The ABINIT Users Mailing List ( CLOSED )

[zmq.lyao@gmail.com]

Deal All,
     I met a problem about runing abinip(build by PGI5.2 and mpich2 using 
4.6.5 version source) on a cluster. The cluster has 4 nodes and each node has 
4 CPUs.
     When I start mpd on one node and mpirun -np (mumber of cpu) abinip 
<files>&log, it is ok. But, if I use lamboot and mpirun,it don't work.
     The boot of LAM is no problem. The log file gives information like this:
     
 PGFIO-F-217/formatted read/unit=5/attempt to read past end of file.
 File name = stdin     formatted, sequential access   record = 1
 In source file iofn1.par.f90, at line number 85
  ABINIT 
  
  Give name for formatted input file: 
-----------------------------------------------------------------------------
It seems that [at least] one of processes that was started with mpirun
did not invoke MPI_INIT before quitting (it is possible that more than
one process did not invoke MPI_INIT -- mpirun was only notified of the
first one, which was on node n0).

mpirun can *only* be used with MPI programs (i.e., programs that
invoke MPI_INIT and MPI_FINALIZE).  You can use the "lamexec" program
to run non-MPI programs over the lambooted nodes.



Somebody knows the reason? Thanks in advance.

Best regards,

Zeming