b_eff = 3920.267 MB/s = 653.378 * 6 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 = 6 1-dim-paterns: size = 6 2-dim-paterns: size = 3 * 2 3-dim-paterns: size = 3 * 2 * 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 = 74.193 sec sum of max elapsed time per entries above = 74.020 sec difference = 0.173 sec = 0.2% The difference is less than 5 % SECTION-LOOP-END SECTION-PATTERN-BEGIN Pattern parameters: p00 ring-3*2fix => 1 sendrecv_calls with 6 messages, i.e. 4.2 msgs/used node, all nodes are used p01 ring-1*6fix => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p02 ring-1*6fix => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p03 ring-1*6fix => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p04 ring-1*6fix => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p05 ring-1*6fix => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p06 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p07 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p08 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p09 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p10 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p11 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p12 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p13 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p14 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p15 random-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p16 worst-cyc-1dim => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p17 best bi-section => 2 sendrecv_calls with 6 messages, i.e. 4.2 msgs/used node, all nodes are used p18 worst bi-section => 2 sendrecv_calls with 6 messages, i.e. 4.2 msgs/used node, all nodes are used p19 acyclic-1dim-all => 2 sendrecv_calls with 10 messages, i.e. 4.2 msgs/used node, all nodes are used p20 acyclic-2dim-all => 4 sendrecv_calls with 14 messages, i.e. 4.2 msgs/used node, all nodes are used p21 acyclic-3dim-all => 4 sendrecv_calls with 14 messages, i.e. 4.2 msgs/used node, all nodes are used p22 cyclic-1dim-all => 2 sendrecv_calls with 12 messages, i.e. 4.2 msgs/used node, all nodes are used p23 cyclic-2dim-all => 3 sendrecv_calls with 18 messages, i.e. 4.2 msgs/used node, all nodes are used p24 cyclic-3dim-all => 3 sendrecv_calls with 18 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-3*2fix : 654.063 345.491 607.025 -> 654.063 -> 3924.376 MByte/s p01 ring-1*6fix : 656.889 551.140 555.176 -> 656.889 -> 3941.332 MByte/s p02 ring-1*6fix : 646.740 548.705 574.962 -> 646.740 -> 3880.440 MByte/s p03 ring-1*6fix : 654.483 551.101 562.789 -> 654.483 -> 3926.900 MByte/s p04 ring-1*6fix : 653.487 547.987 591.340 -> 653.487 -> 3920.920 MByte/s p05 ring-1*6fix : 645.975 551.105 556.826 -> 645.975 -> 3875.852 MByte/s p06 random-cyc-1dim : 652.359 548.294 589.972 -> 652.359 -> 3914.154 MByte/s p07 random-cyc-1dim : 652.926 548.561 562.061 -> 652.926 -> 3917.558 MByte/s p08 random-cyc-1dim : 635.364 548.555 551.694 -> 635.364 -> 3812.185 MByte/s p09 random-cyc-1dim : 639.777 549.772 558.656 -> 639.777 -> 3838.659 MByte/s p10 random-cyc-1dim : 655.622 549.382 575.945 -> 655.622 -> 3933.733 MByte/s p11 random-cyc-1dim : 655.447 550.855 560.791 -> 655.447 -> 3932.682 MByte/s p12 random-cyc-1dim : 654.935 550.882 545.156 -> 654.935 -> 3929.610 MByte/s p13 random-cyc-1dim : 653.478 549.880 579.618 -> 653.478 -> 3920.870 MByte/s p14 random-cyc-1dim : 654.245 549.316 587.272 -> 654.245 -> 3925.469 MByte/s p15 random-cyc-1dim : 656.202 549.813 542.014 -> 656.202 -> 3937.215 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 651.715 548.177 534.827 -> 651.715 -> 3910.292 MByte/s p17 best bi-section : 406.931 343.180 572.552 -> 572.552 -> 3435.312 MByte/s p18 worst bi-section : 407.115 303.769 571.935 -> 571.935 -> 3431.613 MByte/s p19 acyclic-1dim-all : 530.863 463.807 485.052 -> 530.863 -> 3185.179 MByte/s p20 acyclic-2dim-all : 415.229 410.257 470.131 -> 470.131 -> 2820.786 MByte/s p21 acyclic-3dim-all : 415.699 409.759 467.039 -> 467.039 -> 2802.235 MByte/s p22 cyclic-1dim-all : 654.200 548.271 559.557 -> 654.200 -> 3925.199 MByte/s p23 cyclic-2dim-all : 654.470 524.514 541.218 -> 654.470 -> 3926.820 MByte/s p24 cyclic-3dim-all : 654.638 523.306 542.386 -> 654.638 -> 3927.825 MByte/s log_avg of all rings : 651.927 508.994 574.376 || 651.927 -> 3911.559 MByte/s log_avg of all random : 650.999 549.530 565.087 || 650.999 -> 3905.992 MByte/s log_avg(ring,random) : 651.462 528.874 569.713 ||(651.462 -> 3908.775)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-3*2fix : 651.325 565.786 652.333 -> 652.333 -> 3913.997 MByte/s p01 ring-1*6fix : 649.650 591.218 654.355 -> 654.355 -> 3926.128 MByte/s p02 ring-1*6fix : 624.908 534.752 649.255 -> 649.255 -> 3895.528 MByte/s p03 ring-1*6fix : 639.707 591.747 647.196 -> 647.196 -> 3883.173 MByte/s p04 ring-1*6fix : 648.977 584.385 650.123 -> 650.123 -> 3900.736 MByte/s p05 ring-1*6fix : 620.105 530.969 649.209 -> 649.209 -> 3895.252 MByte/s p06 random-cyc-1dim : 625.184 537.345 648.530 -> 648.530 -> 3891.180 MByte/s p07 random-cyc-1dim : 635.008 558.648 651.548 -> 651.548 -> 3909.287 MByte/s p08 random-cyc-1dim : 637.044 558.940 640.276 -> 640.276 -> 3841.656 MByte/s p09 random-cyc-1dim : 614.670 547.046 649.832 -> 649.832 -> 3898.992 MByte/s p10 random-cyc-1dim : 614.698 573.761 653.060 -> 653.060 -> 3918.359 MByte/s p11 random-cyc-1dim : 644.216 577.382 654.059 -> 654.059 -> 3924.355 MByte/s p12 random-cyc-1dim : 591.041 554.998 653.410 -> 653.410 -> 3920.457 MByte/s p13 random-cyc-1dim : 635.611 568.940 650.447 -> 650.447 -> 3902.680 MByte/s p14 random-cyc-1dim : 641.215 586.564 651.113 -> 651.113 -> 3906.681 MByte/s p15 random-cyc-1dim : 625.796 617.269 652.006 -> 652.006 -> 3912.037 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 594.629 564.543 649.175 -> 649.175 -> 3895.050 MByte/s p17 best bi-section : 572.460 477.192 574.186 -> 574.186 -> 3445.115 MByte/s p18 worst bi-section : 569.543 535.105 574.403 -> 574.403 -> 3446.417 MByte/s p19 acyclic-1dim-all : 533.136 480.257 542.539 -> 542.539 -> 3255.232 MByte/s p20 acyclic-2dim-all : 451.988 454.316 467.326 -> 467.326 -> 2803.954 MByte/s p21 acyclic-3dim-all : 448.330 428.148 470.257 -> 470.257 -> 2821.540 MByte/s p22 cyclic-1dim-all : 604.182 601.468 652.898 -> 652.898 -> 3917.389 MByte/s p23 cyclic-2dim-all : 610.963 540.790 642.627 -> 642.627 -> 3855.760 MByte/s p24 cyclic-3dim-all : 604.938 510.834 654.332 -> 654.332 -> 3925.992 MByte/s log_avg of all rings : 638.991 565.904 650.407 || 650.407 -> 3902.444 MByte/s log_avg of all random : 626.258 567.691 650.417 || 650.417 -> 3902.503 MByte/s log_avg(ring,random) : 632.593 566.797 650.412 ||(650.412 -> 3902.474)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-3*2fix p00 method 0 : 0.051 0.812 13.368 163.824 1461.476 3545.698 -> 654.063 -> 3924.376 MByte/s p00 method 1 : 0.009 0.184 2.925 46.063 616.593 1681.564 -> 345.491 -> 2072.948 MByte/s p00 method 2 : 0.035 0.574 8.968 127.008 1219.477 3503.241 -> 607.025 -> 3642.148 MByte/s p01 ring-1*6fix p01 method 0 : 0.051 0.852 13.438 163.061 1467.623 3565.687 -> 656.889 -> 3941.332 MByte/s p01 method 1 : 0.017 0.357 5.744 91.252 942.882 3333.957 -> 551.140 -> 3306.839 MByte/s p01 method 2 : 0.040 0.640 10.513 141.145 1367.806 2871.631 -> 555.176 -> 3331.053 MByte/s p02 ring-1*6fix p02 method 0 : 0.052 0.822 13.418 160.127 1468.321 3520.814 -> 646.740 -> 3880.440 MByte/s p02 method 1 : 0.017 0.363 5.519 90.346 942.674 3326.131 -> 548.705 -> 3292.232 MByte/s p02 method 2 : 0.038 0.659 10.516 138.620 1369.540 2866.654 -> 574.962 -> 3449.770 MByte/s p03 ring-1*6fix p03 method 0 : 0.051 0.852 13.441 161.063 1463.347 3559.708 -> 654.483 -> 3926.900 MByte/s p03 method 1 : 0.017 0.357 5.724 89.601 944.058 3354.713 -> 551.101 -> 3306.607 MByte/s p03 method 2 : 0.039 0.672 10.507 138.092 1369.669 3068.829 -> 562.789 -> 3376.735 MByte/s p04 ring-1*6fix p04 method 0 : 0.050 0.836 13.425 163.386 1448.572 3567.920 -> 653.487 -> 3920.920 MByte/s p04 method 1 : 0.017 0.360 5.504 88.930 940.931 3327.376 -> 547.987 -> 3287.923 MByte/s p04 method 2 : 0.040 0.672 10.519 138.297 1364.280 3355.636 -> 591.340 -> 3548.037 MByte/s p05 ring-1*6fix p05 method 0 : 0.049 0.850 13.450 160.130 1457.443 3526.996 -> 645.975 -> 3875.852 MByte/s p05 method 1 : 0.017 0.360 5.749 91.300 938.149 3352.182 -> 551.105 -> 3306.629 MByte/s p05 method 2 : 0.040 0.649 10.517 142.176 1359.202 2874.181 -> 556.826 -> 3340.954 MByte/s p06 random-cyc-1dim p06 method 0 : 0.051 0.832 13.428 162.051 1447.461 3569.815 -> 652.359 -> 3914.154 MByte/s p06 method 1 : 0.017 0.360 5.515 90.671 934.390 3328.073 -> 548.294 -> 3289.766 MByte/s p06 method 2 : 0.040 0.649 10.507 142.158 1367.772 3429.050 -> 589.972 -> 3539.834 MByte/s p07 random-cyc-1dim p07 method 0 : 0.051 0.851 13.418 157.519 1451.360 3541.410 -> 652.926 -> 3917.558 MByte/s p07 method 1 : 0.016 0.345 5.605 88.447 928.113 3347.046 -> 548.561 -> 3291.369 MByte/s p07 method 2 : 0.040 0.672 10.501 136.330 1364.346 2788.277 -> 562.061 -> 3372.368 MByte/s p08 random-cyc-1dim p08 method 0 : 0.049 0.790 12.806 157.884 1456.556 3566.003 -> 635.364 -> 3812.185 MByte/s p08 method 1 : 0.018 0.354 5.639 89.700 934.431 3336.587 -> 548.555 -> 3291.332 MByte/s p08 method 2 : 0.040 0.658 9.802 136.519 1367.490 2661.158 -> 551.694 -> 3310.166 MByte/s p09 random-cyc-1dim p09 method 0 : 0.051 0.852 13.422 162.191 1456.348 3557.462 -> 639.777 -> 3838.659 MByte/s p09 method 1 : 0.017 0.355 5.734 91.021 936.304 3341.819 -> 549.772 -> 3298.631 MByte/s p09 method 2 : 0.039 0.662 10.381 138.462 1370.542 2761.271 -> 558.656 -> 3351.937 MByte/s p10 random-cyc-1dim p10 method 0 : 0.051 0.842 13.418 157.317 1463.154 3565.978 -> 655.622 -> 3933.733 MByte/s p10 method 1 : 0.018 0.349 5.713 89.258 942.671 3352.911 -> 549.382 -> 3296.294 MByte/s p10 method 2 : 0.040 0.647 10.496 133.961 1368.815 3218.426 -> 575.945 -> 3455.668 MByte/s p11 random-cyc-1dim p11 method 0 : 0.051 0.850 13.428 157.957 1465.113 3570.471 -> 655.447 -> 3932.682 MByte/s p11 method 1 : 0.017 0.350 5.737 90.484 936.313 3365.912 -> 550.855 -> 3305.129 MByte/s p11 method 2 : 0.040 0.672 10.508 141.749 1369.967 2950.162 -> 560.791 -> 3364.749 MByte/s p12 random-cyc-1dim p12 method 0 : 0.052 0.851 13.412 158.011 1451.220 3572.880 -> 654.935 -> 3929.610 MByte/s p12 method 1 : 0.017 0.351 5.741 90.961 943.430 3356.818 -> 550.882 -> 3305.292 MByte/s p12 method 2 : 0.038 0.664 10.510 139.622 1367.978 2601.667 -> 545.156 -> 3270.934 MByte/s p13 random-cyc-1dim p13 method 0 : 0.051 0.781 12.322 164.385 1459.889 3553.266 -> 653.478 -> 3920.870 MByte/s p13 method 1 : 0.017 0.362 5.735 90.260 937.996 3346.704 -> 549.880 -> 3299.280 MByte/s p13 method 2 : 0.037 0.671 10.451 141.559 1367.721 3171.737 -> 579.618 -> 3477.706 MByte/s p14 random-cyc-1dim p14 method 0 : 0.051 0.825 13.411 156.263 1451.533 3569.912 -> 654.245 -> 3925.469 MByte/s p14 method 1 : 0.016 0.356 5.725 90.385 933.316 3371.237 -> 549.316 -> 3295.893 MByte/s p14 method 2 : 0.038 0.659 10.483 135.299 1366.343 3096.506 -> 587.272 -> 3523.634 MByte/s p15 random-cyc-1dim p15 method 0 : 0.050 0.851 13.414 163.318 1469.769 3586.739 -> 656.202 -> 3937.215 MByte/s p15 method 1 : 0.017 0.353 5.512 90.257 942.263 3340.180 -> 549.813 -> 3298.881 MByte/s p15 method 2 : 0.039 0.668 10.445 141.558 1367.061 2658.014 -> 542.014 -> 3252.082 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim p16 method 0 : 0.052 0.852 13.422 163.153 1468.532 3575.706 -> 651.715 -> 3910.292 MByte/s p16 method 1 : 0.017 0.358 5.730 89.324 939.952 3334.232 -> 548.177 -> 3289.061 MByte/s p16 method 2 : 0.039 0.662 10.452 137.409 1366.533 2436.894 -> 534.827 -> 3208.963 MByte/s p17 best bi-section p17 method 0 : 0.039 0.651 10.166 116.867 840.197 2437.620 -> 406.931 -> 2441.586 MByte/s p17 method 1 : 0.009 0.181 2.901 45.374 612.989 1671.229 -> 343.180 -> 2059.083 MByte/s p17 method 2 : 0.025 0.426 6.601 95.955 1078.902 3464.443 -> 572.552 -> 3435.312 MByte/s p18 worst bi-section p18 method 0 : 0.039 0.651 9.734 114.782 840.131 2443.937 -> 407.115 -> 2442.691 MByte/s p18 method 1 : 0.009 0.178 2.880 45.675 609.735 1159.293 -> 303.769 -> 1822.617 MByte/s p18 method 2 : 0.026 0.425 6.616 96.043 1079.299 3443.555 -> 571.935 -> 3431.613 MByte/s p19 acyclic-1dim-all p19 method 0 : 0.042 0.710 11.184 136.891 1226.756 2955.227 -> 530.863 -> 3185.179 MByte/s p19 method 1 : 0.014 0.299 4.730 75.840 806.609 2801.456 -> 463.807 -> 2782.841 MByte/s p19 method 2 : 0.030 0.479 8.483 115.261 1134.401 2376.171 -> 485.052 -> 2910.313 MByte/s p20 acyclic-2dim-all p20 method 0 : 0.034 0.560 8.371 106.261 903.991 2391.379 -> 415.229 -> 2491.377 MByte/s p20 method 1 : 0.020 0.417 6.513 102.403 927.648 2067.177 -> 410.257 -> 2461.539 MByte/s p20 method 2 : 0.027 0.443 6.971 97.791 1037.413 2431.843 -> 470.131 -> 2820.786 MByte/s p21 acyclic-3dim-all p21 method 0 : 0.034 0.555 8.788 106.657 899.559 2396.889 -> 415.699 -> 2494.197 MByte/s p21 method 1 : 0.020 0.407 6.542 102.918 931.773 2045.040 -> 409.759 -> 2458.552 MByte/s p21 method 2 : 0.027 0.448 6.976 97.852 1037.207 2382.911 -> 467.039 -> 2802.235 MByte/s p22 cyclic-1dim-all p22 method 0 : 0.051 0.851 13.399 161.404 1467.475 3542.774 -> 654.200 -> 3925.199 MByte/s p22 method 1 : 0.018 0.351 5.663 88.206 936.350 3338.053 -> 548.271 -> 3289.624 MByte/s p22 method 2 : 0.040 0.645 10.397 136.851 1368.382 3220.700 -> 559.557 -> 3357.344 MByte/s p23 cyclic-2dim-all p23 method 0 : 0.051 0.853 13.413 162.319 1445.676 3548.529 -> 654.470 -> 3926.820 MByte/s p23 method 1 : 0.025 0.527 8.342 131.958 1155.400 2657.430 -> 524.514 -> 3147.087 MByte/s p23 method 2 : 0.037 0.621 8.662 124.228 1464.849 2635.549 -> 541.218 -> 3247.308 MByte/s p24 cyclic-3dim-all p24 method 0 : 0.051 0.852 13.450 164.632 1442.327 3562.207 -> 654.638 -> 3927.825 MByte/s p24 method 1 : 0.025 0.523 8.389 132.495 1152.680 2660.397 -> 523.306 -> 3139.837 MByte/s p24 method 2 : 0.038 0.635 9.958 138.468 1464.173 2739.895 -> 542.386 -> 3254.317 MByte/s log_avg of all rings - ring, method 0 : 0.050 0.837 13.423 161.925 1461.115 3547.756 || 651.927 -> 3911.559 MByte/s - ring, method 1 : 0.015 0.321 5.060 80.703 877.555 2978.171 || 508.994 -> 3053.962 MByte/s - ring, method 2 : 0.039 0.643 10.239 137.464 1340.487 3079.919 || 574.376 -> 3446.256 MByte/s log_avg of all random - random, method 0 : 0.051 0.832 13.243 159.665 1457.225 3565.375 || 650.999 -> 3905.992 MByte/s - random, method 1 : 0.017 0.353 5.665 90.141 936.911 3348.705 || 549.530 -> 3297.183 MByte/s - random, method 2 : 0.039 0.662 10.406 138.692 1367.802 2921.566 || 565.087 -> 3390.522 MByte/s log_avg(ring,random) - average, method 0 : 0.051 0.835 13.333 160.791 1459.168 3556.554 || 651.462 -> 3908.775 MByte/s - average, method 1 : 0.016 0.337 5.354 85.291 906.748 3158.008 || 528.874 -> 3173.243 MByte/s - average, method 2 : 0.039 0.653 10.323 138.076 1354.076 2999.697 || 569.713 -> 3418.275 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 0.303 0.051 0.050 0.051 0.051 0.016 0.039 2 0.591 0.099 0.098 0.099 0.099 0.033 0.077 4 1.241 0.207 0.208 0.205 0.207 0.085 0.161 8 2.541 0.423 0.425 0.422 0.423 0.169 0.329 16 5.008 0.835 0.837 0.832 0.835 0.337 0.653 32 10.120 1.687 1.683 1.690 1.687 0.675 1.304 64 20.118 3.353 3.370 3.336 3.353 1.351 2.597 128 40.133 6.689 6.707 6.671 6.689 2.684 5.087 256 79.997 13.333 13.423 13.243 13.333 5.354 10.323 512 160.298 26.716 26.780 26.653 26.716 10.749 20.625 1024 313.509 52.251 52.556 51.949 52.251 21.552 40.828 2048 485.690 80.948 81.161 80.736 80.948 42.932 69.628 4096 964.746 160.791 161.925 159.665 160.791 85.291 138.076 8933 1262.932 210.489 211.379 209.602 210.489 139.268 186.743 19484 3347.655 557.942 561.207 554.697 557.942 294.610 518.097 42495 5014.769 835.795 836.659 834.932 835.795 501.076 764.267 92682 8755.010 1459.168 1461.115 1457.225 1459.168 906.748 1354.076 202141 10070.527 1678.421 1688.272 1668.627 1669.162 1444.420 1521.583 440872 16986.044 2831.007 2837.136 2824.892 2831.007 2389.723 2457.790 961548 13460.073 2243.345 2236.184 2250.530 2209.674 2081.138 1856.263 2097152 21339.327 3556.554 3547.756 3565.375 3556.554 3158.008 2999.697 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-3*2fix : 0.051 0.812 13.368 163.824 1461.476 3545.698 -> 654.063 -> 3924.376 MByte/s p01 ring-1*6fix : 0.051 0.852 13.438 163.061 1467.623 3565.687 -> 656.889 -> 3941.332 MByte/s p02 ring-1*6fix : 0.052 0.822 13.418 160.127 1468.321 3520.814 -> 651.923 -> 3911.540 MByte/s p03 ring-1*6fix : 0.051 0.852 13.441 161.063 1463.347 3559.708 -> 654.483 -> 3926.900 MByte/s p04 ring-1*6fix : 0.050 0.836 13.425 163.386 1448.572 3567.920 -> 653.487 -> 3920.920 MByte/s p05 ring-1*6fix : 0.049 0.850 13.450 160.130 1457.443 3526.996 -> 651.782 -> 3910.690 MByte/s p06 random-cyc-1dim : 0.051 0.832 13.428 162.051 1447.461 3569.815 -> 652.359 -> 3914.154 MByte/s p07 random-cyc-1dim : 0.051 0.851 13.418 157.519 1451.360 3541.410 -> 652.926 -> 3917.558 MByte/s p08 random-cyc-1dim : 0.049 0.790 12.806 157.884 1456.556 3566.003 -> 642.751 -> 3856.506 MByte/s p09 random-cyc-1dim : 0.051 0.852 13.422 162.191 1456.348 3557.462 -> 652.011 -> 3912.063 MByte/s p10 random-cyc-1dim : 0.051 0.842 13.418 157.317 1463.154 3565.978 -> 655.622 -> 3933.733 MByte/s p11 random-cyc-1dim : 0.051 0.850 13.428 157.957 1465.113 3570.471 -> 655.447 -> 3932.682 MByte/s p12 random-cyc-1dim : 0.052 0.851 13.412 158.011 1451.220 3572.880 -> 654.935 -> 3929.610 MByte/s p13 random-cyc-1dim : 0.051 0.781 12.322 164.385 1459.889 3553.266 -> 653.478 -> 3920.870 MByte/s p14 random-cyc-1dim : 0.051 0.825 13.411 156.263 1451.533 3569.912 -> 654.245 -> 3925.469 MByte/s p15 random-cyc-1dim : 0.050 0.851 13.414 163.318 1469.769 3586.739 -> 656.202 -> 3937.215 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 0.052 0.852 13.422 163.153 1468.532 3575.706 -> 651.715 -> 3910.292 MByte/s p17 best bi-section : 0.039 0.651 10.166 116.867 1078.902 3464.443 -> 575.572 -> 3453.434 MByte/s p18 worst bi-section : 0.039 0.651 9.734 114.782 1079.299 3443.555 -> 574.806 -> 3448.833 MByte/s p19 acyclic-1dim-all : 0.042 0.710 11.184 136.891 1226.756 2955.227 -> 545.359 -> 3272.156 MByte/s p20 acyclic-2dim-all : 0.034 0.560 8.371 106.261 1037.413 2431.843 -> 472.923 -> 2837.540 MByte/s p21 acyclic-3dim-all : 0.034 0.555 8.788 106.657 1037.207 2396.889 -> 470.530 -> 2823.183 MByte/s p22 cyclic-1dim-all : 0.051 0.851 13.399 161.404 1467.475 3542.774 -> 654.200 -> 3925.199 MByte/s p23 cyclic-2dim-all : 0.051 0.853 13.413 162.319 1464.849 3548.529 -> 655.383 -> 3932.298 MByte/s p24 cyclic-3dim-all : 0.051 0.852 13.450 164.632 1464.173 3562.207 -> 655.810 -> 3934.860 MByte/s log_avg of all rings : 0.050 0.837 13.423 161.925 1461.115 3547.756 || 653.769 -> 3922.613 MByte/s log_avg of all random : 0.051 0.832 13.243 159.665 1457.225 3565.375 || 652.987 -> 3917.923 MByte/s log_avg(ring,random) : 0.051 0.835 13.333 160.791 1459.168 3556.554 || 653.378 -> 3920.267 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 3920.267 MByte/s on 6 processes ( = 653.378 MByte/s * 6 processes) system parameters : 6 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 = 3920.267 MB/s = 653.378 * 6 PEs with 256 MB/PE on SUPER-UX hwwsx4 9.1 Rev1 SX-4