The benchmarks were built with the Intel compilers. MPICH was used as the MPI implementation. Process migration to the newest nodes was avoided by locking the ssh deamon (not the best solution). The nodes were pc13, pc14, pc15, pc16 (733 MHz, PIIIs). Results :
NAS Parallel Benchmarks 2.3 -- BT Benchmark
No input file inputbt.data. Using compiled defaults
Size: 64x 64x 64
Iterations: 200 dt: 0.000800
Number of active processes: 4
Time step 1
Time step 20
Time step 40
Time step 60
Time step 80
Time step 100
Time step 120
Time step 140
Time step 160
Time step 180
Time step 200
Verification being performed for class A
accuracy setting for epsilon = 0.1000000000000E-07
Comparison of RMS-norms of residual
1 0.1080634671464E+03 0.1080634671464E+03 0.6969749535109E-14
2 0.1131973090122E+02 0.1131973090122E+02 0.1255405701709E-14
3 0.2597435451158E+02 0.2597435451158E+02 0.3282665917769E-14
4 0.2366562254468E+02 0.2366562254468E+02 0.8406791988557E-14
5 0.2527896321175E+03 0.2527896321175E+03 0.1394160013545E-13
Comparison of RMS-norms of solution error
1 0.4234841604053E+01 0.4234841604053E+01 0.1468118413674E-14
2 0.4439028249700E+00 0.4439028249700E+00 0.6252624235385E-14
3 0.9669248013635E+00 0.9669248013635E+00 0.3789059889763E-14
4 0.8830206303977E+00 0.8830206303977E+00 0.0000000000000E+00
5 0.9737990177083E+01 0.9737990177083E+01 0.2553811957023E-14
Verification Successful
BT Benchmark Completed.
Class = A
Size = 64x 64x 64
Iterations = 200
Time in seconds = 917.25
Total processes = 4
Compiled procs = 4
Mop/s total = 183.47
Mop/s/process = 45.87
Operation type = floating point
Verification = SUCCESSFUL
Version = 2.3
Compile date = 30 Jun 2004
Compile options:
MPIF77 = mpif77
FLINK = mpif77
FMPI_LIB = -L/usr/local/lib
FMPI_INC = -I/usr/local/include
FFLAGS = -O2
FLINKFLAGS = -static
RAND = (none)
Please send the results of this run to:
NPB Development Team
Internet: npb@nas.nasa.gov
If email is not available, send this to:
MS T27A-1
NASA Ames Research Center
Moffett Field, CA 94035-1000
Fax: 415-604-3957