COMPUTE_PI(): FORTRAN90/OpenMP version Estimate the value of PI by summing a series. The number of processors available = 16 The number of threads available = 1 R8_TEST: Estimate the value of PI. N = number of terms computed and added; MODE = SEQ for sequential code; MODE = OMP for Open MP enabled code; (performance depends on whether Open MP is used, and how many processes are available!) ESTIMATE = the computed estimate of PI; ERROR = ( the computed estimate - PI ); TIME = elapsed wall clock time; Note that you can't increase N forever, because: A) ROUNDOFF starts to be a problem, and B) maximum integer size is a problem. The maximum integer: 2147483647 N Mode Estimate Error Time 1 SEQ 3.2000000000 0.584073E-01 0.316002E-06 1 OMP 3.2000000000 0.584073E-01 0.400900E-05 10 SEQ 3.1424259850 0.833331E-03 0.263000E-06 10 OMP 3.1424259850 0.833331E-03 0.688000E-06 100 SEQ 3.1416009869 0.833333E-05 0.190800E-05 100 OMP 3.1416009869 0.833333E-05 0.229300E-05 1000 SEQ 3.1415927369 0.833333E-07 0.185870E-04 1000 OMP 3.1415927369 0.833333E-07 0.189190E-04 10000 SEQ 3.1415926544 0.833341E-09 0.185452E-03 10000 OMP 3.1415926544 0.833341E-09 0.185804E-03 100000 SEQ 3.1415926536 0.836842E-11 0.185136E-02 100000 OMP 3.1415926536 0.836842E-11 0.182228E-02 1000000 SEQ 3.1415926536 0.284217E-13 0.183937E-01 1000000 OMP 3.1415926536 0.284217E-13 0.207610E-01 10000000 SEQ 3.1415926536 0.621725E-13 0.169510 10000000 OMP 3.1415926536 0.621725E-13 0.169340 100000000 SEQ 3.1415926536 0.633271E-12 1.69914 100000000 OMP 3.1415926536 0.633271E-12 1.69317 1000000000 SEQ 3.1415926536 0.177636E-12 16.9645 1000000000 OMP 3.1415926536 0.177636E-12 17.0145 COMPUTE_PI(): Normal end of execution. COMPUTE_PI(): FORTRAN90/OpenMP version Estimate the value of PI by summing a series. The number of processors available = 16 The number of threads available = 2 R8_TEST: Estimate the value of PI. N = number of terms computed and added; MODE = SEQ for sequential code; MODE = OMP for Open MP enabled code; (performance depends on whether Open MP is used, and how many processes are available!) ESTIMATE = the computed estimate of PI; ERROR = ( the computed estimate - PI ); TIME = elapsed wall clock time; Note that you can't increase N forever, because: A) ROUNDOFF starts to be a problem, and B) maximum integer size is a problem. The maximum integer: 2147483647 N Mode Estimate Error Time 1 SEQ 3.2000000000 0.584073E-01 0.379001E-06 1 OMP 3.2000000000 0.584073E-01 0.141469E-03 10 SEQ 3.1424259850 0.833331E-03 0.245000E-06 10 OMP 3.1424259850 0.833331E-03 0.245700E-05 100 SEQ 3.1416009869 0.833333E-05 0.173200E-05 100 OMP 3.1416009869 0.833333E-05 0.193200E-05 1000 SEQ 3.1415927369 0.833333E-07 0.168950E-04 1000 OMP 3.1415927369 0.833333E-07 0.951300E-05 10000 SEQ 3.1415926544 0.833341E-09 0.168603E-03 10000 OMP 3.1415926544 0.833336E-09 0.852330E-04 100000 SEQ 3.1415926536 0.836842E-11 0.168560E-02 100000 OMP 3.1415926536 0.835332E-11 0.843774E-03 1000000 SEQ 3.1415926536 0.284217E-13 0.168746E-01 1000000 OMP 3.1415926536 0.106137E-12 0.100337E-01 10000000 SEQ 3.1415926536 0.621725E-13 0.168872 10000000 OMP 3.1415926536 0.129674E-12 0.845060E-01 100000000 SEQ 3.1415926536 0.633271E-12 1.68642 100000000 OMP 3.1415926536 0.116351E-12 0.843506 1000000000 SEQ 3.1415926536 0.177636E-12 16.8877 1000000000 OMP 3.1415926536 0.107914E-12 8.43212 COMPUTE_PI(): Normal end of execution. COMPUTE_PI(): FORTRAN90/OpenMP version Estimate the value of PI by summing a series. The number of processors available = 16 The number of threads available = 4 R8_TEST: Estimate the value of PI. N = number of terms computed and added; MODE = SEQ for sequential code; MODE = OMP for Open MP enabled code; (performance depends on whether Open MP is used, and how many processes are available!) ESTIMATE = the computed estimate of PI; ERROR = ( the computed estimate - PI ); TIME = elapsed wall clock time; Note that you can't increase N forever, because: A) ROUNDOFF starts to be a problem, and B) maximum integer size is a problem. The maximum integer: 2147483647 N Mode Estimate Error Time 1 SEQ 3.2000000000 0.584073E-01 0.376000E-06 1 OMP 3.2000000000 0.584073E-01 0.142382E-03 10 SEQ 3.1424259850 0.833331E-03 0.230000E-06 10 OMP 3.1424259850 0.833331E-03 0.833060E-04 100 SEQ 3.1416009869 0.833333E-05 0.173300E-05 100 OMP 3.1416009869 0.833333E-05 0.183300E-05 1000 SEQ 3.1415927369 0.833333E-07 0.168920E-04 1000 OMP 3.1415927369 0.833333E-07 0.559700E-05 10000 SEQ 3.1415926544 0.833341E-09 0.168611E-03 10000 OMP 3.1415926544 0.833330E-09 0.434990E-04 100000 SEQ 3.1415926536 0.836842E-11 0.173427E-02 100000 OMP 3.1415926536 0.833289E-11 0.489515E-03 1000000 SEQ 3.1415926536 0.284217E-13 0.169310E-01 1000000 OMP 3.1415926536 0.826006E-13 0.565135E-02 10000000 SEQ 3.1415926536 0.621725E-13 0.169411 10000000 OMP 3.1415926536 0.123457E-12 0.430533E-01 100000000 SEQ 3.1415926536 0.633271E-12 1.69361 100000000 OMP 3.1415926536 0.110578E-12 0.429181 1000000000 SEQ 3.1415926536 0.177636E-12 16.9485 1000000000 OMP 3.1415926536 0.275335E-13 4.29181 COMPUTE_PI(): Normal end of execution. COMPUTE_PI(): FORTRAN90/OpenMP version Estimate the value of PI by summing a series. The number of processors available = 16 The number of threads available = 8 R8_TEST: Estimate the value of PI. N = number of terms computed and added; MODE = SEQ for sequential code; MODE = OMP for Open MP enabled code; (performance depends on whether Open MP is used, and how many processes are available!) ESTIMATE = the computed estimate of PI; ERROR = ( the computed estimate - PI ); TIME = elapsed wall clock time; Note that you can't increase N forever, because: A) ROUNDOFF starts to be a problem, and B) maximum integer size is a problem. The maximum integer: 2147483647 N Mode Estimate Error Time 1 SEQ 3.2000000000 0.584073E-01 0.228003E-06 1 OMP 3.2000000000 0.584073E-01 0.237621E-03 10 SEQ 3.1424259850 0.833331E-03 0.224998E-06 10 OMP 3.1424259850 0.833331E-03 0.277600E-05 100 SEQ 3.1416009869 0.833333E-05 0.179000E-05 100 OMP 3.1416009869 0.833333E-05 0.305500E-05 1000 SEQ 3.1415927369 0.833333E-07 0.173630E-04 1000 OMP 3.1415927369 0.833333E-07 0.507400E-05 10000 SEQ 3.1415926544 0.833341E-09 0.173125E-03 10000 OMP 3.1415926544 0.833333E-09 0.276430E-04 100000 SEQ 3.1415926536 0.836842E-11 0.174147E-02 100000 OMP 3.1415926536 0.833156E-11 0.408342E-03 1000000 SEQ 3.1415926536 0.284217E-13 0.174280E-01 1000000 OMP 3.1415926536 0.781597E-13 0.295031E-02 10000000 SEQ 3.1415926536 0.621725E-13 0.170668 10000000 OMP 3.1415926536 0.102141E-13 0.253574E-01 100000000 SEQ 3.1415926536 0.633271E-12 1.70605 100000000 OMP 3.1415926536 0.217604E-13 0.260407 1000000000 SEQ 3.1415926536 0.177636E-12 17.0599 1000000000 OMP 3.1415926536 0.248690E-13 2.51323 COMPUTE_PI(): Normal end of execution.