***** Summary of parameters
ARCH : IBM
PLATFORM : SNOW_guidec
TIMING_FACTOR : 3
NUM_TRY : 3
NUM_ITER : 256
DELAY : 10.000000 ms
TIMER_RES : 0.001000 ms
SCH_LOOP_CNT : 32
MIN_OVERHEAD(%) : 15
MIN_TIMING : 1 seconds
max_num_threads : 8
***** Start Testing : #pragma omp atomic
-- iter_facotr : 500
-- try_count : 1
-- delay_time : 0.003333 ms
-- Running Reference case
WC Timing = 1.242737 second
Standard deviation = 0.000656 second
CPU Timing = 1.240833 second
Standard deviation = 0.002569 second
-- Testing 8 threads
WC Timing = 5.716722 second
Standard deviation = 0.077004 second
WC overhead = 4.473985 second
Standard deviation = 0.077006 second
WC overhead/iter = 0.034953 ms
WC overhead(%) wrt reference = 360.01
CPU Timing = 5.706250 second
Standard deviation = 0.067938 second
CPU overhead = 4.465417 second
Standard deviation = 0.067987 second
CPU overhead/iter = 0.034886 ms
CPU overhead(%) wrt reference = 359.87
-- Running Reference case
WC Timing = 1.236545 second
Standard deviation = 0.003887 second
CPU Timing = 1.235000 second
Standard deviation = 0.006124 second
-- Testing 4 threads
WC Timing = 1.650249 second
Standard deviation = 0.004301 second
WC overhead = 0.413704 second
Standard deviation = 0.005797 second
WC overhead/iter = 0.003232 ms
WC overhead(%) wrt reference = 33.46
CPU Timing = 1.650833 second
Standard deviation = 0.003118 second
CPU overhead = 0.415833 second
Standard deviation = 0.006872 second
CPU overhead/iter = 0.003249 ms
CPU overhead(%) wrt reference = 33.67
-- Running Reference case
WC Timing = 1.254689 second
Standard deviation = 0.004163 second
CPU Timing = 1.255000 second
Standard deviation = 0.004082 second
-- Testing 2 threads
WC Timing = 1.646358 second
Standard deviation = 0.004872 second
WC overhead = 0.391669 second
Standard deviation = 0.006408 second
WC overhead/iter = 0.003060 ms
WC overhead(%) wrt reference = 31.22
CPU Timing = 1.646667 second
Standard deviation = 0.006236 second
CPU overhead = 0.391667 second
Standard deviation = 0.007454 second
CPU overhead/iter = 0.003060 ms
CPU overhead(%) wrt reference = 31.21
-- Running Reference case
WC Timing = 1.253477 second
Standard deviation = 0.003955 second
CPU Timing = 1.253333 second
Standard deviation = 0.004714 second
-- Testing 1 threads
WC Timing = 1.363254 second
Standard deviation = 0.007774 second
WC overhead = 0.109777 second
Standard deviation = 0.008722 second
WC overhead/iter = 0.000858 ms
WC overhead(%) wrt reference = 8.76
CPU Timing = 1.363333 second
Standard deviation = 0.012472 second
CPU overhead = 0.110000 second
Standard deviation = 0.013333 second
CPU overhead/iter = 0.000859 ms
CPU overhead(%) wrt reference = 8.78
***** Finished

*******************************
* ELAPSE TIME = 46.118339
*******************************


***** Start Testing : #pragma omp barrier
-- iter_facotr : 200
-- try_count : 1
-- delay_time : 0.020000 ms
-- Running Reference case
WC Timing = 1.499071 second
Standard deviation = 0.002728 second
CPU Timing = 11.983333 second
Standard deviation = 0.028674 second
-- Testing 8 threads
WC Timing = 1.884816 second
Standard deviation = 0.004711 second
WC overhead = 0.385745 second
Standard deviation = 0.005444 second
WC overhead/iter = 0.007534 ms
WC overhead(%) wrt reference = 25.73
CPU Timing = 15.066667 second
Standard deviation = 0.041096 second
CPU overhead = 3.083333 second
Standard deviation = 0.050111 second
CPU overhead/iter = 0.060221 ms
CPU overhead(%) wrt reference = 25.73
-- Running Reference case
WC Timing = 1.497412 second
Standard deviation = 0.005259 second
CPU Timing = 5.983333 second
Standard deviation = 0.038586 second
-- Testing 4 threads
WC Timing = 1.756439 second
Standard deviation = 0.009543 second
WC overhead = 0.259027 second
Standard deviation = 0.010896 second
WC overhead/iter = 0.005059 ms
WC overhead(%) wrt reference = 17.30
CPU Timing = 7.013333 second
Standard deviation = 0.040277 second
CPU overhead = 1.030000 second
Standard deviation = 0.055777 second
CPU overhead/iter = 0.020117 ms
CPU overhead(%) wrt reference = 17.21
-- Running Reference case
WC Timing = 1.496472 second
Standard deviation = 0.013170 second
CPU Timing = 2.996667 second
Standard deviation = 0.024944 second
-- Testing 2 threads
WC Timing = 1.661122 second
Standard deviation = 0.010968 second
WC overhead = 0.164650 second
Standard deviation = 0.017139 second
WC overhead/iter = 0.003216 ms
WC overhead(%) wrt reference = 11.00
CPU Timing = 3.313333 second
Standard deviation = 0.026247 second
CPU overhead = 0.316667 second
Standard deviation = 0.036209 second
CPU overhead/iter = 0.006185 ms
CPU overhead(%) wrt reference = 10.57
-- Running Reference case
WC Timing = 1.508919 second
Standard deviation = 0.009463 second
CPU Timing = 1.510000 second
Standard deviation = 0.014142 second
-- Testing 1 threads
WC Timing = 1.554886 second
Standard deviation = 0.005616 second
WC overhead = 0.045967 second
Standard deviation = 0.011004 second
WC overhead/iter = 0.000898 ms
WC overhead(%) wrt reference = 3.05
CPU Timing = 1.556667 second
Standard deviation = 0.004714 second
CPU overhead = 0.046667 second
Standard deviation = 0.014907 second
CPU overhead/iter = 0.000911 ms
CPU overhead(%) wrt reference = 3.09
***** Finished

*******************************
* ELAPSE TIME = 38.663116
*******************************


***** Start Testing : #pragma omp critical
-- iter_facotr : 500
-- try_count : 1
-- delay_time : 0.001100 ms
-- Running Reference case
WC Timing = 1.257543 second
Standard deviation = 0.011997 second
CPU Timing = 10.056667 second
Standard deviation = 0.097411 second
-- Testing 8 threads
WC Timing = 1.487584 second
Standard deviation = 0.027300 second
WC overhead = 0.230041 second
Standard deviation = 0.029820 second
WC overhead/iter = 0.000899 ms
WC overhead(%) wrt reference = 18.29
CPU Timing = 11.866667 second
Standard deviation = 0.172111 second
CPU overhead = 1.810000 second
Standard deviation = 0.197765 second
CPU overhead/iter = 0.007070 ms
CPU overhead(%) wrt reference = 18.00
-- Running Reference case
WC Timing = 1.258336 second
Standard deviation = 0.009770 second
CPU Timing = 5.030000 second
Standard deviation = 0.035590 second
-- Testing 4 threads
WC Timing = 1.482125 second
Standard deviation = 0.006190 second
WC overhead = 0.223789 second
Standard deviation = 0.011566 second
WC overhead/iter = 0.000874 ms
WC overhead(%) wrt reference = 17.78
CPU Timing = 5.930000 second
Standard deviation = 0.021602 second
CPU overhead = 0.900000 second
Standard deviation = 0.041633 second
CPU overhead/iter = 0.003516 ms
CPU overhead(%) wrt reference = 17.89
-- Running Reference case
WC Timing = 1.278228 second
Standard deviation = 0.002188 second
CPU Timing = 2.553333 second
Standard deviation = 0.009428 second
-- Testing 2 threads
WC Timing = 1.490722 second
Standard deviation = 0.004240 second
WC overhead = 0.212493 second
Standard deviation = 0.004771 second
WC overhead/iter = 0.000830 ms
WC overhead(%) wrt reference = 16.62
CPU Timing = 2.980000 second
Standard deviation = 0.008165 second
CPU overhead = 0.426667 second
Standard deviation = 0.012472 second
CPU overhead/iter = 0.001667 ms
CPU overhead(%) wrt reference = 16.71
-- Running Reference case
WC Timing = 1.272185 second
Standard deviation = 0.002769 second
CPU Timing = 1.273333 second
Standard deviation = 0.004714 second
-- Testing 1 threads
WC Timing = 1.494150 second
Standard deviation = 0.006908 second
WC overhead = 0.221965 second
Standard deviation = 0.007443 second
WC overhead/iter = 0.000867 ms
WC overhead(%) wrt reference = 17.45
CPU Timing = 1.493333 second
Standard deviation = 0.009428 second
CPU overhead = 0.220000 second
Standard deviation = 0.010541 second
CPU overhead/iter = 0.000859 ms
CPU overhead(%) wrt reference = 17.28
***** Finished

*******************************
* ELAPSE TIME = 123.574443
*******************************


***** Start Testing : false sharing
overhead means comparision with pirvate ref.
-- iter_facotr : 300000
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.090332 second
Standard deviation = 0.004601 second
CPU Timing = 8.713333 second
Standard deviation = 0.040277 second
-- Testing 8 threads
WC Timing = 4.687789 second
Standard deviation = 0.002658 second
WC overhead = 3.597456 second
Standard deviation = 0.005313 second
WC overhead/iter = 0.000047 ms
WC overhead(%) wrt reference = 329.94
CPU Timing = 37.483333 second
Standard deviation = 0.032998 second
CPU overhead = 28.770000 second
Standard deviation = 0.052068 second
CPU overhead/iter = 0.000375 ms
CPU overhead(%) wrt reference = 330.18
-- Running Reference case
WC Timing = 2.166740 second
Standard deviation = 0.000143 second
CPU Timing = 8.666667 second
Standard deviation = 0.009428 second
-- Testing 4 threads
WC Timing = 5.033634 second
Standard deviation = 0.119450 second
WC overhead = 2.866894 second
Standard deviation = 0.119450 second
WC overhead/iter = 0.000037 ms
WC overhead(%) wrt reference = 132.31
CPU Timing = 20.126667 second
Standard deviation = 0.470484 second
CPU overhead = 11.460000 second
Standard deviation = 0.470579 second
CPU overhead/iter = 0.000149 ms
CPU overhead(%) wrt reference = 132.23
-- Running Reference case
WC Timing = 4.333825 second
Standard deviation = 0.000453 second
CPU Timing = 8.666667 second
Standard deviation = 0.004714 second
-- Testing 2 threads
WC Timing = 6.407175 second
Standard deviation = 0.004452 second
WC overhead = 2.073351 second
Standard deviation = 0.004475 second
WC overhead/iter = 0.000027 ms
WC overhead(%) wrt reference = 47.84
CPU Timing = 12.813333 second
Standard deviation = 0.012472 second
CPU overhead = 4.146667 second
Standard deviation = 0.013333 second
CPU overhead/iter = 0.000054 ms
CPU overhead(%) wrt reference = 47.85
-- Running Reference case
WC Timing = 8.673713 second
Standard deviation = 0.013155 second
CPU Timing = 8.670000 second
Standard deviation = 0.008165 second
-- Testing 1 threads
WC Timing = 8.682041 second
Standard deviation = 0.000368 second
WC overhead = 0.008328 second
Standard deviation = 0.013160 second
WC overhead/iter = 0.000000 ms
WC overhead(%) wrt reference = 0.10
CPU Timing = 8.683333 second
Standard deviation = 0.004714 second
CPU overhead = 0.013333 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.000000 ms
CPU overhead(%) wrt reference = 0.15
***** Finished

*******************************
* ELAPSE TIME = 123.231321
*******************************


***** Start Testing : omp_set(unset)_lock
-- iter_facotr : 40000
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.249319 second
Standard deviation = 0.001518 second
CPU Timing = 9.990000 second
Standard deviation = 0.016330 second
-- Testing 8 threads
WC Timing = 16.768579 second
Standard deviation = 0.019731 second
WC overhead = 15.519261 second
Standard deviation = 0.019789 second
WC overhead/iter = 0.000758 ms
WC overhead(%) wrt reference = 1242.22
CPU Timing = 133.953333 second
Standard deviation = 0.102740 second
CPU overhead = 123.963333 second
Standard deviation = 0.104030 second
CPU overhead/iter = 0.006053 ms
CPU overhead(%) wrt reference = 1240.87
-- Running Reference case
WC Timing = 1.248135 second
Standard deviation = 0.000258 second
CPU Timing = 4.993333 second
Standard deviation = 0.009428 second
-- Testing 4 threads
WC Timing = 16.731567 second
Standard deviation = 0.001402 second
WC overhead = 15.483432 second
Standard deviation = 0.001425 second
WC overhead/iter = 0.000756 ms
WC overhead(%) wrt reference = 1240.53
CPU Timing = 66.920000 second
Standard deviation = 0.000000 second
CPU overhead = 61.926667 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.003024 ms
CPU overhead(%) wrt reference = 1240.19
-- Running Reference case
WC Timing = 1.249075 second
Standard deviation = 0.000786 second
CPU Timing = 2.493333 second
Standard deviation = 0.004714 second
-- Testing 2 threads
WC Timing = 16.735030 second
Standard deviation = 0.001890 second
WC overhead = 15.485955 second
Standard deviation = 0.002047 second
WC overhead/iter = 0.000756 ms
WC overhead(%) wrt reference = 1239.79
CPU Timing = 33.463333 second
Standard deviation = 0.004714 second
CPU overhead = 30.970000 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.001512 ms
CPU overhead(%) wrt reference = 1242.11
-- Running Reference case
WC Timing = 1.248053 second
Standard deviation = 0.000056 second
CPU Timing = 1.246667 second
Standard deviation = 0.004714 second
-- Testing 1 threads
WC Timing = 16.740338 second
Standard deviation = 0.012523 second
WC overhead = 15.492285 second
Standard deviation = 0.012523 second
WC overhead/iter = 0.000756 ms
WC overhead(%) wrt reference = 1241.32
CPU Timing = 16.736667 second
Standard deviation = 0.004714 second
CPU overhead = 15.490000 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.000756 ms
CPU overhead(%) wrt reference = 1242.51
***** Finished

*******************************
* ELAPSE TIME = 810.639927
*******************************


***** Start Testing : pingpong omp_set(unset)_lock
-- iter_facotr : 500
-- try_count : 1
-- delay_time : 0.002000 ms
-- Running Reference case
WC Timing = 1.252916 second
Standard deviation = 0.012946 second
CPU Timing = 2.503333 second
Standard deviation = 0.020548 second
-- Testing 2 threads
WC Timing = 1.657143 second
Standard deviation = 0.000103 second
WC overhead = 0.404227 second
Standard deviation = 0.012947 second
WC overhead/iter = 0.003158 ms
WC overhead(%) wrt reference = 32.26
CPU Timing = 3.313333 second
Standard deviation = 0.004714 second
CPU overhead = 0.810000 second
Standard deviation = 0.021082 second
CPU overhead/iter = 0.006328 ms
CPU overhead(%) wrt reference = 32.36
***** Finished

*******************************
* ELAPSE TIME = 8.731339
*******************************


***** Start Testing : #pragma omp ordered
-- iter_facotr : 200
-- try_count : 1
-- delay_time : 0.020000 ms
-- Running Reference case
WC Timing = 1.508963 second
Standard deviation = 0.013101 second
CPU Timing = 12.070000 second
Standard deviation = 0.098995 second
-- Testing 8 threads
WC Timing = 1.829195 second
Standard deviation = 0.012698 second
WC overhead = 0.320232 second
Standard deviation = 0.018245 second
WC overhead/iter = 0.006255 ms
WC overhead(%) wrt reference = 21.22
CPU Timing = 14.616667 second
Standard deviation = 0.090308 second
CPU overhead = 2.546667 second
Standard deviation = 0.133998 second
CPU overhead/iter = 0.049740 ms
CPU overhead(%) wrt reference = 21.10
-- Running Reference case
WC Timing = 1.497226 second
Standard deviation = 0.007582 second
CPU Timing = 5.986667 second
Standard deviation = 0.030912 second
-- Testing 4 threads
WC Timing = 1.790535 second
Standard deviation = 0.002621 second
WC overhead = 0.293309 second
Standard deviation = 0.008022 second
WC overhead/iter = 0.005729 ms
WC overhead(%) wrt reference = 19.59
CPU Timing = 7.160000 second
Standard deviation = 0.014142 second
CPU overhead = 1.173333 second
Standard deviation = 0.033993 second
CPU overhead/iter = 0.022917 ms
CPU overhead(%) wrt reference = 19.60
-- Running Reference case
WC Timing = 1.492839 second
Standard deviation = 0.009963 second
CPU Timing = 2.983333 second
Standard deviation = 0.018856 second
-- Testing 2 threads
WC Timing = 1.606089 second
Standard deviation = 0.002255 second
WC overhead = 0.113250 second
Standard deviation = 0.010214 second
WC overhead/iter = 0.002212 ms
WC overhead(%) wrt reference = 7.59
CPU Timing = 3.213333 second
Standard deviation = 0.004714 second
CPU overhead = 0.230000 second
Standard deviation = 0.019437 second
CPU overhead/iter = 0.004492 ms
CPU overhead(%) wrt reference = 7.71
-- Running Reference case
WC Timing = 1.493709 second
Standard deviation = 0.009303 second
CPU Timing = 1.493333 second
Standard deviation = 0.009428 second
-- Testing 1 threads
WC Timing = 1.676329 second
Standard deviation = 0.010355 second
WC overhead = 0.182619 second
Standard deviation = 0.013920 second
WC overhead/iter = 0.003567 ms
WC overhead(%) wrt reference = 12.23
CPU Timing = 1.676667 second
Standard deviation = 0.009428 second
CPU overhead = 0.183333 second
Standard deviation = 0.013333 second
CPU overhead/iter = 0.003581 ms
CPU overhead(%) wrt reference = 12.28
***** Finished

*******************************
* ELAPSE TIME = 38.706899
*******************************


***** Start Testing : #pragma omp parallel
-- iter_facotr : 60
-- try_count : 1
-- delay_time : 0.066667 ms
-- Running Reference case
WC Timing = 1.124276 second
Standard deviation = 0.003706 second
CPU Timing = 1.123333 second
Standard deviation = 0.004714 second
-- Testing 8 threads
WC Timing = 1.666947 second
Standard deviation = 0.010111 second
WC overhead = 0.542672 second
Standard deviation = 0.010769 second
WC overhead/iter = 0.035330 ms
WC overhead(%) wrt reference = 48.27
CPU Timing = 1.664167 second
Standard deviation = 0.011380 second
CPU overhead = 0.540833 second
Standard deviation = 0.012318 second
CPU overhead/iter = 0.035211 ms
CPU overhead(%) wrt reference = 48.15
-- Testing 4 threads
WC Timing = 1.448923 second
Standard deviation = 0.001807 second
WC overhead = 0.324647 second
Standard deviation = 0.004123 second
WC overhead/iter = 0.021136 ms
WC overhead(%) wrt reference = 28.88
CPU Timing = 1.447500 second
Standard deviation = 0.002041 second
CPU overhead = 0.324167 second
Standard deviation = 0.005137 second
CPU overhead/iter = 0.021105 ms
CPU overhead(%) wrt reference = 28.86
-- Testing 2 threads
WC Timing = 1.358341 second
Standard deviation = 0.015172 second
WC overhead = 0.234066 second
Standard deviation = 0.015618 second
WC overhead/iter = 0.015239 ms
WC overhead(%) wrt reference = 20.82
CPU Timing = 1.356667 second
Standard deviation = 0.009428 second
CPU overhead = 0.233333 second
Standard deviation = 0.010541 second
CPU overhead/iter = 0.015191 ms
CPU overhead(%) wrt reference = 20.77
-- Testing 1 threads
WC Timing = 1.219241 second
Standard deviation = 0.000586 second
WC overhead = 0.094965 second
Standard deviation = 0.003752 second
WC overhead/iter = 0.006183 ms
WC overhead(%) wrt reference = 8.45
CPU Timing = 1.220000 second
Standard deviation = 0.000000 second
CPU overhead = 0.096667 second
Standard deviation = 0.004714 second
CPU overhead/iter = 0.006293 ms
CPU overhead(%) wrt reference = 8.61
***** Finished

*******************************
* ELAPSE TIME = 20.460926
*******************************


***** Start Testing : #pragma omp parallel for schedule(static)
-- iter_facotr : 2500
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.204532 second
Standard deviation = 0.000014 second
CPU Timing = 1.203333 second
Standard deviation = 0.004714 second
-- Testing 8 threads
WC Timing = 22.532760 second
Standard deviation = 0.136361 second
WC overhead = 21.328228 second
Standard deviation = 0.136361 second
WC overhead/iter = 0.033325 ms
WC overhead(%) wrt reference = 1770.66
CPU Timing = 22.486250 second
Standard deviation = 0.120446 second
CPU overhead = 21.282917 second
Standard deviation = 0.120538 second
CPU overhead/iter = 0.033255 ms
CPU overhead(%) wrt reference = 1768.66
-- Testing 4 threads
WC Timing = 14.473157 second
Standard deviation = 0.020741 second
WC overhead = 13.268624 second
Standard deviation = 0.020741 second
WC overhead/iter = 0.020732 ms
WC overhead(%) wrt reference = 1101.56
CPU Timing = 14.473333 second
Standard deviation = 0.018522 second
CPU overhead = 13.270000 second
Standard deviation = 0.019112 second
CPU overhead/iter = 0.020734 ms
CPU overhead(%) wrt reference = 1102.77
-- Testing 2 threads
WC Timing = 10.643332 second
Standard deviation = 0.016464 second
WC overhead = 9.438799 second
Standard deviation = 0.016464 second
WC overhead/iter = 0.014748 ms
WC overhead(%) wrt reference = 783.61
CPU Timing = 10.643333 second
Standard deviation = 0.016499 second
CPU overhead = 9.440000 second
Standard deviation = 0.017159 second
CPU overhead/iter = 0.014750 ms
CPU overhead(%) wrt reference = 784.49
-- Testing 1 threads
WC Timing = 5.626507 second
Standard deviation = 0.012698 second
WC overhead = 4.421974 second
Standard deviation = 0.012698 second
WC overhead/iter = 0.006909 ms
WC overhead(%) wrt reference = 367.11
CPU Timing = 5.626667 second
Standard deviation = 0.004714 second
CPU overhead = 4.423333 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.006911 ms
CPU overhead(%) wrt reference = 367.59
***** Finished

***** Start Testing : #pragma omp parallel for schedule(dynamic)
-- iter_facotr : 2500
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.204532 second
Standard deviation = 0.000014 second
CPU Timing = 1.203333 second
Standard deviation = 0.004714 second
-- Testing 8 threads
WC Timing = 671.706310 second
Standard deviation = 0.003225 second
WC overhead = 670.501778 second
Standard deviation = 0.003225 second
WC overhead/iter = 1.047659 ms
WC overhead(%) wrt reference = 55664.90
CPU Timing = 133.575755 second
Standard deviation = 0.029303 second
CPU overhead = 132.372421 second
Standard deviation = 0.029680 second
CPU overhead/iter = 0.206832 ms
CPU overhead(%) wrt reference = 11000.48
-- Testing 4 threads
WC Timing = 181.212307 second
Standard deviation = 0.085001 second
WC overhead = 180.007775 second
Standard deviation = 0.085001 second
WC overhead/iter = 0.281262 ms
WC overhead(%) wrt reference = 14944.20
CPU Timing = 181.176667 second
Standard deviation = 0.060358 second
CPU overhead = 179.973333 second
Standard deviation = 0.060542 second
CPU overhead/iter = 0.281208 ms
CPU overhead(%) wrt reference = 14956.23
-- Testing 2 threads
WC Timing = 56.002291 second
Standard deviation = 0.026314 second
WC overhead = 54.797759 second
Standard deviation = 0.026314 second
WC overhead/iter = 0.085621 ms
WC overhead(%) wrt reference = 4549.30
CPU Timing = 55.988333 second
Standard deviation = 0.010274 second
CPU overhead = 54.785000 second
Standard deviation = 0.011304 second
CPU overhead/iter = 0.085602 ms
CPU overhead(%) wrt reference = 4552.77
-- Testing 1 threads
WC Timing = 18.754146 second
Standard deviation = 0.000069 second
WC overhead = 17.549613 second
Standard deviation = 0.000070 second
WC overhead/iter = 0.027421 ms
WC overhead(%) wrt reference = 1456.96
CPU Timing = 18.756667 second
Standard deviation = 0.004714 second
CPU overhead = 17.553333 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.027427 ms
CPU overhead(%) wrt reference = 1458.73
***** Finished

***** Start Testing : #pragma omp parallel for schedule(guided)
-- iter_facotr : 2500
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.204532 second
Standard deviation = 0.000014 second
CPU Timing = 1.203333 second
Standard deviation = 0.004714 second
-- Testing 8 threads
WC Timing = 338.366939 second
Standard deviation = 0.410580 second
WC overhead = 337.162406 second
Standard deviation = 0.410580 second
WC overhead/iter = 0.526816 ms
WC overhead(%) wrt reference = 27991.15
CPU Timing = -199.251745 second
Standard deviation = 0.371904 second
CPU overhead = -200.455079 second
Standard deviation = 0.371934 second
CPU overhead/iter = -0.313211 ms
CPU overhead(%) wrt reference = -16658.32
-- Testing 4 threads
WC Timing = 97.402110 second
Standard deviation = 0.051751 second
WC overhead = 96.197578 second
Standard deviation = 0.051751 second
WC overhead/iter = 0.150309 ms
WC overhead(%) wrt reference = 7986.30
CPU Timing = 97.383333 second
Standard deviation = 0.048705 second
CPU overhead = 96.180000 second
Standard deviation = 0.048933 second
CPU overhead/iter = 0.150281 ms
CPU overhead(%) wrt reference = 7992.80
-- Testing 2 threads
WC Timing = 40.734282 second
Standard deviation = 0.165809 second
WC overhead = 39.529750 second
Standard deviation = 0.165809 second
WC overhead/iter = 0.061765 ms
WC overhead(%) wrt reference = 3281.75
CPU Timing = 40.738333 second
Standard deviation = 0.165848 second
CPU overhead = 39.535000 second
Standard deviation = 0.165915 second
CPU overhead/iter = 0.061773 ms
CPU overhead(%) wrt reference = 3285.46
-- Testing 1 threads
WC Timing = 8.281318 second
Standard deviation = 0.003118 second
WC overhead = 7.076786 second
Standard deviation = 0.003118 second
WC overhead/iter = 0.011057 ms
WC overhead(%) wrt reference = 587.51
CPU Timing = 8.280000 second
Standard deviation = 0.008165 second
CPU overhead = 7.076667 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.011057 ms
CPU overhead(%) wrt reference = 588.09
***** Finished

*******************************
* ELAPSE TIME = 4400.827199
*******************************


***** Start Testing : #pragma omp parallel for schedule (static,chunk_size)
-- iter_facotr : 2500
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.204678 second
Standard deviation = 0.000097 second
CPU Timing = 1.206667 second
Standard deviation = 0.004714 second
CHUNK SIZE = 1
-- Testing 8 threads
WC Timing = 23.163076 second
Standard deviation = 0.105909 second
WC overhead = 21.958398 second
Standard deviation = 0.105909 second
WC overhead/iter = 0.034310 ms
WC overhead(%) wrt reference = 1822.76
CPU Timing = 23.132500 second
Standard deviation = 0.094489 second
CPU overhead = 21.925833 second
Standard deviation = 0.094606 second
CPU overhead/iter = 0.034259 ms
CPU overhead(%) wrt reference = 1817.06
CHUNK SIZE = 2
-- Testing 8 threads
WC Timing = 23.289125 second
Standard deviation = 0.080597 second
WC overhead = 22.084447 second
Standard deviation = 0.080597 second
WC overhead/iter = 0.034507 ms
WC overhead(%) wrt reference = 1833.22
CPU Timing = 23.250417 second
Standard deviation = 0.072070 second
CPU overhead = 22.043750 second
Standard deviation = 0.072224 second
CPU overhead/iter = 0.034443 ms
CPU overhead(%) wrt reference = 1826.83
CHUNK SIZE = 4
-- Testing 8 threads
WC Timing = 23.010117 second
Standard deviation = 0.072785 second
WC overhead = 21.805439 second
Standard deviation = 0.072785 second
WC overhead/iter = 0.034071 ms
WC overhead(%) wrt reference = 1810.06
CPU Timing = 22.981667 second
Standard deviation = 0.063806 second
CPU overhead = 21.775000 second
Standard deviation = 0.063980 second
CPU overhead/iter = 0.034023 ms
CPU overhead(%) wrt reference = 1804.56
CHUNK SIZE = 8
-- Testing 8 threads
WC Timing = 23.027109 second
Standard deviation = 0.171871 second
WC overhead = 21.822431 second
Standard deviation = 0.171871 second
WC overhead/iter = 0.034098 ms
WC overhead(%) wrt reference = 1811.47
CPU Timing = 22.975833 second
Standard deviation = 0.148100 second
CPU overhead = 21.769167 second
Standard deviation = 0.148175 second
CPU overhead/iter = 0.034014 ms
CPU overhead(%) wrt reference = 1804.07
CHUNK SIZE = 16
-- Testing 8 threads
WC Timing = 22.870396 second
Standard deviation = 0.122006 second
WC overhead = 21.665718 second
Standard deviation = 0.122006 second
WC overhead/iter = 0.033853 ms
WC overhead(%) wrt reference = 1798.47
CPU Timing = 22.838750 second
Standard deviation = 0.120420 second
CPU overhead = 21.632083 second
Standard deviation = 0.120513 second
CPU overhead/iter = 0.033800 ms
CPU overhead(%) wrt reference = 1792.71
CHUNK SIZE = 32
-- Testing 8 threads
WC Timing = 22.907438 second
Standard deviation = 0.160819 second
WC overhead = 21.702760 second
Standard deviation = 0.160819 second
WC overhead/iter = 0.033911 ms
WC overhead(%) wrt reference = 1801.54
CPU Timing = 22.875833 second
Standard deviation = 0.138340 second
CPU overhead = 21.669167 second
Standard deviation = 0.138420 second
CPU overhead/iter = 0.033858 ms
CPU overhead(%) wrt reference = 1795.79
CHUNK SIZE = 1
-- Testing 4 threads
WC Timing = 14.736444 second
Standard deviation = 0.006743 second
WC overhead = 13.531766 second
Standard deviation = 0.006743 second
WC overhead/iter = 0.021143 ms
WC overhead(%) wrt reference = 1123.27
CPU Timing = 14.730000 second
Standard deviation = 0.007360 second
CPU overhead = 13.523333 second
Standard deviation = 0.008740 second
CPU overhead/iter = 0.021130 ms
CPU overhead(%) wrt reference = 1120.72
CHUNK SIZE = 2
-- Testing 4 threads
WC Timing = 14.775683 second
Standard deviation = 0.018802 second
WC overhead = 13.571005 second
Standard deviation = 0.018802 second
WC overhead/iter = 0.021205 ms
WC overhead(%) wrt reference = 1126.53
CPU Timing = 14.773333 second
Standard deviation = 0.019401 second
CPU overhead = 13.566667 second
Standard deviation = 0.019965 second
CPU overhead/iter = 0.021198 ms
CPU overhead(%) wrt reference = 1124.31
CHUNK SIZE = 4
-- Testing 4 threads
WC Timing = 14.560032 second
Standard deviation = 0.026736 second
WC overhead = 13.355354 second
Standard deviation = 0.026736 second
WC overhead/iter = 0.020868 ms
WC overhead(%) wrt reference = 1108.62
CPU Timing = 14.563333 second
Standard deviation = 0.028674 second
CPU overhead = 13.356667 second
Standard deviation = 0.029059 second
CPU overhead/iter = 0.020870 ms
CPU overhead(%) wrt reference = 1106.91
CHUNK SIZE = 8
-- Testing 4 threads
WC Timing = 14.440251 second
Standard deviation = 0.020770 second
WC overhead = 13.235573 second
Standard deviation = 0.020771 second
WC overhead/iter = 0.020681 ms
WC overhead(%) wrt reference = 1098.68
CPU Timing = 14.435000 second
Standard deviation = 0.017440 second
CPU overhead = 13.228333 second
Standard deviation = 0.018066 second
CPU overhead/iter = 0.020669 ms
CPU overhead(%) wrt reference = 1096.27
CHUNK SIZE = 16
-- Testing 4 threads
WC Timing = 14.384166 second
Standard deviation = 0.014071 second
WC overhead = 13.179488 second
Standard deviation = 0.014071 second
WC overhead/iter = 0.020593 ms
WC overhead(%) wrt reference = 1094.03
CPU Timing = 14.380833 second
Standard deviation = 0.018966 second
CPU overhead = 13.174167 second
Standard deviation = 0.019543 second
CPU overhead/iter = 0.020585 ms
CPU overhead(%) wrt reference = 1091.78
CHUNK SIZE = 32
-- Testing 4 threads
WC Timing = 14.349991 second
Standard deviation = 0.027158 second
WC overhead = 13.145313 second
Standard deviation = 0.027158 second
WC overhead/iter = 0.020540 ms
WC overhead(%) wrt reference = 1091.19
CPU Timing = 14.346667 second
Standard deviation = 0.028602 second
CPU overhead = 13.140000 second
Standard deviation = 0.028988 second
CPU overhead/iter = 0.020531 ms
CPU overhead(%) wrt reference = 1088.95
CHUNK SIZE = 1
-- Testing 2 threads
WC Timing = 10.830903 second
Standard deviation = 0.013935 second
WC overhead = 9.626225 second
Standard deviation = 0.013935 second
WC overhead/iter = 0.015041 ms
WC overhead(%) wrt reference = 799.07
CPU Timing = 10.828333 second
Standard deviation = 0.008498 second
CPU overhead = 9.621667 second
Standard deviation = 0.009718 second
CPU overhead/iter = 0.015034 ms
CPU overhead(%) wrt reference = 797.38
CHUNK SIZE = 2
-- Testing 2 threads
WC Timing = 10.904678 second
Standard deviation = 0.016218 second
WC overhead = 9.700000 second
Standard deviation = 0.016218 second
WC overhead/iter = 0.015156 ms
WC overhead(%) wrt reference = 805.19
CPU Timing = 10.906667 second
Standard deviation = 0.015456 second
CPU overhead = 9.700000 second
Standard deviation = 0.016159 second
CPU overhead/iter = 0.015156 ms
CPU overhead(%) wrt reference = 803.87
CHUNK SIZE = 4
-- Testing 2 threads
WC Timing = 10.665018 second
Standard deviation = 0.042031 second
WC overhead = 9.460340 second
Standard deviation = 0.042031 second
WC overhead/iter = 0.014782 ms
WC overhead(%) wrt reference = 785.30
CPU Timing = 10.666667 second
Standard deviation = 0.044783 second
CPU overhead = 9.460000 second
Standard deviation = 0.045031 second
CPU overhead/iter = 0.014781 ms
CPU overhead(%) wrt reference = 783.98
CHUNK SIZE = 8
-- Testing 2 threads
WC Timing = 10.573951 second
Standard deviation = 0.003307 second
WC overhead = 9.369273 second
Standard deviation = 0.003308 second
WC overhead/iter = 0.014639 ms
WC overhead(%) wrt reference = 777.74
CPU Timing = 10.576667 second
Standard deviation = 0.006236 second
CPU overhead = 9.370000 second
Standard deviation = 0.007817 second
CPU overhead/iter = 0.014641 ms
CPU overhead(%) wrt reference = 776.52
CHUNK SIZE = 16
-- Testing 2 threads
WC Timing = 10.513305 second
Standard deviation = 0.024609 second
WC overhead = 9.308627 second
Standard deviation = 0.024609 second
WC overhead/iter = 0.014545 ms
WC overhead(%) wrt reference = 772.71
CPU Timing = 10.508333 second
Standard deviation = 0.022485 second
CPU overhead = 9.301667 second
Standard deviation = 0.022973 second
CPU overhead/iter = 0.014534 ms
CPU overhead(%) wrt reference = 770.86
CHUNK SIZE = 32
-- Testing 2 threads
WC Timing = 10.574999 second
Standard deviation = 0.008876 second
WC overhead = 9.370321 second
Standard deviation = 0.008877 second
WC overhead/iter = 0.014641 ms
WC overhead(%) wrt reference = 777.83
CPU Timing = 10.580000 second
Standard deviation = 0.012247 second
CPU overhead = 9.373333 second
Standard deviation = 0.013123 second
CPU overhead/iter = 0.014646 ms
CPU overhead(%) wrt reference = 776.80
CHUNK SIZE = 1
-- Testing 1 threads
WC Timing = 5.854360 second
Standard deviation = 0.013038 second
WC overhead = 4.649682 second
Standard deviation = 0.013039 second
WC overhead/iter = 0.007265 ms
WC overhead(%) wrt reference = 385.97
CPU Timing = 5.850000 second
Standard deviation = 0.008165 second
CPU overhead = 4.643333 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.007255 ms
CPU overhead(%) wrt reference = 384.81
CHUNK SIZE = 2
-- Testing 1 threads
WC Timing = 5.852406 second
Standard deviation = 0.009363 second
WC overhead = 4.647728 second
Standard deviation = 0.009364 second
WC overhead/iter = 0.007262 ms
WC overhead(%) wrt reference = 385.81
CPU Timing = 5.853333 second
Standard deviation = 0.004714 second
CPU overhead = 4.646667 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.007260 ms
CPU overhead(%) wrt reference = 385.08
CHUNK SIZE = 4
-- Testing 1 threads
WC Timing = 5.694707 second
Standard deviation = 0.000383 second
WC overhead = 4.490029 second
Standard deviation = 0.000395 second
WC overhead/iter = 0.007016 ms
WC overhead(%) wrt reference = 372.72
CPU Timing = 5.693333 second
Standard deviation = 0.004714 second
CPU overhead = 4.486667 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.007010 ms
CPU overhead(%) wrt reference = 371.82
CHUNK SIZE = 8
-- Testing 1 threads
WC Timing = 5.568864 second
Standard deviation = 0.001289 second
WC overhead = 4.364186 second
Standard deviation = 0.001293 second
WC overhead/iter = 0.006819 ms
WC overhead(%) wrt reference = 362.27
CPU Timing = 5.570000 second
Standard deviation = 0.000000 second
CPU overhead = 4.363333 second
Standard deviation = 0.004714 second
CPU overhead/iter = 0.006818 ms
CPU overhead(%) wrt reference = 361.60
CHUNK SIZE = 16
-- Testing 1 threads
WC Timing = 5.538416 second
Standard deviation = 0.000697 second
WC overhead = 4.333738 second
Standard deviation = 0.000704 second
WC overhead/iter = 0.006771 ms
WC overhead(%) wrt reference = 359.74
CPU Timing = 5.536667 second
Standard deviation = 0.004714 second
CPU overhead = 4.330000 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.006766 ms
CPU overhead(%) wrt reference = 358.84
CHUNK SIZE = 32
-- Testing 1 threads
WC Timing = 5.587520 second
Standard deviation = 0.013289 second
WC overhead = 4.382842 second
Standard deviation = 0.013289 second
WC overhead/iter = 0.006848 ms
WC overhead(%) wrt reference = 363.82
CPU Timing = 5.583333 second
Standard deviation = 0.004714 second
CPU overhead = 4.376667 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.006839 ms
CPU overhead(%) wrt reference = 362.71
***** Finished

***** Start Testing : #pragma omp parallel for schedule (dynamic,chunk_size)
-- iter_facotr : 2500
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.204678 second
Standard deviation = 0.000097 second
CPU Timing = 1.206667 second
Standard deviation = 0.004714 second
CHUNK SIZE = 1
-- Testing 8 threads
WC Timing = 686.850806 second
Standard deviation = 14.337726 second
WC overhead = 685.646128 second
Standard deviation = 14.337726 second
WC overhead/iter = 1.071322 ms
WC overhead(%) wrt reference = 56915.30
CPU Timing = 146.225338 second
Standard deviation = 12.082456 second
CPU overhead = 145.018671 second
Standard deviation = 12.082457 second
CPU overhead/iter = 0.226592 ms
CPU overhead(%) wrt reference = 12018.12
CHUNK SIZE = 2
-- Testing 8 threads
WC Timing = 379.127625 second
Standard deviation = 0.442476 second
WC overhead = 377.922947 second
Standard deviation = 0.442476 second
WC overhead/iter = 0.590505 ms
WC overhead(%) wrt reference = 31371.28
CPU Timing = -158.654662 second
Standard deviation = 0.386880 second
CPU overhead = -159.861329 second
Standard deviation = 0.386909 second
CPU overhead/iter = -0.249783 ms
CPU overhead(%) wrt reference = -13248.18
CHUNK SIZE = 4
-- Testing 8 threads
WC Timing = 224.692142 second
Standard deviation = 0.410800 second
WC overhead = 223.487464 second
Standard deviation = 0.410800 second
WC overhead/iter = 0.349199 ms
WC overhead(%) wrt reference = 18551.63
CPU Timing = 224.153750 second
Standard deviation = 0.337289 second
CPU overhead = 222.947083 second
Standard deviation = 0.337321 second
CPU overhead/iter = 0.348355 ms
CPU overhead(%) wrt reference = 18476.28
CHUNK SIZE = 8
-- Testing 8 threads
WC Timing = 136.792831 second
Standard deviation = 0.110961 second
WC overhead = 135.588153 second
Standard deviation = 0.110961 second
WC overhead/iter = 0.211856 ms
WC overhead(%) wrt reference = 11255.14
CPU Timing = 136.489583 second
Standard deviation = 0.086989 second
CPU overhead = 135.282917 second
Standard deviation = 0.087116 second
CPU overhead/iter = 0.211380 ms
CPU overhead(%) wrt reference = 11211.29
CHUNK SIZE = 16
-- Testing 8 threads
WC Timing = 86.934743 second
Standard deviation = 0.502950 second
WC overhead = 85.730065 second
Standard deviation = 0.502950 second
WC overhead/iter = 0.133953 ms
WC overhead(%) wrt reference = 7116.43
CPU Timing = 86.741667 second
Standard deviation = 0.416824 second
CPU overhead = 85.535000 second
Standard deviation = 0.416850 second
CPU overhead/iter = 0.133648 ms
CPU overhead(%) wrt reference = 7088.54
CHUNK SIZE = 32
-- Testing 8 threads
WC Timing = 59.727404 second
Standard deviation = 0.160361 second
WC overhead = 58.522726 second
Standard deviation = 0.160361 second
WC overhead/iter = 0.091442 ms
WC overhead(%) wrt reference = 4857.96
CPU Timing = 59.639167 second
Standard deviation = 0.149765 second
CPU overhead = 58.432500 second
Standard deviation = 0.149839 second
CPU overhead/iter = 0.091301 ms
CPU overhead(%) wrt reference = 4842.47
CHUNK SIZE = 1
-- Testing 4 threads
WC Timing = 181.199189 second
Standard deviation = 0.077671 second
WC overhead = 179.994511 second
Standard deviation = 0.077672 second
WC overhead/iter = 0.281241 ms
WC overhead(%) wrt reference = 14941.30
CPU Timing = 181.171667 second
Standard deviation = 0.071132 second
CPU overhead = 179.965000 second
Standard deviation = 0.071288 second
CPU overhead/iter = 0.281195 ms
CPU overhead(%) wrt reference = 14914.23
CHUNK SIZE = 2
-- Testing 4 threads
WC Timing = 100.187488 second
Standard deviation = 0.080637 second
WC overhead = 98.982810 second
Standard deviation = 0.080637 second
WC overhead/iter = 0.154661 ms
WC overhead(%) wrt reference = 8216.54
CPU Timing = 100.183333 second
Standard deviation = 0.078960 second
CPU overhead = 98.976667 second
Standard deviation = 0.079101 second
CPU overhead/iter = 0.154651 ms
CPU overhead(%) wrt reference = 8202.49
CHUNK SIZE = 4
-- Testing 4 threads
WC Timing = 59.200581 second
Standard deviation = 0.032324 second
WC overhead = 57.995903 second
Standard deviation = 0.032324 second
WC overhead/iter = 0.090619 ms
WC overhead(%) wrt reference = 4814.22
CPU Timing = 59.193333 second
Standard deviation = 0.034901 second
CPU overhead = 57.986667 second
Standard deviation = 0.035218 second
CPU overhead/iter = 0.090604 ms
CPU overhead(%) wrt reference = 4805.52
CHUNK SIZE = 8
-- Testing 4 threads
WC Timing = 37.917507 second
Standard deviation = 0.050957 second
WC overhead = 36.712829 second
Standard deviation = 0.050957 second
WC overhead/iter = 0.057364 ms
WC overhead(%) wrt reference = 3047.52
CPU Timing = 37.907500 second
Standard deviation = 0.050785 second
CPU overhead = 36.700833 second
Standard deviation = 0.051004 second
CPU overhead/iter = 0.057345 ms
CPU overhead(%) wrt reference = 3041.51
CHUNK SIZE = 16
-- Testing 4 threads
WC Timing = 28.328832 second
Standard deviation = 0.029384 second
WC overhead = 27.124154 second
Standard deviation = 0.029384 second
WC overhead/iter = 0.042381 ms
WC overhead(%) wrt reference = 2251.57
CPU Timing = 28.324167 second
Standard deviation = 0.033686 second
CPU overhead = 27.117500 second
Standard deviation = 0.034014 second
CPU overhead/iter = 0.042371 ms
CPU overhead(%) wrt reference = 2247.31
CHUNK SIZE = 32
-- Testing 4 threads
WC Timing = 23.329363 second
Standard deviation = 0.049263 second
WC overhead = 22.124685 second
Standard deviation = 0.049263 second
WC overhead/iter = 0.034570 ms
WC overhead(%) wrt reference = 1836.56
CPU Timing = 23.327500 second
Standard deviation = 0.054810 second
CPU overhead = 22.120833 second
Standard deviation = 0.055013 second
CPU overhead/iter = 0.034564 ms
CPU overhead(%) wrt reference = 1833.22
CHUNK SIZE = 1
-- Testing 2 threads
WC Timing = 58.264825 second
Standard deviation = 0.416020 second
WC overhead = 57.060147 second
Standard deviation = 0.416020 second
WC overhead/iter = 0.089156 ms
WC overhead(%) wrt reference = 4736.55
CPU Timing = 58.260000 second
Standard deviation = 0.412876 second
CPU overhead = 57.053333 second
Standard deviation = 0.412903 second
CPU overhead/iter = 0.089146 ms
CPU overhead(%) wrt reference = 4728.18
CHUNK SIZE = 2
-- Testing 2 threads
WC Timing = 33.517030 second
Standard deviation = 0.144628 second
WC overhead = 32.312352 second
Standard deviation = 0.144628 second
WC overhead/iter = 0.050488 ms
WC overhead(%) wrt reference = 2682.24
CPU Timing = 33.500000 second
Standard deviation = 0.141657 second
CPU overhead = 32.293333 second
Standard deviation = 0.141735 second
CPU overhead/iter = 0.050458 ms
CPU overhead(%) wrt reference = 2676.24
CHUNK SIZE = 4
-- Testing 2 threads
WC Timing = 21.159608 second
Standard deviation = 0.075684 second
WC overhead = 19.954930 second
Standard deviation = 0.075684 second
WC overhead/iter = 0.031180 ms
WC overhead(%) wrt reference = 1656.45
CPU Timing = 21.161667 second
Standard deviation = 0.069442 second
CPU overhead = 19.955000 second
Standard deviation = 0.069602 second
CPU overhead/iter = 0.031180 ms
CPU overhead(%) wrt reference = 1653.73
CHUNK SIZE = 8
-- Testing 2 threads
WC Timing = 15.942525 second
Standard deviation = 0.066047 second
WC overhead = 14.737847 second
Standard deviation = 0.066047 second
WC overhead/iter = 0.023028 ms
WC overhead(%) wrt reference = 1223.38
CPU Timing = 15.931667 second
Standard deviation = 0.074087 second
CPU overhead = 14.725000 second
Standard deviation = 0.074237 second
CPU overhead/iter = 0.023008 ms
CPU overhead(%) wrt reference = 1220.30
CHUNK SIZE = 16
-- Testing 2 threads
WC Timing = 13.660754 second
Standard deviation = 0.124794 second
WC overhead = 12.456076 second
Standard deviation = 0.124794 second
WC overhead/iter = 0.019463 ms
WC overhead(%) wrt reference = 1033.98
CPU Timing = 13.661667 second
Standard deviation = 0.122837 second
CPU overhead = 12.455000 second
Standard deviation = 0.122927 second
CPU overhead/iter = 0.019461 ms
CPU overhead(%) wrt reference = 1032.18
CHUNK SIZE = 32
-- Testing 2 threads
WC Timing = 12.929524 second
Standard deviation = 0.007309 second
WC overhead = 11.724846 second
Standard deviation = 0.007310 second
WC overhead/iter = 0.018320 ms
WC overhead(%) wrt reference = 973.28
CPU Timing = 12.931667 second
Standard deviation = 0.008498 second
CPU overhead = 11.725000 second
Standard deviation = 0.009718 second
CPU overhead/iter = 0.018320 ms
CPU overhead(%) wrt reference = 971.69
CHUNK SIZE = 1
-- Testing 1 threads
WC Timing = 18.784525 second
Standard deviation = 0.001027 second
WC overhead = 17.579847 second
Standard deviation = 0.001031 second
WC overhead/iter = 0.027469 ms
WC overhead(%) wrt reference = 1459.30
CPU Timing = 18.786667 second
Standard deviation = 0.004714 second
CPU overhead = 17.580000 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.027469 ms
CPU overhead(%) wrt reference = 1456.91
CHUNK SIZE = 2
-- Testing 1 threads
WC Timing = 12.973006 second
Standard deviation = 0.021969 second
WC overhead = 11.768328 second
Standard deviation = 0.021969 second
WC overhead/iter = 0.018388 ms
WC overhead(%) wrt reference = 976.89
CPU Timing = 12.973333 second
Standard deviation = 0.016997 second
CPU overhead = 11.766667 second
Standard deviation = 0.017638 second
CPU overhead/iter = 0.018385 ms
CPU overhead(%) wrt reference = 975.14
CHUNK SIZE = 4
-- Testing 1 threads
WC Timing = 9.659787 second
Standard deviation = 0.000924 second
WC overhead = 8.455109 second
Standard deviation = 0.000929 second
WC overhead/iter = 0.013211 ms
WC overhead(%) wrt reference = 701.86
CPU Timing = 9.660000 second
Standard deviation = 0.008165 second
CPU overhead = 8.453333 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.013208 ms
CPU overhead(%) wrt reference = 700.55
CHUNK SIZE = 8
-- Testing 1 threads
WC Timing = 8.036165 second
Standard deviation = 0.011666 second
WC overhead = 6.831487 second
Standard deviation = 0.011666 second
WC overhead/iter = 0.010674 ms
WC overhead(%) wrt reference = 567.08
CPU Timing = 8.033333 second
Standard deviation = 0.018856 second
CPU overhead = 6.826667 second
Standard deviation = 0.019437 second
CPU overhead/iter = 0.010667 ms
CPU overhead(%) wrt reference = 565.75
CHUNK SIZE = 16
-- Testing 1 threads
WC Timing = 7.217171 second
Standard deviation = 0.003653 second
WC overhead = 6.012493 second
Standard deviation = 0.003654 second
WC overhead/iter = 0.009395 ms
WC overhead(%) wrt reference = 499.10
CPU Timing = 7.216667 second
Standard deviation = 0.004714 second
CPU overhead = 6.010000 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.009391 ms
CPU overhead(%) wrt reference = 498.07
CHUNK SIZE = 32
-- Testing 1 threads
WC Timing = 6.790687 second
Standard deviation = 0.006733 second
WC overhead = 5.586009 second
Standard deviation = 0.006733 second
WC overhead/iter = 0.008728 ms
WC overhead(%) wrt reference = 463.69
CPU Timing = 6.790000 second
Standard deviation = 0.008165 second
CPU overhead = 5.583333 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.008724 ms
CPU overhead(%) wrt reference = 462.71
***** Finished

***** Start Testing : #pragma omp parallel for schedule (guided,chunk_size)
-- iter_facotr : 2500
-- try_count : 1
-- delay_time : 0.000000 ms
-- Running Reference case
WC Timing = 1.204678 second
Standard deviation = 0.000097 second
CPU Timing = 1.206667 second
Standard deviation = 0.004714 second
CHUNK SIZE = 1
-- Testing 8 threads
WC Timing = 338.246563 second
Standard deviation = 0.614631 second
WC overhead = 337.041885 second
Standard deviation = 0.614631 second
WC overhead/iter = 0.526628 ms
WC overhead(%) wrt reference = 27977.76
CPU Timing = -199.266745 second
Standard deviation = 0.522809 second
CPU overhead = -200.473412 second
Standard deviation = 0.522831 second
CPU overhead/iter = -0.313240 ms
CPU overhead(%) wrt reference = -16613.82
CHUNK SIZE = 2
-- Testing 8 threads
WC Timing = 271.333933 second
Standard deviation = 0.247143 second
WC overhead = 270.129255 second
Standard deviation = 0.247143 second
WC overhead/iter = 0.422077 ms
WC overhead(%) wrt reference = 22423.36
CPU Timing = -266.016329 second
Standard deviation = 0.196809 second
CPU overhead = -267.222995 second
Standard deviation = 0.196865 second
CPU overhead/iter = -0.417536 ms
CPU overhead(%) wrt reference = -22145.55
CHUNK SIZE = 4
-- Testing 8 threads
WC Timing = 216.464655 second
Standard deviation = 0.209422 second
WC overhead = 215.259977 second
Standard deviation = 0.209422 second
WC overhead/iter = 0.336344 ms
WC overhead(%) wrt reference = 17868.67
CPU Timing = 216.092083 second
Standard deviation = 0.180238 second
CPU overhead = 214.885417 second
Standard deviation = 0.180300 second
CPU overhead/iter = 0.335758 ms
CPU overhead(%) wrt reference = 17808.18
CHUNK SIZE = 8
-- Testing 8 threads
WC Timing = 170.766493 second
Standard deviation = 0.256595 second
WC overhead = 169.561815 second
Standard deviation = 0.256595 second
WC overhead/iter = 0.264940 ms
WC overhead(%) wrt reference = 14075.28
CPU Timing = 170.465000 second
Standard deviation = 0.202803 second
CPU overhead = 169.258333 second
Standard deviation = 0.202858 second
CPU overhead/iter = 0.264466 ms
CPU overhead(%) wrt reference = 14026.93
CHUNK SIZE = 16
-- Testing 8 threads
WC Timing = 119.427926 second
Standard deviation = 0.540511 second
WC overhead = 118.223248 second
Standard deviation = 0.540511 second
WC overhead/iter = 0.184724 ms
WC overhead(%) wrt reference = 9813.68
CPU Timing = 119.198750 second
Standard deviation = 0.477262 second
CPU overhead = 117.992083 second
Standard deviation = 0.477285 second
CPU overhead/iter = 0.184363 ms
CPU overhead(%) wrt reference = 9778.35
CHUNK SIZE = 32
-- Testing 8 threads
WC Timing = 85.675633 second
Standard deviation = 0.023910 second
WC overhead = 84.470955 second
Standard deviation = 0.023910 second
WC overhead/iter = 0.131986 ms
WC overhead(%) wrt reference = 7011.91
CPU Timing = 85.547917 second
Standard deviation = 0.027392 second
CPU overhead = 84.341250 second
Standard deviation = 0.027795 second
CPU overhead/iter = 0.131783 ms
CPU overhead(%) wrt reference = 6989.61
CHUNK SIZE = 1
-- Testing 4 threads
WC Timing = 97.150588 second
Standard deviation = 0.038299 second
WC overhead = 95.945910 second
Standard deviation = 0.038299 second
WC overhead/iter = 0.149915 ms
WC overhead(%) wrt reference = 7964.44
CPU Timing = 97.129167 second
Standard deviation = 0.039069 second
CPU overhead = 95.922500 second
Standard deviation = 0.039352 second
CPU overhead/iter = 0.149879 ms
CPU overhead(%) wrt reference = 7949.38
CHUNK SIZE = 2
-- Testing 4 threads
WC Timing = 81.311482 second
Standard deviation = 0.053034 second
WC overhead = 80.106804 second
Standard deviation = 0.053034 second
WC overhead/iter = 0.125167 ms
WC overhead(%) wrt reference = 6649.64
CPU Timing = 81.300000 second
Standard deviation = 0.046143 second
CPU overhead = 80.093333 second
Standard deviation = 0.046383 second
CPU overhead/iter = 0.125146 ms
CPU overhead(%) wrt reference = 6637.57
CHUNK SIZE = 4
-- Testing 4 threads
WC Timing = 68.524482 second
Standard deviation = 0.047557 second
WC overhead = 67.319804 second
Standard deviation = 0.047557 second
WC overhead/iter = 0.105187 ms
WC overhead(%) wrt reference = 5588.20
CPU Timing = 68.520000 second
Standard deviation = 0.057482 second
CPU overhead = 67.313333 second
Standard deviation = 0.057675 second
CPU overhead/iter = 0.105177 ms
CPU overhead(%) wrt reference = 5578.45
CHUNK SIZE = 8
-- Testing 4 threads
WC Timing = 54.426502 second
Standard deviation = 0.077274 second
WC overhead = 53.221824 second
Standard deviation = 0.077274 second
WC overhead/iter = 0.083159 ms
WC overhead(%) wrt reference = 4417.93
CPU Timing = 54.423333 second
Standard deviation = 0.079171 second
CPU overhead = 53.216667 second
Standard deviation = 0.079311 second
CPU overhead/iter = 0.083151 ms
CPU overhead(%) wrt reference = 4410.22
CHUNK SIZE = 16
-- Testing 4 threads
WC Timing = 41.389755 second
Standard deviation = 0.036360 second
WC overhead = 40.185077 second
Standard deviation = 0.036360 second
WC overhead/iter = 0.062789 ms
WC overhead(%) wrt reference = 3335.75
CPU Timing = 41.384167 second
Standard deviation = 0.038424 second
CPU overhead = 40.177500 second
Standard deviation = 0.038712 second
CPU overhead/iter = 0.062777 ms
CPU overhead(%) wrt reference = 3329.63
CHUNK SIZE = 32
-- Testing 4 threads
WC Timing = 31.342109 second
Standard deviation = 0.041902 second
WC overhead = 30.137431 second
Standard deviation = 0.041902 second
WC overhead/iter = 0.047090 ms
WC overhead(%) wrt reference = 2501.70
CPU Timing = 31.325000 second
Standard deviation = 0.036912 second
CPU overhead = 30.118333 second
Standard deviation = 0.037212 second
CPU overhead/iter = 0.047060 ms
CPU overhead(%) wrt reference = 2495.99
CHUNK SIZE = 1
-- Testing 2 threads
WC Timing = 40.413736 second
Standard deviation = 0.012711 second
WC overhead = 39.209058 second
Standard deviation = 0.012712 second
WC overhead/iter = 0.061264 ms
WC overhead(%) wrt reference = 3254.73
CPU Timing = 40.400000 second
Standard deviation = 0.017795 second
CPU overhead = 39.193333 second
Standard deviation = 0.018409 second
CPU overhead/iter = 0.061240 ms
CPU overhead(%) wrt reference = 3248.07
CHUNK SIZE = 2
-- Testing 2 threads
WC Timing = 32.964702 second
Standard deviation = 0.045918 second
WC overhead = 31.760024 second
Standard deviation = 0.045918 second
WC overhead/iter = 0.049625 ms
WC overhead(%) wrt reference = 2636.39
CPU Timing = 32.951667 second
Standard deviation = 0.040893 second
CPU overhead = 31.745000 second
Standard deviation = 0.041164 second
CPU overhead/iter = 0.049602 ms
CPU overhead(%) wrt reference = 2630.80
CHUNK SIZE = 4
-- Testing 2 threads
WC Timing = 29.472372 second
Standard deviation = 0.046916 second
WC overhead = 28.267694 second
Standard deviation = 0.046916 second
WC overhead/iter = 0.044168 ms
WC overhead(%) wrt reference = 2346.49
CPU Timing = 29.461667 second
Standard deviation = 0.051694 second
CPU overhead = 28.255000 second
Standard deviation = 0.051908 second
CPU overhead/iter = 0.044148 ms
CPU overhead(%) wrt reference = 2341.57
CHUNK SIZE = 8
-- Testing 2 threads
WC Timing = 24.808464 second
Standard deviation = 0.050305 second
WC overhead = 23.603786 second
Standard deviation = 0.050305 second
WC overhead/iter = 0.036881 ms
WC overhead(%) wrt reference = 1959.34
CPU Timing = 24.805000 second
Standard deviation = 0.050166 second
CPU overhead = 23.598333 second
Standard deviation = 0.050387 second
CPU overhead/iter = 0.036872 ms
CPU overhead(%) wrt reference = 1955.66
CHUNK SIZE = 16
-- Testing 2 threads
WC Timing = 17.587257 second
Standard deviation = 0.035709 second
WC overhead = 16.382579 second
Standard deviation = 0.035709 second
WC overhead/iter = 0.025598 ms
WC overhead(%) wrt reference = 1359.91
CPU Timing = 17.575000 second
Standard deviation = 0.034881 second
CPU overhead = 16.368333 second
Standard deviation = 0.035198 second
CPU overhead/iter = 0.025576 ms
CPU overhead(%) wrt reference = 1356.49
CHUNK SIZE = 32
-- Testing 2 threads
WC Timing = 16.138609 second
Standard deviation = 0.001872 second
WC overhead = 14.933931 second
Standard deviation = 0.001874 second
WC overhead/iter = 0.023334 ms
WC overhead(%) wrt reference = 1239.66
CPU Timing = 16.143333 second
Standard deviation = 0.008498 second
CPU overhead = 14.936667 second
Standard deviation = 0.009718 second
CPU overhead/iter = 0.023339 ms
CPU overhead(%) wrt reference = 1237.85
CHUNK SIZE = 1
-- Testing 1 threads
WC Timing = 8.306730 second
Standard deviation = 0.002974 second
WC overhead = 7.102052 second
Standard deviation = 0.002975 second
WC overhead/iter = 0.011097 ms
WC overhead(%) wrt reference = 589.54
CPU Timing = 8.310000 second
Standard deviation = 0.000000 second
CPU overhead = 7.103333 second
Standard deviation = 0.004714 second
CPU overhead/iter = 0.011099 ms
CPU overhead(%) wrt reference = 588.67
CHUNK SIZE = 2
-- Testing 1 threads
WC Timing = 8.308393 second
Standard deviation = 0.003511 second
WC overhead = 7.103715 second
Standard deviation = 0.003512 second
WC overhead/iter = 0.011100 ms
WC overhead(%) wrt reference = 589.68
CPU Timing = 8.313333 second
Standard deviation = 0.004714 second
CPU overhead = 7.106667 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.011104 ms
CPU overhead(%) wrt reference = 588.95
CHUNK SIZE = 4
-- Testing 1 threads
WC Timing = 8.312722 second
Standard deviation = 0.010986 second
WC overhead = 7.108044 second
Standard deviation = 0.010986 second
WC overhead/iter = 0.011106 ms
WC overhead(%) wrt reference = 590.04
CPU Timing = 8.310000 second
Standard deviation = 0.008165 second
CPU overhead = 7.103333 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.011099 ms
CPU overhead(%) wrt reference = 588.67
CHUNK SIZE = 8
-- Testing 1 threads
WC Timing = 8.306483 second
Standard deviation = 0.001671 second
WC overhead = 7.101805 second
Standard deviation = 0.001674 second
WC overhead/iter = 0.011097 ms
WC overhead(%) wrt reference = 589.52
CPU Timing = 8.306667 second
Standard deviation = 0.004714 second
CPU overhead = 7.100000 second
Standard deviation = 0.006667 second
CPU overhead/iter = 0.011094 ms
CPU overhead(%) wrt reference = 588.40
CHUNK SIZE = 16
-- Testing 1 threads
WC Timing = 8.303899 second
Standard deviation = 0.005260 second
WC overhead = 7.099221 second
Standard deviation = 0.005261 second
WC overhead/iter = 0.011093 ms
WC overhead(%) wrt reference = 589.30
CPU Timing = 8.300000 second
Standard deviation = 0.014142 second
CPU overhead = 7.093333 second
Standard deviation = 0.014907 second
CPU overhead/iter = 0.011083 ms
CPU overhead(%) wrt reference = 587.85
CHUNK SIZE = 32
-- Testing 1 threads
WC Timing = 7.500948 second
Standard deviation = 0.005031 second
WC overhead = 6.296270 second
Standard deviation = 0.005032 second
WC overhead/iter = 0.009838 ms
WC overhead(%) wrt reference = 522.65
CPU Timing = 7.500000 second
Standard deviation = 0.008165 second
CPU overhead = 6.293333 second
Standard deviation = 0.009428 second
CPU overhead/iter = 0.009833 ms
CPU overhead(%) wrt reference = 521.55
***** Finished

*******************************
* ELAPSE TIME = 13003.785759
*******************************


***** Start Testing : #pragma omp for reduction
-- iter_facotr : 40
-- try_count : 1
-- delay_time : 0.008333 ms
-- Running Reference case
WC Timing = 1.213651 second
Standard deviation = 0.003158 second
CPU Timing = 9.703333 second
Standard deviation = 0.020548 second
-- Testing 8 threads
WC Timing = 1.432424 second
Standard deviation = 0.024122 second
WC overhead = 0.218773 second
Standard deviation = 0.024328 second
WC overhead/iter = 0.021365 ms
WC overhead(%) wrt reference = 18.03
CPU Timing = 1.431250 second
Standard deviation = 0.023341 second
CPU overhead = -8.272083 second
Standard deviation = 0.031097 second
CPU overhead/iter = -0.807821 ms
CPU overhead(%) wrt reference = -85.25
-- Running Reference case
WC Timing = 0.605886 second
Standard deviation = 0.004999 second
CPU Timing = 2.423333 second
Standard deviation = 0.016997 second
-- Testing 4 threads
WC Timing = 0.732198 second
Standard deviation = 0.002104 second
WC overhead = 0.126312 second
Standard deviation = 0.005423 second
WC overhead/iter = 0.012335 ms
WC overhead(%) wrt reference = 20.85
CPU Timing = 0.733333 second
Standard deviation = 0.004249 second
CPU overhead = -1.690000 second
Standard deviation = 0.017520 second
CPU overhead/iter = -0.165039 ms
CPU overhead(%) wrt reference = -69.74
-- Running Reference case
WC Timing = 0.300063 second
Standard deviation = 0.001204 second
CPU Timing = 0.600000 second
Standard deviation = 0.000000 second
-- Testing 2 threads
WC Timing = 0.369007 second
Standard deviation = 0.001628 second
WC overhead = 0.068944 second
Standard deviation = 0.002025 second
WC overhead/iter = 0.006733 ms
WC overhead(%) wrt reference = 22.98
CPU Timing = 0.370000 second
Standard deviation = 0.000000 second
CPU overhead = -0.230000 second
Standard deviation = 0.000000 second
CPU overhead/iter = -0.022461 ms
CPU overhead(%) wrt reference = -38.33
-- Running Reference case
WC Timing = 0.149651 second
Standard deviation = 0.001319 second
CPU Timing = 0.150000 second
Standard deviation = 0.000000 second
-- Testing 1 threads
WC Timing = 0.169525 second
Standard deviation = 0.000314 second
WC overhead = 0.019874 second
Standard deviation = 0.001356 second
WC overhead/iter = 0.001941 ms
WC overhead(%) wrt reference = 13.28
CPU Timing = 0.170000 second
Standard deviation = 0.000000 second
CPU overhead = 0.020000 second
Standard deviation = 0.000000 second
CPU overhead/iter = 0.001953 ms
CPU overhead(%) wrt reference = 13.33
***** Finished

*******************************
* ELAPSE TIME = 14.920530
*******************************


***** Start Testing : #pragma omp single
-- iter_facotr : 500
-- try_count : 1
-- delay_time : 0.003333 ms
-- Running Reference case
WC Timing = 1.255183 second
Standard deviation = 0.005458 second
CPU Timing = 1.254583 second
Standard deviation = 0.005803 second
-- Testing 8 threads
WC Timing = 1.742327 second
Standard deviation = 0.012385 second
WC overhead = 0.487144 second
Standard deviation = 0.013534 second
WC overhead/iter = 0.003806 ms
WC overhead(%) wrt reference = 38.81
CPU Timing = 13.930000 second
Standard deviation = 0.097980 second
CPU overhead = 12.675417 second
Standard deviation = 0.098151 second
CPU overhead/iter = 0.099027 ms
CPU overhead(%) wrt reference = 1010.33
-- Running Reference case
WC Timing = 1.232505 second
Standard deviation = 0.007366 second
CPU Timing = 1.235833 second
Standard deviation = 0.006236 second
-- Testing 4 threads
WC Timing = 1.614114 second
Standard deviation = 0.005807 second
WC overhead = 0.381610 second
Standard deviation = 0.009380 second
WC overhead/iter = 0.002981 ms
WC overhead(%) wrt reference = 30.96
CPU Timing = 6.456667 second
Standard deviation = 0.024944 second
CPU overhead = 5.220833 second
Standard deviation = 0.025712 second
CPU overhead/iter = 0.040788 ms
CPU overhead(%) wrt reference = 422.45
-- Running Reference case
WC Timing = 1.233957 second
Standard deviation = 0.001361 second
CPU Timing = 1.238333 second
Standard deviation = 0.002357 second
-- Testing 2 threads
WC Timing = 1.546214 second
Standard deviation = 0.003910 second
WC overhead = 0.312257 second
Standard deviation = 0.004140 second
WC overhead/iter = 0.002440 ms
WC overhead(%) wrt reference = 25.31
CPU Timing = 3.093333 second
Standard deviation = 0.009428 second
CPU overhead = 1.855000 second
Standard deviation = 0.009718 second
CPU overhead/iter = 0.014492 ms
CPU overhead(%) wrt reference = 149.80
-- Running Reference case
WC Timing = 1.251257 second
Standard deviation = 0.007071 second
CPU Timing = 1.250000 second
Standard deviation = 0.008165 second
-- Testing 1 threads
WC Timing = 1.407003 second
Standard deviation = 0.003756 second
WC overhead = 0.155746 second
Standard deviation = 0.008007 second
WC overhead/iter = 0.001217 ms
WC overhead(%) wrt reference = 12.45
CPU Timing = 1.406667 second
Standard deviation = 0.009428 second
CPU overhead = 0.156667 second
Standard deviation = 0.012472 second
CPU overhead/iter = 0.001224 ms
CPU overhead(%) wrt reference = 12.53
***** Finished

*******************************
* ELAPSE TIME = 33.880997
*******************************