| | | | | | | 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 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 | run_0 | o2 | o4 | o8 | o16 | o26 | o52 |
spmxv.exe:0x402bd4 | spmxv(ooo_options*, ooo_input*) | main.cpp:65 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 286.722 | 166.089 | 76.545 | 38.695 | 21.297 | 12.977 | 8.173 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 0.0 | 7.980 | 1.333 | 1.217 | 1.589 | 0.556 | 0.798 | 0.0 | 7.977 | 1.329 | 1.214 | 1.586 | 0.553 | 0.795 | 0 | 4.80 | 1.74 | 3.14 | 7.46 | 4.28 | 9.77 | 1.000 | 1.050 | 1.018 | 1.032 | 1.081 | 1.045 | 1.108 | 1.000 | 1.012 | 1.004 | 1.008 | 1.019 | 1.011 | 1.024 |
spmxv.exe:0x402b6e | spmxv(ooo_options*, ooo_input*) | main.cpp:65 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 286.705 | 166.148 | 76.538 | 38.685 | 21.291 | 12.981 | 8.242 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 0.0 | 7.974 | 1.327 | 1.207 | 1.587 | 0.561 | 0.867 | 0.0 | 7.970 | 1.324 | 1.204 | 1.584 | 0.558 | 0.864 | 0 | 4.80 | 1.73 | 3.12 | 7.45 | 4.32 | 10.5 | 1.000 | 1.050 | 1.018 | 1.032 | 1.081 | 1.045 | 1.118 | 1.000 | 1.012 | 1.004 | 1.008 | 1.019 | 1.011 | 1.026 |
spmxv.exe:0x402c3a | spmxv(ooo_options*, ooo_input*) | main.cpp:65 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 286.695 | 166.096 | 76.542 | 38.693 | 21.286 | 12.980 | 8.171 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 0.0 | 7.981 | 1.327 | 1.215 | 1.583 | 0.559 | 0.801 | 0.0 | 7.976 | 1.324 | 1.212 | 1.580 | 0.556 | 0.798 | 0 | 4.80 | 1.73 | 3.14 | 7.44 | 4.31 | 9.81 | 1.000 | 1.050 | 1.018 | 1.032 | 1.080 | 1.045 | 1.109 | 1.000 | 1.012 | 1.004 | 1.008 | 1.019 | 1.011 | 1.024 |
spmxv.exe:0x402ca4 | spmxv(ooo_options*, ooo_input*) | main.cpp:65 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 286.620 | 166.097 | 76.544 | 38.687 | 21.289 | 12.990 | 8.307 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 25.0 E3 | 0.0 | 7.988 | 1.326 | 1.209 | 1.584 | 0.566 | 0.933 | 0.0 | 7.984 | 1.323 | 1.206 | 1.582 | 0.563 | 0.930 | 0 | 4.81 | 1.73 | 3.12 | 7.44 | 4.36 | 11.2 | 1.000 | 1.051 | 1.018 | 1.032 | 1.080 | 1.046 | 1.126 | 1.000 | 1.012 | 1.004 | 1.008 | 1.019 | 1.011 | 1.028 |
spmxv.exe:0x40297b | spmxv(ooo_options*, ooo_input*) | main.cpp:42 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 62.9 E-3 | 32.0 E-3 | 25.2 E-3 | 19.7 E-3 | 19.9 E-3 | 20.9 E-3 | 23.5 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 14.9 E-6 | 104 E-6 | 211 E-6 | 206 E-6 | 163 E-6 | 229 E-6 | 0.0 | 14.6 E-6 | 103 E-6 | 210 E-6 | 205 E-6 | 163 E-6 | 229 E-6 | 0 | 0.05 | 0.41 | 1.07 | 1.03 | 0.78 | 0.97 | 1.000 | 1.000 | 1.004 | 1.011 | 1.010 | 1.008 | 1.010 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
spmxv.exe:0x402920 | spmxv(ooo_options*, ooo_input*) | main.cpp:32 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 6.97 E-3 | 7.85 E-3 | 6.36 E-3 | 4.50 E-3 | 5.50 E-3 | 7.36 E-3 | 10.8 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 0.0 | 7.28 E-6 | 5.79 E-6 | 50.3 E-6 | 145 E-6 | 34.7 E-6 | 1.63 E-3 | 0.0 | 6.94 E-6 | 5.49 E-6 | 49.9 E-6 | 144 E-6 | 34.4 E-6 | 1.63 E-3 | 0 | 0.09 | 0.09 | 1.12 | 2.63 | 0.47 | 15.0 | 1.000 | 1.001 | 1.001 | 1.011 | 1.027 | 1.005 | 1.177 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |