b_eff = 775.710 MB/s = 48.482 * 16 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 = 16 2-dim-paterns: size = 4 * 4 3-dim-paterns: size = 4 * 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-8*2fix 1=ring-4*4fix 2=ring-2*8fix 3=ring-1*16fix 4=ring-1*16fix 5=ring-1*16fix 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: 141.014 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 9.5e-01 5.0e-03 3.9e-02 228 7.4e-01 3.7e-03 2.6e-02 228 7.3e-01 3.8e-03 2.7e-02 2 150 4.7e-01 2.4e-03 1.8e-02 154 4.9e-01 2.6e-03 1.9e-02 151 4.9e-01 2.5e-03 1.9e-02 4 153 5.0e-01 2.6e-03 2.3e-02 149 4.8e-01 2.6e-03 2.0e-02 152 5.0e-01 2.6e-03 1.8e-02 8 147 4.8e-01 2.4e-03 1.8e-02 144 4.7e-01 2.4e-03 2.1e-02 145 4.8e-01 2.4e-03 1.8e-02 16 152 5.2e-01 4.8e-03 2.3e-02 152 5.1e-01 2.5e-03 1.8e-02 154 5.1e-01 2.5e-03 2.0e-02 32 78 2.6e-01 1.4e-03 1.1e-02 149 5.0e-01 2.6e-03 1.8e-02 151 5.0e-01 2.6e-03 2.0e-02 64 142 4.9e-01 2.6e-03 1.9e-02 145 4.9e-01 2.6e-03 1.8e-02 144 4.9e-01 2.6e-03 2.0e-02 128 138 5.0e-01 2.7e-03 1.9e-02 140 5.0e-01 2.6e-03 1.8e-02 141 5.3e-01 2.6e-03 2.8e-02 256 127 4.8e-01 2.5e-03 1.7e-02 132 4.7e-01 2.5e-03 1.7e-02 134 4.8e-01 2.6e-03 1.8e-02 512 126 4.9e-01 2.7e-03 1.8e-02 134 4.8e-01 2.7e-03 1.9e-02 131 4.8e-01 2.7e-03 1.8e-02 1024 115 4.5e-01 2.5e-03 1.9e-02 124 4.6e-01 2.6e-03 1.7e-02 119 4.6e-01 2.5e-03 1.8e-02 2048 113 8.0e-01 3.1e-03 2.9e-02 118 7.8e-01 3.4e-03 2.7e-02 117 7.7e-01 3.2e-03 3.1e-02 4096 91 7.5e-01 3.3e-03 2.7e-02 86 7.4e-01 3.1e-03 3.9e-02 90 7.8e-01 3.3e-03 2.6e-02 10624 53 9.4e-01 2.9e-03 4.5e-02 53 9.4e-01 2.9e-03 4.0e-02 52 9.2e-01 3.0e-03 4.3e-02 27554 35 1.1e+00 3.2e-03 6.2e-02 35 1.1e+00 3.0e-03 4.7e-02 33 1.0e+00 3.2e-03 5.7e-02 71468 21 1.4e+00 4.0e-03 5.9e-02 22 1.5e+00 4.1e-03 5.9e-02 19 1.3e+00 3.8e-03 5.4e-02 185364 10 1.3e+00 4.1e-03 5.6e-02 10 1.3e+00 3.9e-03 5.6e-02 9 1.2e+00 3.5e-03 5.1e-02 480774 4 1.2e+00 3.8e-03 5.9e-02 4 1.2e+00 3.7e-03 6.1e-02 4 1.3e+00 3.7e-03 6.0e-02 1246974 2 1.6e+00 5.1e-03 8.0e-02 2 1.6e+00 4.9e-03 7.8e-02 2 1.5e+00 5.4e-03 8.3e-02 3234251 1 1.1e+00 1.7e-02 7.1e-02 M 1 1.1e+00 1.4e-02 6.5e-02 M 1 1.3e+00 2.1e-02 6.6e-02 M 8388608 1 2.7e+00 4.5e-02 1.6e-01 R 1 2.9e+00 3.6e-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 6.3e+00 1.2e-01 2.1e-01 27 5.7e-01 1.1e-02 2.1e-02 9 1.9e-01 3.5e-03 5.8e-03 2 150 3.1e+00 6.0e-02 7.9e-02 13 2.7e-01 5.1e-03 8.7e-03 6 1.2e-01 2.4e-03 3.3e-03 4 75 1.6e+00 3.0e-02 4.6e-02 6 1.2e-01 2.3e-03 3.1e-03 6 1.5e-01 2.3e-03 1.1e-02 8 37 9.9e-01 1.5e-02 9.5e-02 6 1.3e-01 2.3e-03 3.8e-03 6 2.9e-01 2.3e-03 1.7e-01 16 18 3.9e-01 7.2e-03 1.4e-02 6 1.2e-01 2.3e-03 3.4e-03 6 1.3e-01 2.4e-03 8.9e-03 32 9 2.1e-01 3.5e-03 2.3e-02 6 1.2e-01 2.3e-03 3.2e-03 6 1.3e-01 2.3e-03 6.3e-03 64 6 1.2e-01 2.4e-03 3.1e-03 6 1.3e-01 2.3e-03 3.2e-03 6 1.2e-01 2.4e-03 4.4e-03 128 6 1.3e-01 2.4e-03 5.0e-03 6 1.3e-01 2.4e-03 3.4e-03 6 1.4e-01 2.4e-03 1.2e-02 256 6 1.3e-01 2.4e-03 3.9e-03 6 1.3e-01 2.4e-03 6.4e-03 6 1.3e-01 2.4e-03 6.8e-03 512 6 1.3e-01 2.4e-03 6.0e-03 6 1.3e-01 2.4e-03 3.2e-03 6 1.3e-01 2.4e-03 6.3e-03 1024 6 1.3e-01 2.4e-03 4.2e-03 6 1.4e-01 2.4e-03 7.3e-03 6 1.4e-01 2.4e-03 1.1e-02 2048 6 2.0e-01 2.5e-03 1.7e-02 6 1.7e-01 2.5e-03 9.7e-03 6 1.7e-01 2.5e-03 9.9e-03 4096 6 1.8e-01 2.8e-03 5.7e-03 6 1.8e-01 2.6e-03 5.1e-03 6 1.8e-01 2.6e-03 4.6e-03 10624 4 1.6e-01 2.1e-03 4.2e-03 4 1.7e-01 2.3e-03 6.7e-03 4 1.7e-01 2.1e-03 5.9e-03 27554 3 1.8e-01 2.0e-03 5.8e-03 3 1.9e-01 2.0e-03 8.2e-03 3 1.8e-01 2.2e-03 6.4e-03 71468 2 2.2e-01 2.0e-03 9.2e-03 2 2.1e-01 2.0e-03 6.0e-03 2 2.0e-01 2.0e-03 5.8e-03 185364 1 2.4e-01 2.0e-03 9.2e-03 1 2.1e-01 1.9e-03 7.2e-03 1 2.0e-01 1.8e-03 6.2e-03 480774 1 5.0e-01 4.0e-03 1.7e-02 1 4.8e-01 4.9e-03 1.7e-02 1 4.8e-01 4.3e-03 1.7e-02 1246974 1 1.1e+00 9.1e-03 4.4e-02 1 1.1e+00 9.2e-03 5.0e-02 1 1.1e+00 9.2e-03 4.9e-02 3234251 1 2.7e-02 2.7e-02 2.7e-02 M 1 1.1e-01 2.8e-02 4.5e-02 M 1 7.0e-02 2.6e-02 4.4e-02 M 8388608 1 6.8e-02 6.8e-02 6.8e-02 R 1 2.9e-01 6.8e-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 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 1.6e+00 1.2e-02 5.5e-02 93 4.9e-01 3.6e-03 1.7e-02 97 5.1e-01 3.7e-03 2.1e-02 2 150 7.9e-01 6.1e-03 3.1e-02 65 3.4e-01 2.6e-03 1.2e-02 65 3.3e-01 2.5e-03 1.6e-02 4 75 3.9e-01 3.0e-03 1.4e-02 61 3.1e-01 2.4e-03 1.1e-02 65 3.5e-01 2.5e-03 1.2e-02 8 62 3.2e-01 2.5e-03 1.1e-02 64 3.4e-01 2.4e-03 1.8e-02 64 3.3e-01 2.4e-03 1.3e-02 16 62 3.3e-01 2.8e-03 1.3e-02 65 3.5e-01 2.6e-03 1.2e-02 65 3.5e-01 2.5e-03 1.5e-02 32 54 3.0e-01 2.2e-03 1.1e-02 63 3.4e-01 2.4e-03 1.2e-02 63 3.3e-01 2.4e-03 1.2e-02 64 62 3.4e-01 2.5e-03 1.2e-02 64 3.5e-01 2.5e-03 1.3e-02 64 3.5e-01 2.5e-03 1.2e-02 128 61 3.5e-01 2.6e-03 1.4e-02 63 3.4e-01 2.6e-03 1.3e-02 63 3.6e-01 2.7e-03 1.9e-02 256 59 3.5e-01 2.6e-03 1.4e-02 61 3.4e-01 2.6e-03 1.2e-02 59 3.2e-01 2.4e-03 1.2e-02 512 56 3.4e-01 2.5e-03 1.9e-02 59 3.3e-01 2.4e-03 1.2e-02 61 3.4e-01 2.5e-03 1.2e-02 1024 56 3.4e-01 2.7e-03 1.2e-02 60 3.5e-01 2.5e-03 1.5e-02 60 3.4e-01 2.6e-03 1.3e-02 2048 52 4.4e-01 2.6e-03 1.4e-02 59 4.7e-01 2.8e-03 1.7e-02 57 4.6e-01 2.8e-03 1.6e-02 4096 49 4.7e-01 2.7e-03 1.6e-02 51 5.0e-01 2.8e-03 1.7e-02 51 5.0e-01 3.0e-03 1.7e-02 10624 34 5.3e-01 3.1e-03 1.8e-02 34 5.2e-01 2.7e-03 1.7e-02 32 4.8e-01 2.8e-03 1.8e-02 27554 21 5.4e-01 2.4e-03 1.8e-02 24 6.0e-01 2.8e-03 2.0e-02 21 5.3e-01 2.4e-03 1.9e-02 71468 16 9.8e-01 3.7e-03 3.5e-02 16 9.6e-01 3.2e-03 3.3e-02 17 1.0e+00 3.9e-03 3.5e-02 185364 8 9.2e-01 3.6e-03 3.2e-02 9 1.0e+00 3.9e-03 3.5e-02 8 9.1e-01 3.6e-03 3.3e-02 480774 4 1.2e+00 3.9e-03 4.6e-02 4 1.1e+00 3.8e-03 4.4e-02 4 1.1e+00 3.7e-03 4.4e-02 1246974 1 8.4e-01 2.4e-03 4.9e-02 2 1.6e+00 4.8e-03 8.2e-02 2 1.7e+00 4.7e-03 8.5e-02 3234251 1 6.5e-01 7.4e-03 1.1e-01 M 1 4.3e-01 7.3e-03 7.4e-02 M 1 3.8e-01 7.1e-03 5.6e-02 M 8388608 1 1.4e+00 1.8e-02 1.6e-01 R 1 1.0e+00 1.9e-02 1.5e-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 = 141.014 sec sum of max elapsed time per entries above = 139.976 sec difference to elapsed time = 1.038 sec = 0.7% sum based on fastest repetition = 120.275 sec difference to elapsed time = 20.740 sec = 14.7% 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-8*2fix 1 16 1.00 1.00 0 ( 0 0 0 ) p01 ring-4*4fix 2 32 2.00 1.00 0 ( 0 0 0 ) p02 ring-2*8fix 2 32 2.00 1.00 0 ( 0 0 0 ) p03 ring-1*16fix 2 32 2.00 1.00 0 ( 0 0 0 ) p04 ring-1*16fix 2 32 2.00 1.00 0 ( 0 0 0 ) p05 ring-1*16fix 2 32 2.00 1.00 0 ( 0 0 0 ) p06 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 2 ) p07 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p08 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 2 0 ) p09 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 0 0 ) p10 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 2 2 ) p11 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 2 2 ) p12 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p13 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 2 0 ) p14 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 0 2 ) p15 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 0 0 ) p16 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p17 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p18 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 1 0 ) p19 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p20 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 2 0 ) p21 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 2 ) p22 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p23 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 0 0 ) p24 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 2 0 ) p25 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p26 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p27 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p28 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p29 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p30 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 0 0 ) p31 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 1 ) p32 random-cyc-1dim 2 32 2.00 1.00 0 ( 2 2 0 ) p33 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p34 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p35 random-cyc-1dim 2 32 2.00 1.00 0 ( 0 2 0 ) p36 worst-cyc-1dim 2 32 2.00 1.00 0 ( 0 0 0 ) p37 best bi-section 2 16 1.00 0.50 0 ( 2 1 2 ) p38 worst bi-section 2 16 1.00 0.50 0 ( 1 1 1 ) p39 one PingPong Pair 2 2 1.00 0.50 14 ( 0 0 0 ) p40 acyclic-2dim-all 4 48 3.00 0.75 0 ( 2 2 2 ) p41 acyclic-3dim-all 6 56 3.50 0.58 0 ( 2 2 2 ) p42 cyclic-2dim-x 2 32 2.00 1.00 0 ( 2 2 2 ) p43 cyclic-2dim-y 2 32 2.00 1.00 0 ( 0 0 0 ) p44 cyclic-2dim-all 4 64 4.00 1.00 0 ( 2 2 2 ) p45 cyclic-3dim-x 2 32 2.00 1.00 0 ( 2 0 2 ) p46 cyclic-3dim-y 1 16 1.00 1.00 0 ( 2 2 2 ) p47 cyclic-3dim-z 1 16 1.00 1.00 0 ( 2 2 0 ) p48 cyclic-3dim-all 4 64 4.00 1.00 0 ( 2 2 2 ) 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-8*2fix : 37.135 25.854 35.410 -> 37.135 -> 594.167 MByte/s p01 ring-4*4fix : 38.918 30.509 37.016 -> 38.918 -> 622.686 MByte/s p02 ring-2*8fix : 39.245 29.626 36.440 -> 39.245 -> 627.921 MByte/s p03 ring-1*16fix : 40.267 26.077 37.035 -> 40.267 -> 644.279 MByte/s p04 ring-1*16fix : 39.981 24.875 36.056 -> 39.981 -> 639.699 MByte/s p05 ring-1*16fix : 40.409 26.249 37.811 -> 40.409 -> 646.552 MByte/s p06 random-cyc-1dim : 69.734 38.350 63.102 -> 69.734 -> 1115.745 MByte/s p07 random-cyc-1dim : 58.344 35.490 56.804 -> 58.344 -> 933.509 MByte/s p08 random-cyc-1dim : 47.914 28.119 44.797 -> 47.914 -> 766.631 MByte/s p09 random-cyc-1dim : 61.267 35.976 53.773 -> 61.267 -> 980.268 MByte/s p10 random-cyc-1dim : 75.217 40.587 68.670 -> 75.217 -> 1203.467 MByte/s p11 random-cyc-1dim : 64.720 33.531 60.930 -> 64.720 -> 1035.524 MByte/s p12 random-cyc-1dim : 47.677 29.967 44.517 -> 47.677 -> 762.831 MByte/s p13 random-cyc-1dim : 67.203 39.921 59.073 -> 67.203 -> 1075.252 MByte/s p14 random-cyc-1dim : 55.930 32.962 51.611 -> 55.930 -> 894.885 MByte/s p15 random-cyc-1dim : 56.810 33.061 54.284 -> 56.810 -> 908.963 MByte/s p16 random-cyc-1dim : 55.556 32.285 53.045 -> 55.556 -> 888.895 MByte/s p17 random-cyc-1dim : 66.240 36.280 61.277 -> 66.240 -> 1059.834 MByte/s p18 random-cyc-1dim : 68.788 32.714 60.313 -> 68.788 -> 1100.614 MByte/s p19 random-cyc-1dim : 46.544 31.131 43.519 -> 46.544 -> 744.703 MByte/s p20 random-cyc-1dim : 50.915 28.132 49.843 -> 50.915 -> 814.646 MByte/s p21 random-cyc-1dim : 59.815 33.296 58.566 -> 59.815 -> 957.044 MByte/s p22 random-cyc-1dim : 48.435 31.427 46.742 -> 48.435 -> 774.967 MByte/s p23 random-cyc-1dim : 55.911 34.318 50.919 -> 55.911 -> 894.576 MByte/s p24 random-cyc-1dim : 50.174 33.452 48.114 -> 50.174 -> 802.783 MByte/s p25 random-cyc-1dim : 43.997 30.356 40.695 -> 43.997 -> 703.953 MByte/s p26 random-cyc-1dim : 54.763 31.182 50.959 -> 54.763 -> 876.214 MByte/s p27 random-cyc-1dim : 63.059 40.273 59.087 -> 63.059 -> 1008.951 MByte/s p28 random-cyc-1dim : 51.019 30.623 50.496 -> 51.019 -> 816.312 MByte/s p29 random-cyc-1dim : 77.061 44.073 67.497 -> 77.061 -> 1232.969 MByte/s p30 random-cyc-1dim : 51.085 31.918 48.900 -> 51.085 -> 817.355 MByte/s p31 random-cyc-1dim : 53.461 30.737 51.850 -> 53.461 -> 855.373 MByte/s p32 random-cyc-1dim : 61.284 35.117 58.133 -> 61.284 -> 980.544 MByte/s p33 random-cyc-1dim : 55.807 34.816 53.548 -> 55.807 -> 892.911 MByte/s p34 random-cyc-1dim : 66.552 36.800 63.767 -> 66.552 -> 1064.827 MByte/s p35 random-cyc-1dim : 63.023 34.932 57.474 -> 63.023 -> 1008.372 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 69.112 37.803 64.515 -> 69.112 -> 1105.786 MByte/s p37 best bi-section : 29.085 25.030 37.020 -> 37.020 -> 592.323 MByte/s p38 worst bi-section : 35.979 27.046 36.596 -> 36.596 -> 585.537 MByte/s p39 one PingPong Pair : 2.017 0.603 0.603 -> 2.017 -> 32.272 MByte/s p40 acyclic-2dim-all : 53.253 49.402 56.965 -> 56.965 -> 911.437 MByte/s p41 acyclic-3dim-all : 60.409 62.853 88.786 -> 88.786 -> 1420.575 MByte/s p42 cyclic-2dim-x : 150.799 67.804 137.507 -> 150.799 -> 2412.788 MByte/s p43 cyclic-2dim-y : 39.140 30.182 37.699 -> 39.140 -> 626.241 MByte/s p44 cyclic-2dim-all : 61.803 55.161 65.914 -> 65.914 -> 1054.630 MByte/s p45 cyclic-3dim-x : 153.778 70.371 145.707 -> 153.778 -> 2460.445 MByte/s p46 cyclic-3dim-y : 159.688 66.851 141.662 -> 159.688 -> 2555.007 MByte/s p47 cyclic-3dim-z : 38.253 25.368 37.704 -> 38.253 -> 612.051 MByte/s p48 cyclic-3dim-all : 90.889 71.846 101.568 -> 101.568 -> 1625.095 MByte/s log_avg of all rings : 39.310 27.120 36.620 || 39.310 -> 628.959 MByte/s log_avg of all random : 57.675 33.866 53.961 || 57.675 -> 922.794 MByte/s log_avg(ring,random) : 47.615 30.306 44.453 ||( 47.615 -> 761.840)MByte/s * size -> accumulated on all pr.: 761.840 484.894 711.245 ||(761.840)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-8*2fix : 36.819 36.857 37.045 -> 37.045 -> 592.723 MByte/s p01 ring-4*4fix : 35.763 38.402 38.631 -> 38.631 -> 618.097 MByte/s p02 ring-2*8fix : 37.337 38.279 38.534 -> 38.534 -> 616.540 MByte/s p03 ring-1*16fix : 39.001 39.102 39.614 -> 39.614 -> 633.831 MByte/s p04 ring-1*16fix : 39.754 38.394 39.135 -> 39.754 -> 636.064 MByte/s p05 ring-1*16fix : 40.208 38.881 39.778 -> 40.208 -> 643.331 MByte/s p06 random-cyc-1dim : 54.783 68.464 57.669 -> 68.464 -> 1095.425 MByte/s p07 random-cyc-1dim : 51.507 57.838 59.130 -> 59.130 -> 946.087 MByte/s p08 random-cyc-1dim : 44.131 45.052 46.316 -> 46.316 -> 741.052 MByte/s p09 random-cyc-1dim : 48.810 53.899 57.811 -> 57.811 -> 924.975 MByte/s p10 random-cyc-1dim : 64.835 64.025 72.321 -> 72.321 -> 1157.131 MByte/s p11 random-cyc-1dim : 58.931 63.837 62.876 -> 63.837 -> 1021.386 MByte/s p12 random-cyc-1dim : 42.223 47.505 45.800 -> 47.505 -> 760.087 MByte/s p13 random-cyc-1dim : 56.991 61.994 64.326 -> 64.326 -> 1029.211 MByte/s p14 random-cyc-1dim : 53.968 53.801 54.446 -> 54.446 -> 871.142 MByte/s p15 random-cyc-1dim : 48.503 56.770 54.420 -> 56.770 -> 908.323 MByte/s p16 random-cyc-1dim : 51.373 51.561 54.861 -> 54.861 -> 877.772 MByte/s p17 random-cyc-1dim : 61.531 63.375 65.245 -> 65.245 -> 1043.916 MByte/s p18 random-cyc-1dim : 54.873 52.227 68.648 -> 68.648 -> 1098.361 MByte/s p19 random-cyc-1dim : 42.889 45.294 44.292 -> 45.294 -> 724.706 MByte/s p20 random-cyc-1dim : 50.841 47.775 49.418 -> 50.841 -> 813.454 MByte/s p21 random-cyc-1dim : 58.058 61.006 56.018 -> 61.006 -> 976.099 MByte/s p22 random-cyc-1dim : 48.031 48.249 48.601 -> 48.601 -> 777.611 MByte/s p23 random-cyc-1dim : 50.326 52.796 48.620 -> 52.796 -> 844.737 MByte/s p24 random-cyc-1dim : 49.343 47.736 48.122 -> 49.343 -> 789.484 MByte/s p25 random-cyc-1dim : 42.192 42.194 43.432 -> 43.432 -> 694.914 MByte/s p26 random-cyc-1dim : 50.079 55.106 50.441 -> 55.106 -> 881.696 MByte/s p27 random-cyc-1dim : 57.990 57.383 59.915 -> 59.915 -> 958.639 MByte/s p28 random-cyc-1dim : 46.649 51.388 50.392 -> 51.388 -> 822.203 MByte/s p29 random-cyc-1dim : 66.561 75.938 73.882 -> 75.938 -> 1215.001 MByte/s p30 random-cyc-1dim : 46.370 50.852 50.074 -> 50.852 -> 813.640 MByte/s p31 random-cyc-1dim : 50.517 52.730 49.101 -> 52.730 -> 843.676 MByte/s p32 random-cyc-1dim : 58.205 59.083 59.414 -> 59.414 -> 950.627 MByte/s p33 random-cyc-1dim : 54.880 54.034 55.448 -> 55.448 -> 887.172 MByte/s p34 random-cyc-1dim : 61.102 66.071 65.932 -> 66.071 -> 1057.141 MByte/s p35 random-cyc-1dim : 60.687 55.631 58.559 -> 60.687 -> 970.996 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 64.500 66.501 66.376 -> 66.501 -> 1064.021 MByte/s p37 best bi-section : 36.021 30.820 32.461 -> 36.021 -> 576.339 MByte/s p38 worst bi-section : 36.942 35.535 36.208 -> 36.942 -> 591.066 MByte/s p39 one PingPong Pair : 1.909 1.962 1.871 -> 1.962 -> 31.393 MByte/s p40 acyclic-2dim-all : 55.660 57.625 58.300 -> 58.300 -> 932.800 MByte/s p41 acyclic-3dim-all : 85.190 82.833 84.022 -> 85.190 -> 1363.038 MByte/s p42 cyclic-2dim-x : 142.434 150.170 142.255 -> 150.170 -> 2402.721 MByte/s p43 cyclic-2dim-y : 38.331 38.583 38.514 -> 38.583 -> 617.334 MByte/s p44 cyclic-2dim-all : 65.181 65.180 64.048 -> 65.181 -> 1042.890 MByte/s p45 cyclic-3dim-x : 148.208 150.982 149.253 -> 150.982 -> 2415.715 MByte/s p46 cyclic-3dim-y : 156.645 157.797 157.250 -> 157.797 -> 2524.746 MByte/s p47 cyclic-3dim-z : 38.089 37.463 37.649 -> 38.089 -> 609.423 MByte/s p48 cyclic-3dim-all : 98.108 99.467 95.782 -> 99.467 -> 1591.464 MByte/s log_avg of all rings : 38.112 38.312 38.779 || 38.950 -> 623.204 MByte/s log_avg of all random : 52.508 54.956 55.285 || 56.721 -> 907.528 MByte/s log_avg(ring,random) : 44.735 45.886 46.302 ||( 47.003 -> 752.047)MByte/s * size -> accumulated on all pr.: 715.760 734.172 740.835 ||(752.047)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-8*2fix p00 method 0 =Sndrcv :( 39.403) 0.025 0.381 6.280 38.705 89.734 118.651 -> 37.135 -> 594.167 MByte/s p00 method 1 =Alltoal :(402.817) 0.002 0.041 0.650 7.523 61.707 118.651 -> 25.854 -> 413.668 MByte/s p00 method 2 =non-blk :( 68.300) 0.015 0.229 3.695 31.863 84.044 118.651 -> 35.410 -> 566.563 MByte/s p01 ring-4*4fix p01 method 0 =Sndrcv :( 35.147) 0.028 0.446 6.619 41.082 90.346 115.214 -> 38.918 -> 622.686 MByte/s p01 method 1 =Alltoal :(200.351) 0.005 0.081 1.182 13.041 80.699 115.214 -> 30.509 -> 488.144 MByte/s p01 method 2 =non-blk :( 57.119) 0.018 0.265 4.113 36.004 98.875 115.214 -> 37.016 -> 592.262 MByte/s p02 ring-2*8fix p02 method 0 =Sndrcv :( 35.268) 0.028 0.432 6.583 41.973 92.696 116.993 -> 39.245 -> 627.921 MByte/s p02 method 1 =Alltoal :(200.142) 0.005 0.078 1.280 12.285 76.202 116.993 -> 29.626 -> 474.024 MByte/s p02 method 2 =non-blk :( 57.494) 0.017 0.269 4.100 35.715 95.393 116.993 -> 36.440 -> 583.035 MByte/s p03 ring-1*16fix p03 method 0 =Sndrcv :( 35.081) 0.029 0.437 6.517 41.635 100.257 113.743 -> 40.267 -> 644.279 MByte/s p03 method 1 =Alltoal :(195.616) 0.005 0.078 1.263 11.913 59.776 113.743 -> 26.077 -> 417.231 MByte/s p03 method 2 =non-blk :( 56.710) 0.018 0.270 4.102 36.432 93.117 113.743 -> 37.035 -> 592.568 MByte/s p04 ring-1*16fix p04 method 0 =Sndrcv :( 35.579) 0.028 0.440 6.369 42.105 94.571 113.787 -> 39.981 -> 639.699 MByte/s p04 method 1 =Alltoal :(202.592) 0.005 0.080 1.146 11.835 51.539 113.787 -> 24.875 -> 397.992 MByte/s p04 method 2 =non-blk :( 56.376) 0.018 0.274 4.180 36.294 89.728 113.787 -> 36.056 -> 576.899 MByte/s p05 ring-1*16fix p05 method 0 =Sndrcv :( 35.050) 0.029 0.442 6.606 42.703 97.176 116.736 -> 40.409 -> 646.552 MByte/s p05 method 1 =Alltoal :(196.609) 0.005 0.080 1.254 11.809 62.910 116.736 -> 26.249 -> 419.984 MByte/s p05 method 2 =non-blk :( 55.812) 0.018 0.273 4.223 35.709 90.756 116.736 -> 37.811 -> 604.974 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 34.447) 0.029 0.457 6.803 43.206 161.756 201.077 -> 69.734 -> 1115.745 MByte/s p06 method 1 =Alltoal :(219.001) 0.005 0.073 1.131 14.120 68.337 201.077 -> 38.350 -> 613.598 MByte/s p06 method 2 =non-blk :( 56.523) 0.018 0.269 4.126 36.877 155.181 201.077 -> 63.102 -> 1009.624 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 29.712) 0.034 0.502 7.506 52.810 140.918 171.578 -> 58.344 -> 933.509 MByte/s p07 method 1 =Alltoal :(213.497) 0.005 0.073 1.161 13.195 63.676 171.578 -> 35.490 -> 567.843 MByte/s p07 method 2 =non-blk :( 50.103) 0.020 0.308 4.619 39.437 160.234 171.578 -> 56.804 -> 908.870 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 34.781) 0.029 0.448 6.666 42.112 111.558 152.572 -> 47.914 -> 766.631 MByte/s p08 method 1 =Alltoal :(206.253) 0.005 0.078 1.231 12.691 59.737 152.572 -> 28.119 -> 449.911 MByte/s p08 method 2 =non-blk :( 56.640) 0.018 0.271 4.115 37.098 120.042 152.572 -> 44.797 -> 716.756 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 28.702) 0.035 0.537 7.873 52.564 142.025 178.085 -> 61.267 -> 980.268 MByte/s p09 method 1 =Alltoal :(208.504) 0.005 0.076 1.208 14.100 66.726 178.085 -> 35.976 -> 575.620 MByte/s p09 method 2 =non-blk :( 49.773) 0.020 0.307 4.667 42.767 137.702 178.085 -> 53.773 -> 860.361 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 30.028) 0.033 0.504 7.496 52.730 193.541 196.761 -> 75.217 -> 1203.467 MByte/s p10 method 1 =Alltoal :(218.610) 0.005 0.073 1.142 14.801 87.477 196.761 -> 40.587 -> 649.386 MByte/s p10 method 2 =non-blk :( 52.871) 0.019 0.299 4.572 43.489 129.194 196.761 -> 68.670 -> 1098.719 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 32.398) 0.031 0.521 7.736 53.961 173.302 189.618 -> 64.720 -> 1035.524 MByte/s p11 method 1 =Alltoal :(236.015) 0.004 0.069 1.107 14.598 64.486 189.618 -> 33.531 -> 536.498 MByte/s p11 method 2 =non-blk :( 51.850) 0.019 0.297 4.537 41.559 183.791 189.618 -> 60.930 -> 974.880 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 34.918) 0.029 0.452 6.304 43.381 119.355 138.273 -> 47.677 -> 762.831 MByte/s p12 method 1 =Alltoal :(200.609) 0.005 0.079 1.229 12.088 57.495 138.273 -> 29.967 -> 479.480 MByte/s p12 method 2 =non-blk :( 56.533) 0.018 0.271 4.226 36.692 119.344 138.273 -> 44.517 -> 712.274 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 29.225) 0.034 0.516 7.705 52.567 173.256 178.732 -> 67.203 -> 1075.252 MByte/s p13 method 1 =Alltoal :(214.166) 0.005 0.075 1.180 13.822 94.071 178.732 -> 39.921 -> 638.742 MByte/s p13 method 2 =non-blk :( 49.651) 0.020 0.308 4.682 42.703 154.313 178.732 -> 59.073 -> 945.162 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 34.490) 0.029 0.451 6.682 44.320 153.524 145.570 -> 55.930 -> 894.885 MByte/s p14 method 1 =Alltoal :(211.612) 0.005 0.075 1.187 13.842 80.297 145.570 -> 32.962 -> 527.400 MByte/s p14 method 2 =non-blk :( 56.511) 0.018 0.272 4.105 35.200 149.066 145.570 -> 51.611 -> 825.772 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 29.171) 0.034 0.530 7.739 51.665 137.745 172.265 -> 56.810 -> 908.963 MByte/s p15 method 1 =Alltoal :(217.001) 0.005 0.076 1.201 13.830 53.489 172.265 -> 33.061 -> 528.975 MByte/s p15 method 2 =non-blk :( 51.016) 0.020 0.303 4.544 42.063 142.666 172.265 -> 54.284 -> 868.544 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 34.616) 0.029 0.452 6.689 45.670 138.316 171.410 -> 55.556 -> 888.895 MByte/s p16 method 1 =Alltoal :(211.742) 0.005 0.074 1.208 13.156 59.193 171.410 -> 32.285 -> 516.562 MByte/s p16 method 2 =non-blk :( 55.812) 0.018 0.279 4.128 38.059 140.501 171.410 -> 53.045 -> 848.727 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 34.311) 0.029 0.452 6.764 45.216 152.100 198.846 -> 66.240 -> 1059.834 MByte/s p17 method 1 =Alltoal :(218.630) 0.005 0.074 1.156 13.415 67.113 198.846 -> 36.280 -> 580.484 MByte/s p17 method 2 =non-blk :( 55.851) 0.018 0.271 4.192 38.273 160.124 198.846 -> 61.277 -> 980.440 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 29.248) 0.034 0.508 7.570 51.368 184.277 133.248 -> 68.788 -> 1100.614 MByte/s p18 method 1 =Alltoal :(220.409) 0.005 0.071 1.131 14.047 58.715 133.248 -> 32.714 -> 523.426 MByte/s p18 method 2 =non-blk :( 50.667) 0.020 0.304 4.629 41.558 163.236 133.248 -> 60.313 -> 965.003 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 34.871) 0.029 0.449 6.676 44.310 111.505 152.459 -> 46.544 -> 744.703 MByte/s p19 method 1 =Alltoal :(215.722) 0.005 0.079 1.246 12.136 71.680 152.459 -> 31.131 -> 498.101 MByte/s p19 method 2 =non-blk :( 56.521) 0.018 0.271 4.156 36.205 108.266 152.459 -> 43.519 -> 696.301 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 30.037) 0.033 0.491 7.379 51.986 138.907 129.435 -> 50.915 -> 814.646 MByte/s p20 method 1 =Alltoal :(215.233) 0.005 0.078 1.226 12.757 52.010 129.435 -> 28.132 -> 450.109 MByte/s p20 method 2 =non-blk :( 51.649) 0.019 0.297 4.548 41.848 145.391 129.435 -> 49.843 -> 797.487 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 29.281) 0.034 0.520 7.643 52.340 160.322 184.963 -> 59.815 -> 957.044 MByte/s p21 method 1 =Alltoal :(218.131) 0.005 0.074 1.091 14.108 80.663 184.963 -> 33.296 -> 532.729 MByte/s p21 method 2 =non-blk :( 50.639) 0.020 0.282 4.624 42.231 170.380 184.963 -> 58.566 -> 937.055 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 34.638) 0.029 0.449 6.710 44.449 118.762 149.326 -> 48.435 -> 774.967 MByte/s p22 method 1 =Alltoal :(201.333) 0.005 0.080 1.237 12.390 64.800 149.326 -> 31.427 -> 502.827 MByte/s p22 method 2 =non-blk :( 55.918) 0.018 0.271 4.179 37.443 120.881 149.326 -> 46.742 -> 747.866 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 34.660) 0.029 0.442 6.630 44.032 155.337 170.078 -> 55.911 -> 894.576 MByte/s p23 method 1 =Alltoal :(213.100) 0.005 0.074 1.170 13.463 81.605 170.078 -> 34.318 -> 549.083 MByte/s p23 method 2 =non-blk :( 56.525) 0.018 0.268 4.114 37.923 150.607 170.078 -> 50.919 -> 814.706 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 34.645) 0.029 0.444 6.746 45.441 123.506 122.130 -> 50.174 -> 802.783 MByte/s p24 method 1 =Alltoal :(207.331) 0.005 0.078 1.221 12.532 84.334 122.130 -> 33.452 -> 535.228 MByte/s p24 method 2 =non-blk :( 57.022) 0.018 0.269 4.188 37.323 127.666 122.130 -> 48.114 -> 769.829 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 35.215) 0.028 0.437 6.573 44.013 105.925 131.407 -> 43.997 -> 703.953 MByte/s p25 method 1 =Alltoal :(201.669) 0.005 0.079 1.205 12.023 79.864 131.407 -> 30.356 -> 485.700 MByte/s p25 method 2 =non-blk :( 57.150) 0.017 0.271 4.164 37.656 102.355 131.407 -> 40.695 -> 651.124 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 34.349) 0.029 0.454 6.679 44.323 120.183 169.575 -> 54.763 -> 876.214 MByte/s p26 method 1 =Alltoal :(204.241) 0.005 0.079 1.231 13.117 61.808 169.575 -> 31.182 -> 498.916 MByte/s p26 method 2 =non-blk :( 56.248) 0.018 0.273 4.096 36.439 137.977 169.575 -> 50.959 -> 815.341 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 29.362) 0.034 0.500 6.555 52.773 162.414 194.322 -> 63.059 -> 1008.951 MByte/s p27 method 1 =Alltoal :(222.517) 0.004 0.072 1.151 13.672 86.721 194.322 -> 40.273 -> 644.366 MByte/s p27 method 2 =non-blk :( 51.443) 0.019 0.301 4.545 42.352 148.767 194.322 -> 59.087 -> 945.395 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 29.805) 0.034 0.491 7.411 50.637 125.633 158.059 -> 51.019 -> 816.312 MByte/s p28 method 1 =Alltoal :(205.225) 0.005 0.079 1.244 13.055 56.660 158.059 -> 30.623 -> 489.963 MByte/s p28 method 2 =non-blk :( 50.814) 0.020 0.309 4.261 41.722 134.979 158.059 -> 50.496 -> 807.941 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 29.060) 0.034 0.522 7.717 54.281 180.192 246.564 -> 77.061 -> 1232.969 MByte/s p29 method 1 =Alltoal :(224.107) 0.004 0.072 1.138 14.716 78.114 246.564 -> 44.073 -> 705.174 MByte/s p29 method 2 =non-blk :( 49.785) 0.020 0.312 4.697 44.281 189.934 246.564 -> 67.497 -> 1079.955 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 34.402) 0.029 0.454 6.471 44.437 135.793 152.830 -> 51.085 -> 817.355 MByte/s p30 method 1 =Alltoal :(208.667) 0.005 0.075 1.200 13.153 78.032 152.830 -> 31.918 -> 510.696 MByte/s p30 method 2 =non-blk :( 56.273) 0.018 0.273 3.938 37.568 139.365 152.830 -> 48.900 -> 782.400 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 29.379) 0.034 0.504 7.704 51.152 142.648 163.986 -> 53.461 -> 855.373 MByte/s p31 method 1 =Alltoal :(214.557) 0.005 0.075 1.145 13.657 78.081 163.986 -> 30.737 -> 491.795 MByte/s p31 method 2 =non-blk :( 51.737) 0.019 0.294 4.513 40.943 144.577 163.986 -> 51.850 -> 829.596 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 32.086) 0.031 0.461 7.032 51.159 155.325 156.008 -> 61.284 -> 980.544 MByte/s p32 method 1 =Alltoal :(222.925) 0.004 0.073 1.141 13.983 86.516 156.008 -> 35.117 -> 561.877 MByte/s p32 method 2 =non-blk :( 50.672) 0.020 0.302 4.631 42.484 160.680 156.008 -> 58.133 -> 930.132 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 29.905) 0.033 0.457 7.470 52.028 138.627 180.694 -> 55.807 -> 892.911 MByte/s p33 method 1 =Alltoal :(214.612) 0.005 0.076 1.204 13.298 78.032 180.694 -> 34.816 -> 557.063 MByte/s p33 method 2 =non-blk :( 54.858) 0.018 0.296 4.522 41.130 141.142 180.694 -> 53.548 -> 856.775 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 29.832) 0.034 0.506 7.496 52.120 173.108 211.508 -> 66.552 -> 1064.827 MByte/s p34 method 1 =Alltoal :(220.332) 0.005 0.073 1.148 13.850 67.148 211.508 -> 36.800 -> 588.804 MByte/s p34 method 2 =non-blk :( 50.799) 0.020 0.299 4.612 41.814 170.921 211.508 -> 63.767 -> 1020.272 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 34.919) 0.029 0.452 6.806 44.959 156.445 197.235 -> 63.023 -> 1008.372 MByte/s p35 method 1 =Alltoal :(218.166) 0.005 0.073 1.167 14.035 63.319 197.235 -> 34.932 -> 558.911 MByte/s p35 method 2 =non-blk :( 57.062) 0.018 0.273 4.138 36.462 152.661 197.235 -> 57.474 -> 919.588 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 30.020) 0.033 0.500 7.351 53.157 182.015 194.855 -> 69.112 -> 1105.786 MByte/s p36 method 1 =Alltoal :(199.053) 0.005 0.078 1.223 13.209 85.975 194.855 -> 37.803 -> 604.849 MByte/s p36 method 2 =non-blk :( 49.989) 0.020 0.310 4.640 43.443 178.738 194.855 -> 64.515 -> 1032.232 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 33.248) 0.015 0.225 3.484 27.226 80.546 101.601 -> 29.085 -> 465.355 MByte/s p37 method 1 =Alltoal :(198.834) 0.003 0.040 0.648 7.644 62.475 101.601 -> 25.030 -> 400.485 MByte/s p37 method 2 =non-blk :( 35.598) 0.014 0.213 3.416 27.672 92.463 101.601 -> 37.020 -> 592.323 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 28.862) 0.017 0.255 3.839 28.836 92.659 113.141 -> 35.979 -> 575.666 MByte/s p38 method 1 =Alltoal :(201.241) 0.002 0.041 0.641 8.793 49.950 113.141 -> 27.046 -> 432.736 MByte/s p38 method 2 =non-blk :( 34.993) 0.014 0.224 3.359 31.146 96.099 113.141 -> 36.596 -> 585.537 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 36.781) 0.002 0.023 0.315 1.845 4.328 6.478 -> 2.017 -> 32.272 MByte/s p39 method 1 =Alltoal :(-------) 0.000 0.000 0.000 0.000 0.000 6.478 -> 0.603 -> 9.643 MByte/s p39 method 2 =non-blk :(-------) 0.000 0.000 0.000 0.000 0.000 6.478 -> 0.603 -> 9.643 MByte/s p40 acyclic-2dim-all p40 method 0 =Sndrcv :( 24.960) 0.030 0.468 6.946 47.707 134.203 129.167 -> 53.253 -> 852.041 MByte/s p40 method 1 =Alltoal :(101.341) 0.007 0.121 1.806 18.737 139.653 129.167 -> 49.402 -> 790.437 MByte/s p40 method 2 =non-blk :( 42.497) 0.018 0.273 4.136 38.103 149.381 129.167 -> 56.965 -> 911.437 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 18.971) 0.031 0.464 6.854 50.224 128.659 274.214 -> 60.409 -> 966.549 MByte/s p41 method 1 =Alltoal :( 69.037) 0.008 0.139 2.153 23.387 149.662 274.214 -> 62.853 -> 1005.645 MByte/s p41 method 2 =non-blk :( 26.052) 0.022 0.347 5.265 53.193 233.740 274.214 -> 88.786 -> 1420.575 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 16.747) 0.060 0.944 12.675 115.798 380.666 425.031 -> 150.799 -> 2412.788 MByte/s p42 method 1 =Alltoal :(196.391) 0.005 0.079 1.256 15.554 107.769 425.031 -> 67.804 -> 1084.865 MByte/s p42 method 2 =non-blk :( 37.072) 0.027 0.431 6.572 76.267 355.065 425.031 -> 137.507 -> 2200.120 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 35.252) 0.028 0.441 6.662 41.714 92.691 116.174 -> 39.140 -> 626.241 MByte/s p43 method 1 =Alltoal :(201.353) 0.005 0.081 1.254 12.374 81.947 116.174 -> 30.182 -> 482.914 MByte/s p43 method 2 =non-blk :( 57.419) 0.017 0.268 4.167 35.763 97.369 116.174 -> 37.699 -> 603.180 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 25.443) 0.039 0.608 9.001 60.095 145.434 208.615 -> 61.803 -> 988.848 MByte/s p44 method 1 =Alltoal :(101.842) 0.010 0.160 2.486 25.026 146.272 208.615 -> 55.161 -> 882.583 MByte/s p44 method 2 =non-blk :( 45.817) 0.022 0.336 5.117 48.920 193.257 208.615 -> 65.914 -> 1054.630 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 16.292) 0.061 0.968 13.367 112.751 366.090 462.576 -> 153.778 -> 2460.445 MByte/s p45 method 1 =Alltoal :(196.940) 0.005 0.079 1.275 16.690 99.606 462.576 -> 70.371 -> 1125.937 MByte/s p45 method 2 =non-blk :( 36.975) 0.027 0.430 6.543 75.766 388.651 462.576 -> 145.707 -> 2331.313 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 16.737) 0.060 0.930 12.851 112.006 389.050 454.273 -> 159.688 -> 2555.007 MByte/s p46 method 1 =Alltoal :(408.345) 0.002 0.039 0.644 9.398 95.454 454.273 -> 66.851 -> 1069.621 MByte/s p46 method 2 =non-blk :( 37.939) 0.026 0.407 6.306 72.536 360.452 454.273 -> 141.662 -> 2266.593 MByte/s p47 cyclic-3dim-z p47 method 0 =Sndrcv :( 42.057) 0.024 0.417 6.328 37.711 101.011 114.516 -> 38.253 -> 612.051 MByte/s p47 method 1 =Alltoal :(395.219) 0.003 0.041 0.622 7.534 56.983 114.516 -> 25.368 -> 405.892 MByte/s p47 method 2 =non-blk :( 70.144) 0.014 0.231 3.654 31.007 99.509 114.516 -> 37.704 -> 603.270 MByte/s p48 cyclic-3dim-all p48 method 0 =Sndrcv :( 20.638) 0.048 0.723 10.577 75.272 233.359 286.886 -> 90.889 -> 1454.220 MByte/s p48 method 1 =Alltoal :( 99.887) 0.010 0.161 2.446 26.027 173.398 286.886 -> 71.846 -> 1149.539 MByte/s p48 method 2 =non-blk :( 42.320) 0.024 0.369 5.602 58.051 287.769 286.886 -> 101.568 -> 1625.095 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.028 0.429 6.494 41.346 94.057 115.840 || 39.310 -> 628.959 MByte/s - ring, method 1 = Alltoal: 0.004 0.071 1.101 11.231 64.728 115.840 || 27.120 -> 433.924 MByte/s - ring, method 2 = non-blk: 0.017 0.263 4.065 35.299 91.866 115.840 || 36.620 -> 585.920 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.031 0.478 7.091 48.360 144.415 167.800 || 57.675 -> 922.794 MByte/s - random, method 1 = Alltoal: 0.005 0.075 1.180 13.434 70.103 167.800 || 33.866 -> 541.852 MByte/s - random, method 2 = non-blk: 0.019 0.287 4.363 39.632 143.987 167.800 || 53.961 -> 863.376 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.030 0.453 6.786 44.716 116.548 139.420 || 47.615 -> 761.840 MByte/s - average, method 1 = Alltoal: 0.005 0.073 1.140 12.283 67.362 139.420 || 30.306 -> 484.894 MByte/s - average, method 2 = non-blk: 0.018 0.274 4.211 37.403 115.011 139.420 || 44.453 -> 711.245 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.472 7.245 108.578 715.454 1864.761 2230.719 || 761.840 MByte/s - accumulated, mthd 1 = Alltoal: 0.073 1.169 18.243 196.529 1077.792 2230.719 || 484.894 MByte/s - accumulated, mthd 2 = non-blk: 0.286 4.392 67.379 598.446 1840.179 2230.719 || 711.245 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 0.472 0.030 0.028 0.031 0.030 0.005 0.018 2 0.943 0.059 0.056 0.062 0.059 0.009 0.035 4 1.846 0.115 0.108 0.123 0.115 0.018 0.070 8 3.737 0.234 0.219 0.249 0.234 0.037 0.142 16 7.245 0.453 0.429 0.478 0.453 0.073 0.274 32 14.411 0.901 0.857 0.947 0.901 0.147 0.541 64 28.532 1.783 1.703 1.868 1.783 0.293 1.076 128 55.019 3.439 3.281 3.604 3.439 0.581 2.125 256 108.578 6.786 6.494 7.091 6.786 1.140 4.211 512 213.889 13.368 12.753 14.013 13.368 2.306 8.278 1024 414.825 25.927 24.804 27.099 25.927 4.567 16.293 2048 458.898 28.681 26.747 30.755 28.681 7.051 22.921 4096 715.454 44.716 41.346 48.360 44.716 12.283 37.403 10624 933.276 58.330 49.978 68.077 55.716 23.148 58.029 27554 1377.540 86.096 71.134 104.206 79.079 39.110 85.821 71468 1483.759 92.735 74.619 115.248 88.797 56.380 90.712 185364 1910.953 119.435 95.940 148.683 116.548 67.362 115.011 480774 1955.401 122.213 97.791 152.733 120.506 70.529 112.913 1246974 2088.097 130.506 102.212 166.632 130.483 66.618 95.021 3234251 2226.324 139.145 113.541 170.524 139.145 139.145 139.145 8388608 2230.719 139.420 115.840 167.800 139.420 139.420 139.420 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-8*2fix :( 39.403) 0.025 0.381 6.280 38.705 89.734 118.651 -> 38.595 -> 617.526 MByte/s p01 ring-4*4fix :( 35.147) 0.028 0.446 6.619 41.082 98.875 115.214 -> 39.952 -> 639.232 MByte/s p02 ring-2*8fix :( 35.268) 0.028 0.432 6.583 41.973 95.393 116.993 -> 39.597 -> 633.550 MByte/s p03 ring-1*16fix :( 35.081) 0.029 0.437 6.517 41.635 100.257 113.743 -> 40.601 -> 649.615 MByte/s p04 ring-1*16fix :( 35.579) 0.028 0.440 6.369 42.105 94.571 113.787 -> 40.423 -> 646.761 MByte/s p05 ring-1*16fix :( 35.050) 0.029 0.442 6.606 42.703 97.176 116.736 -> 41.035 -> 656.565 MByte/s p06 random-cyc-1dim :( 34.447) 0.029 0.457 6.803 43.206 161.756 201.077 -> 69.734 -> 1115.745 MByte/s p07 random-cyc-1dim :( 29.712) 0.034 0.502 7.506 52.810 160.234 171.578 -> 60.494 -> 967.905 MByte/s p08 random-cyc-1dim :( 34.781) 0.029 0.448 6.666 42.112 120.042 152.572 -> 48.738 -> 779.814 MByte/s p09 random-cyc-1dim :( 28.702) 0.035 0.537 7.873 52.564 142.025 178.085 -> 61.607 -> 985.711 MByte/s p10 random-cyc-1dim :( 30.028) 0.033 0.504 7.496 52.730 193.541 196.761 -> 75.846 -> 1213.540 MByte/s p11 random-cyc-1dim :( 32.398) 0.031 0.521 7.736 53.961 183.791 189.618 -> 66.116 -> 1057.853 MByte/s p12 random-cyc-1dim :( 34.918) 0.029 0.452 6.304 43.381 119.355 138.273 -> 48.528 -> 776.447 MByte/s p13 random-cyc-1dim :( 29.225) 0.034 0.516 7.705 52.567 173.256 178.732 -> 67.490 -> 1079.834 MByte/s p14 random-cyc-1dim :( 34.490) 0.029 0.451 6.682 44.320 153.524 145.570 -> 56.946 -> 911.141 MByte/s p15 random-cyc-1dim :( 29.171) 0.034 0.530 7.739 51.665 142.666 172.265 -> 57.840 -> 925.442 MByte/s p16 random-cyc-1dim :( 34.616) 0.029 0.452 6.689 45.670 140.501 171.410 -> 56.636 -> 906.184 MByte/s p17 random-cyc-1dim :( 34.311) 0.029 0.452 6.764 45.216 160.124 198.846 -> 67.164 -> 1074.621 MByte/s p18 random-cyc-1dim :( 29.248) 0.034 0.508 7.570 51.368 184.277 133.248 -> 69.776 -> 1116.416 MByte/s p19 random-cyc-1dim :( 34.871) 0.029 0.449 6.676 44.310 111.505 152.459 -> 47.492 -> 759.868 MByte/s p20 random-cyc-1dim :( 30.037) 0.033 0.491 7.379 51.986 145.391 129.435 -> 51.762 -> 828.185 MByte/s p21 random-cyc-1dim :( 29.281) 0.034 0.520 7.643 52.340 170.380 184.963 -> 61.838 -> 989.404 MByte/s p22 random-cyc-1dim :( 34.638) 0.029 0.449 6.710 44.449 120.881 149.326 -> 50.066 -> 801.048 MByte/s p23 random-cyc-1dim :( 34.660) 0.029 0.442 6.630 44.032 155.337 170.078 -> 56.341 -> 901.449 MByte/s p24 random-cyc-1dim :( 34.645) 0.029 0.444 6.746 45.441 127.666 122.130 -> 51.188 -> 819.013 MByte/s p25 random-cyc-1dim :( 35.215) 0.028 0.437 6.573 44.013 105.925 131.407 -> 44.733 -> 715.721 MByte/s p26 random-cyc-1dim :( 34.349) 0.029 0.454 6.679 44.323 137.977 169.575 -> 56.202 -> 899.234 MByte/s p27 random-cyc-1dim :( 29.362) 0.034 0.500 6.555 52.773 162.414 194.322 -> 63.734 -> 1019.746 MByte/s p28 random-cyc-1dim :( 29.805) 0.034 0.491 7.411 50.637 134.979 158.059 -> 52.942 -> 847.069 MByte/s p29 random-cyc-1dim :( 29.060) 0.034 0.522 7.717 54.281 189.934 246.564 -> 77.665 -> 1242.646 MByte/s p30 random-cyc-1dim :( 34.402) 0.029 0.454 6.471 44.437 139.365 152.830 -> 52.966 -> 847.452 MByte/s p31 random-cyc-1dim :( 29.379) 0.034 0.504 7.704 51.152 144.577 163.986 -> 54.483 -> 871.727 MByte/s p32 random-cyc-1dim :( 32.086) 0.031 0.461 7.032 51.159 160.680 156.008 -> 62.239 -> 995.820 MByte/s p33 random-cyc-1dim :( 29.905) 0.033 0.457 7.470 52.028 141.142 180.694 -> 57.300 -> 916.798 MByte/s p34 random-cyc-1dim :( 29.832) 0.034 0.506 7.496 52.120 173.108 211.508 -> 67.554 -> 1080.858 MByte/s p35 random-cyc-1dim :( 34.919) 0.029 0.452 6.806 44.959 156.445 197.235 -> 63.452 -> 1015.229 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 30.020) 0.033 0.500 7.351 53.157 182.015 194.855 -> 69.904 -> 1118.458 MByte/s p37 best bi-section :( 33.248) 0.015 0.225 3.484 27.672 92.463 101.601 -> 37.097 -> 593.555 MByte/s p38 worst bi-section :( 28.862) 0.017 0.255 3.839 31.146 96.099 113.141 -> 38.032 -> 608.505 MByte/s p39 one PingPong Pair :( 36.781) 0.002 0.023 0.315 1.845 4.328 6.478 -> 2.017 -> 32.272 MByte/s p40 acyclic-2dim-all :( 24.960) 0.030 0.468 6.946 47.707 149.381 129.167 -> 59.415 -> 950.644 MByte/s p41 acyclic-3dim-all :( 18.971) 0.031 0.464 6.854 53.193 233.740 274.214 -> 89.383 -> 1430.133 MByte/s p42 cyclic-2dim-x :( 16.747) 0.060 0.944 12.675 115.798 380.666 425.031 -> 151.345 -> 2421.515 MByte/s p43 cyclic-2dim-y :( 35.252) 0.028 0.441 6.662 41.714 97.369 116.174 -> 40.145 -> 642.321 MByte/s p44 cyclic-2dim-all :( 25.443) 0.039 0.608 9.001 60.095 193.257 208.615 -> 68.459 -> 1095.349 MByte/s p45 cyclic-3dim-x :( 16.292) 0.061 0.968 13.367 112.751 388.651 462.576 -> 155.165 -> 2482.647 MByte/s p46 cyclic-3dim-y :( 16.737) 0.060 0.930 12.851 112.006 389.050 454.273 -> 161.006 -> 2576.100 MByte/s p47 cyclic-3dim-z :( 42.057) 0.024 0.417 6.328 37.711 101.011 114.516 -> 39.498 -> 631.973 MByte/s p48 cyclic-3dim-all :( 20.638) 0.048 0.723 10.577 75.272 287.769 286.886 -> 104.926 -> 1678.816 MByte/s log_avg of all rings : 0.028 0.429 6.494 41.346 95.940 115.840 || 40.026 -> 640.416 MByte/s log_avg of all random : 0.031 0.478 7.091 48.360 148.683 167.800 || 58.724 -> 939.587 MByte/s log_avg(ring,random) : 0.030 0.453 6.786 44.716 119.435 139.420 || 48.482 -> 775.710 MByte/s * size -> accumulated on all pr.: 0.472 7.245 108.578 715.454 1910.953 2230.719 || 775.710 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 775.710 MByte/s on 16 processes ( = 48.482 MByte/s * 16 processes) Ping-pong latency: 36.781 microsec Ping-pong bandwidth: 103.655 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 16 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 14:31:02 1999 Total execution wall clock time = 142 seconds SECTION-BEFF-END b_eff = 775.710 MB/s = 48.482 * 16 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000