I ran my program on the SP2 with 4 nodes. The augmented matrix size is 256 by 256 +1, and the data is read in from the file datafile, which I have stored in my CPS 615 homework directory, in the subdirectory hw4. Using the compiler directive
!HPF$ DISTRIBUTE augmented (BLOCK,*)I got the following timing:
merlin4:~/CPS615.dir/hw4> source SETENV merlin4:~/CPS615.dir/hw4> pghpf -O gauss.hpf -o gauss ** gauss === End of Compilation 1 === ** gauss_elim === End of Compilation 2 === 1501-510 Compilation successful for file pghpfE_TcVFXAAB.f. Linking: merlin4:~/CPS615.dir/hw4> gauss -pghpf -host merlin1,merlin2,merlin3,merlin4 -np 4 -stat cpus cpu real user sys ratio node 0* 260.34 16.57 13.93 12% merlin4 1 260.38 16.79 13.37 12% merlin1 2 260.06 18.30 13.05 12% merlin2 3 260.07 18.25 14.42 13% merlin3 min 260.06 16.57 13.05 avg 260.21 17.48 13.69 max 260.38 18.30 14.42 total 260.38 69.91 54.77 0.48x merlin4:~/CPS615.dir/hw4>