| | | | | | | requested parallelism | walltime sum (s) | nb instances | any sync average per thread time (s) | any wait average per thread time (s) | parallelism overhead (%) | local speedup if perfectly balanced | global speedup if perfectly balanced |
start addr | function name | source location | level | ancestor thread num | invoker | parallel or teams | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x48 | 1x96 |
exec:0x401938 | main | stream.c:354 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 120.236 | 60.242 | 31.882 | 15.942 | 8.296 | 5.018 | 4.353 | 4.280 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 0.145 | 0.938 | 0.437 | 0.248 | 80.7 E-3 | 65.8 E-3 | 37.6 E-3 | 0.0 | 0.145 | 0.938 | 0.437 | 0.248 | 80.7 E-3 | 65.8 E-3 | 37.5 E-3 | 0 | 0.24 | 2.94 | 2.74 | 2.99 | 1.61 | 1.51 | 0.88 | 1.000 | 1.002 | 1.030 | 1.028 | 1.031 | 1.016 | 1.015 | 1.009 | 1.000 | 1.001 | 1.008 | 1.007 | 1.007 | 1.004 | 1.004 | 1.002 |
exec:0x40188f | main | stream.c:342 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 120.007 | 60.179 | 31.838 | 15.918 | 8.288 | 4.955 | 4.349 | 4.281 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 0.150 | 0.928 | 0.436 | 0.245 | 81.0 E-3 | 66.7 E-3 | 34.1 E-3 | 0.0 | 0.150 | 0.928 | 0.436 | 0.245 | 81.0 E-3 | 66.7 E-3 | 34.1 E-3 | 0 | 0.25 | 2.92 | 2.74 | 2.95 | 1.63 | 1.53 | 0.80 | 1.000 | 1.002 | 1.030 | 1.028 | 1.030 | 1.017 | 1.016 | 1.008 | 1.000 | 1.001 | 1.008 | 1.007 | 1.007 | 1.004 | 1.004 | 1.002 |
exec:0x401737 | main | stream.c:318 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 99.503 | 49.523 | 28.400 | 14.190 | 7.250 | 4.043 | 3.360 | 3.002 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 32.8 E-3 | 1.846 | 0.878 | 0.463 | 0.184 | 0.101 | 50.6 E-3 | 0.0 | 32.7 E-3 | 1.846 | 0.878 | 0.463 | 0.184 | 0.101 | 50.6 E-3 | 0 | 0.07 | 6.50 | 6.19 | 6.38 | 4.56 | 2.99 | 1.69 | 1.000 | 1.001 | 1.070 | 1.066 | 1.068 | 1.048 | 1.031 | 1.017 | 1.000 | 1.000 | 1.015 | 1.014 | 1.014 | 1.009 | 1.006 | 1.003 |
exec:0x4017ea | main | stream.c:330 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 98.382 | 49.023 | 28.060 | 14.032 | 7.166 | 3.963 | 3.301 | 2.995 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 36.4 E-3 | 1.799 | 0.838 | 0.454 | 0.177 | 92.7 E-3 | 42.8 E-3 | 0.0 | 36.4 E-3 | 1.799 | 0.838 | 0.454 | 0.177 | 92.7 E-3 | 42.8 E-3 | 0 | 0.07 | 6.41 | 5.97 | 6.34 | 4.48 | 2.81 | 1.43 | 1.000 | 1.001 | 1.069 | 1.064 | 1.068 | 1.047 | 1.029 | 1.015 | 1.000 | 1.000 | 1.015 | 1.013 | 1.014 | 1.009 | 1.005 | 1.003 |
exec:0x40137d | main | stream.c:278 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 6.611 | 3.302 | 1.882 | 0.939 | 0.476 | 0.247 | 0.179 | 0.131 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 463 E-6 | 0.118 | 43.9 E-3 | 26.1 E-3 | 14.8 E-3 | 11.9 E-3 | 12.5 E-3 | 0.0 | 463 E-6 | 0.118 | 43.9 E-3 | 26.1 E-3 | 14.8 E-3 | 11.9 E-3 | 12.5 E-3 | 0 | 0.01 | 6.25 | 4.67 | 5.48 | 5.97 | 6.68 | 9.53 | 1.000 | 1.000 | 1.067 | 1.049 | 1.058 | 1.064 | 1.072 | 1.105 | 1.000 | 1.000 | 1.001 | 1.001 | 1.001 | 1.001 | 1.001 | 1.001 |
exec:0x4015fb | main | stream.c:290 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 0.417 | 0.208 | 0.104 | 52.5 E-3 | 35.1 E-3 | 28.8 E-3 | 28.4 E-3 | 28.8 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 282 E-6 | 839 E-6 | 633 E-6 | 360 E-6 | 296 E-6 | 300 E-6 | 402 E-6 | 0.0 | 282 E-6 | 839 E-6 | 633 E-6 | 360 E-6 | 296 E-6 | 300 E-6 | 402 E-6 | 0 | 0.14 | 0.80 | 1.21 | 1.02 | 1.03 | 1.06 | 1.40 | 1.000 | 1.001 | 1.008 | 1.012 | 1.010 | 1.010 | 1.011 | 1.014 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
exec:0x40131d | main | stream.c:263 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 17.6 E-6 | 269 E-6 | 364 E-6 | 560 E-6 | 1.24 E-3 | 2.15 E-3 | 3.06 E-3 | 6.29 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 88.4 E-6 | 89.8 E-6 | 114 E-6 | 164 E-6 | 161 E-6 | 108 E-6 | 266 E-6 | 0.0 | 88.3 E-6 | 89.7 E-6 | 114 E-6 | 164 E-6 | 160 E-6 | 108 E-6 | 266 E-6 | 0 | 32.9 | 24.6 | 20.3 | 13.2 | 7.47 | 3.54 | 4.24 | 1.000 | 1.490 | 1.327 | 1.255 | 1.153 | 1.081 | 1.037 | 1.044 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
exec:0x401345 | main | stream.c:267 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 48 | 96 | 860 E-9 | 7.05 E-6 | 5.74 E-6 | 6.79 E-6 | 8.86 E-6 | 9.20 E-6 | 9.10 E-6 | 13.6 E-6 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 3.11 E-6 | 2.07 E-6 | 2.57 E-6 | 3.34 E-6 | 3.94 E-6 | 2.84 E-6 | 5.20 E-6 | 0.0 | 2.92 E-6 | 1.91 E-6 | 2.41 E-6 | 3.14 E-6 | 3.79 E-6 | 2.70 E-6 | 5.05 E-6 | 0 | 44.2 | 36.1 | 37.9 | 37.7 | 42.8 | 31.3 | 38.2 | 1.000 | 1.792 | 1.564 | 1.609 | 1.605 | 1.747 | 1.455 | 1.619 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |