b_eff = 819.624 MB/s = 68.302 * 12 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000 SECTION-HEAD-BEGIN b_eff.c, Revision 3.3 from Nov. 29, 1999 MEMORY_PER_PROCESSOR = 1024 MBytes [1M = 1024*1024] 1-dim-paterns: size = 12 2-dim-paterns: size = 4 * 3 3-dim-paterns: size = 3 * 2 * 2 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-6*2fix 1=ring-3*4fix 2=ring-1*12fix 3=ring-1*12fix 4=ring-1*12fix 5=ring-1*12fix 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 SECTION-HEAD-END SECTION-LOOP-BEGIN measurment loop: 80.993 sec SECTION-LOOP-END SECTION-LOOPLNGS-BEGIN method=0 | ------- repetition 0 --------- ------- repetition 1 --------- ------- repetition 2 --------- [sec] (= Sndrcv)| loop total per pattrn&mthd loop total per pattrn&mthd loop total per pattrn&mthd msg length| lng time minimum maximum lng time minimum maximum lng time minimum maximum ----------| ---- ------- ------- --------- ---- ------- ------- --------- ---- ------- ------- --------- 1 300 8.5e-01 8.4e-03 4.6e-02 133 3.8e-01 3.7e-03 2.0e-02 135 3.8e-01 3.8e-03 2.1e-02 2 150 4.3e-01 4.2e-03 2.3e-02 90 2.6e-01 2.5e-03 1.4e-02 89 2.5e-01 2.5e-03 1.4e-02 4 89 2.6e-01 2.5e-03 1.4e-02 89 2.6e-01 2.5e-03 1.4e-02 89 2.6e-01 2.5e-03 1.4e-02 8 88 2.5e-01 2.4e-03 1.4e-02 88 2.5e-01 2.4e-03 1.3e-02 88 2.5e-01 2.5e-03 1.4e-02 16 89 2.7e-01 2.6e-03 1.5e-02 90 2.7e-01 2.6e-03 1.5e-02 89 2.6e-01 2.6e-03 1.5e-02 32 87 2.6e-01 2.5e-03 1.4e-02 87 2.6e-01 2.5e-03 1.4e-02 85 2.5e-01 2.5e-03 1.4e-02 64 86 2.6e-01 2.5e-03 1.5e-02 86 2.6e-01 2.5e-03 1.5e-02 86 2.6e-01 2.5e-03 1.5e-02 128 85 2.7e-01 2.6e-03 1.5e-02 84 2.7e-01 2.6e-03 1.5e-02 84 2.7e-01 2.6e-03 1.5e-02 256 81 2.7e-01 2.6e-03 1.5e-02 81 2.7e-01 2.6e-03 1.5e-02 82 2.7e-01 2.6e-03 1.5e-02 512 78 2.6e-01 2.5e-03 1.4e-02 78 2.6e-01 2.5e-03 1.4e-02 79 2.6e-01 2.5e-03 1.5e-02 1024 77 2.7e-01 2.5e-03 1.5e-02 76 2.6e-01 2.5e-03 1.4e-02 77 2.6e-01 2.6e-03 1.4e-02 2048 75 4.3e-01 3.7e-03 2.2e-02 77 4.3e-01 3.9e-03 2.3e-02 75 4.2e-01 3.6e-03 2.2e-02 4096 50 3.5e-01 3.2e-03 1.9e-02 49 3.7e-01 3.1e-03 1.9e-02 51 3.8e-01 3.2e-03 1.9e-02 10624 30 4.4e-01 3.3e-03 2.0e-02 30 4.4e-01 3.3e-03 2.0e-02 30 4.4e-01 3.2e-03 2.0e-02 27554 17 4.4e-01 3.2e-03 1.9e-02 17 4.4e-01 3.2e-03 1.9e-02 17 4.4e-01 3.2e-03 1.9e-02 71468 10 5.6e-01 4.0e-03 2.5e-02 10 5.6e-01 3.7e-03 2.5e-02 10 5.6e-01 4.2e-03 2.5e-02 185364 4 4.3e-01 3.1e-03 2.0e-02 5 5.4e-01 3.9e-03 2.5e-02 4 4.3e-01 3.1e-03 1.9e-02 480774 2 5.0e-01 3.0e-03 2.4e-02 2 5.0e-01 3.1e-03 2.5e-02 2 4.9e-01 3.1e-03 2.2e-02 1246974 1 6.0e-01 3.5e-03 2.5e-02 1 5.7e-01 3.6e-03 2.6e-02 1 5.6e-01 3.6e-03 2.8e-02 3234251 1 8.3e-01 8.8e-03 6.7e-02 M 1 8.5e-01 8.6e-03 6.6e-02 M 1 9.6e-01 8.8e-03 6.8e-02 M 8388608 1 1.9e+00 2.2e-02 1.6e-01 R 1 2.1e+00 2.2e-02 1.6e-01 R 0 0.0e+00 1.0e+30 0.0e+00 R Explanation: M = only the best method is used R = only best method and only 2 repetitions method=1 | ------- repetition 0 --------- ------- repetition 1 --------- ------- repetition 2 --------- [sec] (=Alltoal)| loop total per pattrn&mthd loop total per pattrn&mthd loop total per pattrn&mthd msg length| lng time minimum maximum lng time minimum maximum lng time minimum maximum ----------| ---- ------- ------- --------- ---- ------- ------- --------- ---- ------- ------- --------- 1 300 4.5e+00 8.9e-02 9.9e-02 27 4.0e-01 8.0e-03 8.9e-03 12 1.8e-01 3.5e-03 4.0e-03 2 150 2.2e+00 4.5e-02 5.0e-02 13 1.9e-01 3.8e-03 4.4e-03 8 1.2e-01 2.4e-03 2.7e-03 4 75 1.1e+00 2.2e-02 2.5e-02 8 1.2e-01 2.4e-03 2.7e-03 8 1.2e-01 2.4e-03 2.7e-03 8 37 5.5e-01 1.1e-02 1.2e-02 8 1.2e-01 2.3e-03 2.7e-03 8 1.2e-01 2.4e-03 2.7e-03 16 18 2.7e-01 5.4e-03 6.0e-03 8 1.2e-01 2.4e-03 2.7e-03 8 1.2e-01 2.4e-03 2.7e-03 32 9 1.4e-01 2.7e-03 3.1e-03 8 1.2e-01 2.4e-03 2.7e-03 8 1.2e-01 2.4e-03 2.7e-03 64 8 1.2e-01 2.4e-03 2.8e-03 8 1.2e-01 2.4e-03 2.7e-03 8 1.2e-01 2.4e-03 2.7e-03 128 8 1.2e-01 2.4e-03 2.8e-03 8 1.2e-01 2.4e-03 2.8e-03 8 1.2e-01 2.4e-03 2.8e-03 256 8 1.3e-01 2.5e-03 2.8e-03 8 1.3e-01 2.5e-03 2.8e-03 8 1.3e-01 2.5e-03 2.8e-03 512 8 1.3e-01 2.5e-03 2.8e-03 8 1.3e-01 2.4e-03 2.9e-03 8 1.3e-01 2.5e-03 2.8e-03 1024 8 1.3e-01 2.5e-03 2.9e-03 8 1.3e-01 2.5e-03 2.9e-03 8 1.3e-01 2.5e-03 2.8e-03 2048 8 1.6e-01 2.6e-03 4.4e-03 7 1.4e-01 2.3e-03 3.4e-03 8 1.6e-01 2.6e-03 3.7e-03 4096 7 1.6e-01 2.5e-03 4.0e-03 7 1.6e-01 2.4e-03 4.1e-03 7 1.6e-01 2.5e-03 4.1e-03 10624 5 1.6e-01 2.1e-03 4.7e-03 5 1.6e-01 2.1e-03 4.4e-03 5 1.6e-01 2.1e-03 4.6e-03 27554 4 1.9e-01 2.2e-03 5.7e-03 4 1.9e-01 2.1e-03 5.7e-03 4 1.9e-01 2.2e-03 6.0e-03 71468 3 2.6e-01 2.9e-03 8.8e-03 3 2.5e-01 2.5e-03 8.7e-03 3 2.5e-01 2.6e-03 8.8e-03 185364 1 1.5e-01 1.2e-03 5.8e-03 2 3.1e-01 2.6e-03 1.1e-02 2 3.1e-01 2.7e-03 1.0e-02 480774 1 3.4e-01 2.7e-03 1.4e-02 1 3.5e-01 2.7e-03 1.4e-02 1 3.5e-01 2.8e-03 1.4e-02 1246974 1 7.8e-01 6.2e-03 3.3e-02 1 7.8e-01 6.2e-03 3.4e-02 1 7.8e-01 6.1e-03 3.4e-02 3234251 1 0.0e+00 0.0e+00 0.0e+00 M 1 1.5e-01 2.9e-02 5.8e-02 M 1 5.9e-02 2.8e-02 3.1e-02 M 8388608 1 0.0e+00 0.0e+00 0.0e+00 R 1 3.0e-01 7.1e-02 8.1e-02 R 0 0.0e+00 1.0e+30 0.0e+00 R Explanation: M = only the best method is used R = only best method and only 2 repetitions method=2 | ------- repetition 0 --------- ------- repetition 1 --------- ------- repetition 2 --------- [sec] (=non-blk)| loop total per pattrn&mthd loop total per pattrn&mthd loop total per pattrn&mthd msg length| lng time minimum maximum lng time minimum maximum lng time minimum maximum ----------| ---- ------- ------- --------- ---- ------- ------- --------- ---- ------- ------- --------- 1 300 1.4e+00 1.6e-02 5.7e-02 70 3.3e-01 3.6e-03 1.3e-02 72 3.4e-01 3.7e-03 1.4e-02 2 150 7.2e-01 7.9e-03 2.9e-02 48 2.3e-01 2.5e-03 9.1e-03 48 2.3e-01 2.5e-03 9.1e-03 4 75 3.6e-01 4.0e-03 1.4e-02 48 2.3e-01 2.5e-03 9.2e-03 48 2.3e-01 2.5e-03 9.2e-03 8 47 2.2e-01 2.5e-03 9.0e-03 47 2.2e-01 2.4e-03 8.9e-03 48 2.2e-01 2.5e-03 9.1e-03 16 47 2.3e-01 2.6e-03 9.4e-03 48 2.3e-01 2.6e-03 9.5e-03 48 2.3e-01 2.6e-03 9.5e-03 32 45 2.3e-01 2.5e-03 9.1e-03 46 2.3e-01 2.5e-03 9.2e-03 46 2.3e-01 2.5e-03 9.2e-03 64 44 2.2e-01 2.5e-03 9.0e-03 45 2.2e-01 2.5e-03 9.1e-03 45 2.2e-01 2.5e-03 9.1e-03 128 44 2.3e-01 2.5e-03 9.2e-03 45 2.3e-01 2.5e-03 9.3e-03 45 2.3e-01 2.5e-03 9.3e-03 256 43 2.4e-01 2.4e-03 9.6e-03 44 2.3e-01 2.4e-03 9.7e-03 44 2.3e-01 2.4e-03 9.7e-03 512 44 2.4e-01 2.6e-03 9.9e-03 44 2.4e-01 2.5e-03 9.7e-03 44 2.4e-01 2.5e-03 9.8e-03 1024 43 2.4e-01 2.5e-03 9.8e-03 44 2.4e-01 2.5e-03 9.7e-03 44 2.4e-01 2.5e-03 9.7e-03 2048 43 3.1e-01 3.2e-03 1.3e-02 44 3.1e-01 3.2e-03 1.3e-02 44 3.1e-01 3.2e-03 1.3e-02 4096 33 2.9e-01 2.9e-03 1.2e-02 34 3.1e-01 3.2e-03 1.3e-02 33 3.0e-01 2.9e-03 1.3e-02 10624 21 3.1e-01 2.9e-03 1.5e-02 20 2.8e-01 2.7e-03 1.4e-02 21 2.9e-01 3.0e-03 1.3e-02 27554 14 3.4e-01 3.0e-03 1.6e-02 14 3.2e-01 3.0e-03 1.5e-02 13 3.0e-01 2.8e-03 1.5e-02 71468 9 5.1e-01 3.4e-03 2.7e-02 9 5.0e-01 3.5e-03 2.5e-02 8 4.4e-01 3.0e-03 2.2e-02 185364 5 5.5e-01 4.3e-03 2.8e-02 4 4.1e-01 3.5e-03 1.9e-02 5 5.2e-01 4.1e-03 2.7e-02 480774 2 5.3e-01 3.9e-03 2.7e-02 2 5.3e-01 4.1e-03 2.4e-02 2 5.1e-01 3.8e-03 2.6e-02 1246974 1 6.0e-01 4.5e-03 3.3e-02 1 6.2e-01 4.6e-03 3.3e-02 1 6.1e-01 5.0e-03 3.3e-02 3234251 1 6.5e-01 1.3e-02 3.8e-02 M 1 4.3e-01 1.3e-02 4.6e-02 M 1 3.7e-01 1.2e-02 3.5e-02 M 8388608 1 1.6e+00 3.2e-02 1.1e-01 R 1 1.1e+00 3.2e-02 1.1e-01 R 0 0.0e+00 1.0e+30 0.0e+00 R Explanation: M = only the best method is used R = only best method and only 2 repetitions SECTION-LOOPLNGS-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 80.993 sec sum of max elapsed time per entries above = 80.526 sec difference to elapsed time = 0.467 sec = 0.6% sum based on fastest repetition = 74.198 sec difference to elapsed time = 6.795 sec = 8.4% CAUTION: A difference above is more than 5 %. There may be problems with the MPI implementation or processes weren't on dedicated processors 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-6*2fix 1 12 1.00 1.00 0 ( 2 2 2 ) p01 ring-3*4fix 2 24 2.00 1.00 0 ( 2 0 0 ) p02 ring-1*12fix 2 24 2.00 1.00 0 ( 2 0 0 ) p03 ring-1*12fix 2 24 2.00 1.00 0 ( 0 0 0 ) p04 ring-1*12fix 2 24 2.00 1.00 0 ( 0 0 0 ) p05 ring-1*12fix 2 24 2.00 1.00 0 ( 0 0 0 ) p06 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 2 ) p07 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 0 ) p08 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 1 2 ) p09 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 0 0 ) p10 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 0 0 ) p11 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 2 2 ) p12 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 0 ) p13 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 0 ) p14 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 2 0 ) p15 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 1 1 ) p16 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 0 ) p17 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 1 1 ) p18 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 2 2 ) p19 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 0 2 ) p20 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 2 2 ) p21 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 0 ) p22 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 1 0 ) p23 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 0 2 ) p24 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 2 ) p25 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 0 0 ) p26 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 2 0 ) p27 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 2 0 ) p28 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 0 ) p29 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 0 0 ) p30 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 2 0 ) p31 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 2 ) p32 random-cyc-1dim 2 24 2.00 1.00 0 ( 0 0 0 ) p33 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 2 2 ) p34 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 2 2 ) p35 random-cyc-1dim 2 24 2.00 1.00 0 ( 2 0 0 ) p36 worst-cyc-1dim 2 24 2.00 1.00 0 ( 0 2 0 ) p37 best bi-section 2 12 1.00 0.50 0 ( 0 0 0 ) p38 worst bi-section 2 12 1.00 0.50 0 ( 0 0 0 ) p39 one PingPong Pair 2 2 1.00 0.50 10 ( 0 0 0 ) p40 acyclic-2dim-all 4 34 2.83 0.71 0 ( 2 2 2 ) p41 acyclic-3dim-all 6 40 3.33 0.56 0 ( 0 0 0 ) p42 cyclic-2dim-x 2 24 2.00 1.00 0 ( 2 2 2 ) p43 cyclic-2dim-y 2 24 2.00 1.00 0 ( 0 0 0 ) p44 cyclic-2dim-all 4 48 4.00 1.00 0 ( 0 2 0 ) p45 cyclic-3dim-x 2 24 2.00 1.00 0 ( 2 0 0 ) p46 cyclic-3dim-y 1 12 1.00 1.00 0 ( 0 2 0 ) p47 cyclic-3dim-z 1 12 1.00 1.00 0 ( 0 2 0 ) p48 cyclic-3dim-all 4 48 4.00 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-6*2fix : 61.742 38.991 57.813 -> 61.742 -> 740.906 MByte/s p01 ring-3*4fix : 81.425 56.517 77.145 -> 81.425 -> 977.097 MByte/s p02 ring-1*12fix : 61.634 43.734 56.651 -> 61.634 -> 739.603 MByte/s p03 ring-1*12fix : 62.822 45.011 59.175 -> 62.822 -> 753.862 MByte/s p04 ring-1*12fix : 63.571 44.923 59.227 -> 63.571 -> 762.850 MByte/s p05 ring-1*12fix : 62.881 45.144 57.812 -> 62.881 -> 754.577 MByte/s p06 random-cyc-1dim : 72.985 52.035 71.687 -> 72.985 -> 875.823 MByte/s p07 random-cyc-1dim : 65.158 46.759 60.420 -> 65.158 -> 781.900 MByte/s p08 random-cyc-1dim : 58.125 42.114 56.538 -> 58.125 -> 697.497 MByte/s p09 random-cyc-1dim : 70.914 50.131 69.665 -> 70.914 -> 850.965 MByte/s p10 random-cyc-1dim : 96.332 63.016 90.324 -> 96.332 -> 1155.981 MByte/s p11 random-cyc-1dim : 59.264 43.809 57.992 -> 59.264 -> 711.169 MByte/s p12 random-cyc-1dim : 64.644 47.391 62.377 -> 64.644 -> 775.732 MByte/s p13 random-cyc-1dim : 82.375 55.959 78.507 -> 82.375 -> 988.500 MByte/s p14 random-cyc-1dim : 60.898 43.495 57.150 -> 60.898 -> 730.779 MByte/s p15 random-cyc-1dim : 70.457 48.750 68.008 -> 70.457 -> 845.482 MByte/s p16 random-cyc-1dim : 92.145 62.193 91.055 -> 92.145 -> 1105.745 MByte/s p17 random-cyc-1dim : 60.867 43.900 57.012 -> 60.867 -> 730.404 MByte/s p18 random-cyc-1dim : 65.095 47.758 64.274 -> 65.095 -> 781.144 MByte/s p19 random-cyc-1dim : 63.613 46.367 61.796 -> 63.613 -> 763.350 MByte/s p20 random-cyc-1dim : 74.920 51.849 72.577 -> 74.920 -> 899.039 MByte/s p21 random-cyc-1dim : 62.721 44.825 61.286 -> 62.721 -> 752.652 MByte/s p22 random-cyc-1dim : 59.241 43.863 57.825 -> 59.241 -> 710.897 MByte/s p23 random-cyc-1dim : 63.485 46.334 62.698 -> 63.485 -> 761.819 MByte/s p24 random-cyc-1dim : 65.010 46.720 63.021 -> 65.010 -> 780.121 MByte/s p25 random-cyc-1dim : 56.751 41.785 54.617 -> 56.751 -> 681.017 MByte/s p26 random-cyc-1dim : 78.622 53.026 73.690 -> 78.622 -> 943.469 MByte/s p27 random-cyc-1dim : 64.944 46.411 61.412 -> 64.944 -> 779.326 MByte/s p28 random-cyc-1dim : 83.768 56.333 81.297 -> 83.768 -> 1005.214 MByte/s p29 random-cyc-1dim : 64.213 46.743 61.096 -> 64.213 -> 770.550 MByte/s p30 random-cyc-1dim : 61.426 46.161 60.964 -> 61.426 -> 737.108 MByte/s p31 random-cyc-1dim : 76.247 55.326 77.058 -> 77.058 -> 924.702 MByte/s p32 random-cyc-1dim : 104.807 66.945 94.878 -> 104.807 -> 1257.685 MByte/s p33 random-cyc-1dim : 69.168 49.017 67.284 -> 69.168 -> 830.017 MByte/s p34 random-cyc-1dim : 81.310 54.043 78.617 -> 81.310 -> 975.722 MByte/s p35 random-cyc-1dim : 59.797 44.225 57.965 -> 59.797 -> 717.569 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 74.650 49.745 69.773 -> 74.650 -> 895.802 MByte/s p37 best bi-section : 65.543 43.135 63.155 -> 65.543 -> 786.514 MByte/s p38 worst bi-section : 67.996 54.530 74.066 -> 74.066 -> 888.794 MByte/s p39 one PingPong Pair : 16.843 6.058 6.058 -> 16.843 -> 202.114 MByte/s p40 acyclic-2dim-all : 78.608 65.570 81.608 -> 81.608 -> 979.295 MByte/s p41 acyclic-3dim-all : 60.925 51.906 59.107 -> 60.925 -> 731.099 MByte/s p42 cyclic-2dim-x : 166.533 84.982 157.632 -> 166.533 -> 1998.390 MByte/s p43 cyclic-2dim-y : 62.838 44.713 58.669 -> 62.838 -> 754.056 MByte/s p44 cyclic-2dim-all : 89.662 69.666 88.455 -> 89.662 -> 1075.944 MByte/s p45 cyclic-3dim-x : 62.998 45.046 57.989 -> 62.998 -> 755.981 MByte/s p46 cyclic-3dim-y : 61.646 38.463 58.000 -> 61.646 -> 739.754 MByte/s p47 cyclic-3dim-z : 62.315 38.588 58.385 -> 62.315 -> 747.777 MByte/s p48 cyclic-3dim-all : 63.720 52.858 56.246 -> 63.720 -> 764.635 MByte/s log_avg of all rings : 65.339 45.435 60.936 || 65.339 -> 784.072 MByte/s log_avg of all random : 69.419 49.209 66.971 || 69.444 -> 833.325 MByte/s log_avg(ring,random) : 67.348 47.284 63.882 ||( 67.360 -> 808.323)MByte/s * size -> accumulated on all pr.: 808.181 567.411 766.586 ||(808.323)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-6*2fix : 59.163 61.345 60.300 -> 61.345 -> 736.143 MByte/s p01 ring-3*4fix : 68.805 80.970 77.944 -> 80.970 -> 971.639 MByte/s p02 ring-1*12fix : 54.404 60.820 59.068 -> 60.820 -> 729.841 MByte/s p03 ring-1*12fix : 61.558 61.333 62.580 -> 62.580 -> 750.955 MByte/s p04 ring-1*12fix : 61.773 62.811 62.073 -> 62.811 -> 753.728 MByte/s p05 ring-1*12fix : 62.804 61.311 61.594 -> 62.804 -> 753.648 MByte/s p06 random-cyc-1dim : 64.842 73.463 72.561 -> 73.463 -> 881.562 MByte/s p07 random-cyc-1dim : 56.219 64.339 63.565 -> 64.339 -> 772.072 MByte/s p08 random-cyc-1dim : 55.322 54.267 59.019 -> 59.019 -> 708.225 MByte/s p09 random-cyc-1dim : 66.207 71.553 71.318 -> 71.553 -> 858.636 MByte/s p10 random-cyc-1dim : 79.566 90.889 94.728 -> 94.728 -> 1136.738 MByte/s p11 random-cyc-1dim : 56.964 59.156 59.991 -> 59.991 -> 719.889 MByte/s p12 random-cyc-1dim : 58.123 63.956 64.406 -> 64.406 -> 772.876 MByte/s p13 random-cyc-1dim : 73.015 81.804 82.516 -> 82.516 -> 990.193 MByte/s p14 random-cyc-1dim : 57.355 59.271 61.691 -> 61.691 -> 740.298 MByte/s p15 random-cyc-1dim : 70.656 64.973 68.075 -> 70.656 -> 847.867 MByte/s p16 random-cyc-1dim : 80.842 90.656 91.914 -> 91.914 -> 1102.971 MByte/s p17 random-cyc-1dim : 59.841 52.939 59.874 -> 59.874 -> 718.486 MByte/s p18 random-cyc-1dim : 59.934 65.779 65.383 -> 65.779 -> 789.349 MByte/s p19 random-cyc-1dim : 63.898 63.531 63.050 -> 63.898 -> 766.776 MByte/s p20 random-cyc-1dim : 75.319 74.542 73.988 -> 75.319 -> 903.834 MByte/s p21 random-cyc-1dim : 61.339 62.398 61.609 -> 62.398 -> 748.781 MByte/s p22 random-cyc-1dim : 59.179 55.963 59.865 -> 59.865 -> 718.375 MByte/s p23 random-cyc-1dim : 63.294 63.427 63.983 -> 63.983 -> 767.794 MByte/s p24 random-cyc-1dim : 61.409 64.731 64.048 -> 64.731 -> 776.772 MByte/s p25 random-cyc-1dim : 57.227 55.550 56.352 -> 57.227 -> 686.729 MByte/s p26 random-cyc-1dim : 77.242 76.009 76.069 -> 77.242 -> 926.907 MByte/s p27 random-cyc-1dim : 64.273 62.948 65.125 -> 65.125 -> 781.495 MByte/s p28 random-cyc-1dim : 80.802 82.980 80.546 -> 82.980 -> 995.761 MByte/s p29 random-cyc-1dim : 63.146 65.747 63.865 -> 65.747 -> 788.969 MByte/s p30 random-cyc-1dim : 60.496 62.092 62.132 -> 62.132 -> 745.586 MByte/s p31 random-cyc-1dim : 76.823 77.252 74.914 -> 77.252 -> 927.028 MByte/s p32 random-cyc-1dim : 92.829 99.594 103.758 -> 103.758 -> 1245.090 MByte/s p33 random-cyc-1dim : 69.159 68.758 68.917 -> 69.159 -> 829.903 MByte/s p34 random-cyc-1dim : 76.952 80.224 80.666 -> 80.666 -> 967.996 MByte/s p35 random-cyc-1dim : 58.336 59.516 59.839 -> 59.839 -> 718.068 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 73.426 71.671 74.126 -> 74.126 -> 889.513 MByte/s p37 best bi-section : 66.598 66.778 66.034 -> 66.778 -> 801.342 MByte/s p38 worst bi-section : 69.706 71.457 70.346 -> 71.457 -> 857.484 MByte/s p39 one PingPong Pair : 16.632 16.684 16.654 -> 16.684 -> 200.211 MByte/s p40 acyclic-2dim-all : 80.412 81.470 82.419 -> 82.419 -> 989.023 MByte/s p41 acyclic-3dim-all : 59.491 61.633 62.089 -> 62.089 -> 745.068 MByte/s p42 cyclic-2dim-x : 166.452 166.763 165.680 -> 166.763 -> 2001.157 MByte/s p43 cyclic-2dim-y : 61.660 61.125 60.058 -> 61.660 -> 739.916 MByte/s p44 cyclic-2dim-all : 90.632 90.721 91.393 -> 91.393 -> 1096.714 MByte/s p45 cyclic-3dim-x : 57.775 59.924 61.088 -> 61.088 -> 733.055 MByte/s p46 cyclic-3dim-y : 59.978 59.738 60.335 -> 60.335 -> 724.022 MByte/s p47 cyclic-3dim-z : 61.995 61.237 61.428 -> 61.995 -> 743.942 MByte/s p48 cyclic-3dim-all : 61.450 62.808 62.314 -> 62.808 -> 753.691 MByte/s log_avg of all rings : 61.267 64.403 63.639 || 64.879 -> 778.542 MByte/s log_avg of all random : 66.068 68.058 68.964 || 69.540 -> 834.479 MByte/s log_avg(ring,random) : 63.622 66.205 66.248 ||( 67.169 -> 806.025)MByte/s * size -> accumulated on all pr.: 763.467 794.461 794.976 ||(806.025)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-6*2fix p00 method 0 =Sndrcv :( 27.918) 0.036 0.553 7.861 52.389 159.826 188.360 -> 61.742 -> 740.906 MByte/s p00 method 1 =Alltoal :(304.222) 0.003 0.053 0.810 10.050 89.527 188.360 -> 38.991 -> 467.896 MByte/s p00 method 2 =non-blk :( 52.070) 0.019 0.291 4.540 45.882 143.849 188.360 -> 57.813 -> 693.757 MByte/s p01 ring-3*4fix p01 method 0 =Sndrcv :( 27.737) 0.036 0.555 7.872 56.441 184.763 280.377 -> 81.425 -> 977.097 MByte/s p01 method 1 =Alltoal :(150.457) 0.007 0.104 1.579 16.733 128.124 280.377 -> 56.517 -> 678.201 MByte/s p01 method 2 =non-blk :( 48.167) 0.021 0.325 4.720 46.204 185.317 280.377 -> 77.145 -> 925.742 MByte/s p02 ring-1*12fix p02 method 0 =Sndrcv :( 28.267) 0.035 0.544 7.778 55.652 142.753 203.004 -> 61.634 -> 739.603 MByte/s p02 method 1 =Alltoal :(149.836) 0.007 0.103 1.549 15.587 99.927 203.004 -> 43.734 -> 524.812 MByte/s p02 method 2 =non-blk :( 48.850) 0.020 0.312 4.626 44.339 135.762 203.004 -> 56.651 -> 679.818 MByte/s p03 ring-1*12fix p03 method 0 =Sndrcv :( 28.387) 0.035 0.545 7.864 58.206 142.118 220.379 -> 62.822 -> 753.862 MByte/s p03 method 1 =Alltoal :(150.874) 0.007 0.103 1.527 15.566 100.619 220.379 -> 45.011 -> 540.133 MByte/s p03 method 2 =non-blk :( 49.430) 0.020 0.313 4.615 42.829 135.411 220.379 -> 59.175 -> 710.099 MByte/s p04 ring-1*12fix p04 method 0 =Sndrcv :( 28.178) 0.035 0.540 7.681 57.959 141.489 224.492 -> 63.571 -> 762.850 MByte/s p04 method 1 =Alltoal :(150.000) 0.007 0.103 1.537 15.544 101.250 224.492 -> 44.923 -> 539.072 MByte/s p04 method 2 =non-blk :( 49.651) 0.020 0.310 4.520 44.500 145.811 224.492 -> 59.227 -> 710.723 MByte/s p05 ring-1*12fix p05 method 0 =Sndrcv :( 28.245) 0.035 0.546 7.856 59.355 137.215 225.321 -> 62.881 -> 754.577 MByte/s p05 method 1 =Alltoal :(151.557) 0.007 0.102 1.519 15.142 101.224 225.321 -> 45.144 -> 541.732 MByte/s p05 method 2 =non-blk :( 48.671) 0.021 0.313 4.633 44.743 133.499 225.321 -> 57.812 -> 693.748 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 27.700) 0.036 0.554 7.904 57.023 174.397 248.132 -> 72.985 -> 875.823 MByte/s p06 method 1 =Alltoal :(160.058) 0.006 0.099 1.545 17.638 121.095 248.132 -> 52.035 -> 624.418 MByte/s p06 method 2 =non-blk :( 47.879) 0.021 0.326 4.727 46.275 180.119 248.132 -> 71.687 -> 860.245 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 27.963) 0.036 0.548 7.810 57.992 155.077 208.470 -> 65.158 -> 781.900 MByte/s p07 method 1 =Alltoal :(156.555) 0.006 0.102 1.604 17.169 112.512 208.470 -> 46.759 -> 561.107 MByte/s p07 method 2 =non-blk :( 48.465) 0.021 0.313 4.616 44.958 153.272 208.470 -> 60.420 -> 725.041 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 28.144) 0.036 0.544 7.898 54.972 144.600 183.914 -> 58.125 -> 697.497 MByte/s p08 method 1 =Alltoal :(152.926) 0.007 0.104 1.586 16.323 107.534 183.914 -> 42.114 -> 505.372 MByte/s p08 method 2 =non-blk :( 48.687) 0.021 0.312 4.622 44.194 146.072 183.914 -> 56.538 -> 678.460 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 28.143) 0.036 0.545 7.756 55.247 169.919 241.837 -> 70.914 -> 850.965 MByte/s p09 method 1 =Alltoal :(153.863) 0.006 0.103 1.590 17.179 112.976 241.837 -> 50.131 -> 601.575 MByte/s p09 method 2 =non-blk :( 48.007) 0.021 0.316 4.624 44.107 175.650 241.837 -> 69.665 -> 835.975 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 27.715) 0.036 0.565 8.061 54.908 225.423 341.202 -> 96.332 -> 1155.981 MByte/s p10 method 1 =Alltoal :(159.036) 0.006 0.101 1.575 19.198 126.678 341.202 -> 63.016 -> 756.189 MByte/s p10 method 2 =non-blk :( 47.090) 0.021 0.319 4.804 45.244 218.899 341.202 -> 90.324 -> 1083.891 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 28.293) 0.035 0.549 7.863 55.232 137.092 193.819 -> 59.264 -> 711.169 MByte/s p11 method 1 =Alltoal :(163.287) 0.006 0.099 1.559 15.793 111.064 193.819 -> 43.809 -> 525.707 MByte/s p11 method 2 =non-blk :( 48.827) 0.020 0.315 4.612 44.832 138.662 193.819 -> 57.992 -> 695.906 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 27.820) 0.036 0.547 7.804 56.132 147.789 223.550 -> 64.644 -> 775.732 MByte/s p12 method 1 =Alltoal :(158.335) 0.006 0.100 1.558 16.991 111.396 223.550 -> 47.391 -> 568.696 MByte/s p12 method 2 =non-blk :( 48.410) 0.021 0.316 4.606 45.116 158.059 223.550 -> 62.377 -> 748.524 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 27.914) 0.036 0.562 8.127 56.364 227.685 284.490 -> 82.375 -> 988.500 MByte/s p13 method 1 =Alltoal :(163.332) 0.006 0.098 1.509 18.222 122.739 284.490 -> 55.959 -> 671.511 MByte/s p13 method 2 =non-blk :( 47.143) 0.021 0.325 4.792 44.772 202.099 284.490 -> 78.507 -> 942.089 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 28.196) 0.035 0.545 7.747 56.983 142.467 187.279 -> 60.898 -> 730.779 MByte/s p14 method 1 =Alltoal :(151.545) 0.007 0.103 1.600 16.342 107.879 187.279 -> 43.495 -> 521.941 MByte/s p14 method 2 =non-blk :( 49.298) 0.020 0.310 4.579 44.937 144.433 187.279 -> 57.150 -> 685.804 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 28.019) 0.036 0.551 8.034 60.146 192.967 229.185 -> 70.457 -> 845.482 MByte/s p15 method 1 =Alltoal :(157.540) 0.006 0.102 1.609 17.876 117.823 229.185 -> 48.750 -> 585.005 MByte/s p15 method 2 =non-blk :( 47.965) 0.021 0.325 4.656 46.006 176.578 229.185 -> 68.008 -> 816.094 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 27.750) 0.036 0.567 8.080 59.020 196.075 325.443 -> 92.145 -> 1105.745 MByte/s p16 method 1 =Alltoal :(156.542) 0.006 0.102 1.577 19.070 131.580 325.443 -> 62.193 -> 746.321 MByte/s p16 method 2 =non-blk :( 46.636) 0.021 0.329 4.812 46.465 227.441 325.443 -> 91.055 -> 1092.662 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 28.104) 0.036 0.553 7.719 53.833 152.362 206.192 -> 60.867 -> 730.404 MByte/s p17 method 1 =Alltoal :(154.083) 0.006 0.102 1.556 16.162 105.710 206.192 -> 43.900 -> 526.804 MByte/s p17 method 2 =non-blk :( 49.035) 0.020 0.313 4.581 44.728 142.064 206.192 -> 57.012 -> 684.138 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 27.693) 0.036 0.545 7.983 55.895 163.735 217.361 -> 65.095 -> 781.144 MByte/s p18 method 1 =Alltoal :(163.315) 0.006 0.098 1.533 17.515 117.692 217.361 -> 47.758 -> 573.101 MByte/s p18 method 2 =non-blk :( 48.729) 0.021 0.318 4.697 44.817 173.220 217.361 -> 64.274 -> 771.292 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 27.741) 0.036 0.552 8.016 58.116 153.875 209.391 -> 63.613 -> 763.350 MByte/s p19 method 1 =Alltoal :(156.263) 0.006 0.102 1.607 16.802 111.396 209.391 -> 46.367 -> 556.399 MByte/s p19 method 2 =non-blk :( 48.321) 0.021 0.313 4.638 44.921 149.804 209.391 -> 61.796 -> 741.551 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 27.718) 0.036 0.561 7.883 59.831 174.747 237.978 -> 74.920 -> 899.039 MByte/s p20 method 1 =Alltoal :(160.193) 0.006 0.099 1.554 16.911 119.669 237.978 -> 51.849 -> 622.192 MByte/s p20 method 2 =non-blk :( 47.139) 0.021 0.326 4.672 46.204 193.212 237.978 -> 72.577 -> 870.919 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 28.133) 0.036 0.549 7.873 57.455 144.421 200.203 -> 62.721 -> 752.652 MByte/s p21 method 1 =Alltoal :(154.111) 0.006 0.102 1.560 15.978 106.151 200.203 -> 44.825 -> 537.898 MByte/s p21 method 2 =non-blk :( 48.604) 0.021 0.311 4.642 45.229 144.730 200.203 -> 61.286 -> 735.427 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 28.177) 0.035 0.542 7.865 56.849 135.401 188.769 -> 59.241 -> 710.897 MByte/s p22 method 1 =Alltoal :(153.919) 0.006 0.104 1.588 16.318 106.379 188.769 -> 43.863 -> 526.355 MByte/s p22 method 2 =non-blk :( 48.722) 0.021 0.312 4.538 44.603 145.897 188.769 -> 57.825 -> 693.897 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 27.895) 0.036 0.546 7.815 57.231 148.173 208.154 -> 63.485 -> 761.819 MByte/s p23 method 1 =Alltoal :(156.517) 0.006 0.103 1.612 17.052 111.163 208.154 -> 46.334 -> 556.003 MByte/s p23 method 2 =non-blk :( 49.084) 0.020 0.318 4.582 43.702 159.577 208.154 -> 62.698 -> 752.373 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 28.028) 0.036 0.556 8.011 57.440 140.310 218.741 -> 65.010 -> 780.121 MByte/s p24 method 1 =Alltoal :(157.545) 0.006 0.101 1.562 16.413 112.665 218.741 -> 46.720 -> 560.644 MByte/s p24 method 2 =non-blk :( 47.657) 0.021 0.314 4.683 44.900 160.088 218.741 -> 63.021 -> 756.250 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 28.381) 0.035 0.540 7.652 56.992 130.281 180.482 -> 56.751 -> 681.017 MByte/s p25 method 1 =Alltoal :(147.412) 0.007 0.107 1.624 15.411 103.919 180.482 -> 41.785 -> 501.419 MByte/s p25 method 2 =non-blk :( 49.536) 0.020 0.309 4.534 45.146 135.322 180.482 -> 54.617 -> 655.399 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 27.590) 0.036 0.564 8.099 58.448 188.360 266.529 -> 78.622 -> 943.469 MByte/s p26 method 1 =Alltoal :(156.169) 0.006 0.101 1.581 17.775 111.145 266.529 -> 53.026 -> 636.317 MByte/s p26 method 2 =non-blk :( 48.208) 0.021 0.326 4.814 46.085 175.827 266.529 -> 73.690 -> 884.276 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 27.935) 0.036 0.550 7.881 57.561 161.186 207.971 -> 64.944 -> 779.326 MByte/s p27 method 1 =Alltoal :(154.252) 0.006 0.103 1.599 16.811 112.600 207.971 -> 46.411 -> 556.929 MByte/s p27 method 2 =non-blk :( 47.742) 0.021 0.314 4.630 44.486 155.728 207.971 -> 61.412 -> 736.943 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 27.865) 0.036 0.562 7.954 59.552 200.609 298.825 -> 83.768 -> 1005.214 MByte/s p28 method 1 =Alltoal :(154.336) 0.006 0.103 1.594 18.350 118.651 298.825 -> 56.333 -> 676.001 MByte/s p28 method 2 =non-blk :( 47.685) 0.021 0.328 4.671 47.412 206.695 298.825 -> 81.297 -> 975.566 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 27.874) 0.036 0.552 7.892 57.617 142.615 207.436 -> 64.213 -> 770.550 MByte/s p29 method 1 =Alltoal :(152.126) 0.007 0.104 1.594 16.022 112.392 207.436 -> 46.743 -> 560.911 MByte/s p29 method 2 =non-blk :( 49.236) 0.020 0.312 4.658 45.680 157.170 207.436 -> 61.096 -> 733.153 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 27.967) 0.036 0.548 7.709 57.111 143.763 204.033 -> 61.426 -> 737.108 MByte/s p30 method 1 =Alltoal :(157.753) 0.006 0.102 1.599 16.743 111.062 204.033 -> 46.161 -> 553.934 MByte/s p30 method 2 =non-blk :( 48.465) 0.021 0.312 4.563 43.406 155.231 204.033 -> 60.964 -> 731.563 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 27.593) 0.036 0.564 8.097 58.606 186.481 259.898 -> 76.247 -> 914.961 MByte/s p31 method 1 =Alltoal :(164.782) 0.006 0.097 1.539 18.691 127.507 259.898 -> 55.326 -> 663.907 MByte/s p31 method 2 =non-blk :( 47.063) 0.021 0.325 4.680 45.305 195.815 259.898 -> 77.058 -> 924.702 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 27.470) 0.036 0.566 8.189 59.438 251.923 378.658 -> 104.807 -> 1257.685 MByte/s p32 method 1 =Alltoal :(160.518) 0.006 0.099 1.489 18.919 130.816 378.658 -> 66.945 -> 803.345 MByte/s p32 method 2 =non-blk :( 46.396) 0.022 0.331 4.869 47.017 219.260 378.658 -> 94.878 -> 1138.538 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 27.925) 0.036 0.551 7.765 58.910 173.340 226.514 -> 69.168 -> 830.017 MByte/s p33 method 1 =Alltoal :(157.128) 0.006 0.102 1.585 16.559 115.508 226.514 -> 49.017 -> 588.207 MByte/s p33 method 2 =non-blk :( 47.313) 0.021 0.316 4.570 45.983 168.100 226.514 -> 67.284 -> 807.411 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 27.842) 0.036 0.561 8.098 58.698 208.392 268.844 -> 81.310 -> 975.722 MByte/s p34 method 1 =Alltoal :(157.237) 0.006 0.102 1.581 18.039 127.442 268.844 -> 54.043 -> 648.514 MByte/s p34 method 2 =non-blk :( 47.564) 0.021 0.325 4.787 46.046 204.034 268.844 -> 78.617 -> 943.399 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 28.215) 0.035 0.542 7.814 57.319 139.194 192.137 -> 59.797 -> 717.569 MByte/s p35 method 1 =Alltoal :(155.876) 0.006 0.102 1.613 16.478 108.351 192.137 -> 44.225 -> 530.695 MByte/s p35 method 2 =non-blk :( 49.264) 0.020 0.312 4.629 44.259 143.349 192.137 -> 57.965 -> 695.586 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 28.052) 0.036 0.562 7.908 59.020 181.250 236.769 -> 74.650 -> 895.802 MByte/s p36 method 1 =Alltoal :(149.414) 0.007 0.106 1.647 17.831 112.906 236.769 -> 49.745 -> 596.936 MByte/s p36 method 2 =non-blk :( 47.485) 0.021 0.323 4.679 46.393 177.264 236.769 -> 69.773 -> 837.275 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 24.696) 0.020 0.305 4.388 37.372 157.249 230.494 -> 65.543 -> 786.514 MByte/s p37 method 1 =Alltoal :(149.791) 0.003 0.053 0.785 9.739 88.669 230.494 -> 43.135 -> 517.622 MByte/s p37 method 2 =non-blk :( 25.993) 0.019 0.294 4.564 45.282 156.056 230.494 -> 63.155 -> 757.859 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 24.522) 0.020 0.304 4.375 37.495 176.976 232.410 -> 67.996 -> 815.947 MByte/s p38 method 1 =Alltoal :(151.472) 0.003 0.053 0.809 11.703 140.802 232.410 -> 54.530 -> 654.357 MByte/s p38 method 2 =non-blk :( 25.800) 0.019 0.295 4.596 46.070 204.989 232.410 -> 74.066 -> 888.794 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 23.075) 0.004 0.054 0.769 6.570 39.736 64.423 -> 16.843 -> 202.114 MByte/s p39 method 1 =Alltoal :(-------) 0.000 0.000 0.000 0.000 0.000 64.423 -> 6.058 -> 72.701 MByte/s p39 method 2 =non-blk :(-------) 0.000 0.000 0.000 0.000 0.000 64.423 -> 6.058 -> 72.701 MByte/s p40 acyclic-2dim-all p40 method 0 =Sndrcv :( 21.464) 0.033 0.510 7.288 56.314 193.533 257.810 -> 78.608 -> 943.299 MByte/s p40 method 1 =Alltoal :( 75.522) 0.009 0.147 2.186 24.505 170.631 257.810 -> 65.570 -> 786.840 MByte/s p40 method 2 =non-blk :( 37.948) 0.019 0.290 4.161 42.393 216.041 257.810 -> 81.608 -> 979.295 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 25.540) 0.022 0.328 4.702 36.768 149.518 218.276 -> 60.925 -> 731.099 MByte/s p41 method 1 =Alltoal :( 51.167) 0.011 0.169 2.540 25.231 130.769 218.276 -> 51.906 -> 622.868 MByte/s p41 method 2 =non-blk :( 29.018) 0.019 0.298 4.230 39.310 139.319 218.276 -> 59.107 -> 709.283 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 15.555) 0.064 1.021 14.433 125.996 395.648 511.079 -> 166.533 -> 1998.390 MByte/s p42 method 1 =Alltoal :(150.293) 0.007 0.106 1.566 23.160 146.272 511.079 -> 84.982 -> 1019.788 MByte/s p42 method 2 =non-blk :( 34.021) 0.029 0.465 6.778 80.890 418.232 511.079 -> 157.632 -> 1891.581 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 27.859) 0.036 0.555 7.910 59.604 151.256 209.590 -> 62.838 -> 754.056 MByte/s p43 method 1 =Alltoal :(152.023) 0.007 0.103 1.567 15.881 103.801 209.590 -> 44.713 -> 536.557 MByte/s p43 method 2 =non-blk :( 47.396) 0.021 0.318 4.708 46.706 128.491 209.590 -> 58.669 -> 704.029 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 21.698) 0.046 0.704 9.943 77.348 228.264 296.394 -> 89.662 -> 1075.944 MByte/s p44 method 1 =Alltoal :( 75.959) 0.013 0.203 3.020 31.139 173.198 296.394 -> 69.666 -> 835.986 MByte/s p44 method 2 =non-blk :( 41.868) 0.024 0.366 5.375 56.326 240.763 296.394 -> 88.455 -> 1061.458 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 27.703) 0.036 0.560 7.899 57.552 133.376 209.739 -> 62.998 -> 755.981 MByte/s p45 method 1 =Alltoal :(151.462) 0.007 0.103 1.547 15.724 101.584 209.739 -> 45.046 -> 540.553 MByte/s p45 method 2 =non-blk :( 48.000) 0.021 0.320 4.532 45.199 133.128 209.739 -> 57.989 -> 695.866 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 27.873) 0.036 0.556 8.006 58.817 157.387 184.657 -> 61.646 -> 739.754 MByte/s p46 method 1 =Alltoal :(298.838) 0.003 0.053 0.807 9.994 85.009 184.657 -> 38.463 -> 461.561 MByte/s p46 method 2 =non-blk :( 51.820) 0.019 0.293 4.383 43.088 153.221 184.657 -> 58.000 -> 696.005 MByte/s p47 cyclic-3dim-z p47 method 0 =Sndrcv :( 27.986) 0.036 0.554 7.979 58.249 157.622 185.265 -> 62.315 -> 747.777 MByte/s p47 method 1 =Alltoal :(299.662) 0.003 0.052 0.814 9.799 89.012 185.265 -> 38.588 -> 463.050 MByte/s p47 method 2 =non-blk :( 51.999) 0.019 0.291 4.376 43.644 159.328 185.265 -> 58.385 -> 700.622 MByte/s p48 cyclic-3dim-all p48 method 0 =Sndrcv :( 28.337) 0.035 0.528 7.579 55.434 152.000 206.111 -> 63.720 -> 764.635 MByte/s p48 method 1 =Alltoal :( 76.365) 0.013 0.203 3.043 28.459 134.946 206.111 -> 52.858 -> 634.302 MByte/s p48 method 2 =non-blk :( 47.139) 0.021 0.322 4.647 44.765 132.593 206.111 -> 56.246 -> 674.949 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.036 0.547 7.818 56.621 150.523 221.940 || 65.339 -> 784.072 MByte/s - ring, method 1 = Alltoal: 0.006 0.092 1.385 14.579 102.826 221.940 || 45.435 -> 545.223 MByte/s - ring, method 2 = non-blk: 0.020 0.311 4.609 44.736 145.631 221.940 || 60.936 -> 731.226 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.036 0.553 7.912 57.343 165.850 230.479 || 69.419 -> 833.031 MByte/s - random, method 1 = Alltoal: 0.006 0.101 1.576 17.129 114.870 230.479 || 49.209 -> 590.502 MByte/s - random, method 2 = non-blk: 0.021 0.318 4.662 45.219 168.278 230.479 || 66.971 -> 803.655 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.036 0.550 7.865 56.981 158.001 226.169 || 67.348 -> 808.181 MByte/s - average, method 1 = Alltoal: 0.006 0.097 1.477 15.803 108.682 226.169 || 47.284 -> 567.411 MByte/s - average, method 2 = non-blk: 0.020 0.314 4.635 44.976 156.545 226.169 || 63.882 -> 766.586 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.428 6.599 94.380 683.769 1896.011 2714.031 || 808.181 MByte/s - accumulated, mthd 1 = Alltoal: 0.074 1.160 17.729 189.635 1304.179 2714.031 || 567.411 MByte/s - accumulated, mthd 2 = non-blk: 0.246 3.771 55.623 539.717 1878.546 2714.031 || 766.586 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 0.428 0.036 0.036 0.036 0.036 0.006 0.020 2 0.855 0.071 0.071 0.071 0.071 0.012 0.041 4 1.689 0.141 0.140 0.141 0.141 0.024 0.081 8 3.430 0.286 0.285 0.287 0.286 0.049 0.164 16 6.599 0.550 0.547 0.553 0.550 0.097 0.314 32 13.033 1.086 1.084 1.088 1.086 0.191 0.618 64 25.721 2.143 2.137 2.149 2.143 0.382 1.230 128 49.455 4.121 4.112 4.130 4.121 0.754 2.406 256 94.380 7.865 7.818 7.912 7.865 1.477 4.635 512 185.549 15.462 15.429 15.496 15.462 2.918 9.118 1024 366.861 30.572 30.192 30.956 30.572 5.818 18.274 2048 442.317 36.860 37.035 36.685 36.860 9.189 27.779 4096 683.769 56.981 56.621 57.343 56.981 15.803 44.976 10624 875.855 72.988 70.160 75.930 69.735 29.329 72.123 27554 1328.536 110.711 105.163 116.552 101.037 51.985 109.415 71468 1448.073 120.673 114.170 127.546 118.667 76.670 116.232 185364 1935.644 161.304 151.355 171.906 158.001 108.682 156.545 480774 2054.692 171.224 161.681 181.332 170.523 119.829 153.965 1246974 2415.769 201.314 194.554 208.309 200.220 130.859 183.371 3234251 2528.131 210.678 205.776 215.696 210.678 210.678 210.678 8388608 2714.031 226.169 221.940 230.479 226.169 226.169 226.169 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-6*2fix :( 27.918) 0.036 0.553 7.861 52.389 159.826 188.360 -> 62.095 -> 745.135 MByte/s p01 ring-3*4fix :( 27.737) 0.036 0.555 7.872 56.441 185.317 280.377 -> 81.823 -> 981.871 MByte/s p02 ring-1*12fix :( 28.267) 0.035 0.544 7.778 55.652 142.753 203.004 -> 62.164 -> 745.972 MByte/s p03 ring-1*12fix :( 28.387) 0.035 0.545 7.864 58.206 142.118 220.379 -> 63.387 -> 760.642 MByte/s p04 ring-1*12fix :( 28.178) 0.035 0.540 7.681 57.959 145.811 224.492 -> 64.166 -> 769.992 MByte/s p05 ring-1*12fix :( 28.245) 0.035 0.546 7.856 59.355 137.215 225.321 -> 63.356 -> 760.272 MByte/s p06 random-cyc-1dim :( 27.700) 0.036 0.554 7.904 57.023 180.119 248.132 -> 74.766 -> 897.190 MByte/s p07 random-cyc-1dim :( 27.963) 0.036 0.548 7.810 57.992 155.077 208.470 -> 65.694 -> 788.333 MByte/s p08 random-cyc-1dim :( 28.144) 0.036 0.544 7.898 54.972 146.072 183.914 -> 59.193 -> 710.320 MByte/s p09 random-cyc-1dim :( 28.143) 0.036 0.545 7.756 55.247 175.650 241.837 -> 72.791 -> 873.493 MByte/s p10 random-cyc-1dim :( 27.715) 0.036 0.565 8.061 54.908 225.423 341.202 -> 96.903 -> 1162.841 MByte/s p11 random-cyc-1dim :( 28.293) 0.035 0.549 7.863 55.232 138.662 193.819 -> 60.609 -> 727.306 MByte/s p12 random-cyc-1dim :( 27.820) 0.036 0.547 7.804 56.132 158.059 223.550 -> 66.162 -> 793.940 MByte/s p13 random-cyc-1dim :( 27.914) 0.036 0.562 8.127 56.364 227.685 284.490 -> 84.300 -> 1011.600 MByte/s p14 random-cyc-1dim :( 28.196) 0.035 0.545 7.747 56.983 144.433 187.279 -> 62.079 -> 744.948 MByte/s p15 random-cyc-1dim :( 28.019) 0.036 0.551 8.034 60.146 192.967 229.185 -> 72.118 -> 865.417 MByte/s p16 random-cyc-1dim :( 27.750) 0.036 0.567 8.080 59.020 227.441 325.443 -> 94.561 -> 1134.728 MByte/s p17 random-cyc-1dim :( 28.104) 0.036 0.553 7.719 53.833 152.362 206.192 -> 61.964 -> 743.568 MByte/s p18 random-cyc-1dim :( 27.693) 0.036 0.545 7.983 55.895 173.220 217.361 -> 67.023 -> 804.277 MByte/s p19 random-cyc-1dim :( 27.741) 0.036 0.552 8.016 58.116 153.875 209.391 -> 64.755 -> 777.066 MByte/s p20 random-cyc-1dim :( 27.718) 0.036 0.561 7.883 59.831 193.212 237.978 -> 76.825 -> 921.896 MByte/s p21 random-cyc-1dim :( 28.133) 0.036 0.549 7.873 57.455 144.730 200.203 -> 63.789 -> 765.470 MByte/s p22 random-cyc-1dim :( 28.177) 0.035 0.542 7.865 56.849 145.897 188.769 -> 60.511 -> 726.126 MByte/s p23 random-cyc-1dim :( 27.895) 0.036 0.546 7.815 57.231 159.577 208.154 -> 65.250 -> 783.001 MByte/s p24 random-cyc-1dim :( 28.028) 0.036 0.556 8.011 57.440 160.088 218.741 -> 66.812 -> 801.747 MByte/s p25 random-cyc-1dim :( 28.381) 0.035 0.540 7.652 56.992 135.322 180.482 -> 57.694 -> 692.325 MByte/s p26 random-cyc-1dim :( 27.590) 0.036 0.564 8.099 58.448 188.360 266.529 -> 79.291 -> 951.496 MByte/s p27 random-cyc-1dim :( 27.935) 0.036 0.550 7.881 57.561 161.186 207.971 -> 65.743 -> 788.918 MByte/s p28 random-cyc-1dim :( 27.865) 0.036 0.562 7.954 59.552 206.695 298.825 -> 84.600 -> 1015.195 MByte/s p29 random-cyc-1dim :( 27.874) 0.036 0.552 7.892 57.617 157.170 207.436 -> 66.198 -> 794.378 MByte/s p30 random-cyc-1dim :( 27.967) 0.036 0.548 7.709 57.111 155.231 204.033 -> 63.740 -> 764.876 MByte/s p31 random-cyc-1dim :( 27.593) 0.036 0.564 8.097 58.606 195.815 259.898 -> 79.917 -> 959.008 MByte/s p32 random-cyc-1dim :( 27.470) 0.036 0.566 8.189 59.438 251.923 378.658 -> 105.469 -> 1265.630 MByte/s p33 random-cyc-1dim :( 27.925) 0.036 0.551 7.765 58.910 173.340 226.514 -> 70.482 -> 845.785 MByte/s p34 random-cyc-1dim :( 27.842) 0.036 0.561 8.098 58.698 208.392 268.844 -> 82.576 -> 990.907 MByte/s p35 random-cyc-1dim :( 28.215) 0.035 0.542 7.814 57.319 143.349 192.137 -> 60.666 -> 727.997 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 28.052) 0.036 0.562 7.908 59.020 181.250 236.769 -> 74.828 -> 897.931 MByte/s p37 best bi-section :( 24.696) 0.020 0.305 4.564 45.282 157.249 230.494 -> 67.687 -> 812.249 MByte/s p38 worst bi-section :( 24.522) 0.020 0.304 4.596 46.070 204.989 232.410 -> 74.344 -> 892.122 MByte/s p39 one PingPong Pair :( 23.075) 0.004 0.054 0.769 6.570 39.736 64.423 -> 16.843 -> 202.114 MByte/s p40 acyclic-2dim-all :( 21.464) 0.033 0.510 7.288 56.314 216.041 257.810 -> 83.921 -> 1007.051 MByte/s p41 acyclic-3dim-all :( 25.540) 0.022 0.328 4.702 39.310 149.518 218.276 -> 62.740 -> 752.877 MByte/s p42 cyclic-2dim-x :( 15.555) 0.064 1.021 14.433 125.996 418.232 511.079 -> 168.339 -> 2020.068 MByte/s p43 cyclic-2dim-y :( 27.859) 0.036 0.555 7.910 59.604 151.256 209.590 -> 63.110 -> 757.325 MByte/s p44 cyclic-2dim-all :( 21.698) 0.046 0.704 9.943 77.348 240.763 296.394 -> 92.189 -> 1106.272 MByte/s p45 cyclic-3dim-x :( 27.703) 0.036 0.560 7.899 57.552 133.376 209.739 -> 63.204 -> 758.450 MByte/s p46 cyclic-3dim-y :( 27.873) 0.036 0.556 8.006 58.817 157.387 184.657 -> 61.720 -> 740.640 MByte/s p47 cyclic-3dim-z :( 27.986) 0.036 0.554 7.979 58.249 159.328 185.265 -> 62.396 -> 748.752 MByte/s p48 cyclic-3dim-all :( 28.337) 0.035 0.528 7.579 55.434 152.000 206.111 -> 63.720 -> 764.635 MByte/s log_avg of all rings : 0.036 0.547 7.818 56.621 151.355 221.940 || 65.830 -> 789.965 MByte/s log_avg of all random : 0.036 0.553 7.912 57.343 171.906 230.479 || 70.866 -> 850.397 MByte/s log_avg(ring,random) : 0.036 0.550 7.865 56.981 161.304 226.169 || 68.302 -> 819.624 MByte/s * size -> accumulated on all pr.: 0.428 6.599 94.380 683.769 1935.644 2714.031 || 819.624 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 819.624 MByte/s on 12 processes ( = 68.302 MByte/s * 12 processes) Ping-pong latency: 23.075 microsec Ping-pong bandwidth: 773.075 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 12 nodes, 1024 MB/node system name : HI-UX/MPP hostname : himiko OS release : 03-00 OS version : ad2b0 machine : SR8000 Date of measurement: Mon Nov 29 13:46:06 1999 Total execution wall clock time = 82 seconds SECTION-BEFF-END b_eff = 819.624 MB/s = 68.302 * 12 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000