[Wien] Wien2k Compilation on AMD Dual Operton under Suse9.2-64bit

Michael Gurnett michael.gurnett at kau.se
Thu Oct 19 21:01:46 CEST 2006 

Your trying to compile with mpirun, you should be using mpiifort or
similar (this is the intel version).

My options for the conroe are as follows

current:FOPT:-FR -mp1 -w -prec_div -pc80 -pad -ip -axT -DINTEL_VML
current:FPOPT:-FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML
current:LDFLAGS:$(FOPT) -L/opt/intel/cmkl/8.1.1/lib/em64t -i-static
-lguide_stats -lsvml -lpthread
current:DPARALLEL:'-DParallel'
current:R_LIBS:-L/opt/intel/cmkl/8.1.1/lib/em64t -lmkl_lapack64
-lmkl_em64t -lguide -lguide_stats -lpthread
current:RP_LIBS:-L/opt/intel/cmkl/8.1.1/lib/em64t -lmkl_scalapack
-lmkl_blacs_intelmpi20

Hope this helps

Michael

On Thu, 2006-10-19 at 12:07 -0500, Nicholas Dimakis wrote:
> Hello
> 
> I was able to solve the problem with the 32 bit/64 bit compiler issue by using the 64 bit ifort and the following options
> 
> 
>  Compiler options:        -FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML
>      L   Linker Flags:            $(FOPT) -L/opt/intel/mkl80/lib/em64t -lpthread
>      P   Preprocessor flags       '-DParallel'
>      R   R_LIB (LAPACK+BLAS):     -lmkl_lapack64 -lmkl_em64t -lguide
> 
> 
> However I still have problems on MPI. My setting are
> 
> 
> 
> RP  RP_LIB(SCALAPACK+PBLAS): -L /usr/local/SCALAPACK -L /usr/local/BLACS/LIB -lpblas -lredist -ltools -lscalapack -lfblacs -lblacs -lmpi
>      FP  FPOPT(par.comp.options): -FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML
>      MP  MPIRUN commando        : mpirun -np _NP_ -machinefile _HOSTS_ _EXEC_
> 
> 
> Then I am trying to compile lapw0 and I get
> 
> make PARALLEL='-DParallel' lapw0_mpi \
>   FORT=mpirun FFLAGS=' -FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML '-DParallel''
> make[1]: Entering directory `/home/user1/Wien2k/SRC_lapw0'
> mpirun -FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML -DParallel -c modules.F
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -mp1 is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -w is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -prec_div is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -pc80 is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -pad is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -ip is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -DINTEL_VML is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -DParallel is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that -c is a
> command line argument for the program.
> Warning: Command line arguments for program should be given
> after the program name.  Assuming that modules.F is a
> command line argument for the program.
> Missing: program name
> Program -FR either does not exist, is not
> executable, or is an erroneous argument to mpirun.
> make[1]: *** [modules.o] Error 1
> make[1]: Leaving directory `/home/user1/Wien2k/SRC_lapw0'
> make: *** [para] Error 2
> 
> 
> Thanks for your help
> 
> 
> 
> 
> Nikolaos Dimakis
> Assistant Professor
> Physics and Geology
> University of Texas-Pan American
> 
> 
> 
> -----Original Message-----
> From: wien-bounces at zeus.theochem.tuwien.ac.at on behalf of Michael Gurnett
> Sent: Tue 10/17/2006 12:46 PM
> To: A Mailing list for WIEN2k users
> Subject: Re: [Wien] Wien2k Compilation on AMD Dual Operton under Suse	9.2-64	bit
>  
> Seems to me your trying to compile 32bit code on a 64 bit machine
> 
> Michael
> 
> On Tue, 2006-10-17 at 11:54 -0500, Nicholas Dimakis wrote:
> > Hello
> > 
> >   I am new to Wien2k and I have problems on compiling the source code
> > for a dual AMD Opteron system under Suse 9.2
> > 
> >   Compiler is intel ifort9, mkl is installed under /opt/intel
> > 
> >   Compiler options:        -FR -mp -w
> >   Linker Flags:            $(FOPT) -L/opt/intel/mkl80/lib/32 -static
> >   Preprocessor flags       '-DParallel'
> >   R_LIB (LAPACK+BLAS):     -lmkl_lapack -lmkl_ia32 -lguide -lpthread
> > 
> >   I used this info from a previous message on AMD Athlon Wien2k
> > installation.
> > 
> >   I get:
> > 
> >   ld: warning: i386:x86-64 architecture of input file `cputim.o' is
> > incompatible with i386 output
> > 
> >   and I get an error as
> > 
> >   ifort -o lapw0 cputim.o modules.o reallocate.o ainv.o blyp.o
> > charg2.o  charg3.o charge.o chfac.o chslv.o  corgga.ocub_xc_back.o
> > corlsd.o dlu.o drho.o  dfxhpbe.o dylm.o  efg.o  energy.o errclr.o
> > errflg.o ev92.o    ev92ex.o exch.o exch17.o exrevpbe.o  fithi.o
> > fxhpbe.o gbass.o gcor.o  gea.o geaex.o  getfft.o  getff1.o gpoint.o
> > grans.o gtfnam.o hcth.o ifflim.o kcis.o lapw0.o  latgen.o  multfc.o
> > multsu.o outerr.o  pbe1.o poissn.o potfac.o pwxad4.o pwxad5.o  qranf.o
> > readstruct.o rean0.o rean1.o rean3.o  rean4.o  rotate.o  rotdef.o
> > setff0.o  setff1.o  setfft.o setff2.o seval.osevald.o sevaldd.o
> > sevali.o sevalin.o sicpbe.o sphbes.o  spline.o srolyl.o stern.o
> > sumfac.o  suml.o th1.o th2.o vpw91.o   vresp.o vs98.o vxc15.o vxc16.o
> > vxc17.o vxc24.o  vxc26.o  vxclm2.o vxcpw2.o vxi35.o vxi35a.o workf1.o
> > xcener.o xcpot.o  xcpot1.o xcpot3.o ykav.o  ylm.o zfft3d.o
> > sicpbe_tpss.o corpbe_tpss.o fx_tpss.o dfxtpss.o rhopw.o b88.o wc05.o
> > -FR -mp -w -L/opt/intel/mkl80/lib/32 -static
> >   ld: warning: i386:x86-64 architecture of input file `cputim.o' is
> > incompatible with i386 output
> >   make[1]: Leaving directory `/home/user1/Wien2k/SRC_lapw0'
> >   make: *** No rule to make target `complex'.  Stop.
> >   if [ -f .sequential ]; then \
> >      rm -f .sequential modules.o reallocate.o energy.o gtfnam.o
> > lapw0.o  *.mod; \
> >   fi
> >   touch .parallel
> >   make PARALLEL='-DParallel' lapw0_mpi \
> >     FORT=ifort FFLAGS=' -FR -mp1 -w -prec_div -pc80 -pad -ip
> > -DINTEL_VML '-DParallel''
> >   make[1]: Entering directory `/home/user1/Wien2k/SRC_lapw0'
> >   ifort -FR -mp1 -w -prec_div -pc80 -pad -ip -DINTEL_VML -DParallel -c
> > modules.F
> >   fortcom: Error: modules.F, line 19: Cannot open include file
> > 'mpif.h'
> >       INCLUDE 'mpif.h'
> >   ------------^
> >   fortcom: Error: modules.F, line 42: Cannot open include file
> > 'mpif.h'
> >       INCLUDE 'mpif.h'
> >   ------------^
> >   fortcom: Error: modules.F, line 20: This name does not have a type,
> > and must have an explicit type.   [MPI_STATUS_SIZE]
> >       ALLOCATE(statusmpi(MPI_STATUS_SIZE))
> >   -----------------------^
> >   fortcom: Error: modules.F, line 20: The highest data type rank
> > permitted is INTEGER(KIND=8).   [MPI_STATUS_SIZE]
> >       ALLOCATE(statusmpi(MPI_STATUS_SIZE))
> >   -----------------------^
> >   fortcom: Error: modules.F, line 22: This name does not have a type,
> > and must have an explicit type.   [MPI_SUCCESS]
> >       IF(ierr.NE.MPI_SUCCESS) THEN
> >   ---------------^
> >   fortcom: Error: modules.F, line 26: This name does not have a type,
> > and must have an explicit type.   [MPI_COMM_WORLD]
> >       CALL MPI_COMM_SIZE( MPI_COMM_WORLD, npe, ierr)
> >   ------------------------^
> >   fortcom: Error: modules.F, line 44: This name does not have a type,
> > and must have an explicit type.   [MPI_UNDEFINED]
> >       icolor1=MPI_UNDEFINED
> >   ------------^
> >   compilation aborted for modules.F (code 1)
> > 
> > 
> > Thank you for your help
> > 
> > 
> > 
> > Nikolaos Dimakis
> > Assistant Professor
> > Physics and Geology
> > University of Texas-Pan American
> > 
> > 
> > 
> > _______________________________________________
> > Wien mailing list
> > Wien at zeus.theochem.tuwien.ac.at
> > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> 
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien

More information about the Wien mailing list