by the provider) there
> are three computers. Their host names:
>
> deb32 (desktop debian i386)
>
> deb64 (mult
Hi Gus:
I should have set clear at the beginning that on the Zyxel router
(connected to Internet by dynamic IP afforded by the provider) there
are three computers. Their host names:
deb32 (desktop debian i386)
deb64 (multisocket debian amd 64 lenny)
tya64 (multisocket debian amd 64 lenny)
The
Thank you sir, thanks a lot.
The information you provided helped us a lot. Am currently going through the
OpenMPI FAQ and will contact you in case of any doubts.
Regards,
Ankush Kaul
34 matches
Mail list logo
