SECTION-HEAD-BEGIN b_eff.c, Revision 3.5 from July 10, 2001 MEMORY_PER_PROCESSOR = 1024 MBytes [1M = 1024*1024] 2-dim-patterns: size = 8 * 6 3-dim-patterns: size = 4 * 4 * 3 Used message lengths: msglng= 1 2 4 8 16 32 64 128 256 512 1024 2048 4096 10624 27554 71468 185364 480774 1246974 3234251 8388608 Used methods: 0=Sndrcv 1=Alltoal 2=non-blk Used patterns: 0=ring-24*2fix 1=ring-12*4fix 2=ring-6*8fix 3=ring-3*16fix 4=ring-1*48fix 5=ring-1*48fix 6=random-cyc-1dim 7=random-cyc-1dim 8=random-cyc-1dim 9=random-cyc-1dim 10=random-cyc-1dim 11=random-cyc-1dim 12=random-cyc-1dim 13=random-cyc-1dim 14=random-cyc-1dim 15=random-cyc-1dim 16=random-cyc-1dim 17=random-cyc-1dim 18=random-cyc-1dim 19=random-cyc-1dim 20=random-cyc-1dim 21=random-cyc-1dim 22=random-cyc-1dim 23=random-cyc-1dim 24=random-cyc-1dim 25=random-cyc-1dim 26=random-cyc-1dim 27=random-cyc-1dim 28=random-cyc-1dim 29=random-cyc-1dim 30=random-cyc-1dim 31=random-cyc-1dim 32=random-cyc-1dim 33=random-cyc-1dim 34=random-cyc-1dim 35=random-cyc-1dim 36=worst-cyc-1dim 37=best bi-section 38=worst bi-section 39=one PingPong Pair 40=acyclic-2dim-all 41=acyclic-3dim-all 42=cyclic-2dim-x 43=cyclic-2dim-y 44=cyclic-2dim-all 45=cyclic-3dim-x 46=cyclic-3dim-y 47=cyclic-3dim-z 48=cyclic-3dim-all 0-5 used for ring pattern average of b_eff 6-35 used for random pattern average of b_eff 36-47 only reported, not used for b_eff average SECTION-HEAD-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 120.631 sec sum of max elapsed time per entries above = 115.802 sec difference to elapsed time = 4.830 sec = 4.0% sum based on fastest repetition = 114.723 sec difference to elapsed time = 5.908 sec = 4.9% The difference is less than 5 % SECTION-ELAPSED-END SECTION-PATTERN-BEGIN Pattern parameters: sendrecv total number messages/ messages/ unused best method calls of messages used node node&call nodes per repetition ---- ----------------- ----- ------------ --------- --------- ------ -------------- p00 ring-24*2fix 1 48 1.00 1.00 0 ( 2 2 0 ) p01 ring-12*4fix 2 96 2.00 1.00 0 ( 0 2 0 ) p02 ring-6*8fix 2 96 2.00 1.00 0 ( 2 2 2 ) p03 ring-3*16fix 2 96 2.00 1.00 0 ( 2 0 2 ) p04 ring-1*48fix 2 96 2.00 1.00 0 ( 0 0 0 ) p05 ring-1*48fix 2 96 2.00 1.00 0 ( 2 2 0 ) p06 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p07 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p08 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 2 ) p09 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p10 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 2 ) p11 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 2 2 ) p12 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p13 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 2 2 ) p14 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 2 2 ) p15 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p16 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p17 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p18 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p19 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p20 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 2 ) p21 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 2 ) p22 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p23 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p24 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 2 ) p25 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 0 ) p26 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p27 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 2 2 ) p28 random-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 2 ) p29 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 2 2 ) p30 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 2 ) p31 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 0 ) p32 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 2 2 ) p33 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 2 2 ) p34 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 2 ) p35 random-cyc-1dim 2 96 2.00 1.00 0 ( 2 0 0 ) p36 worst-cyc-1dim 2 96 2.00 1.00 0 ( 0 0 0 ) p37 best bi-section 2 48 1.00 0.50 0 ( 2 2 2 ) p38 worst bi-section 2 48 1.00 0.50 0 ( 2 2 1 ) p39 one PingPong Pair 2 2 1.00 0.50 46 ( 0 0 0 ) p40 acyclic-2dim-all 4 164 3.42 0.85 0 ( 2 2 2 ) p41 acyclic-3dim-all 6 208 4.33 0.72 0 ( 2 2 2 ) p42 cyclic-2dim-x 2 96 2.00 1.00 0 ( 0 0 0 ) p43 cyclic-2dim-y 2 96 2.00 1.00 0 ( 0 0 0 ) p44 cyclic-2dim-all 4 192 4.00 1.00 0 ( 2 0 0 ) p45 cyclic-3dim-x 2 96 2.00 1.00 0 ( 0 0 0 ) p46 cyclic-3dim-y 2 96 2.00 1.00 0 ( 2 2 0 ) p47 cyclic-3dim-z 2 96 2.00 1.00 0 ( 0 0 2 ) p48 cyclic-3dim-all 6 288 6.00 1.00 0 ( 0 0 0 ) 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-24*2fix : 151.420 50.271 138.564 -> 151.420 -> 7268.147 MByte/s p01 ring-12*4fix : 152.091 53.801 137.424 -> 152.091 -> 7300.378 MByte/s p02 ring-6*8fix : 149.393 53.340 135.690 -> 149.393 -> 7170.849 MByte/s p03 ring-3*16fix : 110.946 46.042 107.514 -> 110.946 -> 5325.424 MByte/s p04 ring-1*48fix : 110.717 47.722 104.267 -> 110.717 -> 5314.412 MByte/s p05 ring-1*48fix : 107.247 43.515 104.142 -> 107.247 -> 5147.873 MByte/s p06 random-cyc-1dim : 33.165 16.123 29.130 -> 33.165 -> 1591.909 MByte/s p07 random-cyc-1dim : 32.666 15.859 27.903 -> 32.666 -> 1567.951 MByte/s p08 random-cyc-1dim : 29.864 14.031 26.123 -> 29.864 -> 1433.495 MByte/s p09 random-cyc-1dim : 33.742 16.030 29.223 -> 33.742 -> 1619.629 MByte/s p10 random-cyc-1dim : 30.031 14.559 25.626 -> 30.031 -> 1441.510 MByte/s p11 random-cyc-1dim : 33.914 14.874 29.087 -> 33.914 -> 1627.895 MByte/s p12 random-cyc-1dim : 32.575 15.685 28.357 -> 32.575 -> 1563.598 MByte/s p13 random-cyc-1dim : 30.221 13.685 26.167 -> 30.221 -> 1450.629 MByte/s p14 random-cyc-1dim : 33.481 15.446 30.124 -> 33.481 -> 1607.094 MByte/s p15 random-cyc-1dim : 30.237 14.812 26.599 -> 30.237 -> 1451.361 MByte/s p16 random-cyc-1dim : 31.279 14.888 25.882 -> 31.279 -> 1501.409 MByte/s p17 random-cyc-1dim : 33.211 16.443 30.151 -> 33.211 -> 1594.152 MByte/s p18 random-cyc-1dim : 31.250 15.410 28.275 -> 31.250 -> 1500.007 MByte/s p19 random-cyc-1dim : 36.946 16.914 32.308 -> 36.946 -> 1773.425 MByte/s p20 random-cyc-1dim : 34.500 16.158 28.628 -> 34.500 -> 1656.001 MByte/s p21 random-cyc-1dim : 30.077 14.805 25.925 -> 30.077 -> 1443.689 MByte/s p22 random-cyc-1dim : 31.865 14.415 27.534 -> 31.865 -> 1529.523 MByte/s p23 random-cyc-1dim : 32.867 15.592 29.393 -> 32.867 -> 1577.595 MByte/s p24 random-cyc-1dim : 32.712 15.581 28.086 -> 32.712 -> 1570.193 MByte/s p25 random-cyc-1dim : 30.671 14.746 26.166 -> 30.671 -> 1472.211 MByte/s p26 random-cyc-1dim : 31.743 15.208 28.370 -> 31.743 -> 1523.644 MByte/s p27 random-cyc-1dim : 28.792 13.200 24.659 -> 28.792 -> 1382.019 MByte/s p28 random-cyc-1dim : 32.512 15.451 27.627 -> 32.512 -> 1560.597 MByte/s p29 random-cyc-1dim : 32.486 14.611 27.114 -> 32.486 -> 1559.315 MByte/s p30 random-cyc-1dim : 34.481 16.312 30.811 -> 34.481 -> 1655.075 MByte/s p31 random-cyc-1dim : 31.441 15.491 28.118 -> 31.441 -> 1509.179 MByte/s p32 random-cyc-1dim : 31.590 14.583 27.863 -> 31.590 -> 1516.321 MByte/s p33 random-cyc-1dim : 29.124 13.448 24.691 -> 29.124 -> 1397.929 MByte/s p34 random-cyc-1dim : 40.127 18.608 37.035 -> 40.127 -> 1926.105 MByte/s p35 random-cyc-1dim : 32.208 14.889 28.281 -> 32.208 -> 1545.962 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 36.174 15.532 30.584 -> 36.174 -> 1736.365 MByte/s p37 best bi-section : 138.189 51.875 145.332 -> 145.332 -> 6975.919 MByte/s p38 worst bi-section : 27.189 22.028 33.838 -> 33.838 -> 1624.205 MByte/s p39 one PingPong Pair : 7.010 2.247 2.247 -> 7.010 -> 336.460 MByte/s p40 acyclic-2dim-all : 53.698 28.736 51.633 -> 53.698 -> 2577.502 MByte/s p41 acyclic-3dim-all : 38.899 26.915 37.813 -> 38.899 -> 1867.161 MByte/s p42 cyclic-2dim-x : 43.720 20.909 38.517 -> 43.720 -> 2098.567 MByte/s p43 cyclic-2dim-y : 100.007 42.230 91.656 -> 100.007 -> 4800.323 MByte/s p44 cyclic-2dim-all : 62.762 32.728 57.835 -> 62.762 -> 3012.585 MByte/s p45 cyclic-3dim-x : 27.861 14.812 24.281 -> 27.861 -> 1337.338 MByte/s p46 cyclic-3dim-y : 50.503 24.940 46.711 -> 50.503 -> 2424.131 MByte/s p47 cyclic-3dim-z : 93.112 38.942 85.844 -> 93.112 -> 4469.352 MByte/s p48 cyclic-3dim-all : 46.495 30.649 40.230 -> 46.495 -> 2231.772 MByte/s log_avg of all rings : 128.644 48.972 120.203 || 128.644 -> 6174.894 MByte/s log_avg of all random : 32.250 15.225 28.080 || 32.250 -> 1548.018 MByte/s log_avg(ring,random) : 64.411 27.306 58.097 ||( 64.411 -> 3091.739)MByte/s * size -> accumulated on all pr.: 3091.739 1310.686 2788.674 ||(3091.739)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-24*2fix : 148.161 148.077 150.257 -> 150.257 -> 7212.347 MByte/s p01 ring-12*4fix : 150.279 146.435 142.895 -> 150.279 -> 7213.399 MByte/s p02 ring-6*8fix : 145.013 142.182 147.641 -> 147.641 -> 7086.774 MByte/s p03 ring-3*16fix : 90.314 107.908 101.291 -> 107.908 -> 5179.562 MByte/s p04 ring-1*48fix : 80.405 101.704 107.524 -> 107.524 -> 5161.155 MByte/s p05 ring-1*48fix : 85.602 96.075 108.026 -> 108.026 -> 5185.271 MByte/s p06 random-cyc-1dim : 29.789 31.012 32.007 -> 32.007 -> 1536.339 MByte/s p07 random-cyc-1dim : 28.545 31.416 32.226 -> 32.226 -> 1546.854 MByte/s p08 random-cyc-1dim : 25.995 29.261 28.418 -> 29.261 -> 1404.531 MByte/s p09 random-cyc-1dim : 30.246 32.150 33.870 -> 33.870 -> 1625.737 MByte/s p10 random-cyc-1dim : 26.506 29.163 28.633 -> 29.163 -> 1399.840 MByte/s p11 random-cyc-1dim : 29.510 32.618 33.652 -> 33.652 -> 1615.300 MByte/s p12 random-cyc-1dim : 29.218 31.524 32.232 -> 32.232 -> 1547.144 MByte/s p13 random-cyc-1dim : 27.522 29.331 29.044 -> 29.331 -> 1407.866 MByte/s p14 random-cyc-1dim : 30.440 31.730 33.450 -> 33.450 -> 1605.583 MByte/s p15 random-cyc-1dim : 27.500 29.215 30.205 -> 30.205 -> 1449.842 MByte/s p16 random-cyc-1dim : 29.110 30.134 31.145 -> 31.145 -> 1494.949 MByte/s p17 random-cyc-1dim : 27.934 32.209 33.021 -> 33.021 -> 1584.991 MByte/s p18 random-cyc-1dim : 26.975 29.581 31.635 -> 31.635 -> 1518.473 MByte/s p19 random-cyc-1dim : 32.809 34.379 35.574 -> 35.574 -> 1707.537 MByte/s p20 random-cyc-1dim : 30.351 33.433 32.921 -> 33.433 -> 1604.793 MByte/s p21 random-cyc-1dim : 25.694 29.115 27.665 -> 29.115 -> 1397.544 MByte/s p22 random-cyc-1dim : 28.776 30.659 31.815 -> 31.815 -> 1527.120 MByte/s p23 random-cyc-1dim : 29.289 31.186 32.827 -> 32.827 -> 1575.681 MByte/s p24 random-cyc-1dim : 29.224 31.845 30.619 -> 31.845 -> 1528.548 MByte/s p25 random-cyc-1dim : 26.530 29.598 29.618 -> 29.618 -> 1421.681 MByte/s p26 random-cyc-1dim : 28.788 30.802 31.420 -> 31.420 -> 1508.161 MByte/s p27 random-cyc-1dim : 25.485 27.213 28.626 -> 28.626 -> 1374.061 MByte/s p28 random-cyc-1dim : 28.776 31.589 31.472 -> 31.589 -> 1516.251 MByte/s p29 random-cyc-1dim : 29.091 31.258 31.540 -> 31.540 -> 1513.937 MByte/s p30 random-cyc-1dim : 30.706 33.363 33.217 -> 33.363 -> 1601.424 MByte/s p31 random-cyc-1dim : 28.309 30.462 31.173 -> 31.173 -> 1496.282 MByte/s p32 random-cyc-1dim : 29.479 29.949 31.375 -> 31.375 -> 1506.012 MByte/s p33 random-cyc-1dim : 26.846 28.414 28.289 -> 28.414 -> 1363.871 MByte/s p34 random-cyc-1dim : 36.641 38.831 40.161 -> 40.161 -> 1927.732 MByte/s p35 random-cyc-1dim : 28.731 31.065 31.359 -> 31.359 -> 1505.218 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 32.599 35.076 35.824 -> 35.824 -> 1719.532 MByte/s p37 best bi-section : 143.450 140.658 145.799 -> 145.799 -> 6998.365 MByte/s p38 worst bi-section : 32.514 32.162 33.552 -> 33.552 -> 1610.480 MByte/s p39 one PingPong Pair : 5.975 6.875 6.974 -> 6.974 -> 334.738 MByte/s p40 acyclic-2dim-all : 49.562 52.644 52.791 -> 52.791 -> 2533.987 MByte/s p41 acyclic-3dim-all : 37.039 38.834 38.078 -> 38.834 -> 1864.014 MByte/s p42 cyclic-2dim-x : 38.353 42.061 43.549 -> 43.549 -> 2090.346 MByte/s p43 cyclic-2dim-y : 76.612 95.546 98.992 -> 98.992 -> 4751.640 MByte/s p44 cyclic-2dim-all : 55.210 62.023 57.932 -> 62.023 -> 2977.105 MByte/s p45 cyclic-3dim-x : 25.556 26.813 27.330 -> 27.330 -> 1311.838 MByte/s p46 cyclic-3dim-y : 45.948 47.836 49.560 -> 49.560 -> 2378.881 MByte/s p47 cyclic-3dim-z : 82.915 92.231 91.865 -> 92.231 -> 4427.110 MByte/s p48 cyclic-3dim-all : 45.711 45.485 45.119 -> 45.711 -> 2194.126 MByte/s log_avg of all rings : 112.312 121.711 124.531 || 126.913 -> 6091.806 MByte/s log_avg of all random : 28.750 31.015 31.550 || 31.736 -> 1523.308 MByte/s log_avg(ring,random) : 56.824 61.440 62.682 ||( 63.464 -> 3046.260)MByte/s * size -> accumulated on all pr.: 2727.550 2949.119 3008.720 ||(3046.260)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 185364 8388608 -> average -> accumulated (latency of one sendrecv (or equivalent method) in microsec) p00 ring-24*2fix p00 method 0 =Sndrcv :( 15.346) 0.065 1.033 14.536 119.489 345.813 443.162 -> 151.420 -> 7268.147 MByte/s p00 method 1 =Alltoal :(1575.311) 0.001 0.010 0.165 2.603 35.402 443.162 -> 50.271 -> 2412.987 MByte/s p00 method 2 =non-blk :( 37.846) 0.026 0.389 6.126 67.186 345.774 443.162 -> 138.564 -> 6651.057 MByte/s p01 ring-12*4fix p01 method 0 =Sndrcv :( 15.323) 0.065 1.036 14.787 117.586 364.007 462.806 -> 152.091 -> 7300.378 MByte/s p01 method 1 =Alltoal :(767.469) 0.001 0.020 0.328 5.193 45.792 462.806 -> 53.801 -> 2582.427 MByte/s p01 method 2 =non-blk :( 34.902) 0.029 0.445 6.788 73.098 350.095 462.806 -> 137.424 -> 6596.349 MByte/s p02 ring-6*8fix p02 method 0 =Sndrcv :( 15.366) 0.065 1.032 15.010 117.497 358.882 463.765 -> 149.393 -> 7170.849 MByte/s p02 method 1 =Alltoal :(773.847) 0.001 0.021 0.330 5.206 40.114 463.765 -> 53.340 -> 2560.343 MByte/s p02 method 2 =non-blk :( 34.858) 0.029 0.442 6.769 75.157 330.418 463.765 -> 135.690 -> 6513.116 MByte/s p03 ring-3*16fix p03 method 0 =Sndrcv :( 26.044) 0.038 0.564 8.527 62.627 304.384 422.090 -> 110.946 -> 5325.424 MByte/s p03 method 1 =Alltoal :(769.993) 0.001 0.021 0.325 5.006 32.689 422.090 -> 46.042 -> 2210.029 MByte/s p03 method 2 =non-blk :( 46.870) 0.021 0.327 5.073 49.277 284.294 422.090 -> 107.514 -> 5160.668 MByte/s p04 ring-1*48fix p04 method 0 =Sndrcv :( 26.293) 0.038 0.572 8.526 62.428 236.881 440.705 -> 110.717 -> 5314.412 MByte/s p04 method 1 =Alltoal :(772.834) 0.001 0.020 0.331 5.006 29.054 440.705 -> 47.722 -> 2290.676 MByte/s p04 method 2 =non-blk :( 46.576) 0.021 0.326 4.948 47.848 160.834 440.705 -> 104.267 -> 5004.839 MByte/s p05 ring-1*48fix p05 method 0 =Sndrcv :( 26.199) 0.038 0.570 8.543 64.097 212.084 349.963 -> 107.247 -> 5147.873 MByte/s p05 method 1 =Alltoal :(774.503) 0.001 0.021 0.330 5.023 30.485 349.963 -> 43.515 -> 2088.734 MByte/s p05 method 2 =non-blk :( 46.564) 0.021 0.327 4.912 49.176 248.991 349.963 -> 104.142 -> 4998.815 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 30.790) 0.032 0.481 7.371 41.005 73.616 97.520 -> 33.165 -> 1591.909 MByte/s p06 method 1 =Alltoal :(752.509) 0.001 0.021 0.335 3.921 28.302 97.520 -> 16.123 -> 773.893 MByte/s p06 method 2 =non-blk :( 56.532) 0.018 0.271 4.212 33.717 53.550 97.520 -> 29.130 -> 1398.248 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 29.695) 0.034 0.478 7.513 38.662 70.899 98.112 -> 32.666 -> 1567.951 MByte/s p07 method 1 =Alltoal :(748.515) 0.001 0.021 0.338 3.818 26.898 98.112 -> 15.859 -> 761.237 MByte/s p07 method 2 =non-blk :( 55.620) 0.018 0.270 4.112 33.740 47.867 98.112 -> 27.903 -> 1339.359 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 29.765) 0.034 0.465 7.100 36.225 62.618 87.498 -> 29.864 -> 1433.495 MByte/s p08 method 1 =Alltoal :(739.515) 0.001 0.021 0.338 3.676 25.504 87.498 -> 14.031 -> 673.507 MByte/s p08 method 2 =non-blk :( 55.794) 0.018 0.273 4.249 32.646 49.596 87.498 -> 26.123 -> 1253.897 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 30.358) 0.033 0.485 7.579 40.588 71.294 100.502 -> 33.742 -> 1619.629 MByte/s p09 method 1 =Alltoal :(754.535) 0.001 0.021 0.338 3.878 27.064 100.502 -> 16.030 -> 769.445 MByte/s p09 method 2 =non-blk :( 55.458) 0.018 0.273 4.206 35.143 54.494 100.502 -> 29.223 -> 1402.723 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 30.013) 0.033 0.466 7.260 37.558 60.042 79.397 -> 30.031 -> 1441.510 MByte/s p10 method 1 =Alltoal :(754.674) 0.001 0.021 0.336 3.961 25.989 79.397 -> 14.559 -> 698.820 MByte/s p10 method 2 =non-blk :( 56.553) 0.018 0.270 4.202 33.083 45.735 79.397 -> 25.626 -> 1230.039 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 29.705) 0.034 0.498 7.719 43.097 77.243 94.566 -> 33.914 -> 1627.895 MByte/s p11 method 1 =Alltoal :(748.992) 0.001 0.021 0.330 3.962 28.947 94.566 -> 14.874 -> 713.969 MByte/s p11 method 2 =non-blk :( 56.277) 0.018 0.270 4.282 35.363 62.985 94.566 -> 29.087 -> 1396.156 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 29.843) 0.034 0.488 7.533 40.410 67.961 94.800 -> 32.575 -> 1563.598 MByte/s p12 method 1 =Alltoal :(747.025) 0.001 0.021 0.337 3.808 29.011 94.800 -> 15.685 -> 752.880 MByte/s p12 method 2 =non-blk :( 55.648) 0.018 0.273 4.282 32.684 52.392 94.800 -> 28.357 -> 1361.146 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 29.729) 0.034 0.468 7.268 37.698 70.061 82.228 -> 30.221 -> 1450.629 MByte/s p13 method 1 =Alltoal :(744.681) 0.001 0.021 0.339 3.756 27.053 82.228 -> 13.685 -> 656.884 MByte/s p13 method 2 =non-blk :( 56.521) 0.018 0.272 4.196 33.446 55.078 82.228 -> 26.167 -> 1256.028 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 29.646) 0.034 0.498 7.769 42.166 80.019 99.765 -> 33.481 -> 1607.094 MByte/s p14 method 1 =Alltoal :(753.323) 0.001 0.021 0.335 4.063 28.656 99.765 -> 15.446 -> 741.429 MByte/s p14 method 2 =non-blk :( 55.522) 0.018 0.273 4.246 36.154 63.253 99.765 -> 30.124 -> 1445.961 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 30.296) 0.033 0.471 7.362 36.827 66.475 90.052 -> 30.237 -> 1451.361 MByte/s p15 method 1 =Alltoal :(763.337) 0.001 0.021 0.337 3.713 23.556 90.052 -> 14.812 -> 710.968 MByte/s p15 method 2 =non-blk :( 55.798) 0.018 0.269 4.274 33.540 48.671 90.052 -> 26.599 -> 1276.749 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 30.310) 0.033 0.473 7.343 36.640 70.521 91.670 -> 31.279 -> 1501.409 MByte/s p16 method 1 =Alltoal :(749.528) 0.001 0.021 0.337 3.871 26.748 91.670 -> 14.888 -> 714.612 MByte/s p16 method 2 =non-blk :( 55.702) 0.018 0.270 4.197 32.963 46.645 91.670 -> 25.882 -> 1242.356 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 30.281) 0.033 0.489 7.701 38.677 65.488 97.943 -> 33.211 -> 1594.152 MByte/s p17 method 1 =Alltoal :(755.489) 0.001 0.021 0.334 4.054 29.907 97.943 -> 16.443 -> 789.269 MByte/s p17 method 2 =non-blk :( 54.979) 0.018 0.277 4.261 32.655 62.046 97.943 -> 30.151 -> 1447.259 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 29.832) 0.034 0.474 7.574 37.397 71.666 90.789 -> 31.250 -> 1500.007 MByte/s p18 method 1 =Alltoal :(755.668) 0.001 0.021 0.336 3.782 28.211 90.789 -> 15.410 -> 739.657 MByte/s p18 method 2 =non-blk :( 55.847) 0.018 0.274 4.152 33.682 49.411 90.789 -> 28.275 -> 1357.178 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 29.440) 0.034 0.492 7.476 43.614 79.675 109.108 -> 36.946 -> 1773.425 MByte/s p19 method 1 =Alltoal :(756.979) 0.001 0.021 0.337 3.993 28.736 109.108 -> 16.914 -> 811.862 MByte/s p19 method 2 =non-blk :( 56.076) 0.018 0.271 4.219 35.865 71.459 109.108 -> 32.308 -> 1550.801 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 29.741) 0.034 0.491 7.632 41.731 77.027 99.880 -> 34.500 -> 1656.001 MByte/s p20 method 1 =Alltoal :(748.992) 0.001 0.021 0.338 3.978 27.578 99.880 -> 16.158 -> 775.592 MByte/s p20 method 2 =non-blk :( 55.064) 0.018 0.273 4.237 35.195 50.112 99.880 -> 28.628 -> 1374.121 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 30.340) 0.033 0.466 7.268 35.991 63.737 89.301 -> 30.077 -> 1443.689 MByte/s p21 method 1 =Alltoal :(751.972) 0.001 0.021 0.338 3.744 24.495 89.301 -> 14.805 -> 710.649 MByte/s p21 method 2 =non-blk :( 57.261) 0.017 0.271 4.245 32.139 51.092 89.301 -> 25.925 -> 1244.406 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 29.825) 0.034 0.482 7.428 40.124 62.750 97.052 -> 31.865 -> 1529.523 MByte/s p22 method 1 =Alltoal :(749.528) 0.001 0.021 0.335 3.786 22.736 97.052 -> 14.415 -> 691.914 MByte/s p22 method 2 =non-blk :( 55.478) 0.018 0.273 4.251 33.198 50.329 97.052 -> 27.534 -> 1321.630 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 29.611) 0.034 0.480 7.568 39.622 68.042 97.608 -> 32.867 -> 1577.595 MByte/s p23 method 1 =Alltoal :(750.005) 0.001 0.021 0.331 3.748 25.132 97.608 -> 15.592 -> 748.435 MByte/s p23 method 2 =non-blk :( 55.702) 0.018 0.274 4.212 34.491 55.581 97.608 -> 29.393 -> 1410.874 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 29.829) 0.034 0.479 7.459 39.020 69.837 95.859 -> 32.712 -> 1570.193 MByte/s p24 method 1 =Alltoal :(748.833) 0.001 0.021 0.336 3.814 27.500 95.859 -> 15.581 -> 747.901 MByte/s p24 method 2 =non-blk :( 55.653) 0.018 0.267 4.181 33.460 57.727 95.859 -> 28.086 -> 1348.143 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 29.771) 0.034 0.462 7.231 36.517 66.708 87.155 -> 30.671 -> 1472.211 MByte/s p25 method 1 =Alltoal :(752.350) 0.001 0.021 0.337 3.769 26.886 87.155 -> 14.746 -> 707.804 MByte/s p25 method 2 =non-blk :( 56.566) 0.018 0.267 4.227 32.078 51.864 87.155 -> 26.166 -> 1255.967 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 29.939) 0.033 0.477 7.296 37.049 68.337 90.993 -> 31.743 -> 1523.644 MByte/s p26 method 1 =Alltoal :(751.674) 0.001 0.021 0.337 3.803 26.816 90.993 -> 15.208 -> 729.992 MByte/s p26 method 2 =non-blk :( 55.809) 0.018 0.272 4.209 33.254 57.809 90.993 -> 28.370 -> 1361.746 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 30.061) 0.033 0.453 7.241 35.251 63.792 78.211 -> 28.792 -> 1382.019 MByte/s p27 method 1 =Alltoal :(739.992) 0.001 0.021 0.339 3.644 26.218 78.211 -> 13.200 -> 633.600 MByte/s p27 method 2 =non-blk :( 56.032) 0.018 0.270 4.168 32.178 45.024 78.211 -> 24.659 -> 1183.610 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 29.801) 0.034 0.472 7.517 39.395 66.840 94.234 -> 32.512 -> 1560.597 MByte/s p28 method 1 =Alltoal :(746.846) 0.001 0.021 0.332 3.787 27.402 94.234 -> 15.451 -> 741.641 MByte/s p28 method 2 =non-blk :( 57.089) 0.018 0.268 4.251 34.182 47.287 94.234 -> 27.627 -> 1326.073 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 29.687) 0.034 0.496 7.493 40.349 69.011 91.502 -> 32.486 -> 1559.315 MByte/s p29 method 1 =Alltoal :(747.840) 0.001 0.021 0.339 3.850 28.196 91.502 -> 14.611 -> 701.307 MByte/s p29 method 2 =non-blk :( 55.744) 0.018 0.270 4.278 34.798 53.706 91.502 -> 27.114 -> 1301.461 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 29.653) 0.034 0.501 7.556 42.379 73.216 97.740 -> 34.481 -> 1655.075 MByte/s p30 method 1 =Alltoal :(750.005) 0.001 0.021 0.337 4.018 29.173 97.740 -> 16.312 -> 782.980 MByte/s p30 method 2 =non-blk :( 55.664) 0.018 0.276 4.221 35.321 64.914 97.740 -> 30.811 -> 1478.904 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 29.944) 0.033 0.480 7.523 37.727 70.487 91.824 -> 31.441 -> 1509.179 MByte/s p31 method 1 =Alltoal :(750.502) 0.001 0.021 0.336 3.906 29.083 91.824 -> 15.491 -> 743.573 MByte/s p31 method 2 =non-blk :( 55.706) 0.018 0.273 4.262 33.870 53.335 91.824 -> 28.118 -> 1349.661 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 29.795) 0.034 0.478 7.565 39.602 69.269 89.215 -> 31.590 -> 1516.321 MByte/s p32 method 1 =Alltoal :(754.535) 0.001 0.021 0.335 3.835 26.901 89.215 -> 14.583 -> 699.967 MByte/s p32 method 2 =non-blk :( 56.575) 0.018 0.273 4.269 34.621 63.071 89.215 -> 27.863 -> 1337.430 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 29.945) 0.033 0.462 7.217 36.283 64.474 76.139 -> 29.124 -> 1397.929 MByte/s p33 method 1 =Alltoal :(749.528) 0.001 0.021 0.338 3.828 27.753 76.139 -> 13.448 -> 645.508 MByte/s p33 method 2 =non-blk :( 55.663) 0.018 0.269 4.196 32.781 51.212 76.139 -> 24.691 -> 1185.153 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 29.284) 0.034 0.520 7.996 47.475 86.135 124.043 -> 40.127 -> 1926.105 MByte/s p34 method 1 =Alltoal :(754.476) 0.001 0.021 0.335 4.152 29.390 124.043 -> 18.608 -> 893.205 MByte/s p34 method 2 =non-blk :( 54.641) 0.018 0.281 4.262 37.561 88.689 124.043 -> 37.035 -> 1777.682 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 30.427) 0.033 0.479 7.417 38.861 69.076 94.889 -> 32.208 -> 1545.962 MByte/s p35 method 1 =Alltoal :(747.502) 0.001 0.021 0.330 3.738 23.603 94.889 -> 14.889 -> 714.653 MByte/s p35 method 2 =non-blk :( 56.234) 0.018 0.274 4.273 33.679 57.737 94.889 -> 28.281 -> 1357.510 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 30.358) 0.033 0.478 7.380 41.743 82.512 106.343 -> 36.174 -> 1736.365 MByte/s p36 method 1 =Alltoal :(762.045) 0.001 0.021 0.333 3.812 23.306 106.343 -> 15.532 -> 745.515 MByte/s p36 method 2 =non-blk :( 57.648) 0.017 0.269 4.075 34.727 62.433 106.343 -> 30.584 -> 1468.041 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 11.404) 0.044 0.667 9.701 86.085 340.437 448.709 -> 138.189 -> 6633.056 MByte/s p37 method 1 =Alltoal :(767.012) 0.001 0.010 0.165 2.515 35.524 448.709 -> 51.875 -> 2489.996 MByte/s p37 method 2 =non-blk :( 18.456) 0.027 0.427 6.434 68.385 341.371 448.709 -> 145.332 -> 6975.919 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 26.710) 0.019 0.281 4.295 33.940 48.493 110.349 -> 27.189 -> 1305.079 MByte/s p38 method 1 =Alltoal :(786.006) 0.001 0.010 0.165 2.483 39.991 110.349 -> 22.028 -> 1057.365 MByte/s p38 method 2 =non-blk :( 30.098) 0.017 0.246 3.930 36.259 66.058 110.349 -> 33.838 -> 1624.205 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 11.043) 0.002 0.029 0.411 4.539 17.259 24.977 -> 7.010 -> 336.460 MByte/s p39 method 1 =Alltoal :(-------) 0.000 0.000 0.000 0.000 0.000 24.977 -> 2.247 -> 107.877 MByte/s p39 method 2 =non-blk :(-------) 0.000 0.000 0.000 0.000 0.000 24.977 -> 2.247 -> 107.877 MByte/s p40 acyclic-2dim-all p40 method 0 =Sndrcv :( 26.608) 0.032 0.476 7.118 49.320 115.391 166.255 -> 53.698 -> 2577.502 MByte/s p40 method 1 =Alltoal :(384.986) 0.002 0.035 0.562 6.490 56.246 166.255 -> 28.736 -> 1379.343 MByte/s p40 method 2 =non-blk :( 44.803) 0.019 0.297 4.528 42.528 117.284 166.255 -> 51.633 -> 2478.384 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 27.167) 0.027 0.397 6.014 40.147 96.631 128.807 -> 38.899 -> 1867.161 MByte/s p41 method 1 =Alltoal :(258.505) 0.003 0.045 0.709 7.619 66.781 128.807 -> 26.915 -> 1291.899 MByte/s p41 method 2 =non-blk :( 43.126) 0.017 0.261 3.965 35.440 91.915 128.807 -> 37.813 -> 1815.004 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 29.482) 0.034 0.522 7.720 48.505 92.880 150.093 -> 43.720 -> 2098.567 MByte/s p42 method 1 =Alltoal :(765.026) 0.001 0.021 0.329 3.679 30.661 150.093 -> 20.909 -> 1003.634 MByte/s p42 method 2 =non-blk :( 55.294) 0.018 0.282 4.314 37.902 72.083 150.093 -> 38.517 -> 1848.799 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 26.384) 0.038 0.572 8.504 62.243 259.439 350.014 -> 100.007 -> 4800.323 MByte/s p43 method 1 =Alltoal :(770.032) 0.001 0.021 0.330 5.013 41.487 350.014 -> 42.230 -> 2027.020 MByte/s p43 method 2 =non-blk :( 48.106) 0.021 0.313 4.781 47.006 219.099 350.014 -> 91.656 -> 4399.475 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 28.093) 0.036 0.539 8.213 55.186 139.646 212.848 -> 62.762 -> 3012.585 MByte/s p44 method 1 =Alltoal :(386.000) 0.003 0.042 0.658 7.139 54.168 212.848 -> 32.728 -> 1570.928 MByte/s p44 method 2 =non-blk :( 47.990) 0.021 0.322 4.933 45.259 123.064 212.848 -> 57.835 -> 2776.088 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 29.933) 0.033 0.443 7.032 34.930 56.847 81.396 -> 27.861 -> 1337.338 MByte/s p45 method 1 =Alltoal :(782.967) 0.001 0.021 0.328 3.319 28.424 81.396 -> 14.812 -> 710.963 MByte/s p45 method 2 =non-blk :( 56.109) 0.018 0.268 4.155 30.450 48.999 81.396 -> 24.281 -> 1165.472 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 30.167) 0.033 0.532 8.058 50.352 113.722 154.401 -> 50.503 -> 2424.131 MByte/s p46 method 1 =Alltoal :(769.019) 0.001 0.020 0.329 4.591 41.492 154.401 -> 24.940 -> 1197.113 MByte/s p46 method 2 =non-blk :( 52.767) 0.019 0.293 4.400 40.041 115.816 154.401 -> 46.711 -> 2242.151 MByte/s p47 cyclic-3dim-z p47 method 0 =Sndrcv :( 29.086) 0.034 0.528 8.154 56.475 213.555 343.542 -> 93.112 -> 4469.352 MByte/s p47 method 1 =Alltoal :(768.840) 0.001 0.021 0.326 4.834 34.557 343.542 -> 38.942 -> 1869.234 MByte/s p47 method 2 =non-blk :( 54.267) 0.018 0.286 4.522 42.475 231.718 343.542 -> 85.844 -> 4120.495 MByte/s p48 cyclic-3dim-all p48 method 0 =Sndrcv :( 28.370) 0.035 0.514 7.851 47.078 108.337 142.370 -> 46.495 -> 2231.772 MByte/s p48 method 1 =Alltoal :(260.989) 0.004 0.062 0.973 9.664 70.143 142.370 -> 30.649 -> 1471.157 MByte/s p48 method 2 =non-blk :( 47.816) 0.021 0.325 4.971 41.240 81.592 142.370 -> 40.230 -> 1931.060 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.050 0.767 11.228 86.321 297.322 428.521 || 128.644 -> 6174.894 MByte/s - ring, method 1 = Alltoal: 0.001 0.018 0.293 4.549 35.140 428.521 || 48.972 -> 2350.648 MByte/s - ring, method 2 = non-blk: 0.024 0.372 5.711 59.143 277.371 428.521 || 120.203 -> 5769.759 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.033 0.480 7.463 39.176 69.655 93.236 || 32.250 -> 1548.018 MByte/s - random, method 1 = Alltoal: 0.001 0.021 0.336 3.853 27.052 93.236 || 15.225 -> 730.819 MByte/s - random, method 2 = non-blk: 0.018 0.272 4.228 33.892 54.817 93.236 || 28.080 -> 1347.838 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.041 0.607 9.154 58.153 143.910 199.884 || 64.411 -> 3091.739 MByte/s - average, method 1 = Alltoal: 0.001 0.020 0.314 4.187 30.832 199.884 || 27.306 -> 1310.686 MByte/s - average, method 2 = non-blk: 0.021 0.318 4.914 44.771 123.307 199.884 || 58.097 -> 2788.674 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 1.960 29.116 439.406 2791.326 6907.662 9594.412 || 3091.739 MByte/s - accumulated, mthd 1 = Alltoal: 0.059 0.949 15.065 200.956 1479.944 9594.412 || 1310.686 MByte/s - accumulated, mthd 2 = non-blk: 1.004 15.274 235.857 2149.029 5918.745 9594.412 || 2788.674 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: | effective| average rings random method_0 method_1 method_2 | bandwidth| crt,rnd only only Sndrcv Alltoal non-blk 1 1.960 0.041 0.050 0.033 0.041 0.001 0.021 2 3.894 0.081 0.099 0.066 0.081 0.002 0.041 4 7.489 0.156 0.193 0.126 0.156 0.005 0.082 8 15.606 0.325 0.398 0.266 0.325 0.010 0.165 16 29.116 0.607 0.767 0.480 0.607 0.020 0.318 32 57.802 1.204 1.515 0.957 1.204 0.040 0.632 64 113.788 2.371 2.959 1.899 2.371 0.079 1.253 128 218.356 4.549 5.594 3.700 4.549 0.157 2.422 256 439.406 9.154 11.228 7.463 9.154 0.314 4.914 512 855.881 17.831 21.542 14.759 17.831 0.625 9.695 1024 1645.713 34.286 40.734 28.858 34.286 1.251 19.084 2048 1883.324 39.236 55.415 27.780 39.236 2.236 28.133 4096 2791.326 58.153 86.321 39.176 58.153 4.187 44.771 10624 3368.555 70.178 130.985 37.600 69.860 7.963 63.495 27554 5049.264 105.193 207.903 53.225 102.681 15.708 98.765 71468 5830.846 121.476 276.549 53.359 120.313 20.800 112.230 185364 7004.045 145.918 305.379 69.723 143.910 30.832 123.307 480774 7396.382 154.091 334.263 71.034 151.224 36.192 131.448 1246974 9044.790 188.433 407.358 87.164 183.894 38.473 163.516 3234251 9151.306 190.652 411.883 88.249 190.652 190.652 190.652 8388608 9594.412 199.884 428.521 93.236 199.884 199.884 199.884 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 185364 8388608 -> average -> accumulated (latency of one sendrecv (or equivalent method) in microsec) p00 ring-24*2fix :( 15.346) 0.065 1.033 14.536 119.489 345.813 443.162 -> 155.245 -> 7451.780 MByte/s p01 ring-12*4fix :( 15.323) 0.065 1.036 14.787 117.586 364.007 462.806 -> 152.567 -> 7323.205 MByte/s p02 ring-6*8fix :( 15.366) 0.065 1.032 15.010 117.497 358.882 463.765 -> 149.393 -> 7170.849 MByte/s p03 ring-3*16fix :( 26.044) 0.038 0.564 8.527 62.627 304.384 422.090 -> 113.251 -> 5436.037 MByte/s p04 ring-1*48fix :( 26.293) 0.038 0.572 8.526 62.428 236.881 440.705 -> 113.180 -> 5432.632 MByte/s p05 ring-1*48fix :( 26.199) 0.038 0.570 8.543 64.097 248.991 349.963 -> 109.972 -> 5278.644 MByte/s p06 random-cyc-1dim :( 30.790) 0.032 0.481 7.371 41.005 73.616 97.520 -> 33.243 -> 1595.661 MByte/s p07 random-cyc-1dim :( 29.695) 0.034 0.478 7.513 38.662 70.899 98.112 -> 32.714 -> 1570.288 MByte/s p08 random-cyc-1dim :( 29.765) 0.034 0.465 7.100 36.225 62.618 87.498 -> 29.918 -> 1436.054 MByte/s p09 random-cyc-1dim :( 30.358) 0.033 0.485 7.579 40.588 71.294 100.502 -> 33.922 -> 1628.268 MByte/s p10 random-cyc-1dim :( 30.013) 0.033 0.466 7.260 37.558 60.042 79.397 -> 30.137 -> 1446.588 MByte/s p11 random-cyc-1dim :( 29.705) 0.034 0.498 7.719 43.097 77.243 94.566 -> 34.005 -> 1632.249 MByte/s p12 random-cyc-1dim :( 29.843) 0.034 0.488 7.533 40.410 67.961 94.800 -> 32.639 -> 1566.648 MByte/s p13 random-cyc-1dim :( 29.729) 0.034 0.468 7.268 37.698 70.061 82.228 -> 30.343 -> 1456.454 MByte/s p14 random-cyc-1dim :( 29.646) 0.034 0.498 7.769 42.166 80.019 99.765 -> 33.737 -> 1619.376 MByte/s p15 random-cyc-1dim :( 30.296) 0.033 0.471 7.362 36.827 66.475 90.052 -> 30.429 -> 1460.611 MByte/s p16 random-cyc-1dim :( 30.310) 0.033 0.473 7.343 36.640 70.521 91.670 -> 31.295 -> 1502.149 MByte/s p17 random-cyc-1dim :( 30.281) 0.033 0.489 7.701 38.677 65.488 97.943 -> 33.415 -> 1603.919 MByte/s p18 random-cyc-1dim :( 29.832) 0.034 0.474 7.574 37.397 71.666 90.789 -> 31.700 -> 1521.617 MByte/s p19 random-cyc-1dim :( 29.440) 0.034 0.492 7.476 43.614 79.675 109.108 -> 37.119 -> 1781.696 MByte/s p20 random-cyc-1dim :( 29.741) 0.034 0.491 7.632 41.731 77.027 99.880 -> 34.697 -> 1665.441 MByte/s p21 random-cyc-1dim :( 30.340) 0.033 0.466 7.268 35.991 63.737 89.301 -> 30.214 -> 1450.292 MByte/s p22 random-cyc-1dim :( 29.825) 0.034 0.482 7.428 40.124 62.750 97.052 -> 31.996 -> 1535.793 MByte/s p23 random-cyc-1dim :( 29.611) 0.034 0.480 7.568 39.622 68.042 97.608 -> 33.000 -> 1583.994 MByte/s p24 random-cyc-1dim :( 29.829) 0.034 0.479 7.459 39.020 69.837 95.859 -> 32.787 -> 1573.795 MByte/s p25 random-cyc-1dim :( 29.771) 0.034 0.462 7.231 36.517 66.708 87.155 -> 30.726 -> 1474.841 MByte/s p26 random-cyc-1dim :( 29.939) 0.033 0.477 7.296 37.049 68.337 90.993 -> 31.894 -> 1530.894 MByte/s p27 random-cyc-1dim :( 30.061) 0.033 0.453 7.241 35.251 63.792 78.211 -> 28.792 -> 1382.019 MByte/s p28 random-cyc-1dim :( 29.801) 0.034 0.472 7.517 39.395 66.840 94.234 -> 32.512 -> 1560.597 MByte/s p29 random-cyc-1dim :( 29.687) 0.034 0.496 7.493 40.349 69.011 91.502 -> 32.555 -> 1562.618 MByte/s p30 random-cyc-1dim :( 29.653) 0.034 0.501 7.556 42.379 73.216 97.740 -> 34.659 -> 1663.618 MByte/s p31 random-cyc-1dim :( 29.944) 0.033 0.480 7.523 37.727 70.487 91.824 -> 31.583 -> 1515.996 MByte/s p32 random-cyc-1dim :( 29.795) 0.034 0.478 7.565 39.602 69.269 89.215 -> 31.680 -> 1520.645 MByte/s p33 random-cyc-1dim :( 29.945) 0.033 0.462 7.217 36.283 64.474 76.139 -> 29.132 -> 1398.341 MByte/s p34 random-cyc-1dim :( 29.284) 0.034 0.520 7.996 47.475 88.689 124.043 -> 40.605 -> 1949.023 MByte/s p35 random-cyc-1dim :( 30.427) 0.033 0.479 7.417 38.861 69.076 94.889 -> 32.224 -> 1546.729 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 30.358) 0.033 0.478 7.380 41.743 82.512 106.343 -> 36.330 -> 1743.854 MByte/s p37 best bi-section :( 11.404) 0.044 0.667 9.701 86.085 341.371 448.709 -> 147.874 -> 7097.945 MByte/s p38 worst bi-section :( 26.710) 0.019 0.281 4.295 36.259 66.058 110.349 -> 34.977 -> 1678.918 MByte/s p39 one PingPong Pair :( 11.043) 0.002 0.029 0.411 4.539 17.259 24.977 -> 7.010 -> 336.460 MByte/s p40 acyclic-2dim-all :( 26.608) 0.032 0.476 7.118 49.320 117.284 166.255 -> 55.003 -> 2640.159 MByte/s p41 acyclic-3dim-all :( 27.167) 0.027 0.397 6.014 40.147 96.631 128.807 -> 39.452 -> 1893.674 MByte/s p42 cyclic-2dim-x :( 29.482) 0.034 0.522 7.720 48.505 92.880 150.093 -> 43.931 -> 2108.669 MByte/s p43 cyclic-2dim-y :( 26.384) 0.038 0.572 8.504 62.243 259.439 350.014 -> 101.371 -> 4865.817 MByte/s p44 cyclic-2dim-all :( 28.093) 0.036 0.539 8.213 55.186 139.646 212.848 -> 63.523 -> 3049.092 MByte/s p45 cyclic-3dim-x :( 29.933) 0.033 0.443 7.032 34.930 56.847 81.396 -> 27.872 -> 1337.851 MByte/s p46 cyclic-3dim-y :( 30.167) 0.033 0.532 8.058 50.352 115.816 154.401 -> 50.850 -> 2440.778 MByte/s p47 cyclic-3dim-z :( 29.086) 0.034 0.528 8.154 56.475 231.718 343.542 -> 94.206 -> 4521.884 MByte/s p48 cyclic-3dim-all :( 28.370) 0.035 0.514 7.851 47.078 108.337 142.370 -> 46.675 -> 2240.389 MByte/s log_avg of all rings : 0.050 0.767 11.228 86.321 305.379 428.521 || 130.712 -> 6274.192 MByte/s log_avg of all random : 0.033 0.480 7.463 39.176 69.723 93.236 || 32.376 -> 1554.071 MByte/s log_avg(ring,random) : 0.041 0.607 9.154 58.153 145.918 199.884 || 65.054 -> 3122.585 MByte/s * size -> accumulated on all pr.: 1.960 29.116 439.406 2791.326 7004.045 9594.412 || 3122.585 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 3122.585 MByte/s on 48 processes ( = 65.054 MByte/s * 48 processes) Latency: 24.484 microsec Lmax: 8 MB b_eff at Lmax: 9594.412 MByte/s on 48 processes ( : 199.884 MByte/s * 48 processes) b_eff at Lmax (ring pattern): 20569.024 MByte/s on 48 processes ( : 428.521 MByte/s * 48 processes) Latency ring pattern: 0.418 microsec Ping-pong latency: 11.043 microsec Ping-pong bandwidth at Lmax: 1198.888 MByte/s at Lmax= 8.0 MB (MByte/s=1e6 Byte/s) (MB=2**20 Byte) system parameters : 48 nodes, 1024 MB/node system name : HI-UX/MPP hostname : hwwsr8k OS release : 03-04 OS version : 0 machine : SR8000 Date of measurement: Thu Nov 8 10:52:23 2001 Total execution wall clock time = 124 seconds | number | b_eff | Lmax | b_eff | b_eff | Latency | Latency | Latency | ping-pong | of pro | | | at Lmax | at Lmax | rings & | rings | ping- | bandwith | cessors | | | rings & | rings | random | only | pong | | | | | random | only | micro- | micro- | micro- | | | MByte/s | | MByte/s | MByte/s | sec | sec | sec | MByte/s -------------------------------------------------------------------------------------------------------------- | accumulated | 48 3123 8 MB 9594 20569 24.484 20.042 11.043 1199 | per process | 65 200 429 SECTION-BEFF-END b_eff = 3122.585 MB/s = 65.054 * 48 PEs with 1024 MB/PE on HI-UX/MPP hwwsr8k 03-04 0 SR8000