[mpich-discuss] GFORTRAN on MinGW doesn't link to MPICH-2

Wed Sep 17 11:38:24 CDT 2014

Hello, Bland

Thank you for your input, but 1.4.1p is exactly what I am using now,
it should be recognized by the system, I believe.

It is downloaded from
http://www.mcs.anl.gov/research/projects/mpich2staging/goodell/downloads/index.php?s=downloads

On Wed, Sep 17, 2014 at 10:45 AM,  <discuss-request at mpich.org> wrote:
> Send discuss mailing list submissions to
>         discuss at mpich.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
>         https://lists.mpich.org/mailman/listinfo/discuss
> or, via email, send a message with subject or body 'help' to
>         discuss-request at mpich.org
>
> You can reach the person managing the list at
>         discuss-owner at mpich.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of discuss digest..."
>
>
> Today's Topics:
>
>    1.  mpich-3.2a for Blue Gene /Q omits spi libraries  from the
>       wrappers (William Scullin)
>    2.  MPI log via MPE on CRAY XC30 machine (Milind Chabbi)
>    3.  Passwords on small cluster (Bob Ilgner)
>    4. Re:  Passwords on small cluster (Reuti)
>    5. Re:  MPI log via MPE on CRAY XC30 machine (Balaji, Pavan)
>    6.  GFORTRAN on MinGW doesn't link (Miao Li)
>    7.  GFORTRAN on MinGW doesn't link to MPICH-2 (Miao Li)
>    8. Re:  GFORTRAN on MinGW doesn't link (Bland, Wesley B.)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Tue, 16 Sep 2014 16:06:11 -0500
> From: William Scullin <wscullin at alcf.anl.gov>
> To: <discuss at mpich.org>
> Subject: [mpich-discuss] mpich-3.2a for Blue Gene /Q omits spi
>         libraries       from the wrappers
> Message-ID:
>         <CAFmX=Zya7G_TB939v9pLnykzRUyE0O_p5p_oRn4SY0QrHz=nMA at mail.gmail.com>
> Content-Type: text/plain; charset="UTF-8"
>
> When building mpich-3.2a for Blue Gene /Q and following the same
> procedure used for building mpich-3.1.2 for BG/Q, the required linking
> information for spi and pami is omitted from the wrappers. I'm not
> sure if this is intentional or not.
>
> Thanks,
> William
>
>
> Patching the wrappers to reflect the required linking gives the following diff :
>
> [wscullin at vestasn1 ~]$ diff
> /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc
> /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc-postpatch
> 265c265
> <         $Show $CC   $PROFILE_INCPATHS
> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib
> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir
> -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi
> $PROFILE_POSTLIB
> ---
>>         $Show $CC   $PROFILE_INCPATHS    -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi  $PROFILE_POSTLIB  -lpami-gcc -lpthread   -lSPI -lSPI_cnk -lrt -lstdc++
>
> Full diff of mpich-3.1.2 versus 3.2a wrappers:
>
> [wscullin at vestasn1 ~]$ diff
> /projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/bin/mpicc
> /projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/bin/mpicc
> 30,34c30,34
> < prefix=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7
> < exec_prefix=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7
> < sysconfdir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/etc
> < includedir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/include
> < libdir=/projects/Operations/wscullin/mpich-3.1.2/gcc-4.4.7/lib
> ---
>> prefix=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7
>> exec_prefix=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7
>> sysconfdir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/etc
>> includedir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/include
>> libdir=/projects/Operations/wscullin/mpich-3.2a1/gcc-4.4.7/lib
> 40c40
> < MPICH_VERSION="3.1.2"
> ---
>> MPICH_VERSION="3.2a1"
> 262c262
> <         $Show $CC   $PROFILE_INCPATHS
> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib
> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib
> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib
> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir
> ---
>>         $Show $CC   $PROFILE_INCPATHS    -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir
> 265c265
> <         $Show $CC   $PROFILE_INCPATHS
> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib
> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib
> -L/bgsys/drivers/V1R2M2/ppc64/spi/lib
> -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir
> -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi
> $PROFILE_POSTLIB  -lpami-gcc -lpthread   -lSPI -lSPI_cnk -lrt -lstdc++
> ---
>>         $Show $CC   $PROFILE_INCPATHS    -L/bgsys/drivers/V1R2M2/ppc64/spi/lib -L/bgsys/drivers/V1R2M2/ppc64/comm/lib "${allargs[@]}" -I$includedir -L$libdir $PROFILE_PRELIB $PROFILE_FOO $rpath_flags -lmpi  $PROFILE_POSTLIB
>
>
> ------------------------------
>
> Message: 2
> Date: Wed, 17 Sep 2014 00:26:05 -0500
> From: Milind Chabbi <Milind.Chabbi at rice.edu>
> To: mpich-discuss at mcs.anl.gov
> Subject: [mpich-discuss] MPI log via MPE on CRAY XC30 machine
> Message-ID:
>         <CAMmz+Y=vvO5vkwyXaKeGg1BKB+Z7zbktZJiwU3rkMjAh8Z058Q at mail.gmail.com>
> Content-Type: text/plain; charset=UTF-8
>
> I am trying to gather MPI logs on CRAY XC30 (Edison machine at NERSC.)
> I built MPE 2-1.3 (ftp://ftp.mcs.anl.gov/pub/mpi/mpe/mpe2.tar.gz) with
> the following configure command:
>
> ./configure MPI_CC=cc F77=ftn MPI_F77=ftn --prefix=/XXXXX/mpe2-1.3.0-install
>
> I compiled a simple application with the following command:
> /XXXX/mpe2-1.3.0-install/bin/mpecc  test1.cpp -mpilog
>
> The code compiled fine, but the execution did not generate any log files.
>
> I am trying to generate logs files of MPI calls to view with Jumpshot
> on programs compiled on Cray XC30. Can you suggest the steps needed to
> get this working?
>
> Thanks
> -Milind
>
>
> ------------------------------
>
> Message: 3
> Date: Wed, 17 Sep 2014 08:41:00 +0200
> From: Bob Ilgner <bobilgner at gmail.com>
> To: discuss at mpich.org
> Subject: [mpich-discuss] Passwords on small cluster
> Message-ID:
>         <CAKv15b_xROGRhPzxU3ZXka2KiC2-xz8+Vr1DHc=NYFHE-fQ6MA at mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
>
> Dear all,
>
>
> I am trying to run my mpi job on a small cluster with 5 nodes. When I run
>
> mpirun -n 5  --host node01,node02,node03,node04,node05   ./hesp
>
> the system requests a password for node01.
>
> if I run the job only on node05 then no pasword is requested and the job
> runs OK Is there some way I can include a password in the host file, or
> otherwise ?
>
> regards.
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://lists.mpich.org/pipermail/discuss/attachments/20140917/04ab8446/attachment-0001.html>
>
> ------------------------------
>
> Message: 4
> Date: Wed, 17 Sep 2014 13:00:32 +0200
> From: Reuti <reuti at staff.uni-marburg.de>
> To: discuss at mpich.org
> Subject: Re: [mpich-discuss] Passwords on small cluster
> Message-ID:
>         <CBCC63B9-F266-4B59-8961-EFB22FEFD635 at staff.uni-marburg.de>
> Content-Type: text/plain; charset=us-ascii
>
> Hi,
>
> Am 17.09.2014 um 08:41 schrieb Bob Ilgner:
>
>> I am trying to run my mpi job on a small cluster with 5 nodes. When I run
>>
>> mpirun -n 5  --host node01,node02,node03,node04,node05   ./hesp
>>
>> the system requests a password for node01.
>>
>> if I run the job only on node05 then no pasword is requested and the job runs OK Is there some way I can include a password in the host file, or otherwise ?
>
> You will have to set up some kind of passwordless access, either by a passphraseless SSH-key (if you are the only user), or hostbased authentication (to make the setup one time for all users).
>
> https://www.open-mpi.org/faq/?category=rsh#ssh-keys (although this page is from the Open MPI site, the constraints are the same as in MPICH)
>
> or:
>
> https://arc.liv.ac.uk/SGE/howto/hostbased-ssh.html
>
> -- Reuti
>
> PS: You could also use an SSH-agent http://www.unixwiz.net/techtips/ssh-agent-forwarding.html which will answer all further requests for the passphrase after you entered it one time.
>
> ------------------------------
>
> Message: 5
> Date: Wed, 17 Sep 2014 11:20:50 +0000
> From: "Balaji, Pavan" <balaji at anl.gov>
> To: "discuss at mpich.org" <discuss at mpich.org>
> Subject: Re: [mpich-discuss] MPI log via MPE on CRAY XC30 machine
> Message-ID: <77BB388D-E452-48B5-89C2-DA16D773F2CA at anl.gov>
> Content-Type: text/plain; charset="utf-8"
>
> Milind,
>
> Did you try this link?
>
> http://wiki.mpich.org/mpich/index.php/MPE_by_example
>
>  ? Pavan
>
> On Sep 17, 2014, at 12:26 AM, Milind Chabbi <milind.chabbi at rice.edu> wrote:
>
>> I am trying to gather MPI logs on CRAY XC30 (Edison machine at NERSC.)
>> I built MPE 2-1.3 (ftp://ftp.mcs.anl.gov/pub/mpi/mpe/mpe2.tar.gz) with
>> the following configure command:
>>
>> ./configure MPI_CC=cc F77=ftn MPI_F77=ftn --prefix=/XXXXX/mpe2-1.3.0-install
>>
>> I compiled a simple application with the following command:
>> /XXXX/mpe2-1.3.0-install/bin/mpecc  test1.cpp -mpilog
>>
>> The code compiled fine, but the execution did not generate any log files.
>>
>> I am trying to generate logs files of MPI calls to view with Jumpshot
>> on programs compiled on Cray XC30. Can you suggest the steps needed to
>> get this working?
>>
>> Thanks
>> -Milind
>> _______________________________________________
>> discuss mailing list     discuss at mpich.org
>> To manage subscription options or unsubscribe:
>> https://lists.mpich.org/mailman/listinfo/discuss
>
> --
> Pavan Balaji  ??
> http://www.mcs.anl.gov/~balaji
>
>
> ------------------------------
>
> Message: 6
> Date: Wed, 17 Sep 2014 10:39:35 -0500
> From: Miao Li <rockymountai at gmail.com>
> To: mpich-discuss at mcs.anl.gov
> Subject: [mpich-discuss] GFORTRAN on MinGW doesn't link
> Message-ID:
>         <CAKOfFceOwHjAvvpWe5+WPnWm9-Bjn6iXCcsNGbXtFBcuHZbGVA at mail.gmail.com>
> Content-Type: text/plain; charset=UTF-8
>
> Hello, Folks
>
> Sorry to bug you guys with this but I am sure there are tons of people
> have encountered this before, I am creating a MPI program with MPICH-2
> and gfortran on Windows 8 64 with MinGW, but for some reason the
> MPICH-2 can't be linked and errors are:
>
> hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_'
> hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_'
> hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_'
> hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_'
> hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_'
> hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_'
> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe:
> C:\Users\<myid>\AppData\L
> ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame'
> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe:
> final link failed: Inval
> id operation
> collect2.exe: error: ld returned 1 exit status
>
> This is just a "hello world" program and I followed the instructions
> in the README.winbin.rtf file
>
> "
>
> 2) add ?I?mpich2\include
>
> 3) add ?L?mpich2\lib
>
> "
>
> Some people believe that the "-lmpi" option should be used at the very
> end of command, I did that but doesn't help.
>
> I even tried compiling without any makefile but just a single command like:
>
>> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi
>
> But still it doesn't work for me.
>
> Did any of you guys have encountered this before?
>
> I really look forward your response, any inputs are highly appreciated!!!
>
> Thank you so much!
>
> Best Regard
>
> NOTE:
>
> Here is my simple makefile:
>
> F90    = gfortran
> MPI_DIR   = /c/Program\ Files/MPICH2
> MPI_LIB_DIR  = $(MPI_DIR)/lib
> MPI_LIB_INCLUDE = $(MPI_DIR)/include
> MPI_LIB   = -L$(MPI_LIB_DIR) -lmpi
> MPI_INCLUDE  = -I$(MPI_LIB_INCLUDE)
> SRC    = hello_mpi.f90
> OBJ    = $(SRC:.f90=.o)
> EXEC   = hello
> $(EXEC): $(OBJ)
>  $(F90) -o $(EXEC)  $(OBJ) $(MPI_LIB)
> $(OBJ) : $(SRC)
>  $(F90) $(MPI_INCLUDE) -c $<
> clean:
>  rm *.o
>
>
> ------------------------------
>
> Message: 7
> Date: Wed, 17 Sep 2014 10:43:04 -0500
> From: Miao Li <rockymountai at gmail.com>
> To: discuss at mpich.org
> Subject: [mpich-discuss] GFORTRAN on MinGW doesn't link to MPICH-2
> Message-ID:
>         <CAKOfFceNJnTYnzcWQgq9_qwJvpotgk8eroN=Oq--4Me-LJiG=w at mail.gmail.com>
> Content-Type: text/plain; charset=UTF-8
>
> Hello, Folks
>
> Sorry to bug you guys with this but I am sure there are tons of people
> have encountered this before, I am creating a MPI program with MPICH-2
> and gfortran on Windows 8 64 with MinGW, but for some reason the
> MPICH-2 can't be linked and errors are:
>
> hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_'
> hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_'
> hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_'
> hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_'
> hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_'
> hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_'
> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe:
> C:\Users\<myid>\AppData\L
> ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame'
> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe:
> final link failed: Inval
> id operation
> collect2.exe: error: ld returned 1 exit status
>
> This is just a "hello world" program and I followed the instructions
> in the README.winbin.rtf file
>
> "
>
> 2) add ?I?mpich2\include
>
> 3) add ?L?mpich2\lib
>
> "
>
> Some people believe that the "-lmpi" option should be used at the very
> end of command, I did that but doesn't help.
>
> I even tried compiling without any makefile but just a single command like:
>
>> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi
>
> But still it doesn't work for me.
>
> Did any of you guys have encountered this before?
>
> I really look forward your response, any inputs are highly appreciated!!!
>
> Thank you so much!
>
> Best Regard
>
> NOTE:
>
> Here is my simple makefile:
>
> F90    = gfortran
> MPI_DIR   = /c/Program\ Files/MPICH2
> MPI_LIB_DIR  = $(MPI_DIR)/lib
> MPI_LIB_INCLUDE = $(MPI_DIR)/include
> MPI_LIB   = -L$(MPI_LIB_DIR) -lmpi
> MPI_INCLUDE  = -I$(MPI_LIB_INCLUDE)
> SRC    = hello_mpi.f90
> OBJ    = $(SRC:.f90=.o)
> EXEC   = hello
> $(EXEC): $(OBJ)
>  $(F90) -o $(EXEC)  $(OBJ) $(MPI_LIB)
> $(OBJ) : $(SRC)
>  $(F90) $(MPI_INCLUDE) -c $<
> clean:
>  rm *.o
>
>
> ------------------------------
>
> Message: 8
> Date: Wed, 17 Sep 2014 15:45:07 +0000
> From: "Bland, Wesley B." <wbland at anl.gov>
> To: "discuss at mpich.org" <discuss at mpich.org>
> Cc: "mpich-discuss at mcs.anl.gov" <mpich-discuss at mcs.anl.gov>
> Subject: Re: [mpich-discuss] GFORTRAN on MinGW doesn't link
> Message-ID: <667114D6-5B30-4F87-8AD4-857793E47DFA at anl.gov>
> Content-Type: text/plain; charset="utf-8"
>
> Unfortunately, we haven't supported Windows since MPICH version 1.4.1p1. You can find out more at the FAQ page: http://wiki.mpich.org/mpich/index.php/Frequently_Asked_Questions#Q:_Why_can.27t_I_build_MPICH_on_Windows_anymore.3F
>
> Thanks,
> Wesley
>
>> On Sep 17, 2014, at 10:39 AM, Miao Li <rockymountai at gmail.com> wrote:
>>
>> Hello, Folks
>>
>> Sorry to bug you guys with this but I am sure there are tons of people
>> have encountered this before, I am creating a MPI program with MPICH-2
>> and gfortran on Windows 8 64 with MinGW, but for some reason the
>> MPICH-2 can't be linked and errors are:
>>
>> hello_mpi.o:hello_mpi.f90:(.text+0x10): undefined reference to `mpi_init_'
>> hello_mpi.o:hello_mpi.f90:(.text+0x2a): undefined reference to `mpi_comm_size_'
>> hello_mpi.o:hello_mpi.f90:(.text+0x44): undefined reference to `mpi_comm_rank_'
>> hello_mpi.o:hello_mpi.f90:(.text+0x54): undefined reference to `mpi_wtime_'
>> hello_mpi.o:hello_mpi.f90:(.text+0x6bd): undefined reference to `mpi_wtime_'
>> hello_mpi.o:hello_mpi.f90:(.text+0x7f7): undefined reference to `mpi_finalize_'
>> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe:
>> C:\Users\<myid>\AppData\L
>> ocal\Temp\cckYDcnb.o: bad reloc address 0x20 in section `.eh_frame'
>> c:/users/<myid>/program_files/mingw/bin/../lib/gcc/mingw32/4.8.1/../../../../mingw32/bin/ld.exe:
>> final link failed: Inval
>> id operation
>> collect2.exe: error: ld returned 1 exit status
>>
>> This is just a "hello world" program and I followed the instructions
>> in the README.winbin.rtf file
>>
>> "
>>
>> 2) add ?I?mpich2\include
>>
>> 3) add ?L?mpich2\lib
>>
>> "
>>
>> Some people believe that the "-lmpi" option should be used at the very
>> end of command, I did that but doesn't help.
>>
>> I even tried compiling without any makefile but just a single command like:
>>
>>> gfortran.exe -I"C:\Program Files\MPICH2\include" hello_mpi.f90 -L"C:\Program Files\MPICH2\lib" -lmpi
>>
>> But still it doesn't work for me.
>>
>> Did any of you guys have encountered this before?
>>
>> I really look forward your response, any inputs are highly appreciated!!!
>>
>> Thank you so much!
>>
>> Best Regard
>>
>> NOTE:
>>
>> Here is my simple makefile:
>>
>> F90    = gfortran
>> MPI_DIR   = /c/Program\ Files/MPICH2
>> MPI_LIB_DIR  = $(MPI_DIR)/lib
>> MPI_LIB_INCLUDE = $(MPI_DIR)/include
>> MPI_LIB   = -L$(MPI_LIB_DIR) -lmpi
>> MPI_INCLUDE  = -I$(MPI_LIB_INCLUDE)
>> SRC    = hello_mpi.f90
>> OBJ    = $(SRC:.f90=.o)
>> EXEC   = hello
>> $(EXEC): $(OBJ)
>> $(F90) -o $(EXEC)  $(OBJ) $(MPI_LIB)
>> $(OBJ) : $(SRC)
>> $(F90) $(MPI_INCLUDE) -c $<
>> clean:
>> rm *.o
>> _______________________________________________
>> discuss mailing list     discuss at mpich.org
>> To manage subscription options or unsubscribe:
>> https://lists.mpich.org/mailman/listinfo/discuss
>
>
> ------------------------------
>
> _______________________________________________
> discuss mailing list
> discuss at mpich.org
> https://lists.mpich.org/mailman/listinfo/discuss
>
> End of discuss Digest, Vol 23, Issue 34
> ***************************************
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss