Re: [OMPI devel] 1.7.x support statement
On Oct 4, 2013, at 8:38 AM, marco atzeriwrote: > At first glance it does not seems particular user friendly nor with a clear > HOWTO guide for good start. How's this for a start: https://svn.open-mpi.org/trac/mtt/wiki/OMPITesting > Additional LWP::Protocol::https is not available so > some expectation are not fullfilled. We might be able to work around this. > Anything as simple as > http://mvapich.cse.ohio-state.edu/benchmarks/ > is available for performing MTT tests ? Let me clarify: MTT is the engine to run MPI tests -- it's not MPI tests or benchmarks itself. MTT is simply a way to download the nightly tarball, build it N ways, get lots of tests (e.g., the OSU benchmarks), compile each of them against each of the N OMPI builds, and then run each of those tests M different ways, and then submit those results up to our community database. Once you have MTT up and running, it can run fairly largely automated -- mine runs in a cron job, for example. Make sense? -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
Re: [OMPI devel] oshmem 32 bit compile failures
On Oct 4, 2013, at 1:51 PM, Mike Dubmanwrote: > the code passes compilation with gcc/icc 32bit toolkits. > We don`t have absoft fortran compiler in the lab, is there any way we can > have it to try? No -- Absoft themselves run the test and simply upload to our MTT (i.e., I don't have an Absoft license). However, note that this problem is not in the Fortran code (Absoft is a Fortran-only compiler; it uses gcc/g++ for C/C++). It says that it is using gcc 4.1.2. Can you try a 32 bit build with gcc 4.1.x? -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
Re: [OMPI devel] oshmem 32 bit compile failures
Hi, the code passes compilation with gcc/icc 32bit toolkits. We don`t have absoft fortran compiler in the lab, is there any way we can have it to try? Igor has some wild guess about what problem can be and created patch (attached). Could you try to apply it on OMPI tree and check with absoft compiler? Thanks M On Fri, Oct 4, 2013 at 2:46 PM, Jeff Squyres (jsquyres)wrote: > Absoft is seeing compile failures for oshmem. Here's one example: > > http://mtt.open-mpi.org/index.php?do_redir=2132 > > If you scroll down through the stderr, it looks like there's a problem in > oshmsm/op/op.c. Perhaps it's just a missing header file, or some code in > an #if/#else that isn't compiled/checked often...? > > -- > Jeff Squyres > jsquy...@cisco.com > For corporate legal information go to: > http://www.cisco.com/web/about/doing_business/legal/cri/ > > ___ > devel mailing list > de...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/devel > 2943-issue.patch Description: Binary data
Re: [OMPI devel] 1.6.5 large matrix test doesn't pass (decode) ?
It is a bug in the test program, test/datatype/ddt_raw.c, and it was fixed at r24328 in trunk. https://svn.open-mpi.org/trac/ompi/changeset/24328 I've confirmed the failure occurs with plain v1.6.5 and it doesn't occur with patched v1.6.5. Thanks, KAWASHIMA Takahiro > Not sure if this is important, or expected, but I ran a make check out > of interest after seeing recent emails and saw the final one of these > tests be reported as "NOT PASSED" (it seems to be the only failure). > > No idea if this is important or not. The text I see is: > > # > * TEST UPPER MATRIX > # > > test upper matrix > complete raw in 7 microsec > decode [NOT PASSED] > > > This happens on both our Nehalem and SandyBridge clusters and we are > building with the system GCC. I've attached the full log from our > Nehalem cluster (RHEL 6.4). > > > Our configure script is: > > #!/bin/bash > > BASE=`basename $PWD | sed -e s,-,/,` > > module purge > > ./configure --prefix=/usr/local/${BASE} --with-slurm --with-openib \ > --enable-static --enable-shared > > make -j > > > I'm away on leave next week (first break for a year, yay!) but back > the week after.. > > All the best, > Chris
Re: [OMPI devel] 1.7.x support statement
Il 10/4/2013 1:47 PM, Jeff Squyres (jsquyres) ha scritto: Good call; yes. Marco: is there any chance you can run Open MPI through the MPI Testing Tool (MTT) on a regular basis, and submit your results to mtt.open-mpi.org? You can run as few or as many tests a night as you want. For example, the Absoft compiler company runs only hello world and ring MPI tests each night (i.e., their goal is to ensure that everything is *compiling* correctly with their compiler, and then they only have to run a small number of tests to ensure that stuff is actually running properly). I'd be happy to chat with you about this to get you started with MTT. Jeff, At first glance it does not seems particular user friendly nor with a clear HOWTO guide for good start. Additional LWP::Protocol::https is not available so some expectation are not fullfilled. Anything as simple as http://mvapich.cse.ohio-state.edu/benchmarks/ is available for performing MTT tests ? Regards Marco
Re: [OMPI devel] 1.7.x support statement
Good call; yes. Marco: is there any chance you can run Open MPI through the MPI Testing Tool (MTT) on a regular basis, and submit your results to mtt.open-mpi.org? You can run as few or as many tests a night as you want. For example, the Absoft compiler company runs only hello world and ring MPI tests each night (i.e., their goal is to ensure that everything is *compiling* correctly with their compiler, and then they only have to run a small number of tests to ensure that stuff is actually running properly). I'd be happy to chat with you about this to get you started with MTT. On Oct 4, 2013, at 7:33 AM, marco atzeriwrote: > Il 10/4/2013 1:08 PM, Jeff Squyres (jsquyres) ha scritto: >> This is in the README -- is it still accurate? I'm thinking that all >> Solaris support should move to the "lightly but not fully tested" category, >> for example: >> >> - >> - Systems that have been tested are: >> - Linux (various flavors/distros), 32 bit, with gcc >> - Linux (various flavors/distros), 64 bit (x86), with gcc, Absoft, >> Intel, Portland, and Oracle Solaris Studio 12.3 compilers (*) >> - OS X (10.5, 10.6, 10.7), 32 and 64 bit (x86_64), with gcc and >> Absoft compilers (*) >> - Oracle Solaris 10 and 11, 64 bit (SPARC, i386, x86_64), >> with Oracle Solaris Studio 12.2 and 12.3 >> >> (*) Be sure to read the Compiler Notes, below. >> >> - Other systems have been lightly (but not fully tested): >> - Other 64 bit platforms (e.g., Linux on PPC64) >> - 32-bit Solaris >> - >> > > you can add on the "Other systems" > Cygwin 32 & 64 bit with gcc > > Regards > Marco > > ___ > devel mailing list > de...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/devel -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
[OMPI devel] oshmem 32 bit compile failures
Absoft is seeing compile failures for oshmem. Here's one example: http://mtt.open-mpi.org/index.php?do_redir=2132 If you scroll down through the stderr, it looks like there's a problem in oshmsm/op/op.c. Perhaps it's just a missing header file, or some code in an #if/#else that isn't compiled/checked often...? -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
Re: [OMPI devel] 1.7.x support statement
Il 10/4/2013 1:08 PM, Jeff Squyres (jsquyres) ha scritto: This is in the README -- is it still accurate? I'm thinking that all Solaris support should move to the "lightly but not fully tested" category, for example: - - Systems that have been tested are: - Linux (various flavors/distros), 32 bit, with gcc - Linux (various flavors/distros), 64 bit (x86), with gcc, Absoft, Intel, Portland, and Oracle Solaris Studio 12.3 compilers (*) - OS X (10.5, 10.6, 10.7), 32 and 64 bit (x86_64), with gcc and Absoft compilers (*) - Oracle Solaris 10 and 11, 64 bit (SPARC, i386, x86_64), with Oracle Solaris Studio 12.2 and 12.3 (*) Be sure to read the Compiler Notes, below. - Other systems have been lightly (but not fully tested): - Other 64 bit platforms (e.g., Linux on PPC64) - 32-bit Solaris - you can add on the "Other systems" Cygwin 32 & 64 bit with gcc Regards Marco
[OMPI devel] RFC: remove udapl BTL
WHAT: Remove the udapl BTL from the trunk (it's not in v1.7) WHY: No one is using it WHERE: README, config/ompi_check_udapl.m4, and ompi/mca/btl/udapl TIMEOUT: Tuesday October 15 teleconf - While editing the 1.7.x README this morning, I noticed: - we still document --with-udapl - the udapl BTL isn't in the v1.7 branch Sun/Oracle was the only organization using and maintaining the udapl BTL. They're long gone, so why not delete the UDAPL BTL? It can always be brought back out of SVN history if someone wants to resurrect it. There's no real rush to delete this from the trunk; I just bring it up because it's old kruft (that has likely bit-rotted) that we should probably not forget to remove. -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
[OMPI devel] 1.7.x support statement
This is in the README -- is it still accurate? I'm thinking that all Solaris support should move to the "lightly but not fully tested" category, for example: - - Systems that have been tested are: - Linux (various flavors/distros), 32 bit, with gcc - Linux (various flavors/distros), 64 bit (x86), with gcc, Absoft, Intel, Portland, and Oracle Solaris Studio 12.3 compilers (*) - OS X (10.5, 10.6, 10.7), 32 and 64 bit (x86_64), with gcc and Absoft compilers (*) - Oracle Solaris 10 and 11, 64 bit (SPARC, i386, x86_64), with Oracle Solaris Studio 12.2 and 12.3 (*) Be sure to read the Compiler Notes, below. - Other systems have been lightly (but not fully tested): - Other 64 bit platforms (e.g., Linux on PPC64) - 32-bit Solaris - -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
[OMPI devel] Please check 1.7.3 NEWS bullets
In preparation for 1.7.3, I updated the NEWS bullets. Please check and verify that your favorite items are listed (and are correct): https://svn.open-mpi.org/trac/ompi/browser/branches/v1.7/NEWS#L56 -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
[OMPI devel] 1.6.5 large matrix test doesn't pass (decode) ?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Not sure if this is important, or expected, but I ran a make check out of interest after seeing recent emails and saw the final one of these tests be reported as "NOT PASSED" (it seems to be the only failure). No idea if this is important or not. The text I see is: # * TEST UPPER MATRIX # test upper matrix complete raw in 7 microsec decode [NOT PASSED] This happens on both our Nehalem and SandyBridge clusters and we are building with the system GCC. I've attached the full log from our Nehalem cluster (RHEL 6.4). Our configure script is: #!/bin/bash BASE=`basename $PWD | sed -e s,-,/,` module purge ./configure --prefix=/usr/local/${BASE} --with-slurm --with-openib \ --enable-static --enable-shared make -j I'm away on leave next week (first break for a year, yay!) but back the week after.. All the best, Chris - -- Christopher SamuelSenior Systems Administrator VLSCI - Victorian Life Sciences Computation Initiative Email: sam...@unimelb.edu.au Phone: +61 (0)3 903 55545 http://www.vlsci.org.au/ http://twitter.com/vlsci -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.12 (GNU/Linux) Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iEYEARECAAYFAlJOVUcACgkQO2KABBYQAh+J/QCfX+U1kZvtgFL1UxyIZBbNdqyW PC4An2AciGo2BkOq5RnceDYjACcUsV7X =0VKJ -END PGP SIGNATURE- Making check in config make[1]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/config' make[1]: Nothing to be done for `check'. make[1]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/config' Making check in contrib make[1]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/contrib' make[1]: Nothing to be done for `check'. make[1]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/contrib' Making check in opal make[1]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal' Making check in include make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/include' make[2]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/include' Making check in libltdl make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/libltdl' make check-am make[3]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/libltdl' make[3]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/libltdl' make[2]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/libltdl' Making check in asm make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/asm' make[2]: Nothing to be done for `check'. make[2]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/asm' Making check in datatype make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/datatype' make[2]: Nothing to be done for `check'. make[2]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/datatype' Making check in etc make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/etc' make[2]: Nothing to be done for `check'. make[2]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/etc' Making check in event make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event' Making check in compat make[3]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event/compat' Making check in sys make[4]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event/compat/sys' make[4]: Nothing to be done for `check'. make[4]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event/compat/sys' make[4]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event/compat' make[4]: Nothing to be done for `check-am'. make[4]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event/compat' make[3]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event/compat' make[3]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event' make[3]: Nothing to be done for `check-am'. make[3]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event' make[2]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/event' Making check in util make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/util' Making check in keyval make[3]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/util/keyval' make[3]: Nothing to be done for `check'. make[3]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/util/keyval' make[3]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/util' make[3]: Nothing to be done for `check-am'. make[3]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/util' make[2]: Leaving directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/util' Making check in mca/base make[2]: Entering directory `/usr/local/src/OPENMPI/openmpi-1.6.5.1/opal/mca/base' make[2]: Nothing to be done for `check'. make[2]: Leaving directory