MPI benchmark on IBM p-690 POWER4+ cluster (1.7 GHz)
Remarks:
- mod1j  : mod1j is run on 2 processors within 1 node and on 2 processors
           in 2 different nodes. The results are in 'mod1j.p02.log' and
	   'mod1j.p02-1.log', respectively. 
- mod1k  : The system has a problem with the MPI window that was created:
          
	   ERROR: 0032-438 Target buffer ends outside target window  (4)
	   in MPI_Get, task 1

           ERROR: 0031-250  task 1: Terminated
           ERROR: 0031-250  task 0: Terminated
	   
- mod2ci : On 1 processor we get a segmetation fault, probably due to
           an amount of memory that is requested that not can be satisfied:
	   For 4 and 16 processors there is no problem.
