This is the incriminated code (it is related to another question I asked, here):
program foo
use mpi
implicit none
type double_st
sequence
real(kind(0.d0)) :: x,y,z
integer :: acc
end type double_st
integer, parameter :: n=8
INTEGER :: MPI_CADNA_DST
integer :: nproc, iprank
INTEGER :: IERR, STAT(MPI_STATUS_SIZE)
INTEGER :: MPI_CADNA_DST_TMP
INTEGER ::&
COUNT=4,&
BLOCKLENGTHS(4)=(/1,1,1,1/),&
TYPES(4)=(/MPI_DOUBLE_PRECISION,&
MPI_DOUBLE_PRECISION,&
MPI_DOUBLE_PRECISION,&
MPI_INTEGER/)
INTEGER(KIND=MPI_ADDRESS_KIND) :: DISPLS(4), LB, EXTENT
TYPE(DOUBLE_ST) :: DST
INTEGER :: I
type(double_st), allocatable :: bufs(:), bufr(:)
allocate(bufs(n), bufr(n))
CALL MPI_INIT(IERR)
CALL MPI_COMM_SIZE(MPI_COMM_WORLD, NPROC, IERR)
CALL MPI_COMM_RANK(MPI_COMM_WORLD, IPRANK, IERR)
CALL MPI_GET_ADDRESS(DST%X, DISPLS(1))
CALL MPI_GET_ADDRESS(DST%Y, DISPLS(2))
CALL MPI_GET_ADDRESS(DST%Z, DISPLS(3))
CALL MPI_GET_ADDRESS(DST%ACC, DISPLS(4))
DO I=4,1,-1
DISPLS(I)=DISPLS(I)-DISPLS(1)
ENDDO
CALL MPI_TYPE_CREATE_STRUCT(4,BLOCKLENGTHS,DISPLS,TYPES, MPI_CADNA_DST_TMP,IERR)
CALL MPI_TYPE_COMMIT(MPI_CADNA_DST_TMP,IERR)
CALL MPI_TYPE_GET_EXTENT(MPI_CADNA_DST_TMP, LB, EXTENT, IERR)
CALL MPI_TYPE_CREATE_RESIZED(MPI_CADNA_DST_TMP, LB, EXTENT, MPI_CADNA_DST, IERR)
CALL MPI_TYPE_COMMIT(MPI_CADNA_DST,IERR)
bufs(:)%x=iprank
bufs(:)%y=iprank
bufs(:)%z=iprank
bufs(:)%acc=iprank
call mpi_send(bufs(1), n, mpi_cadna_dst, 1-iprank, 0, mpi_comm_world, ierr)
call mpi_recv(bufr(1), n, mpi_cadna_dst, 1-iprank, 0, mpi_comm_world, stat, ierr)
deallocate(bufs, bufr)
end program foo
Compiled with intelMPI, version 4.0 or 5.0, I get invalid read/write errors with valgrind or with dmalloc at the send. With openMPI, it is not that clear with that minimum example, but I got similar problems with this communication in the big code from which it is extracted.
Thanks for helping!
It looks like the use of sequence is the culprit here. Since your data are not aligned the same way, forcing the linear packing with the sequence keyword generate some unaligned accesses, probably while writing the one of the arrays. Removing it does the trick.