b_eff = 1316.320 MB/s = 658.160 * 2 PEs with 256 MB/PE on SUPER-UX hwwsx4 9.1 Rev1 SX-4 SECTION-HEAD-BEGIN b_eff.c, Revision 3.2 from Nov. 07, 1999 MEMORY_PER_PROCESSOR = 256 MBytes [1M = 1024*1024] 1-dim-paterns: size = 2 1-dim-paterns: size = 2 2-dim-paterns: size = 2 * 1 3-dim-paterns: size = 2 * 1 * 1 Used message lengths (and used loop length for each message lengths): msglng= 1 (300), 2 (300), 4 (300), 8 (300), 16 (300), 32 (300), 64 (300), 128 (300), 256 (300), 512 (300), 1024 (300), 2048 (300), 4096 (300), 8933 (234), 19484 (107), 42495 (49), 92682 (22), 202141 (10), 440872 (4), 961548 (2), 2097152 (1), SECTION-HEAD-END SECTION-LOOP-BEGIN measurment loop: elapsed time = 39.631 sec sum of max elapsed time per entries above = 39.393 sec difference = 0.239 sec = 0.6% The difference is less than 5 % SECTION-LOOP-END SECTION-PATTERN-BEGIN Pattern parameters: p00 ring-1*2fix => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p01 ring-1*2fix => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p02 ring-1*2fix => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p03 ring-1*2fix => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p04 ring-1*2fix => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p05 ring-1*2fix => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p06 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p07 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p08 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p09 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p10 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p11 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p12 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p13 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p14 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p15 random-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p16 worst-cyc-1dim => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p17 best bi-section => 2 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p18 worst bi-section => 2 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p19 acyclic-1dim-all => 2 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p20 acyclic-2dim-all => 2 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p21 acyclic-3dim-all => 2 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p22 cyclic-1dim-all => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p23 cyclic-2dim-all => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used p24 cyclic-3dim-all => 1 sendrecv_calls with 2 messages, i.e. 4.2 msgs/used node, all nodes are used SECTION-PATTERN-END Printing accumulated bandwidth / number of processes = bandwidth per process (in MBytes/sec = 1e6 Bytes/sec) Additionally the accumulated value processes is printed in the last column Only the cyclic and random patterns are used to compute b_eff (except p00), the other patterns are only as information. SECTION-BY-METHODS-BEGIN 2nd analysis path, only as information, last row: for all mthd: logavg_pat ( avg_L ( max_rep ( b(L) ) ) ) || logavg_pat ( max_mthd ( avg_L ( max_rep ( b(L) ) ) ) ) pattern / methods: Sndrcv Alltoal non-blk -> best method -> accumulated p00 ring-1*2fix : 658.114 561.552 612.066 -> 658.114 -> 1316.229 MByte/s p01 ring-1*2fix : 657.961 558.408 612.807 -> 657.961 -> 1315.922 MByte/s p02 ring-1*2fix : 658.088 561.097 612.996 -> 658.088 -> 1316.176 MByte/s p03 ring-1*2fix : 658.095 559.508 613.045 -> 658.095 -> 1316.190 MByte/s p04 ring-1*2fix : 658.485 562.995 612.704 -> 658.485 -> 1316.969 MByte/s p05 ring-1*2fix : 657.398 557.956 613.056 -> 657.398 -> 1314.796 MByte/s p06 random-cyc-1dim : 657.695 561.835 613.119 -> 657.695 -> 1315.390 MByte/s p07 random-cyc-1dim : 657.637 559.368 612.025 -> 657.637 -> 1315.274 MByte/s p08 random-cyc-1dim : 657.769 558.080 611.726 -> 657.769 -> 1315.538 MByte/s p09 random-cyc-1dim : 657.051 560.716 612.045 -> 657.051 -> 1314.102 MByte/s p10 random-cyc-1dim : 656.852 556.158 612.164 -> 656.852 -> 1313.705 MByte/s p11 random-cyc-1dim : 657.715 565.570 611.629 -> 657.715 -> 1315.430 MByte/s p12 random-cyc-1dim : 656.070 554.545 611.703 -> 656.070 -> 1312.140 MByte/s p13 random-cyc-1dim : 655.330 556.712 611.406 -> 655.330 -> 1310.659 MByte/s p14 random-cyc-1dim : 657.854 552.528 610.550 -> 657.854 -> 1315.707 MByte/s p15 random-cyc-1dim : 656.552 558.842 612.902 -> 656.552 -> 1313.104 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 656.823 552.984 612.671 -> 656.823 -> 1313.647 MByte/s p17 best bi-section : 407.711 559.256 578.622 -> 578.622 -> 1157.244 MByte/s p18 worst bi-section : 407.626 566.880 578.860 -> 578.860 -> 1157.719 MByte/s p19 acyclic-1dim-all : 408.131 570.723 579.612 -> 579.612 -> 1159.224 MByte/s p20 acyclic-2dim-all : 407.862 564.801 579.279 -> 579.279 -> 1158.558 MByte/s p21 acyclic-3dim-all : 407.566 563.527 578.554 -> 578.554 -> 1157.108 MByte/s p22 cyclic-1dim-all : 657.367 564.588 610.901 -> 657.367 -> 1314.735 MByte/s p23 cyclic-2dim-all : 657.214 558.015 612.952 -> 657.214 -> 1314.428 MByte/s p24 cyclic-3dim-all : 657.284 556.280 612.698 -> 657.284 -> 1314.568 MByte/s log_avg of all rings : 658.023 560.250 612.779 || 658.023 -> 1316.047 MByte/s log_avg of all random : 657.052 558.424 611.927 || 657.052 -> 1314.104 MByte/s log_avg(ring,random) : 657.538 559.336 612.353 ||(657.538 -> 1315.075)MByte/s SECTION-BY-METHODS-END SECTION-BY-REPETITIONS-BEGIN 3rd analysis path, only as information, last row: for all rep.:logavg_pat ( avg_L ( max_mthd ( b(L) ) ) ) || logavg_pat ( max_rep ( avg_L ( max_mthd ( b(L) ) ) ) ) pattern / repetition: rep.0 rep.1 rep.2 -> best repetition -> accumulated p00 ring-1*2fix : 657.738 655.802 634.192 -> 657.738 -> 1315.476 MByte/s p01 ring-1*2fix : 657.124 646.654 650.677 -> 657.124 -> 1314.248 MByte/s p02 ring-1*2fix : 657.478 646.042 639.606 -> 657.478 -> 1314.956 MByte/s p03 ring-1*2fix : 657.330 644.155 648.954 -> 657.330 -> 1314.661 MByte/s p04 ring-1*2fix : 659.872 655.578 655.715 -> 659.872 -> 1319.745 MByte/s p05 ring-1*2fix : 657.649 647.349 649.322 -> 657.649 -> 1315.299 MByte/s p06 random-cyc-1dim : 657.345 643.147 644.369 -> 657.345 -> 1314.689 MByte/s p07 random-cyc-1dim : 656.385 655.733 650.282 -> 656.385 -> 1312.770 MByte/s p08 random-cyc-1dim : 653.861 648.643 647.385 -> 653.861 -> 1307.722 MByte/s p09 random-cyc-1dim : 656.836 654.653 647.386 -> 656.836 -> 1313.673 MByte/s p10 random-cyc-1dim : 654.980 641.764 647.113 -> 654.980 -> 1309.961 MByte/s p11 random-cyc-1dim : 655.028 658.885 655.869 -> 658.885 -> 1317.771 MByte/s p12 random-cyc-1dim : 655.727 649.022 653.901 -> 655.727 -> 1311.455 MByte/s p13 random-cyc-1dim : 650.737 639.549 648.881 -> 650.737 -> 1301.474 MByte/s p14 random-cyc-1dim : 655.437 653.743 646.481 -> 655.437 -> 1310.874 MByte/s p15 random-cyc-1dim : 656.713 648.425 652.458 -> 656.713 -> 1313.426 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 650.309 642.582 641.700 -> 650.309 -> 1300.618 MByte/s p17 best bi-section : 582.621 573.661 576.092 -> 582.621 -> 1165.242 MByte/s p18 worst bi-section : 586.215 587.030 588.628 -> 588.628 -> 1177.256 MByte/s p19 acyclic-1dim-all : 591.659 590.624 580.460 -> 591.659 -> 1183.318 MByte/s p20 acyclic-2dim-all : 589.779 591.545 568.208 -> 591.545 -> 1183.091 MByte/s p21 acyclic-3dim-all : 590.247 573.643 568.914 -> 590.247 -> 1180.495 MByte/s p22 cyclic-1dim-all : 655.519 649.215 647.058 -> 655.519 -> 1311.039 MByte/s p23 cyclic-2dim-all : 654.604 639.557 649.950 -> 654.604 -> 1309.209 MByte/s p24 cyclic-3dim-all : 656.438 655.326 651.011 -> 656.438 -> 1312.876 MByte/s log_avg of all rings : 657.865 649.247 646.370 || 657.865 -> 1315.729 MByte/s log_avg of all random : 655.303 649.328 649.403 || 655.687 -> 1311.375 MByte/s log_avg(ring,random) : 656.582 649.287 647.885 ||(656.775 -> 1313.550)MByte/s SECTION-BY-REPETITIONS-END SECTION-BY-MTHD-MSGLNG-BEGIN 4th analysis path, only as information, last 3 rows: for all methods and some msglng L: logavg_pat ( max_rep ( b(L) ) ) for all methods: logavg_pat ( avg_L ( max_rep ( b(L) ) ) ) pattern & method / msg: 1 16 256 4096 92682 2097152 -> average -> accumulated p00 ring-1*2fix p00 method 0 : 0.051 0.846 13.353 164.509 1466.774 3568.430 -> 658.114 -> 1316.229 MByte/s p00 method 1 : 0.015 0.326 5.093 80.936 893.751 3454.445 -> 561.552 -> 1123.104 MByte/s p00 method 2 : 0.035 0.574 8.980 126.437 1222.542 3541.482 -> 612.066 -> 1224.132 MByte/s p01 ring-1*2fix p01 method 0 : 0.051 0.848 13.366 164.299 1467.458 3569.986 -> 657.961 -> 1315.922 MByte/s p01 method 1 : 0.015 0.322 4.732 73.190 865.987 3486.653 -> 558.408 -> 1116.816 MByte/s p01 method 2 : 0.032 0.536 8.986 119.404 1224.827 3550.644 -> 612.807 -> 1225.615 MByte/s p02 ring-1*2fix p02 method 0 : 0.051 0.847 13.363 164.337 1468.185 3575.391 -> 658.088 -> 1316.176 MByte/s p02 method 1 : 0.015 0.298 4.735 86.132 888.579 3466.872 -> 561.097 -> 1122.194 MByte/s p02 method 2 : 0.035 0.530 8.981 126.550 1224.480 3546.752 -> 612.996 -> 1225.992 MByte/s p03 ring-1*2fix p03 method 0 : 0.051 0.848 13.358 164.507 1467.551 3572.418 -> 658.095 -> 1316.190 MByte/s p03 method 1 : 0.015 0.339 5.395 78.843 879.797 3463.207 -> 559.508 -> 1119.016 MByte/s p03 method 2 : 0.035 0.572 8.979 126.381 1223.487 3546.704 -> 613.045 -> 1226.090 MByte/s p04 ring-1*2fix p04 method 0 : 0.051 0.847 13.361 164.365 1467.771 3573.830 -> 658.485 -> 1316.969 MByte/s p04 method 1 : 0.015 0.315 4.730 85.821 885.418 3414.667 -> 562.995 -> 1125.990 MByte/s p04 method 2 : 0.035 0.573 8.975 126.397 1223.070 3544.450 -> 612.704 -> 1225.409 MByte/s p05 ring-1*2fix p05 method 0 : 0.051 0.847 13.356 164.360 1465.669 3570.375 -> 657.398 -> 1314.796 MByte/s p05 method 1 : 0.015 0.339 5.381 81.743 874.565 3478.510 -> 557.956 -> 1115.912 MByte/s p05 method 2 : 0.035 0.571 8.973 126.652 1221.434 3543.445 -> 613.056 -> 1226.113 MByte/s p06 random-cyc-1dim p06 method 0 : 0.051 0.847 13.363 164.663 1465.248 3572.904 -> 657.695 -> 1315.390 MByte/s p06 method 1 : 0.014 0.325 4.710 76.542 891.167 3369.244 -> 561.835 -> 1123.669 MByte/s p06 method 2 : 0.035 0.572 8.959 126.645 1223.774 3548.048 -> 613.119 -> 1226.238 MByte/s p07 random-cyc-1dim p07 method 0 : 0.051 0.846 13.352 164.634 1462.306 3572.953 -> 657.637 -> 1315.274 MByte/s p07 method 1 : 0.015 0.310 5.469 88.613 872.004 3374.883 -> 559.368 -> 1118.737 MByte/s p07 method 2 : 0.035 0.573 8.960 126.644 1214.694 3545.792 -> 612.025 -> 1224.050 MByte/s p08 random-cyc-1dim p08 method 0 : 0.051 0.847 13.357 164.735 1463.364 3574.708 -> 657.769 -> 1315.538 MByte/s p08 method 1 : 0.015 0.322 4.713 85.024 890.389 3437.369 -> 558.080 -> 1116.159 MByte/s p08 method 2 : 0.035 0.572 8.964 126.634 1222.507 3532.034 -> 611.726 -> 1223.452 MByte/s p09 random-cyc-1dim p09 method 0 : 0.051 0.845 13.357 164.666 1466.082 3567.507 -> 657.051 -> 1314.102 MByte/s p09 method 1 : 0.016 0.298 5.199 74.967 901.668 3435.161 -> 560.716 -> 1121.432 MByte/s p09 method 2 : 0.035 0.573 8.968 126.581 1217.909 3550.019 -> 612.045 -> 1224.090 MByte/s p10 random-cyc-1dim p10 method 0 : 0.051 0.847 13.354 164.445 1460.680 3575.097 -> 656.852 -> 1313.705 MByte/s p10 method 1 : 0.014 0.331 4.854 75.087 890.143 3436.827 -> 556.158 -> 1112.316 MByte/s p10 method 2 : 0.035 0.572 8.972 126.550 1222.102 3547.952 -> 612.164 -> 1224.328 MByte/s p11 random-cyc-1dim p11 method 0 : 0.049 0.847 13.353 164.491 1463.843 3575.195 -> 657.715 -> 1315.430 MByte/s p11 method 1 : 0.014 0.337 4.789 85.372 881.504 3419.566 -> 565.570 -> 1131.141 MByte/s p11 method 2 : 0.035 0.573 8.972 126.611 1221.639 3530.892 -> 611.629 -> 1223.258 MByte/s p12 random-cyc-1dim p12 method 0 : 0.051 0.848 13.359 159.108 1459.200 3565.615 -> 656.070 -> 1312.140 MByte/s p12 method 1 : 0.014 0.336 5.004 80.977 876.891 3401.375 -> 554.545 -> 1109.090 MByte/s p12 method 2 : 0.035 0.571 8.976 122.571 1216.317 3548.817 -> 611.703 -> 1223.406 MByte/s p13 random-cyc-1dim p13 method 0 : 0.051 0.847 13.359 164.482 1461.207 3567.848 -> 655.330 -> 1310.659 MByte/s p13 method 1 : 0.014 0.323 4.719 85.639 866.316 3453.535 -> 556.712 -> 1113.425 MByte/s p13 method 2 : 0.035 0.572 8.972 125.889 1220.113 3540.573 -> 611.406 -> 1222.811 MByte/s p14 random-cyc-1dim p14 method 0 : 0.051 0.848 13.361 163.491 1463.313 3574.122 -> 657.854 -> 1315.707 MByte/s p14 method 1 : 0.014 0.303 5.091 82.103 883.953 3365.437 -> 552.528 -> 1105.055 MByte/s p14 method 2 : 0.033 0.573 8.977 126.028 1220.411 3537.182 -> 610.550 -> 1221.101 MByte/s p15 random-cyc-1dim p15 method 0 : 0.051 0.847 13.365 163.587 1462.457 3572.758 -> 656.552 -> 1313.104 MByte/s p15 method 1 : 0.015 0.324 5.156 77.065 881.516 3370.327 -> 558.842 -> 1117.683 MByte/s p15 method 2 : 0.035 0.572 8.976 126.090 1220.183 3544.834 -> 612.902 -> 1225.805 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim p16 method 0 : 0.051 0.845 13.365 164.610 1462.356 3572.904 -> 656.823 -> 1313.647 MByte/s p16 method 1 : 0.015 0.340 4.911 81.791 892.109 3382.809 -> 552.984 -> 1105.967 MByte/s p16 method 2 : 0.035 0.573 8.981 126.600 1221.757 3541.482 -> 612.671 -> 1225.342 MByte/s p17 best bi-section p17 method 0 : 0.039 0.651 10.181 117.209 840.158 2448.183 -> 407.711 -> 815.422 MByte/s p17 method 1 : 0.015 0.334 5.272 81.606 884.944 3444.866 -> 559.256 -> 1118.512 MByte/s p17 method 2 : 0.027 0.440 6.897 99.195 1092.438 3496.326 -> 578.622 -> 1157.244 MByte/s p18 worst bi-section p18 method 0 : 0.039 0.651 10.146 117.214 839.738 2448.320 -> 407.626 -> 815.253 MByte/s p18 method 1 : 0.015 0.296 5.021 74.126 900.267 3501.182 -> 566.880 -> 1133.761 MByte/s p18 method 2 : 0.027 0.441 6.889 99.191 1094.234 3495.394 -> 578.860 -> 1157.719 MByte/s p19 acyclic-1dim-all p19 method 0 : 0.039 0.651 10.163 117.220 842.658 2446.926 -> 408.131 -> 816.263 MByte/s p19 method 1 : 0.014 0.310 4.488 84.119 888.114 3511.028 -> 570.723 -> 1141.446 MByte/s p19 method 2 : 0.027 0.440 6.587 99.171 1098.980 3496.138 -> 579.612 -> 1159.224 MByte/s p20 acyclic-2dim-all p20 method 0 : 0.039 0.652 10.193 117.192 842.480 2449.349 -> 407.862 -> 815.723 MByte/s p20 method 1 : 0.015 0.295 4.656 74.086 901.678 3433.902 -> 564.801 -> 1129.602 MByte/s p20 method 2 : 0.027 0.441 6.887 99.175 1099.450 3499.780 -> 579.279 -> 1158.558 MByte/s p21 acyclic-3dim-all p21 method 0 : 0.039 0.651 10.179 117.184 838.208 2445.100 -> 407.566 -> 815.132 MByte/s p21 method 1 : 0.015 0.296 5.253 78.300 902.243 3509.902 -> 563.527 -> 1127.054 MByte/s p21 method 2 : 0.027 0.440 6.893 99.066 1098.885 3493.996 -> 578.554 -> 1157.108 MByte/s p22 cyclic-1dim-all p22 method 0 : 0.051 0.848 13.358 164.339 1462.339 3573.100 -> 657.367 -> 1314.735 MByte/s p22 method 1 : 0.016 0.298 5.450 88.059 924.313 3462.201 -> 564.588 -> 1129.176 MByte/s p22 method 2 : 0.035 0.569 8.912 125.951 1223.851 3538.040 -> 610.901 -> 1221.803 MByte/s p23 cyclic-2dim-all p23 method 0 : 0.051 0.847 13.362 164.398 1466.715 3568.480 -> 657.214 -> 1314.428 MByte/s p23 method 1 : 0.015 0.343 5.173 88.189 887.394 3391.299 -> 558.015 -> 1116.029 MByte/s p23 method 2 : 0.035 0.569 8.920 126.089 1228.706 3541.720 -> 612.952 -> 1225.904 MByte/s p24 cyclic-3dim-all p24 method 0 : 0.048 0.847 13.353 164.449 1467.957 3572.076 -> 657.284 -> 1314.568 MByte/s p24 method 1 : 0.015 0.343 4.809 88.287 878.203 3442.558 -> 556.280 -> 1112.560 MByte/s p24 method 2 : 0.035 0.568 8.905 126.051 1224.315 3545.505 -> 612.698 -> 1225.396 MByte/s log_avg of all rings - ring, method 0 : 0.051 0.847 13.360 164.396 1467.235 3571.738 || 658.023 -> 1316.047 MByte/s - ring, method 1 : 0.015 0.323 5.002 80.989 881.302 3460.648 || 560.250 -> 1120.500 MByte/s - ring, method 2 : 0.034 0.559 8.979 125.275 1223.306 3545.578 || 612.779 -> 1225.558 MByte/s log_avg of all random - random, method 0 : 0.051 0.847 13.358 163.822 1462.769 3571.869 || 657.052 -> 1314.104 MByte/s - random, method 1 : 0.015 0.321 4.964 81.002 883.501 3406.219 || 558.424 -> 1116.848 MByte/s - random, method 2 : 0.035 0.572 8.970 126.019 1219.962 3542.608 || 611.927 -> 1223.853 MByte/s log_avg(ring,random) - average, method 0 : 0.051 0.847 13.359 164.109 1465.000 3571.803 || 657.538 -> 1315.075 MByte/s - average, method 1 : 0.015 0.322 4.983 80.995 882.401 3433.326 || 559.336 -> 1118.672 MByte/s - average, method 2 : 0.035 0.566 8.974 125.646 1221.633 3544.093 || 612.353 -> 1224.705 MByte/s SECTION-BY-MTHD-MSGLNG-END SECTION-BY-MSGLNG-BEGIN 5th analysis path only as information: logavg_pat ( max_mthd ( max_rep ( b(L) ) ) ) and for all methods: logavg_pat ( max_rep ( b(L) ) ) msg length|accumulated| effective bandwidth per process: msg length| effective| average rings random methd_1 methd_2 methd_3 | bandwidth| crt,rnd only only Sendrcv Alltoall non-blk 1 0.102 0.051 0.051 0.051 0.051 0.015 0.035 2 0.201 0.101 0.100 0.101 0.101 0.029 0.069 4 0.412 0.206 0.207 0.204 0.206 0.078 0.140 8 0.840 0.420 0.423 0.416 0.420 0.158 0.283 16 1.694 0.847 0.847 0.847 0.847 0.322 0.566 32 3.378 1.689 1.689 1.689 1.689 0.636 1.130 64 6.725 3.362 3.364 3.361 3.362 1.297 2.267 128 13.346 6.673 6.673 6.673 6.673 2.509 4.450 256 26.718 13.359 13.360 13.358 13.359 4.983 8.974 512 53.389 26.694 26.695 26.694 26.694 10.057 17.801 1024 106.437 53.219 53.233 53.204 53.219 20.352 35.718 2048 165.140 82.570 82.759 82.381 82.570 41.558 62.929 4096 328.218 164.109 164.396 163.822 164.109 80.995 125.646 8933 424.382 212.191 212.370 212.012 212.191 119.571 163.787 19484 1137.951 568.976 569.274 568.678 568.976 307.432 480.263 42495 1683.741 841.870 842.269 841.472 841.870 465.998 674.346 92682 2930.000 1465.000 1467.235 1462.769 1465.000 882.401 1221.633 202141 3391.216 1695.608 1695.493 1695.722 1695.608 1544.077 1564.527 440872 5688.447 2844.224 2845.376 2843.071 2844.224 2565.098 2726.974 961548 4536.630 2268.315 2273.266 2263.375 2255.289 2263.690 2223.709 2097152 7143.607 3571.803 3571.738 3571.869 3571.803 3433.326 3544.093 SECTION-BY-MSGLNG-END SECTION-BY-PATTERN-MSGLNG-BEGIN official (1st) analysis path -- see last column: (only columns of some message lengths are printed) logavg_pat ( avg_L ( max_mthd ( max_rep ( b(L) ) ) ) ) pattern / msg-length: 1 16 256 4096 92682 2097152 -> average -> accumulated p00 ring-1*2fix : 0.051 0.846 13.353 164.509 1466.774 3568.430 -> 658.114 -> 1316.229 MByte/s p01 ring-1*2fix : 0.051 0.848 13.366 164.299 1467.458 3569.986 -> 657.961 -> 1315.922 MByte/s p02 ring-1*2fix : 0.051 0.847 13.363 164.337 1468.185 3575.391 -> 658.915 -> 1317.831 MByte/s p03 ring-1*2fix : 0.051 0.848 13.358 164.507 1467.551 3572.418 -> 658.095 -> 1316.190 MByte/s p04 ring-1*2fix : 0.051 0.847 13.361 164.365 1467.771 3573.830 -> 660.539 -> 1321.078 MByte/s p05 ring-1*2fix : 0.051 0.847 13.356 164.360 1465.669 3570.375 -> 658.057 -> 1316.115 MByte/s p06 random-cyc-1dim : 0.051 0.847 13.363 164.663 1465.248 3572.904 -> 658.181 -> 1316.361 MByte/s p07 random-cyc-1dim : 0.051 0.846 13.352 164.634 1462.306 3572.953 -> 657.949 -> 1315.898 MByte/s p08 random-cyc-1dim : 0.051 0.847 13.357 164.735 1463.364 3574.708 -> 657.769 -> 1315.538 MByte/s p09 random-cyc-1dim : 0.051 0.845 13.357 164.666 1466.082 3567.507 -> 657.814 -> 1315.628 MByte/s p10 random-cyc-1dim : 0.051 0.847 13.354 164.445 1460.680 3575.097 -> 656.975 -> 1313.950 MByte/s p11 random-cyc-1dim : 0.049 0.847 13.353 164.491 1463.843 3575.195 -> 660.116 -> 1320.232 MByte/s p12 random-cyc-1dim : 0.051 0.848 13.359 159.108 1459.200 3565.615 -> 656.070 -> 1312.140 MByte/s p13 random-cyc-1dim : 0.051 0.847 13.359 164.482 1461.207 3567.848 -> 655.920 -> 1311.839 MByte/s p14 random-cyc-1dim : 0.051 0.848 13.361 163.491 1463.313 3574.122 -> 657.854 -> 1315.707 MByte/s p15 random-cyc-1dim : 0.051 0.847 13.365 163.587 1462.457 3572.758 -> 658.434 -> 1316.868 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 0.051 0.845 13.365 164.610 1462.356 3572.904 -> 656.823 -> 1313.647 MByte/s p17 best bi-section : 0.039 0.651 10.181 117.209 1092.438 3496.326 -> 586.320 -> 1172.640 MByte/s p18 worst bi-section : 0.039 0.651 10.146 117.214 1094.234 3501.182 -> 591.834 -> 1183.669 MByte/s p19 acyclic-1dim-all : 0.039 0.651 10.163 117.220 1098.980 3511.028 -> 596.253 -> 1192.505 MByte/s p20 acyclic-2dim-all : 0.039 0.652 10.193 117.192 1099.450 3499.780 -> 594.672 -> 1189.344 MByte/s p21 acyclic-3dim-all : 0.039 0.651 10.179 117.184 1098.885 3509.902 -> 590.879 -> 1181.758 MByte/s p22 cyclic-1dim-all : 0.051 0.848 13.358 164.339 1462.339 3573.100 -> 657.367 -> 1314.735 MByte/s p23 cyclic-2dim-all : 0.051 0.847 13.362 164.398 1466.715 3568.480 -> 657.214 -> 1314.428 MByte/s p24 cyclic-3dim-all : 0.048 0.847 13.353 164.449 1467.957 3572.076 -> 658.303 -> 1316.605 MByte/s log_avg of all rings : 0.051 0.847 13.360 164.396 1467.235 3571.738 || 658.613 -> 1317.226 MByte/s log_avg of all random : 0.051 0.847 13.358 163.822 1462.769 3571.869 || 657.707 -> 1315.414 MByte/s log_avg(ring,random) : 0.051 0.847 13.359 164.109 1465.000 3571.803 || 658.160 -> 1316.320 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 1316.320 MByte/s on 2 processes ( = 658.160 MByte/s * 2 processes) system parameters : 2 nodes, 256 MB/node system name: SUPER-UX hostname : hwwsx4 OS release : 9.1 OS version : Rev1 machine : SX-4 SECTION-BEFF-END b_eff = 1316.320 MB/s = 658.160 * 2 PEs with 256 MB/PE on SUPER-UX hwwsx4 9.1 Rev1 SX-4