| | | | | | | 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 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 | m1o1 | m1o2 | m1o4 | m1o8 | m1o16 | m1o26 | m1o52 |
|---|
| libqmckl.so.0.0.0:0x3274d | qmckl_compute_dtmp_c_hpc | qmckl_jastrow_champ.c:3993 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 83.618 | 41.971 | 22.900 | 11.707 | 6.108 | 4.489 | 3.915 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 5.33 E-3 | 1.385 | 0.712 | 0.429 | 0.529 | 0.542 | 0.0 | 5.32 E-3 | 1.385 | 0.712 | 0.429 | 0.529 | 0.542 | 0 | 0.01 | 6.05 | 6.08 | 7.02 | 11.8 | 13.8 | 1.000 | 1.000 | 1.064 | 1.065 | 1.075 | 1.134 | 1.161 | 1.000 | 1.000 | 1.014 | 1.009 | 1.007 | 1.008 | 1.009 |
| libqmckl.so.0.0.0:0x31f6a | qmckl_compute_tmp_c_hpc | qmckl_jastrow_champ.c:3923 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 43.412 | 21.825 | 11.759 | 6.124 | 3.212 | 2.209 | 1.967 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 0.0 | 4.45 E-3 | 0.605 | 0.365 | 0.245 | 0.191 | 0.201 | 0.0 | 4.44 E-3 | 0.605 | 0.365 | 0.245 | 0.191 | 0.201 | 0 | 0.02 | 5.14 | 5.96 | 7.62 | 8.64 | 10.2 | 1.000 | 1.000 | 1.054 | 1.063 | 1.082 | 1.095 | 1.114 | 1.000 | 1.000 | 1.006 | 1.005 | 1.004 | 1.003 | 1.003 |
| libqmckl.so.0.0.0:0x85b2f | qmckl_compute_jastrow_champ_factor_een_rescaled_e_gl_f_ | qmckl_jastrow_champ_f.F90:1150 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 11.282 | 5.561 | 3.674 | 2.537 | 2.398 | 2.208 | 2.264 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 6.52 E-3 | 0.662 | 0.276 | 0.127 | 0.117 | 0.199 | 0.0 | 6.51 E-3 | 0.662 | 0.276 | 0.127 | 0.117 | 0.199 | 0 | 0.12 | 18.0 | 10.9 | 5.30 | 5.29 | 8.79 | 1.000 | 1.001 | 1.220 | 1.122 | 1.056 | 1.056 | 1.096 | 1.000 | 1.000 | 1.007 | 1.004 | 1.002 | 1.002 | 1.003 |
| libqmckl.so.0.0.0:0x337fc | qmckl_compute_jastrow_champ_factor_een_gl_hpc | qmckl_jastrow_champ.c:4375 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 10.055 | 5.419 | 2.999 | 1.900 | 1.634 | 1.701 | 2.123 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 445 E-6 | 6.59 E-3 | 64.3 E-3 | 82.8 E-3 | 67.7 E-3 | 0.237 | 0.0 | 439 E-6 | 6.59 E-3 | 64.3 E-3 | 82.8 E-3 | 67.7 E-3 | 0.237 | 0 | 0.01 | 0.22 | 3.38 | 5.07 | 3.98 | 11.2 | 1.000 | 1.000 | 1.002 | 1.035 | 1.053 | 1.041 | 1.126 | 1.000 | 1.000 | 1.000 | 1.001 | 1.001 | 1.001 | 1.004 |
| libqmckl.so.0.0.0:0x2fa67 | qmckl_compute_een_rescaled_e_hpc | qmckl_jastrow_champ.c:2966 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 8.314 | 4.761 | 2.930 | 2.153 | 1.542 | 1.316 | 1.320 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 0.0 | 5.79 E-3 | 0.163 | 0.356 | 0.295 | 0.128 | 87.0 E-3 | 0.0 | 5.78 E-3 | 0.163 | 0.356 | 0.295 | 0.128 | 87.0 E-3 | 0 | 0.12 | 5.57 | 16.5 | 19.1 | 9.69 | 6.59 | 1.000 | 1.001 | 1.059 | 1.198 | 1.236 | 1.107 | 1.071 | 1.000 | 1.000 | 1.002 | 1.005 | 1.004 | 1.002 | 1.001 |
| libqmckl.so.0.0.0:0x2bcc9 | qmckl_compute_jastrow_champ_factor_ee_gl_hpc | qmckl_jastrow_champ.c:1652 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 5.965 | 2.986 | 1.526 | 0.784 | 0.421 | 0.243 | 0.127 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 992 E-6 | 23.1 E-3 | 32.4 E-3 | 46.0 E-3 | 12.4 E-3 | 9.03 E-3 | 0.0 | 989 E-6 | 23.1 E-3 | 32.4 E-3 | 46.0 E-3 | 12.4 E-3 | 9.03 E-3 | 0 | 0.03 | 1.51 | 4.14 | 10.9 | 5.10 | 7.09 | 1.000 | 1.000 | 1.015 | 1.043 | 1.123 | 1.054 | 1.076 | 1.000 | 1.000 | 1.000 | 1.000 | 1.001 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2b751 | qmckl_compute_ee_distance_rescaled_gl_hpc | qmckl_jastrow_champ.c:1984 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 1.872 | 0.941 | 0.493 | 0.265 | 0.193 | 0.186 | 0.192 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 20.3 E-6 | 2.41 E-3 | 15.8 E-3 | 19.5 E-3 | 23.7 E-3 | 15.4 E-3 | 18.2 E-3 | 10.3 E-6 | 2.39 E-3 | 15.8 E-3 | 19.5 E-3 | 23.7 E-3 | 15.4 E-3 | 18.2 E-3 | 0.00 | 0.26 | 3.21 | 7.34 | 12.2 | 8.31 | 9.46 | 1.000 | 1.003 | 1.033 | 1.079 | 1.140 | 1.091 | 1.104 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2ea39 | qmckl_compute_jastrow_champ_factor_en_gl_hpc | qmckl_jastrow_champ.c:2443 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 1.458 | 0.732 | 0.365 | 0.193 | 0.103 | 58.9 E-3 | 30.6 E-3 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 557 E-6 | 679 E-6 | 10.1 E-3 | 11.1 E-3 | 2.48 E-3 | 1.95 E-3 | 0.0 | 553 E-6 | 676 E-6 | 10.1 E-3 | 11.1 E-3 | 2.47 E-3 | 1.95 E-3 | 0 | 0.08 | 0.19 | 5.21 | 10.8 | 4.20 | 6.37 | 1.000 | 1.001 | 1.002 | 1.055 | 1.121 | 1.044 | 1.068 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2d6a8 | qmckl_compute_jastrow_champ_factor_en_hpc | qmckl_jastrow_champ.c:2276 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 0.877 | 0.445 | 0.223 | 0.122 | 64.9 E-3 | 40.4 E-3 | 25.9 E-3 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 0.0 | 1.53 E-3 | 3.17 E-3 | 9.82 E-3 | 8.65 E-3 | 5.13 E-3 | 6.20 E-3 | 0.0 | 1.53 E-3 | 3.16 E-3 | 9.82 E-3 | 8.64 E-3 | 5.12 E-3 | 6.20 E-3 | 0 | 0.35 | 1.42 | 8.07 | 13.3 | 12.7 | 23.9 | 1.000 | 1.003 | 1.014 | 1.088 | 1.154 | 1.146 | 1.315 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2a265 | qmckl_compute_jastrow_champ_factor_ee_hpc | qmckl_jastrow_champ.c:1432 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 0.487 | 0.456 | 0.500 | 0.468 | 0.468 | 0.507 | 0.612 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 0.0 | 55.2 E-6 | 133 E-6 | 185 E-6 | 794 E-6 | 693 E-6 | 17.3 E-3 | 0.0 | 45.5 E-6 | 122 E-6 | 171 E-6 | 778 E-6 | 678 E-6 | 17.2 E-3 | 0 | 0.01 | 0.03 | 0.04 | 0.17 | 0.14 | 2.82 | 1.000 | 1.000 | 1.000 | 1.000 | 1.002 | 1.001 | 1.029 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x29de9 | qmckl_compute_ee_distance_rescaled_hpc | qmckl_jastrow_champ.c:1851 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 85.6 E-3 | 43.1 E-3 | 22.0 E-3 | 12.1 E-3 | 8.03 E-3 | 7.46 E-3 | 25.6 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 4.28 E-6 | 53.1 E-6 | 164 E-6 | 659 E-6 | 755 E-6 | 426 E-6 | 12.7 E-3 | 497 E-9 | 46.4 E-6 | 155 E-6 | 651 E-6 | 747 E-6 | 416 E-6 | 12.7 E-3 | 0.00 | 0.12 | 0.75 | 5.44 | 9.41 | 5.71 | 49.6 | 1.000 | 1.001 | 1.008 | 1.058 | 1.104 | 1.061 | 1.982 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2e20e | qmckl_compute_en_distance_rescaled_gl_hpc | qmckl_jastrow_champ.c:2794 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 44.5 E-3 | 22.5 E-3 | 11.6 E-3 | 6.35 E-3 | 4.02 E-3 | 3.82 E-3 | 3.42 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.68 E-6 | 261 E-6 | 244 E-6 | 518 E-6 | 610 E-6 | 747 E-6 | 339 E-6 | 276 E-9 | 260 E-6 | 243 E-6 | 518 E-6 | 609 E-6 | 746 E-6 | 337 E-6 | 0.00 | 1.16 | 2.10 | 8.16 | 15.2 | 19.5 | 9.89 | 1.000 | 1.012 | 1.021 | 1.089 | 1.179 | 1.243 | 1.110 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2cf85 | qmckl_compute_en_distance_rescaled_hpc | qmckl_jastrow_champ.c:2638 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 20.6 E-3 | 10.4 E-3 | 5.23 E-3 | 2.75 E-3 | 1.53 E-3 | 895 E-6 | 1.46 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.30 E-6 | 7.25 E-6 | 28.0 E-6 | 128 E-6 | 183 E-6 | 48.7 E-6 | 850 E-6 | 464 E-9 | 6.11 E-6 | 27.0 E-6 | 127 E-6 | 182 E-6 | 48.0 E-6 | 849 E-6 | 0.01 | 0.07 | 0.53 | 4.64 | 12.0 | 5.44 | 58.3 | 1.000 | 1.001 | 1.005 | 1.049 | 1.136 | 1.058 | 2.401 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
