Intel Paragon
| This data set was obtained on the
smaller Paragon at Sandia National Laboratory as an interactive job. This
machine has a total of 64 nodes, with the compute nodes running the SUNMOS/PUMA
operating system. All nodes have at least 16MB of DRAM, so this problem
should fit (not much paging). Wall-clock time was used in place of "tused" to compute the number of zone-cycles per second because the UNIX etime routine, which returns CPU time, requires some missing system library modules. All routines were compiled with: sif77 -c -O4
GRID: 32 x 32 x 32 per processor(tile) (4 Steps)
Speedup/
Processors Wall Clock tused(s) Zone-Cycles/sec MFLOPS C90s Speedup Processor
1 23.76 ? 5517 4.61 0.05 1.00 1.00
2 23.83 ? 10996 9.19 0.09 2.00 1.00
3 24.31 ? 16170 13.52 0.14 2.93 0.98
4 23.88 ? 21946 18.35 0.18 3.98 0.99
6 24.33 ? 32313 27.01 0.27 5.86 0.98
8 23.89 ? 43875 36.68 0.37 7.95 0.99
9 25.01 ? 47152 39.42 0.39 8.55 0.95
12 24.33 ? 64634 54.03 0.54 11.72 0.98
Another test run in interactive mode:
GRID: 32 x 32 x 32 per processor(tile) (4 Steps)
Speedup/
Processors Wall Clock tused(s) Zone-Cycles/sec MFLOPS C90s Speedup Processor
1 23.76 23.31 5517 4.61 0.05 1.00 1.00
8 23.89 23.45 43865 36.67 0.37 7.95 0.99
27 25.69 24.62 137708 115.12 1.15 24.96 0.92
64 24.31 23.72 344767 288.23 2.88 62.49 0.98
125 27.41 25.81 597431 499.45 4.99 108.29 0.87
Back to Pure Hydro Main |