COMPUTE_PI FORTRAN77/OpenMP version Estimate PI by summing a series. The number of processors = 16 The number of threads = 1 R8_TEST: Estimate the value of PI, using double precision arithmetic. N = number of terms computed and added; MODE = SEQ for sequential code; MODE = OMP for Open MP enabled code; (performance depends on if Open MP is used, and how many processes are availablec) ESTIMATE = the computed estimate of PI; ERROR = ( the computed estimate - PI ); TIME = elapsed wall clock time; You can't increase N forever, because: A) ROUNDOFF starts to be a problem, and B) maximum integer size is a problem. N Mode Estimate Error Time 1 SEQ 3.2000000000 0.584073E-01 0.339998E-06 1 OMP 3.2000000000 0.584073E-01 0.514500E-05 10 SEQ 3.1424259850 0.833331E-03 0.250002E-06 10 OMP 3.1424259850 0.833331E-03 0.697000E-06 100 SEQ 3.1416009869 0.833333E-05 0.200300E-05 100 OMP 3.1416009869 0.833333E-05 0.238600E-05 1000 SEQ 3.1415927369 0.833333E-07 0.195830E-04 1000 OMP 3.1415927369 0.833333E-07 0.199130E-04 10000 SEQ 3.1415926544 0.833341E-09 0.195218E-03 10000 OMP 3.1415926544 0.833341E-09 0.195577E-03 100000 SEQ 3.1415926536 0.836842E-11 0.190385E-02 100000 OMP 3.1415926536 0.836842E-11 0.185913E-02 1000000 SEQ 3.1415926536 0.284217E-13 0.176358E-01 1000000 OMP 3.1415926536 0.284217E-13 0.168979E-01 10000000 SEQ 3.1415926536 0.621725E-13 0.168656 10000000 OMP 3.1415926536 0.621725E-13 0.168646 100000000 SEQ 3.1415926536 0.633271E-12 1.68643 100000000 OMP 3.1415926536 0.633271E-12 1.68643 1000000000 SEQ 3.1415926536 0.177636E-12 16.8750 1000000000 OMP 3.1415926536 0.177636E-12 16.8629 COMPUTE_PI Normal end of execution. COMPUTE_PI FORTRAN77/OpenMP version Estimate PI by summing a series. The number of processors = 16 The number of threads = 2 R8_TEST: Estimate the value of PI, using double precision arithmetic. N = number of terms computed and added; MODE = SEQ for sequential code; MODE = OMP for Open MP enabled code; (performance depends on if Open MP is used, and how many processes are availablec) ESTIMATE = the computed estimate of PI; ERROR = ( the computed estimate - PI ); TIME = elapsed wall clock time; You can't increase N forever, because: A) ROUNDOFF starts to be a problem, and B) maximum integer size is a problem. N Mode Estimate Error Time 1 SEQ 3.2000000000 0.584073E-01 0.314001E-06 1 OMP 3.2000000000 0.584073E-01 0.128598E-03 10 SEQ 3.1424259850 0.833331E-03 0.218002E-06 10 OMP 3.1424259850 0.833331E-03 0.215800E-05 100 SEQ 3.1416009869 0.833333E-05 0.173100E-05 100 OMP 3.1416009869 0.833333E-05 0.213000E-05 1000 SEQ 3.1415927369 0.833333E-07 0.169170E-04 1000 OMP 3.1415927369 0.833333E-07 0.950599E-05 10000 SEQ 3.1415926544 0.833341E-09 0.168630E-03 10000 OMP 3.1415926544 0.833336E-09 0.853900E-04 100000 SEQ 3.1415926536 0.836842E-11 0.168557E-02 100000 OMP 3.1415926536 0.835332E-11 0.843958E-03 1000000 SEQ 3.1415926536 0.284217E-13 0.168708E-01 1000000 OMP 3.1415926536 0.106137E-12 0.101335E-01 10000000 SEQ 3.1415926536 0.621725E-13 0.168857 10000000 OMP 3.1415926536 0.129674E-12 0.843923E-01 100000000 SEQ 3.1415926536 0.633271E-12 1.68630 100000000 OMP 3.1415926536 0.116351E-12 0.843568 1000000000 SEQ 3.1415926536 0.177636E-12 16.8639 1000000000 OMP 3.1415926536 0.107914E-12 8.43169 COMPUTE_PI Normal end of execution. COMPUTE_PI FORTRAN77/OpenMP version Estimate PI by summing a series. The number of processors = 16 The number of threads = 4 R8_TEST: Estimate the value of PI, using double precision arithmetic. N = number of terms computed and added; MODE = SEQ for sequential code; MODE = OMP for Open MP enabled code; (performance depends on if Open MP is used, and how many processes are availablec) ESTIMATE = the computed estimate of PI; ERROR = ( the computed estimate - PI ); TIME = elapsed wall clock time; You can't increase N forever, because: A) ROUNDOFF starts to be a problem, and B) maximum integer size is a problem. N Mode Estimate Error Time 1 SEQ 3.2000000000 0.584073E-01 0.234999E-06 1 OMP 3.2000000000 0.584073E-01 0.182830E-03 10 SEQ 3.1424259850 0.833331E-03 0.214000E-06 10 OMP 3.1424259850 0.833331E-03 0.208100E-05 100 SEQ 3.1416009869 0.833333E-05 0.173600E-05 100 OMP 3.1416009869 0.833333E-05 0.230500E-05 1000 SEQ 3.1415927369 0.833333E-07 0.168950E-04 1000 OMP 3.1415927369 0.833333E-07 0.611500E-05 10000 SEQ 3.1415926544 0.833341E-09 0.168585E-03 10000 OMP 3.1415926544 0.833331E-09 0.488010E-04 100000 SEQ 3.1415926536 0.836842E-11 0.169396E-02 100000 OMP 3.1415926536 0.833333E-11 0.531938E-03 1000000 SEQ 3.1415926536 0.284217E-13 0.168745E-01 1000000 OMP 3.1415926536 0.821565E-13 0.549107E-02 10000000 SEQ 3.1415926536 0.621725E-13 0.168711 10000000 OMP 3.1415926536 0.123457E-12 0.425977E-01 100000000 SEQ 3.1415926536 0.633271E-12 1.69030 100000000 OMP 3.1415926536 0.110578E-12 0.421931 1000000000 SEQ 3.1415926536 0.177636E-12 16.8635 1000000000 OMP 3.1415926536 0.275335E-13 4.22151 COMPUTE_PI Normal end of execution.