The ABINIT Users Mailing List ( CLOSED )

[DELAVEAU Muriel <muriel.delaveau@cea.fr>]

In the uptodate version of trunk 5.9.0  
I found some trouble when i compile the code with ifort disappearing if  
i compile without any optimisation
the file  src/51_manage_mpi/xderivewrite.F90 .
It might be the optimiser or some trouble with memory somewhere in the 
code. The problem desappear also when I change
the location of  (displace(:)-1) * nboct * n1
like  that

subroutine 
xderiveWrite_dp2d_mpio_displ(wff,xval,n1,n2,ierr,spaceComm,displace)

use defs_basis
use defs_datatypes


 implicit none

#if defined MPI_IO
#ifndef __VMS
        include 'mpif.h'
#endif
          integer  :: statux(MPI_STATUS_SIZE)
#endif
type(wffile_type),intent(inout) :: wff
integer,intent(in) :: n1,n2,spaceComm
integer,intent(out) :: ierr
real(dp),intent(in):: xval(:,:)
integer,intent(in):: displace(:)

integer(abinit_offset) :: nboct,totoct
integer(abinit_offset) :: posit
integer(abinit_offset),allocatable :: dispoct(:)
integer :: i1,i2
real(dp), allocatable :: val(:)

ierr=0

#if defined MPI_IO

allocate(dispoct(n2))
allocate(val(n1))

nboct       = wff%nbOct_dp
dispoct(:)  = (displace(:)-1) * nboct * n1

do i2=1,n2
   posit = wff%offwff + dispoct(i2)
   do i1=1,n1
      val(i1) = xval(i1,i2)
   enddo
   call 
MPI_FILE_WRITE_AT(wff%fhwff,posit,val,n1,MPI_DOUBLE_PRECISION,statux,ierr)
!   call 
MPI_FILE_WRITE_AT(wff%fhwff,posit,xval(1,i2),n1,MPI_DOUBLE_PRECISION,statux,ierr)
enddo


! total offset
nboct = nboct * n1 * n2
call MPI_ALLREDUCE(nboct,totoct,1,MPI_INTEGER8,MPI_SUM,spaceComm,ierr)

wff%offwff = wff%offwff + totoct

deallocate(dispoct)
deallocate(val)

#endif

end subroutine xderiveWrite_dp2d_mpio_displ


Anyway , I work on it to see if i reproduce your problem in my kind of 
station

Muriel

David Waroquiers a écrit :
> Hello,
>
> I tried with the last 5.9.0 (revision 485) and it crashed (even for few
> bands : nband 256) with 8 cpus. Note that I decreased the number of
> steps to speed up the test (but it doesnt matter anyway).
>
> The end of the log file is at the end of the message.
>
> Any suggestion ?
>
> David
>
>  scprqt:  WARNING -
>   nstep=    5 was not enough SCF cycles to converge;
>   potential residual=  4.649E+00 exceeds tolvrs=  1.000E-12
>
>  ioarr: writing density data
>  ioarr: file name is asio2test_para8o_DS1_DEN
>  ioarr: data written to disk file asio2test_para8o_DS1_DEN
> -P-0000  leave_test : synchronization done...
> ================================================================================
>
>  ----iterations are completed or convergence reached----
>
>  outwf  : write wavefunction to file asio2test_para8o_DS1_WFK
> -P-0000  leave_test : synchronization done...
> [node008:27384] *** Process received signal ***
> [node008:27385] *** Process received signal ***
> [node008:27385] Signal: Segmentation fault (11)
> [node008:27385] Signal code: Address not mapped (1)
> [node008:27385] Failing at address: 0xc2c37e54
> [node008:27389] *** Process received signal ***
> [node008:27389] Signal: Segmentation fault (11)
> [node008:27389] Signal code: Address not mapped (1)
> [node008:27389] Failing at address: 0xb2ee4574
> [node008:27390] *** Process received signal ***
> [node008:27390] Signal: Segmentation fault (11)
> [node008:27390] Signal code: Address not mapped (1)
> [node008:27390] Failing at address: 0xb83e1914
> [node008:27391] *** Process received signal ***
> [node008:27391] Signal: Segmentation fault (11)
> [node008:27391] Signal code: Address not mapped (1)
> [node008:27391] Failing at address: 0xb83c32e4
> [node008:27386] *** Process received signal ***
> [node008:27386] Signal: Segmentation fault (11)
> [node008:27386] Signal code: Address not mapped (1)
> [node008:27386] Failing at address: 0xc9cb7dd4
> [node008:27387] *** Process received signal ***
> [node008:27387] Signal: Segmentation fault (11)
> [node008:27387] Signal code: Address not mapped (1)
> [node008:27387] Failing at address: 0xb67bd5a4
> [node008:27388] *** Process received signal ***
> [node008:27388] Signal: Segmentation fault (11)
> [node008:27388] Signal code: Address not mapped (1)
> [node008:27388] Failing at address: 0xc2f74d94
> [node008:27384] Signal: Segmentation fault (11)
> [node008:27384] Signal code: Address not mapped (1)
> [node008:27384] Failing at address: 0xbdd70364
> [node008:27389] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27389]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27389]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27389]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27389]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27389]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27389]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27389]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27389]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27389] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27389]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27389] *** End of error message ***
> [node008:27388] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27388]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27388]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27388]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27388]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27388]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27388]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27388]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27388]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27388] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27388]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27388] *** End of error message ***
> [node008:27391] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27391]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27391]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27391]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27391]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27391]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27391]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27391]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27391]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27391] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27391]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27391] *** End of error message ***
> [node008:27390] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27390]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27390]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27390]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27390]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27390]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27390]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27390]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27390]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27390] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27390]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27390] *** End of error message ***
> [node008:27386] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27386]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27386]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27386]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27386]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27386]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27386]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27386]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27386]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27386] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27386]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27386] *** End of error message ***
> [node008:27385] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27385]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27385]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27385]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27385]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27385]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27385]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27385]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27385]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27385] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27385]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27385] *** End of error message ***
> [node008:27387] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27384] [ 0] /lib64/libpthread.so.0 [0x3db920e4c0]
> [node008:27384]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27384]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27384]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27384]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27384]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27384]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27387]
> [ 1] 
> /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(xderivewrite_int2d_mpio_displ_+0x939)
>  [0x148614f]
> [node008:27384]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27384]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27384] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27384]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27384] *** End of error message ***
> [node008:27387]
> [ 2] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(writewf_
> +0xe96) [0x11fe522]
> [node008:27387]
> [ 3] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(rwwf_
> +0x4e36) [0x11fd682]
> [node008:27387]
> [ 4] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(outwf_
> +0x2983) [0x62d93b]
> [node008:27387]
> [ 5] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(gstate_
> +0x16f5e) [0x46deae]
> [node008:27387]
> [ 6] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(driver_
> +0xaec4) [0x451a64]
> [node008:27387]
> [ 7] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(MAIN__
> +0x2f7d) [0x44348d]
> [node008:27387]
> [ 8] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(main+0x2a)
> [0x440502]
> [node008:27387] [ 9] /lib64/libc.so.6(__libc_start_main+0xf4)
> [0x3db861d974]
> [node008:27387]
> [10] /home/pcpm/waroquiers/590_r485bis/abinit/5.9/bin/abinip(mpi_bcast_
> +0x49) [0x440429]
> [node008:27387] *** End of error message ***
> --------------------------------------------------------------------------
> mpirun noticed that process rank 6 with PID 27390 on node node008 exited
> on signal 11 (Segmentation fault).
> --------------------------------------------------------------------------
>
> On Mon, 2009-06-22 at 12:01 +0200, TORRENT Marc wrote:
>   
> > Hi again David,
> >
> > To simplify...
> > Could you test with the last 5.9/trunk/5.9.0-public ?
> > The treatment of MPI_IO WFK has been changed for the 5.9 and it's more
> > convenient for us to debug this last branch.
> > Thanks
> >
> > Marc
> >
> >
> > Marc.TORRENT@cea.fr a écrit : 
> >     
> > > Hi David, 
> > >
> > > 1) Did you try with the last corrections contained in the last 5.8.3
> > > bzr revision or 5.8.4 (at least revision 507) ? Muriel Delaveau and
> > > I found several improvements for the writing of the WFK file with
> > > MPI-IO; these corrections improve the portability of the code and
> > > have been merged in the revision 507. We found that the code
> > > produced crashes on several architectures because of wrong treatment
> > > of buffers... and hope to have correct that.
> > >
> > > 2) If you want to be able to use the file with anaddb you have to : 
> > > - use the last 5.8.3 branch (or 5.8.4) 
> > > or 
> > > - use the --enable-mpi-io-buggy option when building the code
> > > (unuseful after 5.8.3 rev507); but you could have buffer problems in
> > > that case.
> > >
> > >
> > > We tested the new changes on ifort and gcc43 with mpich, open-mpi. 
> > >
> > > In band-fft, the memory is splitted for the wfk but not for other
> > > quantities, especially if you use PAW. We plan to correct that soon.
> > >
> > > Marc 
> > >
> > >
> > >
> > >
> > > -------- Message d'origine-------- 
> > > De: David Waroquiers [mailto:david.waroquiers@uclouvain.be] 
> > > Date: ven. 19/06/2009 12:29 
> > > À: forum@abinit.org 
> > > Objet : [abinit-forum] Band/FFT parallelism on large systems 
> > >   
> > > Hello all, 
> > >
> > > I have tried to use the band/fft parallelism on a large supercell
> > > (a-SiO2, 72 
> > > atoms and 108 atoms). I encountered a problem while using a lot of
> > > bands (4480 
> > > bands). It reaches convergences but crashes at the end of the run
> > > when it is 
> > > supposed to write the WFK file (outwf call). I tried to run a
> > > calculation with 
> > > 16, 32 and 64 processors. 
> > >
> > > I have tried with fewer bands (640) and it works. 
> > > Do you have any idea how to overcome this problem ? The WFK file is
> > > supposed to 
> > > be 4 GB and the available memory on the clusters is more than that.
> > > By the way, 
> > > in the band/fft parallelism approach, the memory for the wfk is
> > > split into the 
> > > different cpus, isn't it ? 
> > >
> > > I encountered another problem while using cut3d to analyse the wfk
> > > generated 
> > > with the band/fft parallelism. It does not recognise the file as a
> > > valid wfk 
> > > file (about the same message as when band/fft parallelism didn't
> > > allow to 
> > > restart with a different number of processors, before version 5.8 if
> > > I'm 
> > > right). Any idea too ? 
> > >
> > > My input file is hereafter and the log messages are after the input
> > > file. I'm 
> > > using public version 5.8.3, revision 485 and the machines used are
> > > the "green" 
> > > clusters in UCL :  102 Dual Quad-Core Xeon L5420/2.5GHz in Dell
> > > Blade M1000e 
> > > with 16 GB (or 32 GB for some nodes) per node of 8 processors. 
> > >
> > > Thanks a lot 
> > >
> > > David Waroquiers 
> > > PhD Student 
> > > UCL - PCPM - ETSF 
> > >
> > >
> > >
> > >
> > > My input file : 
> > >
> > > # Amorphous SiO2 : Generation of the WFK file needed for the KSS
> > > (for GW 
> > > corrections) 
> > > # Dataset 1 : GS calculation (_DEN generation) 
> > > # Dataset 2 : GS calculation with many bands (_WFK generation) 
> > >
> > >   ndtset      2 
> > >   jdtset       1 2 
> > >   timopt      2 
> > >
> > > # Dataset 1 : _DEN file generation (Density) 
> > >
> > >   tolvrs1     1.0d-12 
> > >   prtden1    1 
> > >   nstep1     5 #5 for testing 
> > >   iscf1        7 
> > >   npulayit1  7 
> > >   nband1    256 
> > >
> > > # Dataset 2 : _WFK file (Wavefunction) 
> > >
> > >   tolwfr2     1.0d-12 
> > >   nband2     4480 
> > >   nbdbuf2    384 
> > >   istwfk2      1 
> > >   iscf2         7 
> > >   nstep2      5 #5 for testing 
> > >   getden2    1 
> > >
> > > # Options for Band/FFT Parallelism 
> > >
> > >   paral_kgb   1 
> > >   wfoptalg    14 
> > >   nloalg      4 
> > >   fftalg      401 
> > >   iprcch      4 
> > >   intxc       0 
> > >   istwfk      1 
> > >   fft_opt_lob 2 
> > >   npfft       1 
> > >   npband      16 #32 #64 
> > >
> > > # K-point mesh 
> > >
> > >   kptopt      0 
> > >   kpt         0.0 0.0 0.0 
> > >
> > > # System definition 
> > > # Unit cell 
> > >
> > >   acell       1.9465690950E+01  1.9465690950E+01  1.9465690950E+01 
> > >   rprim       1 0 0 
> > >               0 1 0 
> > >               0 0 1 
> > >
> > > # Atom types 
> > >
> > >   ntypat      2 
> > >   znucl       8 14 
> > >
> > > # Atoms and coordinates 
> > >
> > >   natom       72 
> > >   typat       48*1 24*2 
> > >   xcart       1.8342971905E+01  1.0013093348E+01  4.9948115472E+00 
> > >               1.8450118788E+01  5.1100335358E+00  1.1410341879E+01 
> > >               3.0243029960E+00  1.7006888337E+01  1.0689037523E+01 
> > >               6.3068666011E+00  1.4446482399E+01  7.9505060279E+00 
> > >               1.9178811503E+01  4.4712567836E-01  3.4641995090E+00 
> > >               9.5178783093E+00  1.2762912471E+01  1.4947329016E+01 
> > >               1.7402433472E+01  4.7067303120E+00  1.5833402903E+00 
> > >               1.0623164695E+01  2.7299953166E+00  8.7471659694E+00 
> > >               1.2931573871E+01  1.8128981231E+01  6.7007362518E+00 
> > >               1.8660924236E+01  1.4792395464E+01  3.1319031106E+00 
> > >               7.0217232014E+00  6.3190579071E+00  2.1266991430E+00 
> > >               4.1181163909E-01  5.0929210080E+00  5.7193503290E+00 
> > >               7.6209880479E+00  1.5443775482E+00  6.1023412080E-01 
> > >               1.7923134211E+01  9.4056919719E+00  1.3628670860E+01 
> > >               1.4710748045E+01  9.1118601940E+00  1.7566857742E+01 
> > >               1.0411995344E+01  1.0041061607E+00  1.5870123306E+01 
> > >               1.0980496920E+01  1.3629862231E+01  6.8821852197E+00 
> > >               1.2756648650E+01  9.3922889131E+00  1.2966781879E+01 
> > >               1.3710153187E+01  2.2151381385E+00  1.9176017166E+01 
> > >               5.9015247795E+00  1.8254646045E+01  1.6364133902E+01 
> > >               3.5889689987E+00  8.6729161022E+00  4.9047876611E+00 
> > >               1.4649631278E+01  1.1782133781E+01  2.4189697381E+00 
> > >               1.3094524372E+01  1.5574388332E+01  1.1017906884E+01 
> > >               1.8122798453E+00  1.5904671691E+01  1.5390374184E+01 
> > >               8.0934509994E+00  9.9606459884E+00  5.6351418737E+00 
> > >               1.0388873243E+01  1.1258002356E+01  1.9535431306E+01 
> > >               1.7801695829E+01  1.5681701759E+01  1.1954743795E+01 
> > >               2.9395289639E+00  3.6212308778E+00  1.4808160737E+00 
> > >               1.3785141980E+01  3.1146153451E+00  4.7897808777E+00 
> > >               6.6125694236E+00  3.8955369666E+00  1.1802613942E+01 
> > >               1.0543336669E+00  8.8480531151E+00  9.2302571597E+00 
> > >               1.5034376672E+01  1.3207034271E+01  1.5126390258E+01 
> > >               1.9223920516E+01  6.5595988246E-01  1.3020475817E+01 
> > >               6.6553078921E+00  5.1934209327E+00  6.9894256581E+00 
> > >               1.4918361618E+01  3.1596212425E+00  1.4324193688E+01 
> > >               8.0804273193E+00  7.9884008127E+00  1.4307619386E+01 
> > >               5.7570753518E+00  1.3551949199E+01  1.8079850277E+01 
> > >               1.2833144388E+01  6.9576781789E+00  1.8702339976E+00 
> > >               2.7890960157E+00  1.7032376017E+01  6.7568473875E-01 
> > >               8.6760457768E+00  1.0859908527E+01  1.0407253204E+01 
> > >               6.3690907257E+00  2.2769273004E-01  8.2629069843E+00 
> > >               1.4623475391E+01  1.7952319809E+01  1.5406783784E+01 
> > >               1.5775821227E+01  1.3896960139E+01  6.9539101570E+00 
> > >               1.5477566296E+01  1.7519166868E+00  9.5117606862E+00 
> > >               3.1098755647E+00  7.2414373656E+00  1.3444441571E+01 
> > >               2.9576688783E+00  1.7045648497E+01  5.6738016905E+00 
> > >               9.7659864282E+00  1.6334927247E+01  1.8709494220E+01 
> > >               5.6015780233E+00  4.6820174692E+00  1.6849684158E+01 
> > >               1.3193293623E+01  1.6296954721E+00  7.4269549058E+00 
> > >               4.0153579861E+00  1.6089810803E+01  1.7511617105E+01 
> > >               1.5080013653E+01  1.5674902127E+01  1.3378910449E+01 
> > >               1.3468917372E+01  1.2396666756E+00  1.6246453919E+01 
> > >               3.1443097800E-01  3.4518653529E+00  3.0738155414E+00 
> > >               1.6864054813E+01  1.2620177700E+01  4.3720388857E+00 
> > >               1.3252228290E+01  1.5343974821E+01  7.9284144425E+00 
> > >               8.4872425534E+00  1.9054897865E+01  1.7815010425E+01 
> > >               1.5170448087E+01  1.0186883021E+01  1.4748027393E+01 
> > >               7.5516402653E+00  3.0013700719E+00  8.9766200084E+00 
> > >               6.4090355722E+00  7.4843741588E+00  4.9295671605E+00 
> > >               4.3705611827E-01  7.6893073781E+00  1.2001555962E+01 
> > >               8.4238741309E+00  1.2232714786E+01  7.6995337657E+00 
> > >               5.8387974184E+00  5.9155119378E+00  1.4039991791E+01 
> > >               1.3107235988E+01  9.8055489044E+00  6.4400593019E-01 
> > >               8.3270647814E-01  1.7227458132E+01  1.2775664290E+01 
> > >               1.4372625432E+01  4.2560000137E+00  1.9730406948E+00 
> > >               5.7914453145E+00  4.0664955533E+00  3.9036518542E-01 
> > >               9.7815513593E+00  1.0257448955E+01  1.3164763822E+01 
> > >               1.6979663973E+01  2.5757556368E+00  1.2070399003E+01 
> > >               9.1476280310E-01  8.1192625454E+00  6.2498371664E+00 
> > >               8.8902943261E+00  1.3433615492E+01  1.7894990037E+01 
> > >               4.7238007437E+00  1.7074503731E+01  8.1487422033E+00 
> > >               1.1337419675E+00  1.7170180156E+01  3.2442179093E+00 
> > >
> > > # Energy cutoff for the planewaves 
> > >
> > >   ecut        32.0 
> > >
> > > # Parameters for the SCF cycles 
> > >
> > >   nstep       5 
> > >   diemac      4.0 
> > >   ixc         11 
> > >
> > >
> > >
> > >
> > >
> > >
> > > Here is the end of the message log for the 72 atoms cell with 4480
> > > bands run on 
> > > 16 processors : 
> > >
> > > ================================================================================ 
> > >
> > >  ----iterations are completed or convergence reached---- 
> > >
> > >  outwf  : write wavefunction to file asio2test_para16_4096o_DS2_WFK 
> > > -P-0000  leave_test : synchronization done... 
> > > -------------------------------------------------------------------------- 
> > > MPI_ABORT was invoked on rank 15 in communicator MPI_COMM_WORLD 
> > > with errorcode 1. 
> > >
> > > NOTE: invoking MPI_ABORT causes Open MPI to kill all MPI processes. 
> > > You may or may not see output from other processes, depending on 
> > > exactly when Open MPI kills them. 
> > > -------------------------------------------------------------------------- 
> > > -------------------------------------------------------------------------- 
> > > mpirun has exited due to process rank 1 with PID 6159 on 
> > > node node054 exiting without calling "finalize". This may 
> > > have caused other processes in the application to be 
> > > terminated by signals sent by mpirun (as reported here). 
> > > -------------------------------------------------------------------------- 
> > > [green:29817] 15 more processes have sent help message
> > > help-mpi-api.txt / 
> > > mpi-abort 
> > > [green:29817] Set MCA parameter "orte_base_help_aggregate" to 0 to
> > > see all help 
> > > / error messages 
> > >
> > >
> > >
> > >
> > >
> > > Here is the end of the log file I got from the 108 atoms cell (with
> > > 3200 bands) 
> > > run on 32 processors : 
> > >
> > > ================================================================================ 
> > >
> > >  ----iterations are completed or convergence reached---- 
> > >
> > >  outwf  : write wavefunction to file as108nr_004o_DS2_WFK 
> > > -P-0000  leave_test : synchronization done... 
> > > [node090:26797] *** Process received signal *** 
> > > [node090:26797] Signal: Segmentation fault (11) 
> > > [node090:26797] Signal code: Address not mapped (1) 
> > > [node090:26797] Failing at address: 0x2 
> > > [node090:26797] [ 0] /lib64/libpthread.so.0 [0x395300e4c0] 
> > > [node090:26797] [ 1] 
> > > /cvos/shared/apps/openmpi/intel/64/1.3.1/lib64/libmpi.so.0(ompi_ddt_add+0x6c1) 
> > > [0x2b389ea74951] 
> > > [node090:26797] [ 2] 
> > > /cvos/shared/apps/openmpi/intel/64/1.3.1/lib64/libmpi.so.0(ompi_ddt_create_indexed_block+0x1b3) 
> > > [0x2b389ea750c3] 
> > > [node090:26797] [ 3] 
> > > /cvos/shared/apps/openmpi/intel/64/1.3.1/lib64/libmpi.so.0(MPI_Type_create_indexed_block+0xb8) 
> > > [0x2b389ea9d848] 
> > > [node090:26797] [ 4] 
> > > /cvos/shared/apps/openmpi/intel/64/1.3.1/lib64/libmpi_f77.so.0(mpi_type_create_indexed_block_f+0x38) 
> > > [0x2b389e828780] 
> > > [node090:26797] [ 5] 
> > > /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(wffwritecg_+0xc29)
> > > [0x10823a9] 
> > > [node090:26797] [ 6] 
> > > /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(writewf_+0x1ef9)
> > > [0x107f0b7] 
> > > [node090:26797] [ 7] 
> > > /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(rwwf_+0x3e88)
> > > [0x107d1b4] 
> > > [node090:26797] [ 8] 
> > > /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(outwf_+0x2616)
> > > [0x5f5a72] 
> > > [node090:26797] [ 9] 
> > > /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(gstate_+0x15074)
> > > [0x4675cc] 
> > > [node090:26797] [10] 
> > > /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(driver_+0x740e)
> > > [0x44ea52] 
> > > [node090:26797] [11] 
> > > /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(MAIN__+0x52a6)
> > > [0x4448f6] 
> > > [node090:26797]
> > > [12] /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip(main+0x2a) 
> > > [0x43f642] 
> > > [node090:26797] [13] /lib64/libc.so.6(__libc_start_main+0xf4)
> > > [0x395281d974] 
> > > [node090:26797] [14] /home/pcpm/waroquiers/583/abinit/5.8/bin/abinip
> > > [0x43f569] 
> > > [node090:26797] *** End of error message *** 
> > > -------------------------------------------------------------------------- 
> > > mpirun noticed that process rank 8 with PID 26797 on node node090
> > > exited on 
> > > signal 11 (Segmentation fault). 
> > > -------------------------------------------------------------------------- 
> > >
> > >       
>
>