Running the program on 1 node gives a very interesting result:
merlin4:~/CPS615.dir/hw4> gauss -pghpf -host merlin4 -np 1 -stat cpus cpu real user sys ratio node 0* 10.76 10.29 0.05 96% merlin4 total 10.76 10.29 0.05 0.96x merlin4:~/CPS615.dir/hw4>
We see that the program runs over 10 times faster (real time) on one processor!