SECTION-HEAD-BEGIN b_eff.c, Revision 3.5 from March 27, 2002 MEMORY_PER_PROCESSOR = 1024 MBytes [1M = 1024*1024] 2-dim-patterns: size = 8 * 8 3-dim-patterns: size = 4 * 4 * 4 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-32*2fix 1=ring-16*4fix 2=ring-8*8fix 3=ring-4*16fix 4=ring-2*32fix 5=ring-1*64fix 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 = 132.087 sec sum of max elapsed time per entries above = 127.768 sec difference to elapsed time = 4.319 sec = 3.3% sum based on fastest repetition = 127.785 sec difference to elapsed time = 4.302 sec = 3.3% 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-32*2fix 1 64 1.00 1.00 0 ( 0 2 0 ) p01 ring-16*4fix 2 128 2.00 1.00 0 ( 0 2 0 ) p02 ring-8*8fix 2 128 2.00 1.00 0 ( 0 2 0 ) p03 ring-4*16fix 2 128 2.00 1.00 0 ( 2 2 0 ) p04 ring-2*32fix 2 128 2.00 1.00 0 ( 0 0 2 ) p05 ring-1*64fix 2 128 2.00 1.00 0 ( 2 0 0 ) p06 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 0 2 ) p07 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 0 ) p08 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 0 ) p09 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 0 0 ) p10 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 0 ) p11 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 2 2 ) p12 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 2 ) p13 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 0 0 ) p14 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 0 0 ) p15 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 0 ) p16 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 2 ) p17 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 2 ) p18 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 0 ) p19 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 0 ) p20 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 0 0 ) p21 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 0 ) p22 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 0 ) p23 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 0 0 ) p24 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 2 2 ) p25 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 0 ) p26 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 2 ) p27 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 0 0 ) p28 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 0 ) p29 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 2 ) p30 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 2 ) p31 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 0 ) p32 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 2 ) p33 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 2 ) p34 random-cyc-1dim 2 128 2.00 1.00 0 ( 2 2 0 ) p35 random-cyc-1dim 2 128 2.00 1.00 0 ( 0 2 0 ) p36 worst-cyc-1dim 2 128 2.00 1.00 0 ( 0 0 0 ) p37 best bi-section 2 64 1.00 0.50 0 ( 2 2 2 ) p38 worst bi-section 2 64 1.00 0.50 0 ( 2 2 2 ) p39 one PingPong Pair 2 2 1.00 0.50 62 ( 0 0 0 ) p40 acyclic-2dim-all 4 224 3.50 0.88 0 ( 2 2 2 ) p41 acyclic-3dim-all 6 288 4.50 0.75 0 ( 2 2 2 ) p42 cyclic-2dim-x 2 128 2.00 1.00 0 ( 0 0 0 ) p43 cyclic-2dim-y 2 128 2.00 1.00 0 ( 2 0 2 ) p44 cyclic-2dim-all 4 256 4.00 1.00 0 ( 0 2 0 ) p45 cyclic-3dim-x 2 128 2.00 1.00 0 ( 2 0 0 ) p46 cyclic-3dim-y 2 128 2.00 1.00 0 ( 0 0 2 ) p47 cyclic-3dim-z 2 128 2.00 1.00 0 ( 0 0 0 ) p48 cyclic-3dim-all 6 384 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-32*2fix : 182.837 66.670 162.702 -> 182.837 -> 11701.594 MByte/s p01 ring-16*4fix : 178.137 68.649 162.563 -> 178.137 -> 11400.784 MByte/s p02 ring-8*8fix : 172.659 66.608 162.550 -> 172.659 -> 11050.185 MByte/s p03 ring-4*16fix : 100.132 44.564 102.261 -> 102.261 -> 6544.693 MByte/s p04 ring-2*32fix : 102.636 41.531 96.664 -> 102.636 -> 6568.674 MByte/s p05 ring-1*64fix : 107.867 45.268 101.749 -> 107.867 -> 6903.468 MByte/s p06 random-cyc-1dim : 31.674 13.858 29.288 -> 31.674 -> 2027.136 MByte/s p07 random-cyc-1dim : 30.759 12.621 26.720 -> 30.759 -> 1968.548 MByte/s p08 random-cyc-1dim : 29.488 12.595 27.363 -> 29.488 -> 1887.244 MByte/s p09 random-cyc-1dim : 31.366 13.029 29.253 -> 31.366 -> 2007.434 MByte/s p10 random-cyc-1dim : 32.929 14.315 29.152 -> 32.929 -> 2107.444 MByte/s p11 random-cyc-1dim : 30.495 13.203 28.884 -> 30.495 -> 1951.691 MByte/s p12 random-cyc-1dim : 28.855 12.339 26.296 -> 28.855 -> 1846.708 MByte/s p13 random-cyc-1dim : 33.315 14.626 30.898 -> 33.315 -> 2132.174 MByte/s p14 random-cyc-1dim : 31.034 13.312 27.032 -> 31.034 -> 1986.201 MByte/s p15 random-cyc-1dim : 30.055 13.214 26.998 -> 30.055 -> 1923.489 MByte/s p16 random-cyc-1dim : 29.324 12.567 27.184 -> 29.324 -> 1876.733 MByte/s p17 random-cyc-1dim : 31.110 13.784 29.073 -> 31.110 -> 1991.041 MByte/s p18 random-cyc-1dim : 31.705 13.830 29.752 -> 31.705 -> 2029.150 MByte/s p19 random-cyc-1dim : 29.745 13.300 26.950 -> 29.745 -> 1903.649 MByte/s p20 random-cyc-1dim : 31.686 13.960 29.396 -> 31.686 -> 2027.896 MByte/s p21 random-cyc-1dim : 32.404 14.289 30.075 -> 32.404 -> 2073.853 MByte/s p22 random-cyc-1dim : 30.509 12.949 27.675 -> 30.509 -> 1952.577 MByte/s p23 random-cyc-1dim : 29.535 13.240 26.758 -> 29.535 -> 1890.220 MByte/s p24 random-cyc-1dim : 31.049 13.303 28.128 -> 31.049 -> 1987.132 MByte/s p25 random-cyc-1dim : 32.287 13.672 29.835 -> 32.287 -> 2066.383 MByte/s p26 random-cyc-1dim : 29.228 12.717 25.361 -> 29.228 -> 1870.585 MByte/s p27 random-cyc-1dim : 29.953 13.351 26.912 -> 29.953 -> 1916.985 MByte/s p28 random-cyc-1dim : 29.043 12.380 25.550 -> 29.043 -> 1858.763 MByte/s p29 random-cyc-1dim : 30.253 12.787 27.596 -> 30.253 -> 1936.214 MByte/s p30 random-cyc-1dim : 29.872 12.688 25.003 -> 29.872 -> 1911.803 MByte/s p31 random-cyc-1dim : 30.364 13.209 29.135 -> 30.364 -> 1943.327 MByte/s p32 random-cyc-1dim : 32.148 13.890 28.511 -> 32.148 -> 2057.492 MByte/s p33 random-cyc-1dim : 29.589 13.427 27.854 -> 29.589 -> 1893.676 MByte/s p34 random-cyc-1dim : 28.988 12.236 25.836 -> 28.988 -> 1855.244 MByte/s p35 random-cyc-1dim : 33.630 14.704 31.150 -> 33.630 -> 2152.291 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 36.013 14.625 31.994 -> 36.013 -> 2304.814 MByte/s p37 best bi-section : 166.774 66.514 166.012 -> 166.774 -> 10673.533 MByte/s p38 worst bi-section : 29.347 21.992 35.947 -> 35.947 -> 2300.612 MByte/s p39 one PingPong Pair : 5.619 1.885 1.885 -> 5.619 -> 359.592 MByte/s p40 acyclic-2dim-all : 46.239 23.246 44.273 -> 46.239 -> 2959.291 MByte/s p41 acyclic-3dim-all : 47.402 26.438 44.662 -> 47.402 -> 3033.719 MByte/s p42 cyclic-2dim-x : 33.693 15.949 29.349 -> 33.693 -> 2156.339 MByte/s p43 cyclic-2dim-y : 172.691 66.684 159.794 -> 172.691 -> 11052.218 MByte/s p44 cyclic-2dim-all : 57.151 27.992 54.871 -> 57.151 -> 3657.650 MByte/s p45 cyclic-3dim-x : 34.966 15.234 31.076 -> 34.966 -> 2237.840 MByte/s p46 cyclic-3dim-y : 71.457 28.744 66.492 -> 71.457 -> 4573.246 MByte/s p47 cyclic-3dim-z : 175.141 67.931 161.671 -> 175.141 -> 11209.008 MByte/s p48 cyclic-3dim-all : 61.656 33.037 51.351 -> 61.656 -> 3945.977 MByte/s log_avg of all rings : 135.663 54.268 127.639 || 136.139 -> 8712.924 MByte/s log_avg of all random : 30.719 13.297 27.941 || 30.719 -> 1965.995 MByte/s log_avg(ring,random) : 64.555 26.862 59.719 ||( 64.669 -> 4138.788)MByte/s * size -> accumulated on all pr.: 4131.540 1719.197 3822.035 ||(4138.788)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-32*2fix : 174.004 173.867 177.627 -> 177.627 -> 11368.102 MByte/s p01 ring-16*4fix : 172.106 169.142 174.823 -> 174.823 -> 11188.681 MByte/s p02 ring-8*8fix : 166.170 170.787 170.961 -> 170.961 -> 10941.493 MByte/s p03 ring-4*16fix : 84.203 101.349 97.133 -> 101.349 -> 6486.358 MByte/s p04 ring-2*32fix : 84.286 98.285 97.320 -> 98.285 -> 6290.259 MByte/s p05 ring-1*64fix : 85.901 107.501 107.095 -> 107.501 -> 6880.091 MByte/s p06 random-cyc-1dim : 26.736 31.259 30.847 -> 31.259 -> 2000.571 MByte/s p07 random-cyc-1dim : 25.821 29.068 30.312 -> 30.312 -> 1939.956 MByte/s p08 random-cyc-1dim : 24.998 28.911 29.284 -> 29.284 -> 1874.165 MByte/s p09 random-cyc-1dim : 26.599 30.957 30.755 -> 30.957 -> 1981.222 MByte/s p10 random-cyc-1dim : 27.101 30.802 32.271 -> 32.271 -> 2065.319 MByte/s p11 random-cyc-1dim : 27.069 29.050 30.883 -> 30.883 -> 1976.517 MByte/s p12 random-cyc-1dim : 24.263 28.499 28.344 -> 28.499 -> 1823.966 MByte/s p13 random-cyc-1dim : 29.151 32.914 33.380 -> 33.380 -> 2136.298 MByte/s p14 random-cyc-1dim : 25.639 29.398 30.074 -> 30.074 -> 1924.741 MByte/s p15 random-cyc-1dim : 25.611 29.736 29.153 -> 29.736 -> 1903.091 MByte/s p16 random-cyc-1dim : 25.742 28.853 29.104 -> 29.104 -> 1862.633 MByte/s p17 random-cyc-1dim : 26.889 29.559 31.025 -> 31.025 -> 1985.619 MByte/s p18 random-cyc-1dim : 26.762 31.040 31.499 -> 31.499 -> 2015.918 MByte/s p19 random-cyc-1dim : 24.790 28.438 29.221 -> 29.221 -> 1870.119 MByte/s p20 random-cyc-1dim : 26.867 30.929 30.564 -> 30.929 -> 1979.436 MByte/s p21 random-cyc-1dim : 27.967 31.553 31.846 -> 31.846 -> 2038.154 MByte/s p22 random-cyc-1dim : 25.146 29.721 30.095 -> 30.095 -> 1926.088 MByte/s p23 random-cyc-1dim : 25.211 29.136 28.814 -> 29.136 -> 1864.730 MByte/s p24 random-cyc-1dim : 26.895 29.917 31.061 -> 31.061 -> 1987.935 MByte/s p25 random-cyc-1dim : 28.252 31.981 31.386 -> 31.981 -> 2046.814 MByte/s p26 random-cyc-1dim : 25.307 28.851 27.093 -> 28.851 -> 1846.465 MByte/s p27 random-cyc-1dim : 25.489 29.294 29.311 -> 29.311 -> 1875.872 MByte/s p28 random-cyc-1dim : 25.683 28.637 28.530 -> 28.637 -> 1832.768 MByte/s p29 random-cyc-1dim : 26.154 29.739 29.649 -> 29.739 -> 1903.318 MByte/s p30 random-cyc-1dim : 25.025 28.516 28.578 -> 28.578 -> 1828.978 MByte/s p31 random-cyc-1dim : 26.492 29.743 30.154 -> 30.154 -> 1929.869 MByte/s p32 random-cyc-1dim : 26.195 30.931 31.368 -> 31.368 -> 2007.583 MByte/s p33 random-cyc-1dim : 26.920 29.479 28.770 -> 29.479 -> 1886.667 MByte/s p34 random-cyc-1dim : 25.321 27.759 28.583 -> 28.583 -> 1829.288 MByte/s p35 random-cyc-1dim : 29.543 32.423 33.311 -> 33.311 -> 2131.885 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 29.431 34.335 34.661 -> 34.661 -> 2218.277 MByte/s p37 best bi-section : 167.301 164.305 166.414 -> 167.301 -> 10707.267 MByte/s p38 worst bi-section : 33.096 33.706 35.047 -> 35.047 -> 2243.010 MByte/s p39 one PingPong Pair : 5.496 5.593 5.581 -> 5.593 -> 357.977 MByte/s p40 acyclic-2dim-all : 38.849 45.364 46.833 -> 46.833 -> 2997.310 MByte/s p41 acyclic-3dim-all : 40.315 47.049 46.998 -> 47.049 -> 3011.126 MByte/s p42 cyclic-2dim-x : 30.736 31.911 33.706 -> 33.706 -> 2157.203 MByte/s p43 cyclic-2dim-y : 167.463 169.435 170.717 -> 170.717 -> 10925.892 MByte/s p44 cyclic-2dim-all : 54.072 52.545 57.146 -> 57.146 -> 3657.371 MByte/s p45 cyclic-3dim-x : 28.232 33.354 33.059 -> 33.354 -> 2134.686 MByte/s p46 cyclic-3dim-y : 56.003 69.421 67.141 -> 69.421 -> 4442.935 MByte/s p47 cyclic-3dim-z : 170.334 173.838 173.131 -> 173.838 -> 11125.654 MByte/s p48 cyclic-3dim-all : 55.477 58.140 58.846 -> 58.846 -> 3766.173 MByte/s log_avg of all rings : 120.318 132.365 132.350 || 133.594 -> 8550.034 MByte/s log_avg of all random : 26.293 29.877 30.140 || 30.322 -> 1940.635 MByte/s log_avg(ring,random) : 56.246 62.886 63.159 ||( 63.647 -> 4073.389)MByte/s * size -> accumulated on all pr.: 3599.726 4024.707 4042.170 ||(4073.389)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-32*2fix p00 method 0 =Sndrcv :( 15.382) 0.065 1.025 14.070 108.031 406.097 629.259 -> 182.837 -> 11701.594 MByte/s p00 method 1 =Alltoal :(2125.788) 0.000 0.008 0.120 1.917 28.369 629.259 -> 66.670 -> 4266.903 MByte/s p00 method 2 =non-blk :( 39.648) 0.025 0.414 6.267 69.423 335.841 629.259 -> 162.702 -> 10412.908 MByte/s p01 ring-16*4fix p01 method 0 =Sndrcv :( 15.296) 0.065 1.036 14.576 109.392 408.069 625.784 -> 178.137 -> 11400.784 MByte/s p01 method 1 =Alltoal :(1061.904) 0.001 0.015 0.240 3.814 37.470 625.784 -> 68.649 -> 4393.533 MByte/s p01 method 2 =non-blk :( 36.882) 0.027 0.443 6.658 73.296 386.995 625.784 -> 162.563 -> 10404.063 MByte/s p02 ring-8*8fix p02 method 0 =Sndrcv :( 15.315) 0.065 1.031 14.623 109.228 403.411 633.773 -> 172.659 -> 11050.185 MByte/s p02 method 1 =Alltoal :(1061.499) 0.001 0.015 0.236 3.780 34.071 633.773 -> 66.608 -> 4262.913 MByte/s p02 method 2 =non-blk :( 36.098) 0.028 0.457 6.651 74.676 362.754 633.773 -> 162.550 -> 10403.186 MByte/s p03 ring-4*16fix p03 method 0 =Sndrcv :( 26.420) 0.038 0.590 8.440 66.964 150.513 382.570 -> 100.132 -> 6408.466 MByte/s p03 method 1 =Alltoal :(1061.499) 0.001 0.015 0.240 3.699 31.992 382.570 -> 44.564 -> 2852.104 MByte/s p03 method 2 =non-blk :( 42.315) 0.024 0.373 5.658 51.344 187.614 382.570 -> 102.261 -> 6544.693 MByte/s p04 ring-2*32fix p04 method 0 =Sndrcv :( 26.259) 0.038 0.585 8.605 67.841 167.975 433.105 -> 102.636 -> 6568.674 MByte/s p04 method 1 =Alltoal :(1061.404) 0.001 0.015 0.240 3.730 30.224 433.105 -> 41.531 -> 2658.002 MByte/s p04 method 2 =non-blk :( 42.195) 0.024 0.366 5.760 51.377 210.754 433.105 -> 96.664 -> 6186.508 MByte/s p05 ring-1*64fix p05 method 0 =Sndrcv :( 26.439) 0.038 0.585 8.436 66.392 224.007 383.900 -> 107.867 -> 6903.468 MByte/s p05 method 1 =Alltoal :(1062.298) 0.001 0.015 0.240 3.699 26.903 383.900 -> 45.268 -> 2897.169 MByte/s p05 method 2 =non-blk :( 42.284) 0.024 0.372 5.764 52.134 196.779 383.900 -> 101.749 -> 6511.962 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 32.117) 0.031 0.481 7.248 39.222 67.009 94.382 -> 31.674 -> 2027.136 MByte/s p06 method 1 =Alltoal :(1034.307) 0.001 0.015 0.245 2.859 22.266 94.382 -> 13.858 -> 886.935 MByte/s p06 method 2 =non-blk :( 50.882) 0.020 0.309 4.787 34.611 55.482 94.382 -> 29.288 -> 1874.439 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 31.994) 0.031 0.484 7.258 37.218 66.124 89.322 -> 30.759 -> 1968.548 MByte/s p07 method 1 =Alltoal :(1042.998) 0.001 0.015 0.244 2.873 18.277 89.322 -> 12.621 -> 807.745 MByte/s p07 method 2 =non-blk :( 50.275) 0.020 0.306 4.859 33.208 50.591 89.322 -> 26.720 -> 1710.082 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 32.031) 0.031 0.484 7.012 35.682 63.227 81.456 -> 29.488 -> 1887.244 MByte/s p08 method 1 =Alltoal :(1036.704) 0.001 0.015 0.245 2.876 20.448 81.456 -> 12.595 -> 806.062 MByte/s p08 method 2 =non-blk :( 50.019) 0.020 0.309 4.893 32.700 54.296 81.456 -> 27.363 -> 1751.211 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 32.049) 0.031 0.485 7.136 37.175 68.017 86.208 -> 31.366 -> 2007.434 MByte/s p09 method 1 =Alltoal :(1036.906) 0.001 0.015 0.245 2.864 14.435 86.208 -> 13.029 -> 833.876 MByte/s p09 method 2 =non-blk :( 50.696) 0.020 0.310 4.819 34.219 58.190 86.208 -> 29.253 -> 1872.211 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 32.013) 0.031 0.481 7.291 39.639 69.451 97.083 -> 32.929 -> 2107.444 MByte/s p10 method 1 =Alltoal :(1037.908) 0.001 0.015 0.245 2.903 21.882 97.083 -> 14.315 -> 916.132 MByte/s p10 method 2 =non-blk :( 49.991) 0.020 0.311 4.848 34.756 51.086 97.083 -> 29.152 -> 1865.745 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 32.025) 0.031 0.485 7.102 35.891 63.611 89.108 -> 30.495 -> 1951.691 MByte/s p11 method 1 =Alltoal :(1037.908) 0.001 0.016 0.245 2.814 21.149 89.108 -> 13.203 -> 844.969 MByte/s p11 method 2 =non-blk :( 50.313) 0.020 0.305 4.872 32.687 61.339 89.108 -> 28.884 -> 1848.566 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 32.247) 0.031 0.485 7.008 35.773 61.742 81.025 -> 28.855 -> 1846.708 MByte/s p12 method 1 =Alltoal :(1036.298) 0.001 0.015 0.246 2.829 21.509 81.025 -> 12.339 -> 789.692 MByte/s p12 method 2 =non-blk :( 50.333) 0.020 0.309 4.791 32.060 55.217 81.025 -> 26.296 -> 1682.975 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 31.933) 0.031 0.485 7.371 40.756 70.014 97.126 -> 33.315 -> 2132.174 MByte/s p13 method 1 =Alltoal :(1038.802) 0.001 0.015 0.244 2.961 23.607 97.126 -> 14.626 -> 936.074 MByte/s p13 method 2 =non-blk :( 49.725) 0.020 0.312 4.845 35.988 60.655 97.126 -> 30.898 -> 1977.446 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 32.178) 0.031 0.480 7.097 35.952 69.608 86.214 -> 31.034 -> 1986.201 MByte/s p14 method 1 =Alltoal :(1041.210) 0.001 0.015 0.244 2.911 18.994 86.214 -> 13.312 -> 851.981 MByte/s p14 method 2 =non-blk :( 51.001) 0.020 0.305 4.849 33.065 53.870 86.214 -> 27.032 -> 1730.016 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 32.025) 0.031 0.483 7.044 36.712 63.227 84.862 -> 30.055 -> 1923.489 MByte/s p15 method 1 =Alltoal :(1037.800) 0.001 0.015 0.245 2.724 22.219 84.862 -> 13.214 -> 845.726 MByte/s p15 method 2 =non-blk :( 50.843) 0.020 0.307 4.841 32.508 49.259 84.862 -> 26.998 -> 1727.872 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 32.019) 0.031 0.484 7.015 36.617 65.005 85.644 -> 29.324 -> 1876.733 MByte/s p16 method 1 =Alltoal :(1038.897) 0.001 0.015 0.245 2.858 20.023 85.644 -> 12.567 -> 804.282 MByte/s p16 method 2 =non-blk :( 50.216) 0.020 0.310 4.802 32.700 49.990 85.644 -> 27.184 -> 1739.757 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 31.944) 0.031 0.481 7.277 38.989 71.958 91.505 -> 31.110 -> 1991.041 MByte/s p17 method 1 =Alltoal :(1038.504) 0.001 0.015 0.245 2.820 23.037 91.505 -> 13.784 -> 882.160 MByte/s p17 method 2 =non-blk :( 49.902) 0.020 0.310 4.837 34.778 59.297 91.505 -> 29.073 -> 1860.664 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 32.031) 0.031 0.484 7.311 38.271 66.792 90.026 -> 31.705 -> 2029.150 MByte/s p18 method 1 =Alltoal :(1045.907) 0.001 0.015 0.244 2.931 24.382 90.026 -> 13.830 -> 885.141 MByte/s p18 method 2 =non-blk :( 49.902) 0.020 0.306 4.873 34.551 62.118 90.026 -> 29.752 -> 1904.144 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 32.019) 0.031 0.483 6.994 36.387 62.544 81.915 -> 29.745 -> 1903.649 MByte/s p19 method 1 =Alltoal :(1036.298) 0.001 0.015 0.246 2.810 23.294 81.915 -> 13.300 -> 851.215 MByte/s p19 method 2 =non-blk :( 50.491) 0.020 0.309 4.782 32.186 55.707 81.915 -> 26.950 -> 1724.831 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 31.994) 0.031 0.485 7.189 38.984 67.719 93.326 -> 31.686 -> 2027.896 MByte/s p20 method 1 =Alltoal :(1038.504) 0.001 0.015 0.246 2.776 22.062 93.326 -> 13.960 -> 893.415 MByte/s p20 method 2 =non-blk :( 50.186) 0.020 0.309 4.826 33.958 59.127 93.326 -> 29.396 -> 1881.375 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 32.050) 0.031 0.483 7.288 40.113 59.882 96.801 -> 32.404 -> 2073.853 MByte/s p21 method 1 =Alltoal :(1037.800) 0.001 0.015 0.245 2.917 20.834 96.801 -> 14.289 -> 914.486 MByte/s p21 method 2 =non-blk :( 50.226) 0.020 0.305 4.901 34.701 63.189 96.801 -> 30.075 -> 1924.795 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 32.013) 0.031 0.484 7.072 35.075 64.195 83.198 -> 30.509 -> 1952.577 MByte/s p22 method 1 =Alltoal :(1035.798) 0.001 0.015 0.243 2.815 18.697 83.198 -> 12.949 -> 828.732 MByte/s p22 method 2 =non-blk :( 49.921) 0.020 0.306 4.880 32.624 52.215 83.198 -> 27.675 -> 1771.188 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 32.106) 0.031 0.483 7.020 35.519 62.676 85.895 -> 29.535 -> 1890.220 MByte/s p23 method 1 =Alltoal :(1038.206) 0.001 0.015 0.245 2.844 21.405 85.895 -> 13.240 -> 847.369 MByte/s p23 method 2 =non-blk :( 50.353) 0.020 0.309 4.812 32.069 49.299 85.895 -> 26.758 -> 1712.526 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 32.228) 0.031 0.478 7.162 37.007 65.720 88.522 -> 31.049 -> 1987.132 MByte/s p24 method 1 =Alltoal :(1040.006) 0.001 0.015 0.245 2.943 20.985 88.522 -> 13.303 -> 851.368 MByte/s p24 method 2 =non-blk :( 50.215) 0.020 0.310 4.892 33.870 59.939 88.522 -> 28.128 -> 1800.191 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 31.932) 0.031 0.480 7.309 38.395 67.034 93.268 -> 32.287 -> 2066.383 MByte/s p25 method 1 =Alltoal :(1035.404) 0.001 0.015 0.243 2.875 18.945 93.268 -> 13.672 -> 874.984 MByte/s p25 method 2 =non-blk :( 49.911) 0.020 0.307 4.906 34.644 53.542 93.268 -> 29.835 -> 1909.434 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 32.129) 0.031 0.483 6.994 35.721 64.362 79.577 -> 29.228 -> 1870.585 MByte/s p26 method 1 =Alltoal :(1034.796) 0.001 0.015 0.246 2.780 21.468 79.577 -> 12.717 -> 813.874 MByte/s p26 method 2 =non-blk :( 50.814) 0.020 0.308 4.782 32.380 45.634 79.577 -> 25.361 -> 1623.127 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 32.050) 0.031 0.482 7.117 35.574 64.018 85.973 -> 29.953 -> 1916.985 MByte/s p27 method 1 =Alltoal :(1035.500) 0.001 0.015 0.245 2.825 19.889 85.973 -> 13.351 -> 854.476 MByte/s p27 method 2 =non-blk :( 50.195) 0.020 0.309 4.797 32.584 50.309 85.973 -> 26.912 -> 1722.375 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 32.198) 0.031 0.477 7.069 35.566 58.949 84.554 -> 29.043 -> 1858.763 MByte/s p28 method 1 =Alltoal :(1032.603) 0.001 0.016 0.246 2.735 18.254 84.554 -> 12.380 -> 792.291 MByte/s p28 method 2 =non-blk :( 50.373) 0.020 0.306 4.847 31.948 40.883 84.554 -> 25.550 -> 1635.203 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 31.988) 0.031 0.484 7.065 35.519 65.114 83.382 -> 30.253 -> 1936.214 MByte/s p29 method 1 =Alltoal :(1033.497) 0.001 0.016 0.245 2.808 19.611 83.382 -> 12.787 -> 818.362 MByte/s p29 method 2 =non-blk :( 50.313) 0.020 0.304 4.858 32.611 55.457 83.382 -> 27.596 -> 1766.169 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 32.031) 0.031 0.486 7.046 36.092 63.606 76.540 -> 29.872 -> 1911.803 MByte/s p30 method 1 =Alltoal :(1036.799) 0.001 0.015 0.245 2.829 22.297 76.540 -> 12.688 -> 812.054 MByte/s p30 method 2 =non-blk :( 50.147) 0.020 0.309 4.778 29.326 43.749 76.540 -> 25.003 -> 1600.174 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 31.833) 0.031 0.486 7.222 36.517 64.424 86.225 -> 30.364 -> 1943.327 MByte/s p31 method 1 =Alltoal :(1035.297) 0.001 0.015 0.245 2.862 23.192 86.225 -> 13.209 -> 845.389 MByte/s p31 method 2 =non-blk :( 50.059) 0.020 0.310 4.911 33.446 56.522 86.225 -> 29.135 -> 1864.609 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 31.809) 0.031 0.484 7.330 40.103 72.585 88.756 -> 32.148 -> 2057.492 MByte/s p32 method 1 =Alltoal :(1036.608) 0.001 0.015 0.246 2.830 19.901 88.756 -> 13.890 -> 888.963 MByte/s p32 method 2 =non-blk :( 50.530) 0.020 0.307 4.882 35.143 54.407 88.756 -> 28.511 -> 1824.719 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 32.106) 0.031 0.485 7.038 35.912 58.743 87.074 -> 29.589 -> 1893.676 MByte/s p33 method 1 =Alltoal :(1036.096) 0.001 0.016 0.245 2.893 20.088 87.074 -> 13.427 -> 859.358 MByte/s p33 method 2 =non-blk :( 49.991) 0.020 0.306 4.796 32.975 52.939 87.074 -> 27.854 -> 1782.665 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 32.204) 0.031 0.483 7.061 35.251 60.320 81.245 -> 28.988 -> 1855.244 MByte/s p34 method 1 =Alltoal :(1034.296) 0.001 0.015 0.247 2.713 19.937 81.245 -> 12.236 -> 783.078 MByte/s p34 method 2 =non-blk :( 50.500) 0.020 0.309 4.775 32.017 49.802 81.245 -> 25.836 -> 1653.477 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 31.858) 0.031 0.480 7.303 40.778 72.863 98.223 -> 33.630 -> 2152.291 MByte/s p35 method 1 =Alltoal :(1038.206) 0.001 0.015 0.245 2.961 23.038 98.223 -> 14.704 -> 941.026 MByte/s p35 method 2 =non-blk :( 50.451) 0.020 0.312 4.923 34.536 62.975 98.223 -> 31.150 -> 1993.587 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 32.562) 0.031 0.472 7.125 42.233 82.622 104.691 -> 36.013 -> 2304.814 MByte/s p36 method 1 =Alltoal :(1051.199) 0.001 0.015 0.239 2.838 22.448 104.691 -> 14.625 -> 936.026 MByte/s p36 method 2 =non-blk :( 50.775) 0.020 0.301 4.848 36.083 78.345 104.691 -> 31.994 -> 2047.606 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 11.438) 0.044 0.665 9.580 80.163 392.663 632.289 -> 166.774 -> 10673.533 MByte/s p37 method 1 =Alltoal :(1059.592) 0.000 0.007 0.120 1.920 28.518 632.289 -> 66.514 -> 4256.877 MByte/s p37 method 2 =non-blk :( 18.452) 0.027 0.436 6.437 71.945 372.175 632.289 -> 166.012 -> 10624.796 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 26.957) 0.019 0.287 4.161 33.582 52.939 110.744 -> 29.347 -> 1878.213 MByte/s p38 method 1 =Alltoal :(1059.604) 0.000 0.008 0.120 1.846 35.626 110.744 -> 21.992 -> 1407.496 MByte/s p38 method 2 =non-blk :( 30.811) 0.016 0.259 4.363 28.029 70.213 110.744 -> 35.947 -> 2300.612 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 11.173) 0.001 0.021 0.307 2.901 13.257 20.085 -> 5.619 -> 359.592 MByte/s p39 method 1 =Alltoal :(-------) 0.000 0.000 0.000 0.000 0.000 20.085 -> 1.885 -> 120.640 MByte/s p39 method 2 =non-blk :(-------) 0.000 0.000 0.000 0.000 0.000 20.085 -> 1.885 -> 120.640 MByte/s p40 acyclic-2dim-all p40 method 0 =Sndrcv :( 24.000) 0.036 0.571 8.354 54.654 110.280 131.986 -> 46.239 -> 2959.291 MByte/s p40 method 1 =Alltoal :(529.903) 0.002 0.026 0.419 4.429 47.662 131.986 -> 23.246 -> 1487.772 MByte/s p40 method 2 =non-blk :( 42.936) 0.020 0.321 4.969 42.917 94.285 131.986 -> 44.273 -> 2833.492 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 24.675) 0.030 0.475 6.980 47.924 111.374 139.508 -> 47.402 -> 3033.719 MByte/s p41 method 1 =Alltoal :(354.000) 0.002 0.033 0.538 5.922 54.299 139.508 -> 26.438 -> 1692.039 MByte/s p41 method 2 =non-blk :( 42.059) 0.018 0.282 4.365 39.373 94.178 139.508 -> 44.662 -> 2858.386 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 32.154) 0.031 0.479 7.190 41.028 60.330 109.938 -> 33.693 -> 2156.339 MByte/s p42 method 1 =Alltoal :(1058.507) 0.001 0.015 0.240 2.473 24.648 109.938 -> 15.949 -> 1020.734 MByte/s p42 method 2 =non-blk :( 50.597) 0.020 0.303 4.806 34.095 36.797 109.938 -> 29.349 -> 1878.307 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 15.327) 0.065 1.033 14.682 109.834 386.178 622.787 -> 172.691 -> 11052.218 MByte/s p43 method 1 =Alltoal :(1058.197) 0.001 0.015 0.237 3.763 34.140 622.787 -> 66.684 -> 4267.748 MByte/s p43 method 2 =non-blk :( 36.108) 0.028 0.456 6.679 74.148 380.229 622.787 -> 159.794 -> 10226.816 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 24.296) 0.041 0.639 9.287 60.532 124.740 189.783 -> 57.151 -> 3657.650 MByte/s p44 method 1 =Alltoal :(529.152) 0.002 0.030 0.471 4.840 44.343 189.783 -> 27.992 -> 1791.477 MByte/s p44 method 2 =non-blk :( 43.838) 0.023 0.360 5.565 47.907 117.447 189.783 -> 54.871 -> 3511.712 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 32.204) 0.031 0.483 7.370 39.051 67.633 101.126 -> 34.966 -> 2237.840 MByte/s p45 method 1 =Alltoal :(1060.903) 0.001 0.015 0.235 2.457 22.804 101.126 -> 15.234 -> 974.991 MByte/s p45 method 2 =non-blk :( 50.912) 0.020 0.306 4.851 33.900 52.765 101.126 -> 31.076 -> 1988.854 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 27.191) 0.037 0.561 8.252 62.140 180.666 224.580 -> 71.457 -> 4573.246 MByte/s p46 method 1 =Alltoal :(1060.498) 0.001 0.015 0.241 3.348 31.554 224.580 -> 28.744 -> 1839.617 MByte/s p46 method 2 =non-blk :( 44.715) 0.022 0.349 5.497 49.400 152.185 224.580 -> 66.492 -> 4255.494 MByte/s p47 cyclic-3dim-z p47 method 0 =Sndrcv :( 15.265) 0.066 1.032 14.634 108.786 382.779 633.365 -> 175.141 -> 11209.008 MByte/s p47 method 1 =Alltoal :(1060.200) 0.001 0.015 0.237 3.828 39.168 633.365 -> 67.931 -> 4347.557 MByte/s p47 method 2 =non-blk :( 37.000) 0.027 0.443 6.637 73.913 367.079 633.365 -> 161.671 -> 10346.962 MByte/s p48 cyclic-3dim-all p48 method 0 =Sndrcv :( 25.152) 0.040 0.619 8.939 60.326 141.752 202.090 -> 61.656 -> 3945.977 MByte/s p48 method 1 =Alltoal :(353.734) 0.003 0.045 0.717 7.267 60.892 202.090 -> 33.037 -> 2114.390 MByte/s p48 method 2 =non-blk :( 43.601) 0.023 0.363 5.598 46.669 91.357 202.090 -> 51.351 -> 3286.455 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.050 0.778 11.067 85.451 268.967 501.324 || 135.663 -> 8682.432 MByte/s - ring, method 1 = Alltoal: 0.001 0.013 0.213 3.349 31.310 501.324 || 54.268 -> 3473.132 MByte/s - ring, method 2 = non-blk: 0.025 0.403 6.112 61.144 267.554 501.324 || 127.639 -> 8168.921 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.031 0.483 7.147 37.172 65.245 87.440 || 30.719 -> 1965.995 MByte/s - random, method 1 = Alltoal: 0.001 0.015 0.245 2.847 20.765 87.440 || 13.297 -> 851.001 MByte/s - random, method 2 = non-blk: 0.020 0.308 4.842 33.268 53.945 87.440 || 27.941 -> 1788.235 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.039 0.613 8.894 56.360 132.472 209.369 || 64.555 -> 4131.540 MByte/s - average, method 1 = Alltoal: 0.001 0.014 0.229 3.088 25.498 209.369 || 26.862 -> 1719.197 MByte/s - average, method 2 = non-blk: 0.022 0.352 5.440 45.102 120.139 209.369 || 59.719 -> 3822.035 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 2.522 39.220 569.202 3607.011 8478.203 13399.636 || 4131.540 MByte/s - accumulated, mthd 1 = Alltoal: 0.058 0.921 14.631 197.630 1631.897 13399.636 || 1719.197 MByte/s - accumulated, mthd 2 = non-blk: 1.430 22.544 348.160 2886.507 7688.878 13399.636 || 3822.035 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 2.522 0.039 0.050 0.031 0.039 0.001 0.022 2 5.005 0.078 0.099 0.062 0.078 0.002 0.044 4 9.590 0.150 0.191 0.118 0.150 0.004 0.087 8 19.676 0.307 0.390 0.243 0.307 0.007 0.177 16 39.220 0.613 0.778 0.483 0.613 0.014 0.352 32 77.290 1.208 1.522 0.958 1.208 0.029 0.695 64 152.506 2.383 2.984 1.903 2.383 0.057 1.377 128 284.732 4.449 5.568 3.555 4.449 0.114 2.672 256 569.202 8.894 11.067 7.147 8.894 0.229 5.440 512 1115.289 17.426 21.518 14.113 17.426 0.458 10.719 1024 2137.859 33.404 40.377 27.635 33.404 0.914 21.015 2048 2416.561 37.759 53.558 26.620 37.759 1.651 28.726 4096 3607.011 56.360 85.451 37.172 56.360 3.088 45.102 10624 4365.073 68.204 126.224 36.854 63.193 5.688 61.769 27554 6661.294 104.083 210.003 51.586 102.675 11.449 96.894 71468 7170.899 112.045 247.573 50.709 101.010 15.546 108.580 185364 8808.019 137.625 289.780 65.362 132.472 25.498 120.139 480774 10081.529 157.524 363.557 68.253 157.180 31.542 140.039 1246974 12698.415 198.413 481.362 81.784 197.072 33.657 171.932 3234251 12876.288 201.192 468.879 86.330 201.192 201.192 201.192 8388608 13399.636 209.369 501.324 87.440 209.369 209.369 209.369 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-32*2fix :( 15.382) 0.065 1.025 14.070 108.031 406.097 629.259 -> 182.837 -> 11701.594 MByte/s p01 ring-16*4fix :( 15.296) 0.065 1.036 14.576 109.392 408.069 625.784 -> 178.137 -> 11400.784 MByte/s p02 ring-8*8fix :( 15.315) 0.065 1.031 14.623 109.228 403.411 633.773 -> 174.041 -> 11138.594 MByte/s p03 ring-4*16fix :( 26.420) 0.038 0.590 8.440 66.964 187.614 382.570 -> 107.191 -> 6860.235 MByte/s p04 ring-2*32fix :( 26.259) 0.038 0.585 8.605 67.841 210.754 433.105 -> 107.025 -> 6849.591 MByte/s p05 ring-1*64fix :( 26.439) 0.038 0.585 8.436 66.392 224.007 383.900 -> 111.252 -> 7120.100 MByte/s p06 random-cyc-1dim :( 32.117) 0.031 0.481 7.248 39.222 67.009 94.382 -> 31.869 -> 2039.631 MByte/s p07 random-cyc-1dim :( 31.994) 0.031 0.484 7.258 37.218 66.124 89.322 -> 30.791 -> 1970.605 MByte/s p08 random-cyc-1dim :( 32.031) 0.031 0.484 7.012 35.682 63.227 81.456 -> 29.724 -> 1902.337 MByte/s p09 random-cyc-1dim :( 32.049) 0.031 0.485 7.136 37.175 68.017 86.208 -> 31.366 -> 2007.434 MByte/s p10 random-cyc-1dim :( 32.013) 0.031 0.481 7.291 39.639 69.451 97.083 -> 32.993 -> 2111.559 MByte/s p11 random-cyc-1dim :( 32.025) 0.031 0.485 7.102 35.891 63.611 89.108 -> 30.969 -> 1982.023 MByte/s p12 random-cyc-1dim :( 32.247) 0.031 0.485 7.008 35.773 61.742 81.025 -> 28.855 -> 1846.708 MByte/s p13 random-cyc-1dim :( 31.933) 0.031 0.485 7.371 40.756 70.014 97.126 -> 33.989 -> 2175.309 MByte/s p14 random-cyc-1dim :( 32.178) 0.031 0.480 7.097 35.952 69.608 86.214 -> 31.034 -> 1986.201 MByte/s p15 random-cyc-1dim :( 32.025) 0.031 0.483 7.044 36.712 63.227 84.862 -> 30.281 -> 1937.995 MByte/s p16 random-cyc-1dim :( 32.019) 0.031 0.484 7.015 36.617 65.005 85.644 -> 29.401 -> 1881.669 MByte/s p17 random-cyc-1dim :( 31.944) 0.031 0.481 7.277 38.989 71.958 91.505 -> 31.432 -> 2011.672 MByte/s p18 random-cyc-1dim :( 32.031) 0.031 0.484 7.311 38.271 66.792 90.026 -> 31.979 -> 2046.677 MByte/s p19 random-cyc-1dim :( 32.019) 0.031 0.483 6.994 36.387 62.544 81.915 -> 29.745 -> 1903.649 MByte/s p20 random-cyc-1dim :( 31.994) 0.031 0.485 7.189 38.984 67.719 93.326 -> 31.903 -> 2041.768 MByte/s p21 random-cyc-1dim :( 32.050) 0.031 0.483 7.288 40.113 63.189 96.801 -> 32.593 -> 2085.938 MByte/s p22 random-cyc-1dim :( 32.013) 0.031 0.484 7.072 35.075 64.195 83.198 -> 30.594 -> 1957.989 MByte/s p23 random-cyc-1dim :( 32.106) 0.031 0.483 7.020 35.519 62.676 85.895 -> 29.747 -> 1903.827 MByte/s p24 random-cyc-1dim :( 32.228) 0.031 0.478 7.162 37.007 65.720 88.522 -> 31.095 -> 1990.079 MByte/s p25 random-cyc-1dim :( 31.932) 0.031 0.480 7.309 38.395 67.034 93.268 -> 32.518 -> 2081.167 MByte/s p26 random-cyc-1dim :( 32.129) 0.031 0.483 6.994 35.721 64.362 79.577 -> 29.228 -> 1870.585 MByte/s p27 random-cyc-1dim :( 32.050) 0.031 0.482 7.117 35.574 64.018 85.973 -> 30.049 -> 1923.138 MByte/s p28 random-cyc-1dim :( 32.198) 0.031 0.477 7.069 35.566 58.949 84.554 -> 29.050 -> 1859.180 MByte/s p29 random-cyc-1dim :( 31.988) 0.031 0.484 7.065 35.519 65.114 83.382 -> 30.437 -> 1947.958 MByte/s p30 random-cyc-1dim :( 32.031) 0.031 0.486 7.046 36.092 63.606 76.540 -> 29.872 -> 1911.803 MByte/s p31 random-cyc-1dim :( 31.833) 0.031 0.486 7.222 36.517 64.424 86.225 -> 30.698 -> 1964.645 MByte/s p32 random-cyc-1dim :( 31.809) 0.031 0.484 7.330 40.103 72.585 88.756 -> 32.370 -> 2071.664 MByte/s p33 random-cyc-1dim :( 32.106) 0.031 0.485 7.038 35.912 58.743 87.074 -> 30.101 -> 1926.483 MByte/s p34 random-cyc-1dim :( 32.204) 0.031 0.483 7.061 35.251 60.320 81.245 -> 29.200 -> 1868.799 MByte/s p35 random-cyc-1dim :( 31.858) 0.031 0.480 7.303 40.778 72.863 98.223 -> 33.794 -> 2162.792 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 32.562) 0.031 0.472 7.125 42.233 82.622 104.691 -> 36.225 -> 2318.386 MByte/s p37 best bi-section :( 11.438) 0.044 0.665 9.580 80.163 392.663 632.289 -> 169.579 -> 10853.037 MByte/s p38 worst bi-section :( 26.957) 0.019 0.287 4.363 33.582 70.213 110.744 -> 36.214 -> 2317.708 MByte/s p39 one PingPong Pair :( 11.173) 0.001 0.021 0.307 2.901 13.257 20.085 -> 5.619 -> 359.592 MByte/s p40 acyclic-2dim-all :( 24.000) 0.036 0.571 8.354 54.654 110.280 131.986 -> 47.870 -> 3063.684 MByte/s p41 acyclic-3dim-all :( 24.675) 0.030 0.475 6.980 47.924 111.374 139.508 -> 48.916 -> 3130.641 MByte/s p42 cyclic-2dim-x :( 32.154) 0.031 0.479 7.190 41.028 60.330 109.938 -> 33.879 -> 2168.276 MByte/s p43 cyclic-2dim-y :( 15.327) 0.065 1.033 14.682 109.834 386.178 622.787 -> 172.691 -> 11052.218 MByte/s p44 cyclic-2dim-all :( 24.296) 0.041 0.639 9.287 60.532 124.740 189.783 -> 58.094 -> 3718.017 MByte/s p45 cyclic-3dim-x :( 32.204) 0.031 0.483 7.370 39.051 67.633 101.126 -> 34.966 -> 2237.840 MByte/s p46 cyclic-3dim-y :( 27.191) 0.037 0.561 8.252 62.140 180.666 224.580 -> 71.843 -> 4597.946 MByte/s p47 cyclic-3dim-z :( 15.265) 0.066 1.032 14.634 108.786 382.779 633.365 -> 175.141 -> 11209.008 MByte/s p48 cyclic-3dim-all :( 25.152) 0.040 0.619 8.939 60.326 141.752 202.090 -> 61.656 -> 3945.977 MByte/s log_avg of all rings : 0.050 0.778 11.067 85.451 289.780 501.324 || 139.071 -> 8900.546 MByte/s log_avg of all random : 0.031 0.483 7.147 37.172 65.362 87.440 || 30.893 -> 1977.125 MByte/s log_avg(ring,random) : 0.039 0.613 8.894 56.360 137.625 209.369 || 65.546 -> 4194.937 MByte/s * size -> accumulated on all pr.: 2.522 39.220 569.202 3607.011 8808.019 13399.636 || 4194.937 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 4194.937 MByte/s on 64 processes ( = 65.546 MByte/s * 64 processes) Latency: 25.381 microsec Lmax: 8 MB b_eff at Lmax: 13399.636 MByte/s on 64 processes ( : 209.369 MByte/s * 64 processes) b_eff at Lmax (ring pattern): 32084.718 MByte/s on 64 processes ( : 501.324 MByte/s * 64 processes) Latency ring pattern: 0.314 microsec Ping-pong latency: 11.173 microsec Ping-pong bandwidth at Lmax: 1285.415 MByte/s at Lmax= 8.0 MB (MByte/s=1e6 Byte/s) (MB=2**20 Byte) system parameters : 64 nodes, 1024 MB/node system name : HI-UX/MPP hostname : hwwsr8k OS release : 03-05 OS version : 0 machine : SR8000 Date of measurement: Thu Apr 25 21:29:32 2002 Total execution wall clock time = 136 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 | 64 4195 8 MB 13400 32085 25.381 20.108 11.173 1285 | per process | 66 209 501 SECTION-BEFF-END b_eff = 4194.937 MB/s = 65.546 * 64 PEs with 1024 MB/PE on HI-UX/MPP hwwsr8k 03-05 0 SR8000