| | | | | | | 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.0.0.0:0x3438d | qmckl_compute_dtmp_c_hpc | qmckl_jastrow_champ.c:4124 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 83.639 | 41.993 | 22.951 | 11.727 | 6.166 | 4.247 | 4.014 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 3.39 E-3 | 1.466 | 0.644 | 0.498 | 0.412 | 0.574 | 0.0 | 3.38 E-3 | 1.466 | 0.644 | 0.498 | 0.412 | 0.574 | 0 | 0.01 | 6.39 | 5.49 | 8.08 | 9.69 | 14.3 | 1.000 | 1.000 | 1.068 | 1.058 | 1.088 | 1.107 | 1.167 | 1.000 | 1.000 | 1.015 | 1.009 | 1.008 | 1.007 | 1.009 |
| libqmckl.so.0.0.0:0x33baa | qmckl_compute_tmp_c_hpc | qmckl_jastrow_champ.c:4054 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 43.471 | 21.847 | 11.810 | 6.218 | 3.222 | 2.211 | 2.064 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 0.0 | 6.30 E-3 | 0.629 | 0.439 | 0.259 | 0.186 | 0.267 | 0.0 | 6.28 E-3 | 0.629 | 0.439 | 0.259 | 0.186 | 0.267 | 0 | 0.03 | 5.32 | 7.05 | 8.04 | 8.42 | 12.9 | 1.000 | 1.000 | 1.056 | 1.076 | 1.087 | 1.092 | 1.148 | 1.000 | 1.000 | 1.007 | 1.006 | 1.004 | 1.003 | 1.004 |
| libqmckl.so.0.0.0:0x3543c | qmckl_compute_jastrow_champ_factor_een_gl_hpc | qmckl_jastrow_champ.c:4506 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 10.123 | 5.454 | 3.039 | 1.964 | 1.618 | 1.706 | 2.031 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 956 E-6 | 25.1 E-3 | 69.6 E-3 | 73.3 E-3 | 82.9 E-3 | 0.207 | 0.0 | 950 E-6 | 25.1 E-3 | 69.6 E-3 | 73.3 E-3 | 82.9 E-3 | 0.207 | 0 | 0.02 | 0.83 | 3.54 | 4.53 | 4.86 | 10.2 | 1.000 | 1.000 | 1.008 | 1.037 | 1.047 | 1.051 | 1.114 | 1.000 | 1.000 | 1.000 | 1.001 | 1.001 | 1.001 | 1.003 |
| libqmckl.so.0.0.0:0x3169c | qmckl_compute_jastrow_champ_factor_een_rescaled_e_gl_hpc | qmckl_jastrow_champ.c:3196 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 8.783 | 4.559 | 3.345 | 1.911 | 1.339 | 1.141 | 1.128 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 7.94 E-3 | 0.646 | 0.338 | 0.166 | 59.9 E-3 | 0.110 | 0.0 | 7.93 E-3 | 0.646 | 0.338 | 0.166 | 59.9 E-3 | 0.110 | 0 | 0.17 | 19.3 | 17.7 | 12.4 | 5.26 | 9.72 | 1.000 | 1.002 | 1.240 | 1.215 | 1.142 | 1.055 | 1.108 | 1.000 | 1.000 | 1.007 | 1.004 | 1.003 | 1.001 | 1.002 |
| libqmckl.so.0.0.0:0x2fba1 | qmckl_compute_een_rescaled_e_hpc | qmckl_jastrow_champ.c:2970 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 7.880 | 4.516 | 2.862 | 2.079 | 1.470 | 1.266 | 1.325 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 41.9 E-6 | 3.63 E-3 | 0.231 | 0.375 | 0.269 | 0.102 | 78.6 E-3 | 15.9 E-6 | 3.58 E-3 | 0.231 | 0.375 | 0.269 | 0.102 | 78.5 E-3 | 0.00 | 0.08 | 8.08 | 18.0 | 18.3 | 8.05 | 5.93 | 1.000 | 1.001 | 1.088 | 1.220 | 1.224 | 1.088 | 1.063 | 1.000 | 1.000 | 1.002 | 1.005 | 1.004 | 1.002 | 1.001 |
| libqmckl.so.0.0.0:0x2bde9 | 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 | 1.510 | 0.789 | 0.424 | 0.245 | 0.126 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 973 E-6 | 13.7 E-3 | 37.1 E-3 | 48.1 E-3 | 13.6 E-3 | 7.94 E-3 | 0.0 | 969 E-6 | 13.7 E-3 | 37.1 E-3 | 48.1 E-3 | 13.6 E-3 | 7.94 E-3 | 0 | 0.03 | 0.91 | 4.70 | 11.4 | 5.54 | 6.31 | 1.000 | 1.000 | 1.009 | 1.049 | 1.128 | 1.059 | 1.067 | 1.000 | 1.000 | 1.000 | 1.000 | 1.001 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2b871 | qmckl_compute_ee_distance_rescaled_gl_hpc | qmckl_jastrow_champ.c:1984 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 1.869 | 0.934 | 0.492 | 0.266 | 0.190 | 0.193 | 0.189 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 12.7 E-6 | 3.67 E-3 | 16.7 E-3 | 19.1 E-3 | 22.7 E-3 | 13.2 E-3 | 17.2 E-3 | 2.96 E-6 | 3.65 E-3 | 16.7 E-3 | 19.1 E-3 | 22.7 E-3 | 13.2 E-3 | 17.1 E-3 | 0.00 | 0.39 | 3.40 | 7.19 | 12.0 | 6.84 | 9.07 | 1.000 | 1.004 | 1.035 | 1.077 | 1.136 | 1.073 | 1.100 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2eb59 | qmckl_compute_jastrow_champ_factor_en_gl_hpc | qmckl_jastrow_champ.c:2446 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 1.458 | 0.732 | 0.366 | 0.191 | 0.103 | 59.1 E-3 | 30.3 E-3 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 10.0 | 0.0 | 703 E-6 | 993 E-6 | 7.75 E-3 | 11.4 E-3 | 2.65 E-3 | 1.47 E-3 | 0.0 | 699 E-6 | 990 E-6 | 7.74 E-3 | 11.4 E-3 | 2.65 E-3 | 1.47 E-3 | 0 | 0.10 | 0.27 | 4.06 | 11.0 | 4.48 | 4.86 | 1.000 | 1.001 | 1.003 | 1.042 | 1.124 | 1.047 | 1.051 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2d7c8 | qmckl_compute_jastrow_champ_factor_en_hpc | qmckl_jastrow_champ.c:2277 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 0.879 | 0.446 | 0.225 | 0.123 | 65.7 E-3 | 41.8 E-3 | 25.1 E-3 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 0.0 | 1.62 E-3 | 4.08 E-3 | 10.9 E-3 | 9.57 E-3 | 5.77 E-3 | 5.62 E-3 | 0.0 | 1.61 E-3 | 4.07 E-3 | 10.9 E-3 | 9.56 E-3 | 5.77 E-3 | 5.62 E-3 | 0 | 0.36 | 1.81 | 8.84 | 14.6 | 13.8 | 22.4 | 1.000 | 1.004 | 1.018 | 1.097 | 1.171 | 1.160 | 1.289 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2a385 | qmckl_compute_jastrow_champ_factor_ee_hpc | qmckl_jastrow_champ.c:1432 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 0.498 | 0.467 | 0.482 | 0.507 | 0.503 | 0.547 | 0.616 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 20.0 | 0.0 | 57.7 E-6 | 468 E-6 | 167 E-6 | 1.08 E-3 | 2.01 E-3 | 13.4 E-3 | 0.0 | 46.3 E-6 | 454 E-6 | 151 E-6 | 1.07 E-3 | 1.99 E-3 | 13.4 E-3 | 0 | 0.01 | 0.10 | 0.03 | 0.21 | 0.37 | 2.18 | 1.000 | 1.000 | 1.001 | 1.000 | 1.002 | 1.004 | 1.022 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x29f09 | 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 | 12.0 E-3 | 8.56 E-3 | 8.84 E-3 | 19.4 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 4.84 E-6 | 58.2 E-6 | 151 E-6 | 559 E-6 | 757 E-6 | 1.58 E-3 | 7.32 E-3 | 392 E-9 | 49.8 E-6 | 142 E-6 | 552 E-6 | 750 E-6 | 1.57 E-3 | 7.31 E-3 | 0.01 | 0.14 | 0.69 | 4.66 | 8.85 | 17.8 | 37.7 | 1.000 | 1.001 | 1.007 | 1.049 | 1.097 | 1.217 | 1.605 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2e32e | qmckl_compute_en_distance_rescaled_gl_hpc | qmckl_jastrow_champ.c:2798 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 44.5 E-3 | 22.4 E-3 | 11.6 E-3 | 6.33 E-3 | 4.03 E-3 | 3.78 E-3 | 3.44 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.35 E-6 | 180 E-6 | 237 E-6 | 487 E-6 | 654 E-6 | 413 E-6 | 370 E-6 | 321 E-9 | 179 E-6 | 236 E-6 | 486 E-6 | 653 E-6 | 412 E-6 | 369 E-6 | 0.00 | 0.81 | 2.05 | 7.70 | 16.2 | 10.9 | 10.8 | 1.000 | 1.008 | 1.021 | 1.083 | 1.194 | 1.123 | 1.121 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
| libqmckl.so.0.0.0:0x2d0a5 | qmckl_compute_en_distance_rescaled_hpc | qmckl_jastrow_champ.c:2642 | 0 | 0 | runtime | parallel | 1 | 2 | 4 | 8 | 16 | 26 | 52 | 20.6 E-3 | 10.3 E-3 | 5.24 E-3 | 2.76 E-3 | 1.49 E-3 | 901 E-6 | 1.24 E-3 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.37 E-6 | 15.1 E-6 | 37.6 E-6 | 137 E-6 | 162 E-6 | 58.8 E-6 | 629 E-6 | 516 E-9 | 13.9 E-6 | 36.7 E-6 | 136 E-6 | 161 E-6 | 58.2 E-6 | 629 E-6 | 0.01 | 0.15 | 0.72 | 4.95 | 10.9 | 6.53 | 50.7 | 1.000 | 1.001 | 1.007 | 1.052 | 1.122 | 1.070 | 2.027 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 | 1.000 |
