[MPICH] ROMIO MPI_FILE_WRITE ALL

[Rajeev Thakur]

MPICH-1.2.6 may not have the Fortran 90 module mpi.mod. MPICH2 does.
 
Rajeev
 


  _____  

From: owner-mpich-discuss at mcs.anl.gov
[mailto:owner-mpich-discuss at mcs.anl.gov] On Behalf Of Stephen Scott
Sent: Tuesday, June 28, 2005 3:17 PM
To: Stephen Scott
Cc: mpich-discuss at mcs.anl.gov
Subject: Re: [MPICH] ROMIO MPI_FILE_WRITE ALL


Dear list again,

I may have found the problem. If I change 'USE mpi' to 'INCLUDE 'mpif.h' the
program appears to run and compile without errors. Does anyone have an
explanation for this?

Cheers,

Steve

On 28 Jun 2005, at 19:52, Stephen Scott wrote:



Dear list,

I have a question/problem related to the use of MPI_FILE_WRITE_ALL from the
ROMIO package. I want to write a distributed 4D fortran array to file using
the ROMIO library. The array is divided along the third dimension. A section
of the code is listed below. 

The purpose of the subroutine is to write the 4D fluid_uk(:,:,:,:)
distributed array to file on node 0. However, I get a compile time error for
the call to MPI_FILE_WRITE_ALL - 'There is no matching specific subroutine
for this generic subroutine call. [MPI_FILE_WRITE_ALL]'

I presumed that MPI_FILE_WRITE_ALL would accept an array of any dimension
but it appears I am wrong. I would be most grateful for any feedback or
suggestions for the list!

Thanks in advance!

Steve

mpich-1.2.6
intel compilers 8.0
Red Hat Enterprise Linux WS release 3 (Taroon Update 1)


SUBROUTINE fluid_restart_write(time,ierr)

USE precision
USE fluid_arrays, ONLY : fluid_uk
USE domain_params, ONLY : ni,nj,nk
USE mpi

IMPLICIT NONE

INTEGER,INTENT(INOUT) :: ierr
INTEGER,INTENT(IN) :: time
INTEGER :: myrank
INTEGER :: nprocs
INTEGER*8 :: disp=0
CHARACTER(len=100) :: tstep 
CHARACTER(len=10) :: execute_date
CHARACTER(len=10) :: execute_time
INTEGER,PARAMETER :: MASTER = 0

INTEGER :: gsizes(4)
INTEGER :: distribs(4)
INTEGER :: dargs(4)
INTEGER :: psizes(4)
INTEGER :: local_size
INTEGER :: PANDORA_RESTART_TYPE
INTEGER :: PANDORA_RESTART_FILE
INTEGER :: PANDORA_COMM
INTEGER :: status(MPI_STATUS_SIZE)

CALL MPI_COMM_RANK(MPI_COMM_WORLD,myrank,ierr)
CALL MPI_COMM_SIZE(MPI_COMM_WORLD,nprocs,ierr)

gsizes = (/ni,nj,nk,3/)
distribs = MPI_DISTRIBUTE_BLOCK
dargs = MPI_DISTRIBUTE_DFLT_DARG
psizes = (/1,1,nprocs,1/)

CALL MPI_TYPE_CREATE_DARRAY(nprocs,myrank,4,gsizes,distribs,dargs,psizes, &
MPI_ORDER_FORTRAN,MPI_DOUBLE_COMPLEX,PANDORA_RESTART_TYPE,ierr)

CALL MPI_TYPE_COMMIT(PANDORA_RESTART_TYPE,ierr)

! fname_frestart defined earlier in module

CALL
MPI_FILE_OPEN(MPI_COMM_WORLD,fname_frestart,MPI_MODE_WRONLY+MPI_MODE_CREATE,
&
MPI_INFO_NULL,PANDORA_RESTART_FILE,ierr)

CALL
MPI_FILE_SET_VIEW(PANDORA_RESTART_FILE,disp,MPI_DOUBLE_COMPLEX,PANDORA_RESTA
RT_TYPE, &
"native",MPI_INFO_NULL,ierr)

! fluid_uk(ni,nj,nk/nprocs,3)
local_size = ni*nj*(nk/nprocs)*3

CALL
MPI_FILE_WRITE_ALL(PANDORA_RESTART_FILE,fluid_uk,local_size,MPI_DOUBLE_COMPL
EX,status,ierr)

CALL MPI_FILE_CLOSE(PANDORA_RESTART_FILE,ierr)

END SUBROUTINE


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20050628/85a25dfb/attachment.htm>