| | | | | | | 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 | 1x64 | 1x112 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x64 | 1x112 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x64 | 1x112 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x64 | 1x112 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x64 | 1x112 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x64 | 1x112 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x64 | 1x112 | 1x1 | 1x2 | 1x4 | 1x8 | 1x16 | 1x32 | 1x64 | 1x112 |
exec:0x400f29 | main | stream.c:342 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 132.572 | 66.219 | 35.106 | 17.544 | 8.997 | 5.069 | 4.158 | 4.249 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 48.0 E-3 | 1.025 | 0.445 | 0.215 | 83.8 E-3 | 23.4 E-3 | 31.4 E-3 | 0.0 | 48.0 E-3 | 1.025 | 0.445 | 0.215 | 83.8 E-3 | 23.4 E-3 | 31.4 E-3 | 0 | 0.07 | 2.92 | 2.54 | 2.39 | 1.65 | 0.56 | 0.74 | 1.000 | 1.001 | 1.030 | 1.026 | 1.025 | 1.017 | 1.006 | 1.007 | 1.000 | 1.000 | 1.007 | 1.006 | 1.006 | 1.004 | 1.001 | 1.002 |
exec:0x400fcf | main | stream.c:354 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 132.526 | 66.252 | 35.201 | 17.589 | 9.003 | 5.082 | 4.159 | 4.242 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 57.0 E-3 | 1.069 | 0.462 | 0.221 | 84.2 E-3 | 20.9 E-3 | 31.8 E-3 | 0.0 | 57.0 E-3 | 1.069 | 0.462 | 0.221 | 84.2 E-3 | 20.9 E-3 | 31.8 E-3 | 0 | 0.09 | 3.04 | 2.63 | 2.45 | 1.66 | 0.50 | 0.75 | 1.000 | 1.001 | 1.031 | 1.027 | 1.025 | 1.017 | 1.005 | 1.008 | 1.000 | 1.000 | 1.008 | 1.007 | 1.006 | 1.004 | 1.001 | 1.002 |
exec:0x400dd7 | main | stream.c:318 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 110.866 | 55.386 | 31.433 | 15.713 | 7.949 | 4.316 | 3.066 | 2.986 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 51.1 E-3 | 1.893 | 0.909 | 0.472 | 0.209 | 55.3 E-3 | 32.2 E-3 | 0.0 | 51.1 E-3 | 1.893 | 0.909 | 0.472 | 0.209 | 55.2 E-3 | 32.2 E-3 | 0 | 0.09 | 6.02 | 5.78 | 5.94 | 4.85 | 1.80 | 1.08 | 1.000 | 1.001 | 1.064 | 1.061 | 1.063 | 1.051 | 1.018 | 1.011 | 1.000 | 1.000 | 1.014 | 1.013 | 1.013 | 1.010 | 1.003 | 1.002 |
exec:0x400e87 | main | stream.c:330 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 110.487 | 55.078 | 31.041 | 15.519 | 7.881 | 4.285 | 3.060 | 2.990 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 0.0 | 39.7 E-3 | 1.772 | 0.842 | 0.453 | 0.208 | 56.0 E-3 | 29.7 E-3 | 0.0 | 39.7 E-3 | 1.772 | 0.842 | 0.453 | 0.208 | 56.0 E-3 | 29.7 E-3 | 0 | 0.07 | 5.71 | 5.43 | 5.75 | 4.85 | 1.83 | 0.99 | 1.000 | 1.001 | 1.061 | 1.057 | 1.061 | 1.051 | 1.019 | 1.010 | 1.000 | 1.000 | 1.013 | 1.012 | 1.012 | 1.009 | 1.003 | 1.002 |
exec:0x400a2d | main | stream.c:278 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 9.650 | 5.501 | 3.034 | 2.039 | 1.625 | 1.484 | 1.445 | 1.538 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 14.0 E-3 | 66.1 E-3 | 0.109 | 22.9 E-3 | 24.0 E-3 | 26.4 E-3 | 0.159 | 0.0 | 14.0 E-3 | 66.1 E-3 | 0.109 | 22.9 E-3 | 24.0 E-3 | 26.4 E-3 | 0.159 | 0 | 0.25 | 2.18 | 5.33 | 1.41 | 1.62 | 1.83 | 10.3 | 1.000 | 1.003 | 1.022 | 1.056 | 1.014 | 1.016 | 1.019 | 1.115 | 1.000 | 1.000 | 1.000 | 1.002 | 1.001 | 1.001 | 1.001 | 1.009 |
exec:0x400c96 | main | stream.c:290 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 0.494 | 0.247 | 0.124 | 61.7 E-3 | 37.0 E-3 | 30.9 E-3 | 29.4 E-3 | 29.6 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 360 E-6 | 1.27 E-3 | 684 E-6 | 248 E-6 | 227 E-6 | 211 E-6 | 531 E-6 | 0.0 | 360 E-6 | 1.27 E-3 | 684 E-6 | 247 E-6 | 227 E-6 | 211 E-6 | 530 E-6 | 0 | 0.15 | 1.03 | 1.11 | 0.67 | 0.73 | 0.72 | 1.80 | 1.000 | 1.001 | 1.010 | 1.011 | 1.007 | 1.007 | 1.007 | 1.018 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
exec:0x4009cd | main | stream.c:263 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 29.3 E-6 | 320 E-6 | 457 E-6 | 750 E-6 | 1.48 E-3 | 2.53 E-3 | 4.27 E-3 | 7.12 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 92.3 E-6 | 73.4 E-6 | 71.5 E-6 | 188 E-6 | 181 E-6 | 149 E-6 | 112 E-6 | 0.0 | 92.2 E-6 | 73.2 E-6 | 71.3 E-6 | 188 E-6 | 181 E-6 | 149 E-6 | 112 E-6 | 0 | 28.9 | 16.1 | 9.53 | 12.7 | 7.16 | 3.49 | 1.57 | 1.000 | 1.406 | 1.191 | 1.105 | 1.146 | 1.077 | 1.036 | 1.016 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
exec:0x4009f5 | main | stream.c:267 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 112 | 1.16 E-6 | 6.10 E-6 | 6.33 E-6 | 6.57 E-6 | 7.49 E-6 | 7.99 E-6 | 11.6 E-6 | 16.7 E-6 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 2.91 E-6 | 2.16 E-6 | 1.75 E-6 | 2.29 E-6 | 2.88 E-6 | 4.25 E-6 | 7.34 E-6 | 0.0 | 2.68 E-6 | 1.91 E-6 | 1.49 E-6 | 2.07 E-6 | 2.68 E-6 | 4.05 E-6 | 7.16 E-6 | 0 | 47.7 | 34.0 | 26.6 | 30.5 | 36.0 | 36.7 | 43.9 | 1.000 | 1.912 | 1.516 | 1.362 | 1.439 | 1.563 | 1.579 | 1.783 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |