I'm testing biobrew v0.9 on a 5 node cluster, each with dual 2.4 GHz Xeons. I've never used sge or rocks before, so I'm a little confused. I want to run a 2 cpu mpi job, but sge schedules 2 nodes with one mpi thread each instead of both processors on a single node. I'm running everything with the defaults chosen by biobrew. Here's my qsub script, in PBS, I can specify #PBS -l nodes=1:ppn=2 to get both processors on a single node, what's the equivalent sge magic? #!/bin/sh #$ -pe mpi 2 /opt/mpich/ethernet/gcc/bin/mpirun -np $NSLOTS -machinefile $TMPDIR/machines /opt/hpl-eth/bin/gcc/xhpl -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 226 bytes Desc: not available Url : http://bioinformatics.org/pipermail/biobrew-users/attachments/20031211/30266f20/attachment.bin