Re: [OMPI users] resolution of MPI_Wtime

Open MPI uses clock_gettime when it is available, and defaults to gettimeofday only when this better option can't be found. Check that your system has clock_gettime and the resolution of this timer. Aurélien -- Aurélien Bouteiller, Ph.D. ~~ https://icl.cs.utk.edu/~bouteill/ > Le 5 a

Re: [OMPI users] Setting coll_sm_priority = 35 didn't improve communication performance

Try to run with coll_base_verbose 1000, just to see what collective module got effectively loaded. Aurélien -- Aurélien Bouteiller, Ph.D. ~~ https://icl.cs.utk.edu/~bouteill/ <https://icl.cs.utk.edu/~bouteill/> > Le 9 déc. 2015 à 09:53, Saliya Ekanayake a écrit : > > Hi, >

Re: [OMPI users] OpenMPI with infiniband, child processes of mpirun are missing or overlapped on the same cpu

Not by default. It can be done with a rankfile, but the observed behavior is normal when launching two mpirun with the same machinefile and all default options. Aurélien -- Aurélien Bouteiller, Ph.D. ~~ https://icl.cs.utk.edu/~bouteill/ <https://icl.cs.utk.edu/~bouteill/> > Le 24 no

Re: [OMPI users] OpenMPI with infiniband, child processes of mpirun are missing or overlapped on the same cpu

You can use the 'mpirun -report-bindings’ option to see how your processes have been mapped in your deployment. If you are unhappy with the default, you can play with the -map-by option. Aurélien -- Aurélien Bouteiller, Ph.D. ~~ https://icl.cs.utk.edu/~bouteill/ <https://icl.cs

Re: [OMPI users] Problems running linpack benchmark on old Sunfire opteron nodes

ev/all, type: string) MCA orte: parameter "orte_local_tmpdir_base" (current value: "", data source: default, level: 9 dev/all, type: string) MCA orte: parameter "orte_remote_tmpdir_base" (current value: "", data source: default, leve

Re: [OMPI users] error building BLACS with openmpi 1.8.4 and intel 2015

Irena, This is a known problem in BLACS. I have pushed a patch to the scalapack devs and I believe the latest version (the one that is integrated into scalapack 2.0) does include the fix. Aurelien -- Aurélien Bouteiller ~ https://icl.cs.utk.edu/~bouteill/ > Le 6 mars 2015 à 09:31, Ir

Re: [OMPI users] Help on getting CMA works

Nathan, I think I already pushed a patch for this particular issue last month. I do not know if it has been back ported to release yet. See here:https://github.com/open-mpi/ompi/commit/ee3b0903164898750137d3b71a8f067e16521102 Aurelien -- ~~~ Aurélien Bouteiller, Ph.D

Re: [OMPI users] knem in Open MPI 1.8.3

Are you sure you are not using the vader BTL ? Setting mca_btl_base_verbose and/or sm_verbose should spit out some knem initialization info. The CMA linux system (that ships with most 3.1x linux kernels) has similar features, and is also supported in sm. Aurelien -- ~~~ Aurélien

[OMPI users] Open MPI on Cray xc30 and getpwuid

ions requires at runtime the shared libraries from the glibc version used for linking Of course, the resulting code does crash in getpwuid. I know Nathan has successfully compiled for cray machines. What’s the trick ? Aurelien -- ~~~ Aurélien Bouteiller, Ph.D. ~~~ ~

Re: [OMPI users] [Boost-mpi] openmpi 1.6.2 boost 1.54 mswin7 vs2010 Threading support:No

Le 13 févr. 2014 à 15:23, MM a écrit : > my ompi_info says (openmpi) > Threading support: No > > Does that mean it's not supported? > Yes, that’s what it means. > If so, what to do? > Gently ignore that information. Open MPI works for “serialized” workloads, even when thread support is di

Re: [OMPI users] Message queue in MPI?

an MPI > message queue can I expect before something breaks? > > ---John > > ___ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Researcher at Inno

Re: [OMPI users] How to reduce Isend & Irecv bandwidth?

>Jacky >> >> >>_ >>users mailing list >>us...@open-mpi.org <mailto:us...@open-mpi.org> >>http://www.open-mpi.org/__mailman/listinfo.cgi/users >><h

Re: [OMPI users] Myricom MX2G Segmentation fault on OMPI 1.6

Le 11 juin 2012 à 18:57, Aurélien Bouteiller a écrit : > Hi, > > If some mx devices are found, the logic is not only to use the mx BTL but > also to use the mx MTL. You can try to disable this with --mca mtl ob1. > Sorry, I meant --mca pml ob1 > Aurelien > > >

Re: [OMPI users] Myricom MX2G Segmentation fault on OMPI 1.6

> mpirun noticed that process rank 0 with PID 3460 on node n0007.scs00 > exited on signal 11 (Segmentation fault). > -- > <> > > > Can anybody shed some light here? It looks like omp

Re: [OMPI users] mpicc, mpif90, ... not created during installation

elien Le 1 juin 2012 à 09:27, Jeff Squyres a écrit : > On Jun 1, 2012, at 8:20 AM, Aurélien Bouteiller wrote: > >> You need to pass the following option to configure: >> --with-devel-headers --enable-binaries >> >> I don't know exactly why the default is not

Re: [OMPI users] mpicc, mpif90, ... not created during installation

> users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Researcher at Innovative Computing Laboratory * University of Tennessee * 1122 Volunteer Boulevard, suite 309b * Knoxville, TN 37996

Re: [OMPI users] Need Performance estimation of MPI_Bcast

You can use the intel mpi benchmark, or skampi. These two programs are designed to evaluate Moi performance. Envoyé de mon iPad Le 2012-04-04 à 08:46, anas trad a écrit : > Hi all, > > I need to know the time estimation of executing MPI_Bcast function on Neolith > Cluster. Please, can anyone

[OMPI users] mpi_abort_delay

) ? -- * Dr. Aurélien Bouteiller * Researcher at Innovative Computing Laboratory * University of Tennessee * 1122 Volunteer Boulevard, suite 350 * Knoxville, TN 37996 * 865 974 6321 signature.asc Description: Message signed with OpenPGP using GPGMail

Re: [OMPI users] MPI_Bcast issue

You should consider reading about communicators in MPI. Aurelien -- Aurelien Bouteiller, Ph.D. Innovative Computing Laboratory, The University of Tennessee. Envoyé de mon iPad Le Aug 7, 2010 à 1:05, Randolph Pullen a écrit : > I seem to be having a problem with MPI_Bcast. > My massive I/O int

Re: [OMPI users] OpenMPI providing rank?

Yves, In Open MPI you can have a very fine control over how the deployment is bound to the cores. For more information, please refer to the faq concerning the rankfile description (in a rankfile you can specify very precisely what rank goes on what physical PU). For a more single shot option,

Re: [OMPI users] Segmentation fault when Send/Recv on heterogeneouscluster (32/64 bit machines)

Hi, setting the eager limit to such a drastically high value will have the effect of generating gigantic memory consumption for unexpected messages. Any message you send which does not have a preposted ready recv will mallocate 150mb of temporary storage, and will be memcopied from that intern

Re: [OMPI users] Error message when using MPI_Type_struct()

Hi Thomas, The message you get comes from the convertor. The convertor is in charge of packing/unpacking the data. As you add yourself an extra int to the wire data, the convertor gets confused on the receiver side, as it gets a message that's not in the expected format. What you should

Re: [OMPI users] OpenMPI 1.3RC2 job startup issue

___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteille

Re: [OMPI users] help with mpi

tp://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Sr. Research Associate at Innovative Computing Laboratory * University of Tennessee * 1122 Volunteer Boulevard, suite 350 * Knoxville, TN 37996 * 865 974 6321

Re: [OMPI users] using of MPI_Publish_name with openmpi

external name server called ompi-server. I can give you more details if you want to try the svn version. Regards, Aurelien -- * Dr. Aurélien Bouteiller * Sr. Research Associate at Innovative Computing Laboratory * University of Tennessee * 1122 Volunteer Boulevard, suite 350 * Knoxville, TN 37996

Re: [OMPI users] Performance: MPICH2 vs OpenMPI

Cheers, - Brian Brian Dobbins Yale Engineering HPC ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Sr. Research Associate at Innovative Computing Laboratory * University

Re: [OMPI users] Problem launching onto Bourne shell

set properly? Thanks! Hahn -- Hahn Kim, h...@ll.mit.edu MIT Lincoln Laboratory 244 Wood St., Lexington, MA 02420 Tel: 781-981-0940, Fax: 781-981-5255 ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users

Re: [OMPI users] Crashes over TCP/ethernet but not on shared memory

If you have several network cards in your system, it can sometime get the endpoints confused. Especially if you don't have the same number of cards or don't use the same subnet for all "eth0, eth1". You should try to restrict Open MPI to use only one of the available networks by using the -

Re: [OMPI users] Segmentation Fault--libc.so.6(__libc_start_main...

replaced that with OMPI. Could that be the problem?? Do I need to change any part of my source code if I migrate from MPICH-1.2.6 to OpenMPI-1.2.7?? Please let me know. --- On Sat, 9/20/08, Aurélien Bouteiller wrote: From: Aurélien Bouteiller Subject: Re: [OMPI users] Segmentation Fault--li

Re: [OMPI users] Segmentation Fault--libc.so.6(__libc_start_main...

list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Sr. Research Associate at Innovative Computing Laboratory * University of Tennessee * 1122 Volunteer Boulevard, suite 350 * Knoxville, TN 37996 * 865 974 6321

Re: [OMPI users] MPI_sendrecv = MPI_Send+ MPI_RECV ?

ORLD,ierr) end do end if ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bout

[OMPI users] Opal documentation

Do you know where to find a comprehensive document for Opal interface functions and user guide ? thanks, Aurelien -- * Dr. Aurélien Bouteiller * Sr. Research Associate at Innovative Computing Laboratory * University of Tennessee * 1122 Volunteer Boulevard, suite 350 * Knoxville, TN 37996

Re: [OMPI users] how to make a process start and then join a MPI group

comm_merge returns (long pause inserted via parent sleep) parent sends data to kid 1 (long pause inserted via parent sleep) parent starts to receive data from kid 1 all children's calls to MPI_Intercomm_merge return -- Mark Aurélien Bouteiller wrote: Ok, I'll check to see what happens.

Re: [OMPI users] how to make a process start and then join a MPI group

users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Sr. Resear

Re: [OMPI users] Want to build a static openmpi with both myrinet and tcp

___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Sr. Research Associate at Innovative Computing Laboratory * University of Tennessee * 1122 Volunteer Boulevard, suite 350 * Knoxville, TN

Re: [OMPI users] how to make a process start and then join a MPI group

MPI_Intercomm_merge is what you are looking for. Aurelien Le 26 juil. 08 à 13:23, Mark Borgerding a écrit : Okay, so I've gotten a little bit closer. I'm using MPI_Comm_spawn to start several children processes. The problem is that the children are in their own group, separate from the pa

Re: [OMPI users] vprotocol pessimist

This is a harmless error, related to fault tolerance component. If you don't need FT, you can safely ignore it. It will disappear soon. Aurelien Le 15 juil. 08 à 11:22, Tom Riddle a écrit : Hi, I wonder if anyone can shed some light on what exactly this is referring to? At the start of a

Re: [OMPI users] A simple mpi code hangs at MPI_Init?

Hi, There is no mpd in Open MPI. mpirun will spawn everything needed for you. Make sure all your processes call MPI_Init, and not only the root process. If you mpirun -np 10, 10 processes need to go trough MPI_Init to allow for further progression. If this does not solve you problem, plea

Re: [OMPI users] Enabling progress thread

You can add --enable-progress-threads to the configure. However, please consider this as a beta feature. We know for sure there is some bugs in current thread safety. Aurelien Le 1 mai 08 à 09:46, Alberto Giannetti a écrit : In message http://www.open-mpi.org/community/lists/users/ 2007/03

Re: [OMPI users] Client/Server test

ERN: internal error [alberto-giannettis-computer.local:07933] *** MPI_ERRORS_ARE_FATAL (goodbye) Why do I have an internal error? If I try to connect to 0.1.1:2001 from the client the program hangs. ___ users mailing list us...@open-mpi.org http://www.

Re: [OMPI users] Message compression in OpenMPI

From a pretty old experiment I made, compression was giving good results on 10Mbps network but was actually decreasing RTT on 100Mbs and more. I played with all the zlib settings from 1 to 9, and actually even the low compression setting was unable to reach decent performance. I don't belie

Re: [OMPI users] i386 with x64

). Aurelien Le 11 avr. 08 à 05:34, jody a écrit : Aurelien: What is the cause of this performance penalty? Jody On Fri, Apr 11, 2008 at 1:44 AM, Aurélien Bouteiller wrote: Open MPI can manage heterogeneous system. Though you prefer to avoid this because it has a performance penalty. I suggest

Re: [OMPI users] i386 with x64

Open MPI can manage heterogeneous system. Though you prefer to avoid this because it has a performance penalty. I suggest you compile on the 32bit machine and use the same version everywhere. Aurelien Le 10 avr. 08 à 18:09, clark...@clarktx.com a écrit : Thanks to those who answered my post i

Re: [OMPI users] MPI_Allreduce()

If you can avoid them it is better to avoid them. However it is always better to use a MPI_Alltoall than coding your own all to all with point to point, and in some algorithms you *need* to make a all to all communication. What you should understand by "avoid all to all" is not avoid MPI_al

Re: [OMPI users] pml_v question

Autonoma de Barcelona - UAB ETSE, Edifcio Q, QC/3088 http://www.caos.uab.es Phone: +34-93-581-2888 Fax: +34-93-581-2478 ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Sr

Re: [OMPI users] -prefix option to mpirun.

http://www.open-mpi.org/community/lists/users/2006/01/0480.php Yours, Ashley Pittman. ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- * Dr. Aurélien Bouteiller * Sr. Research Associate at Innovat

Re: [OMPI users] Performance do not scale at all when run jobs on same single node (Rocks, AMD Barcelona, Torque, Maui, Vasp, Openmpi, Gigabit Ethernet)

and suggestions on how to resolve these performance issues. Thank you very much. ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- Dr. Aurélien Bouteiller Sr. Research Associate - Innovative Computing Labor

Re: [OMPI users] funnel-threaded application blocks from time to time

your time and looking forward to your answer(s)! Alex ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users Dr. Aurélien Bouteiller Sr. Research Associate - Innovative Computing Laboratory Suite 350, 1122 Volunteer Boulevard Knoxville, TN 37996 865 974 6321

Re: [OMPI users] A beginer's question

@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- Dr. Aurélien Bouteiller Sr. Research Associate - Innovative Computing Laboratory Suite 350, 1122 Volunteer Boulevard Knoxville, TN 37996 865 974 6321

Re: [OMPI users] MPI piggyback mechanism

ynamic Statistical Profiling of Communication Activity in Distributed Applications". They add support for piggyback at MPI implementation level and report very low overheads (no surprise). Regards, Oleg Morajko On Feb 1, 2008 5:08 PM, Aurélien Bouteiller wrote: I don't know of

Re: [OMPI users] MPI piggyback mechanism

ailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users -- Dr. Aurélien Bouteiller Sr. Research Associate - Innovative Computing Laboratory Suite 350, 1122 Volunteer Boulevard Knoxville, TN 37996 865 974 6321

Re: [OMPI users] Using open-mpi app on a normal network

You can do it, it might or might not make sense, depending on your application. Load imbalance in regular MPI applications kills performance. Therefore if your cluster is very heterogeneous, you might prefer some different programming paradigm that take care of this by nature (let say RPC).

Re: [OMPI users] mixed myrinet/non-myrinet nodes

Using the --mca btl ^mx totally prevents use of mx interface. So everybody uses tcp (even mx capable nodes). If you want a mixed configuration you have to enforce use of the ob1 pml, but let the mx btl be used where it is suitable (it will be disabled at runtime if it can't run). You're pro

Re: [OMPI users] how to select a specific network

led --> Returned "Unreachable" (-12) instead of "Success" (0) -- *** An error occurred in MPI_Init *** before MPI was initialized *** MPI_ERRORS_ARE_FATAL (goodbye) *** An error occurred in MPI_Init *** before MPI was initialized *** MPI_ERRORS_ARE_FATAL (goodbye) burl-ct-v4

Re: [OMPI users] how to select a specific network

___ ___ users mailing list us...@open-mpi.org http://www.open-mpi.org/mailman/listinfo.cgi/users Dr. Aurélien Bouteiller Sr. Research Associate - Innovative Computing Laboratory Suite 350, 1122 Volunteer Boulevard Knoxville, TN 37996 865 974 6321