March 2014 - discuss - mailman3.cels.anl.gov

Re: [mpich-discuss] Problems with running make
by Reuti 01 Mar '14

01 Mar '14

Hi, Am 01.03.2014 um 12:18 schrieb Ron Palmer: > Gus and others, > many thanks for your comments and suggestions. I am unsure whether I need fortran included as I am not in control of the software to be run on this linux cluster. I have asked but not yet got a reply... > > However, I did a yum search gfortran and installed the gcc-gfortran.x86_64 (I hope that was the one you referred to). I followed up with the ./configure ... as per your suggestion. That did not work. I then tried with only ./configure --prefix=/my/bin/folder. That worked so I also did make and make install. > > I have a machinefile with three linux computers, all sharing the same mpi binaries. Running hostname on all 20 cores works, so I guess I should conclude that mpi works, right? Are they using the same binaries /my/bin/folder for a non-interactive startup too, i.e.: $ ssh sargeant which hydra_pmi_proxy returns the same as on the master (maybe ~/.bashrc needs to set the $PATH)? -- Reuti > I then tried the software I am supposed to run on the cluster. It works on all nodes on the master computer, but not if other computers are involved. I have captured the output from such failed attempt to run that software on all available nodes on all available computers in the cluster, see below. I have attached c2.txt and m2.txt (and the output of the failed run) in the attached gzipped file (the failed run in run2.txt and in the image below may not be from the same failed run...). > > So, is it an issue for the software developers or is it an issue with mpich? > > I would appreciate if you could let me know if mpich is properly compiled and installed and whether I should follow up with the application developers instead. I now that they are successfully running this code on V1.4.1. > > Thanks for your prompt support. > > Cheers, > Ron > > > > <ghdahehb.png> > > > > On 1/03/2014 08:19, Gus Correa wrote: >> Hi Ron >> >> Your config.log shows that configure is picking up Gnu >> /usr/bin/f77 as the Fortran compiler. >> See an excerpt of config.log below. >> >> The Gnu f77/g77, which cannot compile Fortran-90 and later code. >> >> You may want to install gfortran. >> Configure didn't find gfortran. >> However, you can install it easily from RPM through yum. >> >> Once you install gfortran, to avoid picking up wrong compilers, >> you can also point configure to the compilers. >> Assuming you want to use all Gnu compilers, this would do it: >> >> ./configure CC=gcc, CXX=g++, F77=gfortran, FC=gfortran, --prefix=/wherever/you/want ... >> >> Another possibility is follow Reuti's suggestion of >> not compiling the MPICH Fortran-90 interface. >> >> I hope this helps, >> Gus Correa >> >> ******* from your config.log ********* >> ... >> configure:17977: result: no >> configure:17947: checking for gfortran >> configure:17977: result: no >> configure:17947: checking for f77 >> configure:17963: found /usr/bin/f77 >> configure:17974: result: f77 >> configure:18000: checking for Fortran 77 compiler version >> configure:18009: f77 --version >&5 >> GNU Fortran (GCC) 3.4.6 20060404 (Red Hat 3.4.6-19.el6) >> ... >> ***************************************** >> >> On 02/28/2014 05:02 AM, Reuti wrote: >>> Hi, >>> >>> Am 28.02.2014 um 09:22 schrieb Ron Palmer: >>> >>>> I am struggling with running make on MPICH, V3.1. I believe that ./configure went well but I do not understand what caused the errors in make. I thought it may be associated with the fortran compile but I have F77 installed (though somewhat confused whether fortran 90 is also installed). The README file suggested that I send an email to this list with nominated four text files attached. >>> >>> You can try to skip f90: >>> >>> $ ./configure --disable-fc ... >>> >>> -- Reuti >>> >>> >>>> The end of the m.txt file is included here for easy access, full details are attached... >>>> >>>> CC src/mpi/topo/nhb_alltoallw.lo >>>> CC src/binding/f90/create_f90_int.lo >>>> CC src/binding/f90/create_f90_real.lo >>>> src/binding/f90/create_f90_real.c: In function 'PMPI_Type_create_f90_real': >>>> src/binding/f90/create_f90_real.c:73: error: expected expression before ',' token >>>> src/binding/f90/create_f90_real.c:74: error: expected expression before ',' token >>>> make[2]: *** [src/binding/f90/create_f90_real.lo] Error 1 >>>> make[2]: Leaving directory `/inv/mpich-3.1' >>>> make[1]: *** [all-recursive] Error 1 >>>> make[1]: Leaving directory `/inv/mpich-3.1' >>>> make: *** [all] Error 2 >>>> >>>> I look forward to any suggestions any of you may have. >>>> Regards, Ron >>>> >>>> >>>> <mpi_logs.tar.gz>_______________________________________________ >>>> discuss mailing list discuss(a)mpich.org >>>> To manage subscription options or unsubscribe: >>>> https://lists.mpich.org/mailman/listinfo/discuss >>> >>> _______________________________________________ >>> discuss mailing list discuss(a)mpich.org >>> To manage subscription options or unsubscribe: >>> https://lists.mpich.org/mailman/listinfo/discuss >> >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss > > > > <run2.tar.gz>_______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] Problems with running make
by Ron Palmer 01 Mar '14

01 Mar '14

Gus and others, many thanks for your comments and suggestions. I am unsure whether I need fortran included as I am not in control of the software to be run on this linux cluster. I have asked but not yet got a reply... However, I did a yum search gfortran and installed the gcc-gfortran.x86_64 (I hope that was the one you referred to). I followed up with the ./configure ... as per your suggestion. That did not work. I then tried with only ./configure --prefix=/my/bin/folder. That worked so I also did make and make install. I have a machinefile with three linux computers, all sharing the same mpi binaries. Running hostname on all 20 cores works, so I guess I should conclude that mpi works, right? I then tried the software I am supposed to run on the cluster. It works on all nodes on the master computer, but not if other computers are involved. I have captured the output from such failed attempt to run that software on all available nodes on all available computers in the cluster, see below. I have attached c2.txt and m2.txt (and the output of the failed run) in the attached gzipped file (the failed run in run2.txt and in the image below may not be from the same failed run...). So, is it an issue for the software developers or is it an issue with mpich? I would appreciate if you could let me know if mpich is properly compiled and installed and whether I should follow up with the application developers instead. I now that they are successfully running this code on V1.4.1. Thanks for your prompt support. Cheers, Ron On 1/03/2014 08:19, Gus Correa wrote: > Hi Ron > > Your config.log shows that configure is picking up Gnu > /usr/bin/f77 as the Fortran compiler. > See an excerpt of config.log below. > > The Gnu f77/g77, which cannot compile Fortran-90 and later code. > > You may want to install gfortran. > Configure didn't find gfortran. > However, you can install it easily from RPM through yum. > > Once you install gfortran, to avoid picking up wrong compilers, > you can also point configure to the compilers. > Assuming you want to use all Gnu compilers, this would do it: > > ./configure CC=gcc, CXX=g++, F77=gfortran, FC=gfortran, > --prefix=/wherever/you/want ... > > Another possibility is follow Reuti's suggestion of > not compiling the MPICH Fortran-90 interface. > > I hope this helps, > Gus Correa > > ******* from your config.log ********* > ... > configure:17977: result: no > configure:17947: checking for gfortran > configure:17977: result: no > configure:17947: checking for f77 > configure:17963: found /usr/bin/f77 > configure:17974: result: f77 > configure:18000: checking for Fortran 77 compiler version > configure:18009: f77 --version >&5 > GNU Fortran (GCC) 3.4.6 20060404 (Red Hat 3.4.6-19.el6) > ... > ***************************************** > > On 02/28/2014 05:02 AM, Reuti wrote: >> Hi, >> >> Am 28.02.2014 um 09:22 schrieb Ron Palmer: >> >>> I am struggling with running make on MPICH, V3.1. I believe that >>> ./configure went well but I do not understand what caused the errors >>> in make. I thought it may be associated with the fortran compile but >>> I have F77 installed (though somewhat confused whether fortran 90 is >>> also installed). The README file suggested that I send an email to >>> this list with nominated four text files attached. >> >> You can try to skip f90: >> >> $ ./configure --disable-fc ... >> >> -- Reuti >> >> >>> The end of the m.txt file is included here for easy access, full >>> details are attached... >>> >>> CC src/mpi/topo/nhb_alltoallw.lo >>> CC src/binding/f90/create_f90_int.lo >>> CC src/binding/f90/create_f90_real.lo >>> src/binding/f90/create_f90_real.c: In function >>> 'PMPI_Type_create_f90_real': >>> src/binding/f90/create_f90_real.c:73: error: expected expression >>> before ',' token >>> src/binding/f90/create_f90_real.c:74: error: expected expression >>> before ',' token >>> make[2]: *** [src/binding/f90/create_f90_real.lo] Error 1 >>> make[2]: Leaving directory `/inv/mpich-3.1' >>> make[1]: *** [all-recursive] Error 1 >>> make[1]: Leaving directory `/inv/mpich-3.1' >>> make: *** [all] Error 2 >>> >>> I look forward to any suggestions any of you may have. >>> Regards, Ron >>> >>> >>> <mpi_logs.tar.gz>_______________________________________________ >>> discuss mailing list discuss(a)mpich.org >>> To manage subscription options or unsubscribe: >>> https://lists.mpich.org/mailman/listinfo/discuss >> >> _______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss

1 0

Re: [mpich-discuss] Error "hydra requires VA_ARGS support", RHEL 5.10, icc
by Бакиров, Медер 01 Mar '14

01 Mar '14

On Fri, Feb 28, 2014 at 7:33 PM, Balaji, Pavan <balaji(a)anl.gov> wrote: > That's surprising, given that it's incorrect. :-) I have a corrected patch pending. Is it this commit, which fixes the bug?: http://git.mpich.org/mpich.git/commit/de80ec8704071f3b9c810509fb8acee345865… I downloaded the corresponding nightly snapshot release from here: http://www.mpich.org/static/downloads/nightly/master/mpich/ With the best regards, Meder Bakirov

1 0

Re: [mpich-discuss] Problems with running make
by Ron Palmer 01 Mar '14

01 Mar '14

Reuti, thanks for your suggestion... I tried but I had also to disable the F77 to make it compile... I do not yet know if the software I will run on the cluseter is written in fortran or c/c++. Cheers, Ron On 28/02/2014 20:02, Reuti wrote: > Hi, > > Am 28.02.2014 um 09:22 schrieb Ron Palmer: > >> I am struggling with running make on MPICH, V3.1. I believe that ./configure went well but I do not understand what caused the errors in make. I thought it may be associated with the fortran compile but I have F77 installed (though somewhat confused whether fortran 90 is also installed). The README file suggested that I send an email to this list with nominated four text files attached. > You can try to skip f90: > > $ ./configure --disable-fc ... > > -- Reuti > > >> The end of the m.txt file is included here for easy access, full details are attached... >> >> CC src/mpi/topo/nhb_alltoallw.lo >> CC src/binding/f90/create_f90_int.lo >> CC src/binding/f90/create_f90_real.lo >> src/binding/f90/create_f90_real.c: In function 'PMPI_Type_create_f90_real': >> src/binding/f90/create_f90_real.c:73: error: expected expression before ',' token >> src/binding/f90/create_f90_real.c:74: error: expected expression before ',' token >> make[2]: *** [src/binding/f90/create_f90_real.lo] Error 1 >> make[2]: Leaving directory `/inv/mpich-3.1' >> make[1]: *** [all-recursive] Error 1 >> make[1]: Leaving directory `/inv/mpich-3.1' >> make: *** [all] Error 2 >> >> I look forward to any suggestions any of you may have. >> Regards, Ron >> >> >> <mpi_logs.tar.gz>_______________________________________________ >> discuss mailing list discuss(a)mpich.org >> To manage subscription options or unsubscribe: >> https://lists.mpich.org/mailman/listinfo/discuss > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss -- *Ron Palmer*MSc MBA. Principal Geophysicist ron.palmer(a)pgcgroup.com.au <mailto:[email protected]> 0413 579 099 07 3103 4963

1 0

Re: [mpich-discuss] Problems with running make
by Dave Goodell (dgoodell) 28 Feb '14

28 Feb '14

On Feb 28, 2014, at 3:47 PM, Junchao Zhang <jczhang(a)mcs.anl.gov> wrote: > I think is a bug to have a compiler named no :) IMO it's really not, but then again, I wrote this comment: http://git.mpich.org/mpich.git/blob/de80ec8704071f3b9c810509fb8acee34586590… Given Rajeev's comment, f77/f90 interaction issues or MPICH home-grown m4 macro problems seem like more likely candidates. -Dave > Created a ticket at http://trac.mpich.org/projects/mpich/ticket/2048 > > --Junchao Zhang > > > On Fri, Feb 28, 2014 at 4:54 PM, Reuti <reuti(a)staff.uni-marburg.de> wrote: > Am 28.02.2014 um 23:19 schrieb Gus Correa: > > > Hi Ron > > > > Your config.log shows that configure is picking up Gnu > > /usr/bin/f77 as the Fortran compiler. > > See an excerpt of config.log below. > > > > The Gnu f77/g77, which cannot compile Fortran-90 and later code. > > > > You may want to install gfortran. > > Configure didn't find gfortran. > > However, you can install it easily from RPM through yum. > > > > Once you install gfortran, to avoid picking up wrong compilers, > > you can also point configure to the compilers. > > Assuming you want to use all Gnu compilers, this would do it: > > > > ./configure CC=gcc, CXX=g++, F77=gfortran, FC=gfortran, --prefix=/wherever/you/want ... > > > > Another possibility is follow Reuti's suggestion of > > not compiling the MPICH Fortran-90 interface. > > I just found, that --disable-fc is not working. Reason seems to be, that it tries to make a conftest with the compiler "no" when checking Fortran 90 integer kind: > > configure:39186: no -o conftest conftest.f >&5 > ./configure: line 2896: no: command not found > configure:39186: $? = 127 > configure: program exited with status 127 > configure: failed program was: > > -- Reuti > > [siehe angehängte Datei: config.log] > > I hope this helps, > > Gus Correa > > > > ******* from your config.log ********* > > ... > > configure:17977: result: no > > configure:17947: checking for gfortran > > configure:17977: result: no > > configure:17947: checking for f77 > > configure:17963: found /usr/bin/f77 > > configure:17974: result: f77 > > configure:18000: checking for Fortran 77 compiler version > > configure:18009: f77 --version >&5 > > GNU Fortran (GCC) 3.4.6 20060404 (Red Hat 3.4.6-19.el6) > > ... > > ***************************************** > > > > On 02/28/2014 05:02 AM, Reuti wrote: > >> Hi, > >> > >> Am 28.02.2014 um 09:22 schrieb Ron Palmer: > >> > >>> I am struggling with running make on MPICH, V3.1. I believe that ./configure went well but I do not understand what caused the errors in make. I thought it may be associated with the fortran compile but I have F77 installed (though somewhat confused whether fortran 90 is also installed). The README file suggested that I send an email to this list with nominated four text files attached. > >> > >> You can try to skip f90: > >> > >> $ ./configure --disable-fc ... > >> > >> -- Reuti > >> > >> > >>> The end of the m.txt file is included here for easy access, full details are attached... > >>> > >>> CC src/mpi/topo/nhb_alltoallw.lo > >>> CC src/binding/f90/create_f90_int.lo > >>> CC src/binding/f90/create_f90_real.lo > >>> src/binding/f90/create_f90_real.c: In function 'PMPI_Type_create_f90_real': > >>> src/binding/f90/create_f90_real.c:73: error: expected expression before ',' token > >>> src/binding/f90/create_f90_real.c:74: error: expected expression before ',' token > >>> make[2]: *** [src/binding/f90/create_f90_real.lo] Error 1 > >>> make[2]: Leaving directory `/inv/mpich-3.1' > >>> make[1]: *** [all-recursive] Error 1 > >>> make[1]: Leaving directory `/inv/mpich-3.1' > >>> make: *** [all] Error 2 > >>> > >>> I look forward to any suggestions any of you may have. > >>> Regards, Ron > >>> > >>> > >>> <mpi_logs.tar.gz>_______________________________________________ > >>> discuss mailing list discuss(a)mpich.org > >>> To manage subscription options or unsubscribe: > >>> https://lists.mpich.org/mailman/listinfo/discuss > >> > >> _______________________________________________ > >> discuss mailing list discuss(a)mpich.org > >> To manage subscription options or unsubscribe: > >> https://lists.mpich.org/mailman/listinfo/discuss > > > > _______________________________________________ > > discuss mailing list discuss(a)mpich.org > > To manage subscription options or unsubscribe: > > https://lists.mpich.org/mailman/listinfo/discuss > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss > > _______________________________________________ > discuss mailing list discuss(a)mpich.org > To manage subscription options or unsubscribe: > https://lists.mpich.org/mailman/listinfo/discuss

1 0