At first glance, the test looks ok.
Why do you think <= is incorrect? Is there a buffer length problem
somewhere?
I am able to reproduce the problem with 10 procs, though. But it runs
successfully at 8. Same results with both openib btl and tcp btl.
Can you file a ticket / dig a
I am running mtt test on our cluster and I found error for
IBM reduce_scatter_in_place test for np>8
/home/USERS/lenny/OMPI_1_3_TRUNK/bin/mpirun -np 10 -H witch2
./reduce_scatter_in_place
**WARNING**]: MPI_COMM_WORLD rank 4, file reduce_scatter_in_place.c:80:
bad answer (0) at index 0 of 1000