b_eff = 706.801 MB/s = 176.700 * 4 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 = 4 2-dim-paterns: size = 2 * 2 3-dim-paterns: size = 2 * 2 * 1 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-2*2fix 1=ring-1*4fix 2=ring-1*4fix 3=ring-1*4fix 4=ring-1*4fix 5=ring-1*4fix 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-all SECTION-HEAD-END SECTION-LOOP-BEGIN measurment loop: 64.444 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 4.2e-01 4.6e-03 1.4e-02 243 3.4e-01 3.8e-03 1.1e-02 241 3.4e-01 3.7e-03 1.1e-02 2 163 2.3e-01 2.6e-03 7.8e-03 161 2.3e-01 2.5e-03 7.7e-03 162 2.3e-01 2.5e-03 7.7e-03 4 159 2.3e-01 2.5e-03 7.7e-03 160 2.3e-01 2.5e-03 7.8e-03 161 2.3e-01 2.5e-03 7.9e-03 8 160 2.3e-01 2.5e-03 7.6e-03 160 2.3e-01 2.5e-03 7.7e-03 160 2.3e-01 2.5e-03 7.7e-03 16 162 2.3e-01 2.5e-03 7.9e-03 161 2.3e-01 2.5e-03 8.0e-03 160 2.3e-01 2.5e-03 7.9e-03 32 159 2.3e-01 2.5e-03 8.1e-03 159 2.3e-01 2.5e-03 8.1e-03 159 2.3e-01 2.5e-03 8.0e-03 64 157 2.4e-01 2.6e-03 8.3e-03 157 2.4e-01 2.6e-03 8.4e-03 156 2.4e-01 2.6e-03 8.3e-03 128 150 2.4e-01 2.7e-03 8.7e-03 151 2.5e-01 2.7e-03 8.8e-03 148 2.4e-01 2.6e-03 8.5e-03 256 141 2.3e-01 2.5e-03 7.9e-03 141 2.3e-01 2.5e-03 8.0e-03 141 2.3e-01 2.5e-03 7.7e-03 512 143 2.4e-01 2.6e-03 8.4e-03 143 2.4e-01 2.5e-03 8.2e-03 143 2.4e-01 2.5e-03 8.1e-03 1024 140 2.5e-01 2.6e-03 8.7e-03 140 2.5e-01 2.6e-03 8.6e-03 140 2.5e-01 2.6e-03 8.6e-03 2048 132 3.0e-01 3.3e-03 9.3e-03 132 3.0e-01 3.4e-03 9.3e-03 132 3.0e-01 3.3e-03 9.3e-03 4096 100 2.9e-01 3.2e-03 8.4e-03 97 2.9e-01 3.2e-03 8.3e-03 100 3.0e-01 3.2e-03 8.5e-03 10624 60 3.0e-01 3.0e-03 9.6e-03 59 2.9e-01 2.9e-03 9.5e-03 60 3.0e-01 2.9e-03 9.9e-03 27554 39 3.3e-01 3.2e-03 1.0e-02 38 3.2e-01 3.0e-03 1.0e-02 39 3.3e-01 3.0e-03 1.0e-02 71468 23 3.8e-01 3.5e-03 9.3e-03 24 4.0e-01 3.8e-03 9.9e-03 24 4.0e-01 3.8e-03 1.0e-02 185364 12 4.7e-01 4.2e-03 1.2e-02 12 4.7e-01 4.4e-03 1.1e-02 12 4.7e-01 3.9e-03 1.2e-02 480774 5 4.5e-01 4.4e-03 1.2e-02 5 4.5e-01 4.4e-03 1.1e-02 5 4.6e-01 4.5e-03 1.2e-02 1246974 2 4.6e-01 4.3e-03 1.4e-02 2 4.4e-01 4.4e-03 1.1e-02 2 4.7e-01 4.5e-03 1.6e-02 3234251 1 5.7e-01 6.0e-03 1.5e-02 1 5.6e-01 6.0e-03 1.4e-02 1 5.6e-01 6.0e-03 1.4e-02 8388608 1 1.4e+00 1.4e-02 3.3e-02 1 1.4e+00 1.4e-02 3.2e-02 1 1.4e+00 1.4e-02 3.2e-02 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 8.6e-01 1.8e-02 1.9e-02 61 1.8e-01 3.6e-03 3.8e-03 61 1.8e-01 3.6e-03 3.8e-03 2 150 4.3e-01 9.0e-03 9.4e-03 41 1.2e-01 2.4e-03 2.6e-03 41 1.2e-01 2.5e-03 2.6e-03 4 75 2.2e-01 4.5e-03 4.8e-03 41 1.2e-01 2.5e-03 2.6e-03 41 1.2e-01 2.4e-03 2.6e-03 8 41 1.2e-01 2.4e-03 2.6e-03 41 1.2e-01 2.4e-03 2.6e-03 41 1.2e-01 2.4e-03 2.6e-03 16 41 1.2e-01 2.4e-03 2.6e-03 41 1.2e-01 2.4e-03 2.6e-03 41 1.2e-01 2.5e-03 2.7e-03 32 41 1.2e-01 2.5e-03 2.7e-03 41 1.2e-01 2.5e-03 2.7e-03 41 1.2e-01 2.5e-03 2.6e-03 64 41 1.2e-01 2.5e-03 2.7e-03 41 1.2e-01 2.5e-03 2.7e-03 41 1.2e-01 2.5e-03 2.7e-03 128 41 1.3e-01 2.5e-03 2.8e-03 41 1.3e-01 2.5e-03 2.8e-03 41 1.3e-01 2.6e-03 2.9e-03 256 40 1.2e-01 2.5e-03 2.8e-03 40 1.2e-01 2.5e-03 2.7e-03 39 1.2e-01 2.4e-03 2.6e-03 512 40 1.2e-01 2.5e-03 2.8e-03 40 1.2e-01 2.5e-03 2.8e-03 40 1.2e-01 2.5e-03 2.8e-03 1024 40 1.3e-01 2.5e-03 2.8e-03 40 1.3e-01 2.5e-03 2.9e-03 40 1.3e-01 2.5e-03 2.9e-03 2048 39 1.5e-01 2.7e-03 3.4e-03 39 1.5e-01 2.7e-03 3.4e-03 39 1.5e-01 2.7e-03 3.4e-03 4096 35 1.6e-01 2.7e-03 3.6e-03 35 1.6e-01 2.7e-03 3.6e-03 35 1.6e-01 2.7e-03 3.6e-03 10624 24 1.6e-01 2.4e-03 4.3e-03 24 1.6e-01 2.4e-03 4.2e-03 24 1.6e-01 2.3e-03 4.3e-03 27554 19 2.0e-01 2.5e-03 5.5e-03 19 2.0e-01 2.5e-03 5.3e-03 19 2.0e-01 2.4e-03 5.5e-03 71468 14 2.5e-01 2.9e-03 7.3e-03 14 2.5e-01 3.0e-03 7.5e-03 15 2.7e-01 3.2e-03 8.2e-03 185364 9 3.7e-01 4.0e-03 1.1e-02 9 3.7e-01 4.1e-03 1.2e-02 9 3.7e-01 4.1e-03 1.2e-02 480774 4 3.8e-01 4.1e-03 1.3e-02 4 3.8e-01 4.0e-03 1.2e-02 4 3.8e-01 4.1e-03 1.1e-02 1246974 1 2.4e-01 2.1e-03 1.1e-02 1 2.5e-01 2.2e-03 1.3e-02 1 2.3e-01 2.1e-03 7.1e-03 3234251 1 5.9e-01 6.0e-03 2.0e-02 1 5.8e-01 6.1e-03 1.9e-02 1 5.8e-01 6.1e-03 1.9e-02 8388608 1 1.5e+00 1.6e-02 4.7e-02 1 1.5e+00 1.6e-02 4.7e-02 1 1.5e+00 1.6e-02 4.7e-02 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 9.2e-01 1.1e-02 2.1e-02 105 3.2e-01 3.7e-03 7.4e-03 106 3.2e-01 3.7e-03 7.4e-03 2 150 4.6e-01 5.3e-03 1.1e-02 71 2.2e-01 2.5e-03 5.0e-03 71 2.2e-01 2.5e-03 5.0e-03 4 75 2.3e-01 2.7e-03 5.3e-03 71 2.2e-01 2.5e-03 5.1e-03 71 2.2e-01 2.6e-03 5.0e-03 8 70 2.1e-01 2.5e-03 5.0e-03 70 2.1e-01 2.5e-03 4.9e-03 68 2.1e-01 2.4e-03 4.8e-03 16 70 2.2e-01 2.5e-03 5.0e-03 71 2.2e-01 2.5e-03 5.0e-03 70 2.1e-01 2.5e-03 5.0e-03 32 70 2.2e-01 2.5e-03 5.0e-03 70 2.2e-01 2.5e-03 5.0e-03 70 2.2e-01 2.5e-03 5.0e-03 64 69 2.2e-01 2.5e-03 5.0e-03 68 2.1e-01 2.5e-03 4.9e-03 70 2.2e-01 2.6e-03 5.1e-03 128 68 2.2e-01 2.6e-03 5.1e-03 67 2.2e-01 2.5e-03 5.1e-03 67 2.2e-01 2.5e-03 5.0e-03 256 64 2.1e-01 2.5e-03 5.0e-03 65 2.2e-01 2.5e-03 5.1e-03 65 2.1e-01 2.4e-03 4.9e-03 512 63 2.2e-01 2.5e-03 5.0e-03 64 2.1e-01 2.4e-03 5.1e-03 67 2.2e-01 2.5e-03 5.1e-03 1024 62 2.2e-01 2.5e-03 5.1e-03 65 2.2e-01 2.5e-03 5.1e-03 65 2.2e-01 2.5e-03 5.1e-03 2048 60 2.3e-01 2.7e-03 5.3e-03 64 2.4e-01 2.9e-03 5.6e-03 65 2.5e-01 2.9e-03 5.7e-03 4096 56 2.5e-01 2.9e-03 5.8e-03 55 2.4e-01 2.8e-03 5.7e-03 56 2.5e-01 2.9e-03 5.8e-03 10624 37 2.3e-01 2.6e-03 5.5e-03 37 2.3e-01 2.6e-03 5.5e-03 37 2.3e-01 2.5e-03 5.5e-03 27554 27 2.6e-01 2.6e-03 6.0e-03 27 2.6e-01 2.9e-03 6.0e-03 27 2.6e-01 2.6e-03 6.1e-03 71468 19 3.2e-01 3.3e-03 7.9e-03 18 3.0e-01 3.3e-03 7.2e-03 19 3.2e-01 3.5e-03 7.7e-03 185364 10 3.9e-01 3.5e-03 9.6e-03 10 3.9e-01 3.9e-03 9.6e-03 10 3.9e-01 3.5e-03 1.0e-02 480774 5 4.4e-01 4.2e-03 1.2e-02 4 3.5e-01 3.4e-03 9.5e-03 5 4.4e-01 4.2e-03 1.2e-02 1246974 2 4.5e-01 4.4e-03 1.3e-02 2 4.7e-01 4.3e-03 1.5e-02 2 4.6e-01 4.3e-03 1.3e-02 3234251 1 5.6e-01 6.1e-03 1.4e-02 1 5.6e-01 6.1e-03 1.4e-02 1 5.6e-01 6.1e-03 1.4e-02 8388608 1 1.4e+00 1.6e-02 3.3e-02 1 1.4e+00 1.6e-02 3.3e-02 1 1.4e+00 1.6e-02 3.3e-02 SECTION-LOOPLNGS-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 64.444 sec sum of max elapsed time per entries above = 64.162 sec difference to elapsed time = 0.282 sec = 0.4% sum based on fastest repetition = 60.685 sec difference to elapsed time = 3.759 sec = 5.8% 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-2*2fix 1 4 1.00 1.00 0 ( -1 -1 -1 ) p01 ring-1*4fix 2 8 2.00 1.00 0 ( -1 -1 -1 ) p02 ring-1*4fix 2 8 2.00 1.00 0 ( -1 -1 -1 ) p03 ring-1*4fix 2 8 2.00 1.00 0 ( -1 -1 -1 ) p04 ring-1*4fix 2 8 2.00 1.00 0 ( -1 -1 -1 ) p05 ring-1*4fix 2 8 2.00 1.00 0 ( -1 -1 -1 ) p06 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p07 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p08 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p09 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p10 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p11 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p12 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p13 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p14 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p15 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p16 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p17 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p18 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p19 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p20 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p21 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p22 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p23 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p24 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p25 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p26 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p27 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p28 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p29 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p30 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p31 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p32 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p33 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p34 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p35 random-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p36 worst-cyc-1dim 2 8 2.00 1.00 0 ( -1 -1 -1 ) p37 best bi-section 2 4 1.00 0.50 0 ( -1 -1 -1 ) p38 worst bi-section 2 4 1.00 0.50 0 ( -1 -1 -1 ) p39 one PingPong Pair 2 2 1.00 0.50 2 ( -1 -1 -1 ) p40 acyclic-2dim-all 4 8 2.00 0.50 0 ( -1 -1 -1 ) p41 acyclic-3dim-all 4 8 2.00 0.50 0 ( -1 -1 -1 ) p42 cyclic-2dim-x 1 4 1.00 1.00 0 ( -1 -1 -1 ) p43 cyclic-2dim-y 1 4 1.00 1.00 0 ( -1 -1 -1 ) p44 cyclic-2dim-all 2 8 2.00 1.00 0 ( -1 -1 -1 ) p45 cyclic-3dim-x 1 4 1.00 1.00 0 ( -1 -1 -1 ) p46 cyclic-3dim-y 1 4 1.00 1.00 0 ( -1 -1 -1 ) p47 cyclic-3dim-all 2 8 2.00 1.00 0 ( -1 -1 -1 ) 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-2*2fix : 183.181 155.599 160.779 -> 183.181 -> 732.725 MByte/s p01 ring-1*4fix : 173.954 163.846 161.722 -> 173.954 -> 695.816 MByte/s p02 ring-1*4fix : 173.903 162.349 163.589 -> 173.903 -> 695.614 MByte/s p03 ring-1*4fix : 171.980 163.111 161.536 -> 171.980 -> 687.920 MByte/s p04 ring-1*4fix : 173.210 163.044 164.231 -> 173.210 -> 692.842 MByte/s p05 ring-1*4fix : 174.887 164.035 162.380 -> 174.887 -> 699.547 MByte/s p06 random-cyc-1dim : 175.556 164.679 160.022 -> 175.556 -> 702.226 MByte/s p07 random-cyc-1dim : 172.383 163.770 160.028 -> 172.383 -> 689.531 MByte/s p08 random-cyc-1dim : 173.356 163.348 163.501 -> 173.356 -> 693.423 MByte/s p09 random-cyc-1dim : 175.108 165.474 162.620 -> 175.108 -> 700.432 MByte/s p10 random-cyc-1dim : 172.846 163.553 160.914 -> 172.846 -> 691.385 MByte/s p11 random-cyc-1dim : 173.114 163.356 162.540 -> 173.114 -> 692.456 MByte/s p12 random-cyc-1dim : 173.568 165.770 163.466 -> 173.568 -> 694.273 MByte/s p13 random-cyc-1dim : 174.483 165.321 162.871 -> 174.483 -> 697.933 MByte/s p14 random-cyc-1dim : 174.016 163.948 162.479 -> 174.016 -> 696.064 MByte/s p15 random-cyc-1dim : 172.828 164.374 162.562 -> 172.828 -> 691.313 MByte/s p16 random-cyc-1dim : 173.567 164.830 162.429 -> 173.567 -> 694.268 MByte/s p17 random-cyc-1dim : 174.291 163.940 163.686 -> 174.291 -> 697.162 MByte/s p18 random-cyc-1dim : 174.806 163.586 163.602 -> 174.806 -> 699.224 MByte/s p19 random-cyc-1dim : 172.322 164.233 162.125 -> 172.322 -> 689.287 MByte/s p20 random-cyc-1dim : 173.183 163.198 163.847 -> 173.183 -> 692.730 MByte/s p21 random-cyc-1dim : 173.344 164.973 161.259 -> 173.344 -> 693.376 MByte/s p22 random-cyc-1dim : 175.451 163.364 159.849 -> 175.451 -> 701.806 MByte/s p23 random-cyc-1dim : 171.620 164.749 161.350 -> 171.620 -> 686.479 MByte/s p24 random-cyc-1dim : 173.840 163.312 162.353 -> 173.840 -> 695.359 MByte/s p25 random-cyc-1dim : 173.873 161.706 163.509 -> 173.873 -> 695.490 MByte/s p26 random-cyc-1dim : 174.388 164.800 162.778 -> 174.388 -> 697.553 MByte/s p27 random-cyc-1dim : 173.278 162.947 161.655 -> 173.278 -> 693.111 MByte/s p28 random-cyc-1dim : 175.192 165.466 162.244 -> 175.192 -> 700.770 MByte/s p29 random-cyc-1dim : 173.813 162.379 161.761 -> 173.813 -> 695.251 MByte/s p30 random-cyc-1dim : 174.026 165.538 163.735 -> 174.026 -> 696.103 MByte/s p31 random-cyc-1dim : 173.081 164.032 162.939 -> 173.081 -> 692.325 MByte/s p32 random-cyc-1dim : 175.132 162.905 162.463 -> 175.132 -> 700.528 MByte/s p33 random-cyc-1dim : 174.576 161.929 162.226 -> 174.576 -> 698.304 MByte/s p34 random-cyc-1dim : 174.202 163.444 163.027 -> 174.202 -> 696.810 MByte/s p35 random-cyc-1dim : 174.197 165.173 163.090 -> 174.197 -> 696.789 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 174.458 164.404 161.808 -> 174.458 -> 697.833 MByte/s p37 best bi-section : 160.544 155.234 166.528 -> 166.528 -> 666.113 MByte/s p38 worst bi-section : 160.050 156.714 168.715 -> 168.715 -> 674.859 MByte/s p39 one PingPong Pair : 83.932 0.000 0.000 -> 83.932 -> 335.729 MByte/s p40 acyclic-2dim-all : 160.386 119.691 164.577 -> 164.577 -> 658.309 MByte/s p41 acyclic-3dim-all : 161.832 120.803 163.939 -> 163.939 -> 655.756 MByte/s p42 cyclic-2dim-x : 183.376 91.530 160.521 -> 183.376 -> 733.503 MByte/s p43 cyclic-2dim-y : 181.789 156.259 164.496 -> 181.789 -> 727.154 MByte/s p44 cyclic-2dim-all : 177.324 120.722 163.044 -> 177.324 -> 709.294 MByte/s p45 cyclic-3dim-x : 183.388 90.936 159.830 -> 183.388 -> 733.553 MByte/s p46 cyclic-3dim-y : 182.675 157.071 162.169 -> 182.675 -> 730.700 MByte/s p47 cyclic-3dim-all : 176.445 121.348 160.808 -> 176.445 -> 705.780 MByte/s log_avg of all rings : 175.148 161.970 162.368 || 175.148 -> 700.592 MByte/s log_avg of all random : 173.845 164.000 162.361 || 173.845 -> 695.382 MByte/s log_avg(ring,random) : 174.496 162.982 162.365 ||(174.496 -> 697.982)MByte/s * size -> accumulated on all pr.: 697.982 651.928 649.458 ||(697.982)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-2*2fix : 179.966 181.732 182.368 -> 182.368 -> 729.471 MByte/s p01 ring-1*4fix : 171.037 174.158 172.950 -> 174.158 -> 696.630 MByte/s p02 ring-1*4fix : 173.483 174.003 174.761 -> 174.761 -> 699.045 MByte/s p03 ring-1*4fix : 174.170 172.153 172.411 -> 174.170 -> 696.681 MByte/s p04 ring-1*4fix : 174.695 173.088 173.405 -> 174.695 -> 698.781 MByte/s p05 ring-1*4fix : 172.511 174.921 173.795 -> 174.921 -> 699.685 MByte/s p06 random-cyc-1dim : 174.582 174.383 174.873 -> 174.873 -> 699.492 MByte/s p07 random-cyc-1dim : 173.185 173.391 173.120 -> 173.391 -> 693.565 MByte/s p08 random-cyc-1dim : 172.946 171.654 172.861 -> 172.946 -> 691.786 MByte/s p09 random-cyc-1dim : 175.626 176.155 174.833 -> 176.155 -> 704.621 MByte/s p10 random-cyc-1dim : 173.511 174.135 172.830 -> 174.135 -> 696.542 MByte/s p11 random-cyc-1dim : 173.053 174.571 173.283 -> 174.571 -> 698.285 MByte/s p12 random-cyc-1dim : 175.074 171.397 174.730 -> 175.074 -> 700.294 MByte/s p13 random-cyc-1dim : 174.262 175.232 173.942 -> 175.232 -> 700.929 MByte/s p14 random-cyc-1dim : 172.138 172.992 174.465 -> 174.465 -> 697.861 MByte/s p15 random-cyc-1dim : 172.557 173.656 174.158 -> 174.158 -> 696.632 MByte/s p16 random-cyc-1dim : 173.477 172.076 174.226 -> 174.226 -> 696.905 MByte/s p17 random-cyc-1dim : 174.245 173.108 173.915 -> 174.245 -> 696.980 MByte/s p18 random-cyc-1dim : 173.111 174.349 173.618 -> 174.349 -> 697.397 MByte/s p19 random-cyc-1dim : 173.689 174.817 173.098 -> 174.817 -> 699.269 MByte/s p20 random-cyc-1dim : 174.022 173.513 173.415 -> 174.022 -> 696.087 MByte/s p21 random-cyc-1dim : 175.092 173.523 173.002 -> 175.092 -> 700.369 MByte/s p22 random-cyc-1dim : 174.811 173.059 173.701 -> 174.811 -> 699.246 MByte/s p23 random-cyc-1dim : 171.742 174.111 172.541 -> 174.111 -> 696.444 MByte/s p24 random-cyc-1dim : 173.989 173.141 173.105 -> 173.989 -> 695.956 MByte/s p25 random-cyc-1dim : 172.957 173.927 173.587 -> 173.927 -> 695.707 MByte/s p26 random-cyc-1dim : 171.625 175.280 172.571 -> 175.280 -> 701.118 MByte/s p27 random-cyc-1dim : 172.848 174.353 173.492 -> 174.353 -> 697.412 MByte/s p28 random-cyc-1dim : 176.348 174.173 175.885 -> 176.348 -> 705.392 MByte/s p29 random-cyc-1dim : 174.267 172.923 173.429 -> 174.267 -> 697.066 MByte/s p30 random-cyc-1dim : 173.419 175.947 173.731 -> 175.947 -> 703.787 MByte/s p31 random-cyc-1dim : 173.256 174.217 173.280 -> 174.217 -> 696.870 MByte/s p32 random-cyc-1dim : 173.410 173.999 172.754 -> 173.999 -> 695.998 MByte/s p33 random-cyc-1dim : 171.931 172.399 172.920 -> 172.920 -> 691.679 MByte/s p34 random-cyc-1dim : 174.106 173.421 173.028 -> 174.106 -> 696.422 MByte/s p35 random-cyc-1dim : 173.124 174.479 174.805 -> 174.805 -> 699.221 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 174.486 173.460 175.011 -> 175.011 -> 700.045 MByte/s p37 best bi-section : 168.932 171.227 167.017 -> 171.227 -> 684.908 MByte/s p38 worst bi-section : 170.967 172.875 173.149 -> 173.149 -> 692.595 MByte/s p39 one PingPong Pair : 83.228 80.384 78.347 -> 83.228 -> 332.913 MByte/s p40 acyclic-2dim-all : 168.226 164.038 165.274 -> 168.226 -> 672.903 MByte/s p41 acyclic-3dim-all : 166.289 166.267 164.982 -> 166.289 -> 665.157 MByte/s p42 cyclic-2dim-x : 181.860 180.647 182.551 -> 182.551 -> 730.204 MByte/s p43 cyclic-2dim-y : 180.672 181.417 181.623 -> 181.623 -> 726.491 MByte/s p44 cyclic-2dim-all : 175.323 172.323 176.326 -> 176.326 -> 705.302 MByte/s p45 cyclic-3dim-x : 181.576 181.515 181.686 -> 181.686 -> 726.743 MByte/s p46 cyclic-3dim-y : 181.426 182.810 181.055 -> 182.810 -> 731.242 MByte/s p47 cyclic-3dim-all : 173.727 176.050 174.401 -> 176.050 -> 704.202 MByte/s log_avg of all rings : 174.288 174.981 174.916 || 175.822 -> 703.287 MByte/s log_avg of all random : 173.610 173.809 173.638 || 174.493 -> 697.971 MByte/s log_avg(ring,random) : 173.949 174.394 174.276 ||(175.156 -> 700.624)MByte/s * size -> accumulated on all pr.: 695.796 697.578 697.104 ||(700.624)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-2*2fix p00 method 0 =Sndrcv :( 15.316) 0.065 1.002 14.456 126.299 453.767 529.451 -> 183.181 -> 732.725 MByte/s p00 method 1 =Alltoal :( 60.099) 0.017 0.267 4.158 52.743 415.415 528.715 -> 155.599 -> 622.394 MByte/s p00 method 2 =non-blk :( 36.896) 0.027 0.439 6.734 77.552 392.306 528.151 -> 160.779 -> 643.115 MByte/s p01 ring-1*4fix p01 method 0 =Sndrcv :( 15.325) 0.065 1.022 14.626 124.555 425.959 524.928 -> 173.954 -> 695.816 MByte/s p01 method 1 =Alltoal :( 30.550) 0.033 0.521 7.841 85.031 418.853 527.569 -> 163.846 -> 655.383 MByte/s p01 method 2 =non-blk :( 34.838) 0.029 0.459 6.978 81.593 424.611 524.369 -> 161.722 -> 646.887 MByte/s p02 ring-1*4fix p02 method 0 =Sndrcv :( 15.392) 0.065 1.023 14.596 125.493 423.648 524.699 -> 173.903 -> 695.614 MByte/s p02 method 1 =Alltoal :( 30.808) 0.032 0.518 7.886 84.654 423.851 526.344 -> 162.349 -> 649.394 MByte/s p02 method 2 =non-blk :( 34.576) 0.029 0.457 6.986 81.731 428.832 525.766 -> 163.589 -> 654.357 MByte/s p03 ring-1*4fix p03 method 0 =Sndrcv :( 15.336) 0.065 1.015 14.649 124.668 428.379 524.453 -> 171.980 -> 687.920 MByte/s p03 method 1 =Alltoal :( 30.760) 0.033 0.522 7.902 85.031 415.046 525.387 -> 163.111 -> 652.444 MByte/s p03 method 2 =non-blk :( 34.547) 0.029 0.459 6.905 80.994 421.955 524.682 -> 161.536 -> 646.143 MByte/s p04 ring-1*4fix p04 method 0 =Sndrcv :( 15.422) 0.065 1.021 14.872 124.668 413.834 525.109 -> 173.210 -> 692.842 MByte/s p04 method 1 =Alltoal :( 30.459) 0.033 0.521 7.918 85.106 397.730 526.726 -> 163.044 -> 652.176 MByte/s p04 method 2 =non-blk :( 34.642) 0.029 0.460 6.869 81.819 428.933 525.848 -> 164.231 -> 656.926 MByte/s p05 ring-1*4fix p05 method 0 =Sndrcv :( 15.430) 0.065 1.019 14.694 124.608 437.264 523.863 -> 174.887 -> 699.547 MByte/s p05 method 1 =Alltoal :( 30.631) 0.033 0.520 7.886 84.929 422.291 526.377 -> 164.035 -> 656.141 MByte/s p05 method 2 =non-blk :( 34.721) 0.029 0.458 6.962 83.018 417.301 525.585 -> 162.380 -> 649.521 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 15.359) 0.065 1.029 14.748 125.850 409.870 524.451 -> 175.556 -> 702.226 MByte/s p06 method 1 =Alltoal :( 30.533) 0.033 0.518 7.853 84.728 431.078 523.780 -> 164.679 -> 658.718 MByte/s p06 method 2 =non-blk :( 34.896) 0.029 0.454 6.964 81.432 422.913 525.585 -> 160.022 -> 640.086 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 15.516) 0.064 1.020 14.652 125.994 422.722 525.224 -> 172.383 -> 689.531 MByte/s p07 method 1 =Alltoal :( 30.475) 0.033 0.519 7.874 85.639 417.485 525.685 -> 163.770 -> 655.082 MByte/s p07 method 2 =non-blk :( 34.769) 0.029 0.459 6.863 81.239 407.033 524.451 -> 160.028 -> 640.113 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 15.436) 0.065 1.019 14.900 124.218 423.811 525.848 -> 173.356 -> 693.423 MByte/s p08 method 1 =Alltoal :( 30.442) 0.033 0.519 7.896 85.004 410.198 524.336 -> 163.348 -> 653.393 MByte/s p08 method 2 =non-blk :( 34.750) 0.029 0.457 6.896 81.833 432.488 526.029 -> 163.501 -> 654.003 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 15.285) 0.065 1.026 14.971 126.714 425.270 525.009 -> 175.108 -> 700.432 MByte/s p09 method 1 =Alltoal :( 30.532) 0.033 0.519 7.844 84.654 460.785 525.882 -> 165.474 -> 661.896 MByte/s p09 method 2 =non-blk :( 34.876) 0.029 0.455 6.998 82.658 418.007 524.254 -> 162.620 -> 650.480 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 15.354) 0.065 1.020 14.682 127.941 405.391 525.717 -> 172.846 -> 691.385 MByte/s p10 method 1 =Alltoal :( 30.476) 0.033 0.519 7.908 84.956 430.078 524.402 -> 163.553 -> 654.211 MByte/s p10 method 2 =non-blk :( 34.825) 0.029 0.458 7.005 82.346 422.913 521.323 -> 160.914 -> 643.656 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 15.359) 0.065 1.013 14.733 125.220 430.291 525.931 -> 173.114 -> 692.456 MByte/s p11 method 1 =Alltoal :( 30.630) 0.033 0.519 7.899 84.803 425.417 523.992 -> 163.356 -> 653.424 MByte/s p11 method 2 =non-blk :( 34.700) 0.029 0.458 6.848 82.491 414.636 525.222 -> 162.540 -> 650.161 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 15.413) 0.065 1.020 14.860 126.754 426.817 525.356 -> 173.568 -> 694.273 MByte/s p12 method 1 =Alltoal :( 30.738) 0.033 0.519 7.871 85.284 405.315 524.320 -> 165.770 -> 663.079 MByte/s p12 method 2 =non-blk :( 34.580) 0.029 0.457 6.855 82.406 431.480 524.322 -> 163.466 -> 653.866 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 15.488) 0.065 1.016 14.757 126.311 418.427 526.360 -> 174.483 -> 697.933 MByte/s p13 method 1 =Alltoal :( 30.567) 0.033 0.519 7.793 86.152 437.465 526.460 -> 165.321 -> 661.285 MByte/s p13 method 2 =non-blk :( 34.637) 0.029 0.455 6.965 82.265 420.278 525.899 -> 162.871 -> 651.482 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 15.425) 0.065 1.024 14.688 126.613 427.555 526.757 -> 174.016 -> 696.064 MByte/s p14 method 1 =Alltoal :( 30.566) 0.033 0.519 7.871 85.031 436.265 526.013 -> 163.948 -> 655.793 MByte/s p14 method 2 =non-blk :( 34.863) 0.029 0.458 6.980 80.992 417.817 524.566 -> 162.479 -> 649.917 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 15.397) 0.065 1.015 14.623 127.007 421.680 524.697 -> 172.828 -> 691.313 MByte/s p15 method 1 =Alltoal :( 30.459) 0.033 0.520 7.924 84.304 425.799 524.911 -> 164.374 -> 657.496 MByte/s p15 method 2 =non-blk :( 34.852) 0.029 0.457 6.916 80.879 413.571 526.460 -> 162.562 -> 650.246 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 15.500) 0.065 1.022 14.827 125.294 419.415 524.584 -> 173.567 -> 694.268 MByte/s p16 method 1 =Alltoal :( 30.558) 0.033 0.517 7.844 85.336 425.087 524.551 -> 164.830 -> 659.319 MByte/s p16 method 2 =non-blk :( 34.807) 0.029 0.456 6.915 81.311 424.078 526.228 -> 162.429 -> 649.714 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 15.419) 0.065 1.018 14.808 128.261 427.477 525.899 -> 174.291 -> 697.162 MByte/s p17 method 1 =Alltoal :( 30.427) 0.033 0.520 7.817 85.664 425.851 523.943 -> 163.940 -> 655.760 MByte/s p17 method 2 =non-blk :( 34.962) 0.029 0.460 6.987 82.406 407.801 525.815 -> 163.686 -> 654.742 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 15.358) 0.065 1.022 14.703 126.910 431.495 523.063 -> 174.806 -> 699.224 MByte/s p18 method 1 =Alltoal :( 30.565) 0.033 0.519 7.902 84.878 434.444 526.178 -> 163.586 -> 654.344 MByte/s p18 method 2 =non-blk :( 34.830) 0.029 0.459 7.005 82.869 417.581 520.822 -> 163.602 -> 654.406 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 15.263) 0.066 1.028 14.745 124.473 428.793 524.256 -> 172.322 -> 689.287 MByte/s p19 method 1 =Alltoal :( 30.386) 0.033 0.519 7.833 84.878 429.471 524.877 -> 164.233 -> 656.932 MByte/s p19 method 2 =non-blk :( 34.915) 0.029 0.455 6.866 81.686 415.056 527.122 -> 162.125 -> 648.500 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 15.348) 0.065 1.023 14.854 125.858 419.057 525.158 -> 173.183 -> 692.730 MByte/s p20 method 1 =Alltoal :( 30.587) 0.033 0.518 7.865 83.714 394.996 525.505 -> 163.198 -> 652.791 MByte/s p20 method 2 =non-blk :( 34.667) 0.029 0.456 6.948 82.642 433.749 526.478 -> 163.847 -> 655.387 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 15.390) 0.065 1.024 14.709 124.481 410.931 524.780 -> 173.344 -> 693.376 MByte/s p21 method 1 =Alltoal :( 30.727) 0.033 0.519 7.799 84.980 417.280 524.320 -> 164.973 -> 659.891 MByte/s p21 method 2 =non-blk :( 34.580) 0.029 0.460 7.008 81.549 420.614 522.281 -> 161.259 -> 645.035 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 15.415) 0.065 1.026 14.775 126.948 421.680 525.289 -> 175.451 -> 701.806 MByte/s p22 method 1 =Alltoal :( 30.730) 0.033 0.520 7.867 85.103 408.688 525.191 -> 163.364 -> 653.454 MByte/s p22 method 2 =non-blk :( 34.679) 0.029 0.456 6.999 82.941 421.663 522.900 -> 159.849 -> 639.395 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 15.370) 0.065 1.021 14.561 126.265 420.445 524.008 -> 171.620 -> 686.479 MByte/s p23 method 1 =Alltoal :( 30.492) 0.033 0.520 7.902 85.206 419.959 525.964 -> 164.749 -> 658.997 MByte/s p23 method 2 =non-blk :( 34.773) 0.029 0.458 6.906 82.824 410.238 521.486 -> 161.350 -> 645.401 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 15.503) 0.065 1.023 14.922 125.533 412.494 522.378 -> 173.840 -> 695.359 MByte/s p24 method 1 =Alltoal :( 30.451) 0.033 0.520 7.850 85.612 405.221 524.043 -> 163.312 -> 653.247 MByte/s p24 method 2 =non-blk :( 34.953) 0.029 0.458 7.006 81.411 417.963 524.353 -> 162.353 -> 649.413 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 15.337) 0.065 1.016 14.775 124.529 425.794 524.600 -> 173.873 -> 695.490 MByte/s p25 method 1 =Alltoal :( 30.402) 0.033 0.519 7.924 83.155 428.530 525.505 -> 161.706 -> 646.823 MByte/s p25 method 2 =non-blk :( 34.838) 0.029 0.458 7.024 82.550 432.584 525.075 -> 163.509 -> 654.036 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 15.451) 0.065 1.024 14.703 126.323 428.463 523.030 -> 174.388 -> 697.553 MByte/s p26 method 1 =Alltoal :( 30.500) 0.033 0.519 7.959 85.664 440.065 524.418 -> 164.800 -> 659.199 MByte/s p26 method 2 =non-blk :( 34.807) 0.029 0.458 6.997 81.528 430.280 522.558 -> 162.778 -> 651.112 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 15.372) 0.065 1.021 14.745 125.913 428.877 525.405 -> 173.278 -> 693.111 MByte/s p27 method 1 =Alltoal :( 30.541) 0.033 0.521 7.890 83.592 410.300 526.295 -> 162.947 -> 651.786 MByte/s p27 method 2 =non-blk :( 34.886) 0.029 0.455 6.851 81.905 409.056 525.093 -> 161.655 -> 646.622 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 15.263) 0.066 1.026 14.867 127.145 410.628 523.764 -> 175.192 -> 700.770 MByte/s p28 method 1 =Alltoal :( 30.668) 0.033 0.518 7.826 84.830 429.359 525.436 -> 165.466 -> 661.865 MByte/s p28 method 2 =non-blk :( 34.786) 0.029 0.457 6.975 81.564 431.031 524.977 -> 162.244 -> 648.974 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 15.413) 0.065 1.018 14.715 124.233 423.729 521.890 -> 173.813 -> 695.251 MByte/s p29 method 1 =Alltoal :( 30.762) 0.033 0.521 7.874 85.181 433.710 522.768 -> 162.379 -> 649.518 MByte/s p29 method 2 =non-blk :( 34.495) 0.029 0.456 6.986 81.368 425.540 525.436 -> 161.761 -> 647.043 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 15.345) 0.065 1.027 14.679 127.322 414.068 522.591 -> 174.026 -> 696.103 MByte/s p30 method 1 =Alltoal :( 30.509) 0.033 0.519 7.868 84.404 433.878 523.667 -> 165.538 -> 662.150 MByte/s p30 method 2 =non-blk :( 34.703) 0.029 0.455 6.865 82.399 430.179 518.393 -> 163.735 -> 654.938 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 15.455) 0.065 1.022 14.857 125.770 427.105 525.173 -> 173.081 -> 692.325 MByte/s p31 method 1 =Alltoal :( 30.459) 0.033 0.522 7.896 85.743 423.582 525.884 -> 164.032 -> 656.130 MByte/s p31 method 2 =non-blk :( 34.703) 0.029 0.460 6.879 80.258 427.994 524.074 -> 162.939 -> 651.758 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 15.471) 0.065 1.021 14.882 127.166 424.902 522.426 -> 175.132 -> 700.528 MByte/s p32 method 1 =Alltoal :( 30.476) 0.033 0.521 7.829 86.078 409.095 525.256 -> 162.905 -> 651.619 MByte/s p32 method 2 =non-blk :( 34.781) 0.029 0.459 6.999 82.450 423.443 523.782 -> 162.463 -> 649.852 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 15.333) 0.065 1.020 14.572 124.902 435.168 523.928 -> 174.576 -> 698.304 MByte/s p33 method 1 =Alltoal :( 30.541) 0.033 0.518 7.902 84.905 426.071 524.615 -> 161.929 -> 647.714 MByte/s p33 method 2 =non-blk :( 34.852) 0.029 0.457 6.995 81.296 420.995 523.895 -> 162.226 -> 648.902 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 15.417) 0.065 1.025 14.727 127.148 423.648 523.112 -> 174.202 -> 696.810 MByte/s p34 method 1 =Alltoal :( 30.532) 0.033 0.520 7.930 85.130 427.379 524.174 -> 163.444 -> 653.777 MByte/s p34 method 2 =non-blk :( 34.847) 0.029 0.455 6.872 82.657 425.296 524.764 -> 163.027 -> 652.107 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 15.274) 0.065 1.028 14.944 126.576 434.530 522.995 -> 174.197 -> 696.789 MByte/s p35 method 1 =Alltoal :( 30.625) 0.033 0.518 7.855 84.505 429.800 524.518 -> 165.173 -> 660.694 MByte/s p35 method 2 =non-blk :( 34.781) 0.029 0.459 6.860 82.718 435.078 524.059 -> 163.090 -> 652.359 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 15.243) 0.066 1.029 14.906 125.816 412.685 523.912 -> 174.458 -> 697.833 MByte/s p36 method 1 =Alltoal :( 30.525) 0.033 0.520 7.829 84.304 425.365 525.191 -> 164.404 -> 657.616 MByte/s p36 method 2 =non-blk :( 34.729) 0.029 0.456 6.913 82.385 427.941 523.503 -> 161.808 -> 647.233 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 11.688) 0.043 0.657 9.203 95.611 381.996 593.969 -> 160.544 -> 642.176 MByte/s p37 method 1 =Alltoal :( 30.057) 0.017 0.264 4.076 51.961 403.754 528.449 -> 155.234 -> 620.936 MByte/s p37 method 2 =non-blk :( 17.500) 0.029 0.450 6.825 79.287 450.018 521.517 -> 166.528 -> 666.113 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 11.658) 0.043 0.657 9.206 93.902 384.444 589.580 -> 160.050 -> 640.200 MByte/s p38 method 1 =Alltoal :( 30.222) 0.017 0.264 4.076 51.642 405.803 526.858 -> 156.714 -> 626.855 MByte/s p38 method 2 =non-blk :( 17.495) 0.029 0.453 6.806 77.231 469.503 521.323 -> 168.715 -> 674.859 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 11.521) 0.022 0.332 4.665 50.122 212.943 301.445 -> 83.932 -> 335.729 MByte/s p39 method 1 =Alltoal :(-------) 0.000 0.000 0.000 0.000 0.000 0.000 -> 0.000 -> 0.000 MByte/s p39 method 2 =non-blk :(-------) 0.000 0.000 0.000 0.000 0.000 0.000 -> 0.000 -> 0.000 MByte/s p40 acyclic-2dim-all p40 method 0 =Sndrcv :( 11.709) 0.043 0.653 9.345 96.946 396.114 592.771 -> 160.386 -> 641.543 MByte/s p40 method 1 =Alltoal :( 15.545) 0.032 0.509 7.595 81.084 311.391 357.228 -> 119.691 -> 478.765 MByte/s p40 method 2 =non-blk :( 16.767) 0.030 0.476 7.103 81.701 432.085 525.618 -> 164.577 -> 658.309 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 11.684) 0.043 0.655 9.350 96.993 404.394 594.685 -> 161.832 -> 647.328 MByte/s p41 method 1 =Alltoal :( 15.702) 0.032 0.509 7.575 81.155 312.500 358.212 -> 120.803 -> 483.211 MByte/s p41 method 2 =non-blk :( 16.629) 0.030 0.474 7.202 81.683 426.615 525.964 -> 163.939 -> 655.756 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 15.585) 0.064 1.022 14.661 127.561 442.931 528.183 -> 183.376 -> 733.503 MByte/s p42 method 1 =Alltoal :( 59.755) 0.017 0.267 4.163 47.361 249.857 271.855 -> 91.530 -> 366.120 MByte/s p42 method 2 =non-blk :( 36.352) 0.028 0.436 6.531 77.412 398.725 523.826 -> 160.521 -> 642.086 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 15.572) 0.064 1.008 14.703 124.763 452.019 522.364 -> 181.789 -> 727.154 MByte/s p43 method 1 =Alltoal :( 59.802) 0.017 0.266 4.152 52.843 406.015 524.486 -> 156.259 -> 625.035 MByte/s p43 method 2 =non-blk :( 36.967) 0.027 0.438 6.781 76.133 398.551 524.486 -> 164.496 -> 657.984 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 15.288) 0.065 1.022 14.910 126.265 438.600 525.964 -> 177.324 -> 709.294 MByte/s p44 method 1 =Alltoal :( 30.617) 0.033 0.520 7.877 83.447 318.068 357.069 -> 120.722 -> 482.890 MByte/s p44 method 2 =non-blk :( 34.595) 0.029 0.457 6.996 80.061 416.223 523.928 -> 163.044 -> 652.176 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 15.398) 0.065 1.017 14.626 125.837 442.836 527.055 -> 183.388 -> 733.553 MByte/s p45 method 1 =Alltoal :( 59.671) 0.017 0.266 4.148 47.173 240.175 271.187 -> 90.936 -> 363.744 MByte/s p45 method 2 =non-blk :( 36.907) 0.027 0.436 6.614 78.338 397.776 524.518 -> 159.830 -> 639.319 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 15.577) 0.064 1.005 14.643 124.537 455.162 524.877 -> 182.675 -> 730.700 MByte/s p46 method 1 =Alltoal :( 59.673) 0.017 0.266 4.158 52.724 407.196 524.811 -> 157.071 -> 628.282 MByte/s p46 method 2 =non-blk :( 36.095) 0.028 0.439 6.525 77.415 383.861 524.123 -> 162.169 -> 648.674 MByte/s p47 cyclic-3dim-all p47 method 0 =Sndrcv :( 15.352) 0.065 1.024 14.772 126.167 434.914 523.863 -> 176.445 -> 705.780 MByte/s p47 method 1 =Alltoal :( 30.484) 0.033 0.519 7.921 82.866 322.373 358.128 -> 121.348 -> 485.394 MByte/s p47 method 2 =non-blk :( 34.765) 0.029 0.458 6.856 80.213 407.887 521.356 -> 160.808 -> 643.230 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.065 1.017 14.648 125.047 430.296 525.414 || 175.148 -> 700.592 MByte/s - ring, method 1 = Alltoal: 0.029 0.465 7.088 78.463 415.441 526.852 || 161.970 -> 647.882 MByte/s - ring, method 2 = non-blk: 0.029 0.455 6.905 81.100 418.795 525.732 || 162.368 -> 649.474 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.065 1.022 14.766 126.118 422.620 524.454 || 173.845 -> 695.382 MByte/s - random, method 1 = Alltoal: 0.033 0.519 7.872 84.968 424.228 524.895 || 164.000 -> 655.999 MByte/s - random, method 2 = non-blk: 0.029 0.457 6.941 81.960 421.971 524.253 || 162.361 -> 649.442 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.065 1.019 14.707 125.581 426.441 524.934 || 174.496 -> 697.982 MByte/s - average, method 1 = Alltoal: 0.031 0.492 7.470 81.650 419.811 525.873 || 162.982 -> 651.928 MByte/s - average, method 2 = non-blk: 0.029 0.456 6.923 81.528 420.380 524.992 || 162.365 -> 649.458 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.260 4.078 58.828 502.325 1705.763 2099.736 || 697.982 MByte/s - accumulated, mthd 1 = Alltoal: 0.124 1.967 29.879 326.602 1679.244 2103.491 || 651.928 MByte/s - accumulated, mthd 2 = non-blk: 0.115 1.825 27.692 326.114 1681.519 2099.969 || 649.458 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 0.260 0.065 0.065 0.065 0.065 0.031 0.029 2 0.516 0.129 0.129 0.129 0.129 0.062 0.057 4 1.026 0.257 0.256 0.257 0.257 0.123 0.114 8 2.062 0.515 0.515 0.516 0.515 0.247 0.229 16 4.078 1.019 1.017 1.022 1.019 0.492 0.456 32 8.033 2.008 2.007 2.009 2.008 0.976 0.904 64 15.475 3.869 3.863 3.875 3.869 1.917 1.778 128 29.129 7.282 7.286 7.279 7.282 3.717 3.445 256 58.828 14.707 14.648 14.766 14.707 7.470 6.923 512 114.146 28.537 28.388 28.686 28.537 14.727 13.541 1024 216.092 54.023 53.945 54.101 54.023 28.562 26.364 2048 326.882 81.720 82.002 81.440 81.720 48.579 47.330 4096 502.325 125.581 125.047 126.118 125.581 81.650 81.528 10624 798.496 199.624 200.316 198.935 199.624 142.290 147.190 27554 1218.894 304.724 309.543 299.979 304.724 245.908 253.445 71468 1558.243 389.561 389.261 389.861 387.708 368.682 373.346 185364 1728.693 432.173 433.752 430.600 426.441 419.811 420.380 480774 1949.087 487.272 488.684 485.864 476.974 480.222 481.434 1246974 2111.946 527.986 534.216 521.830 504.613 526.611 511.764 3234251 2091.163 522.791 523.206 522.376 519.117 521.504 513.320 8388608 2105.141 526.285 526.974 525.598 524.934 525.873 524.992 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-2*2fix :( 15.316) 0.065 1.002 14.456 126.299 453.767 529.451 -> 184.939 -> 739.757 MByte/s p01 ring-1*4fix :( 15.325) 0.065 1.022 14.626 124.555 425.959 527.569 -> 176.075 -> 704.299 MByte/s p02 ring-1*4fix :( 15.392) 0.065 1.023 14.596 125.493 428.832 526.344 -> 175.767 -> 703.067 MByte/s p03 ring-1*4fix :( 15.336) 0.065 1.015 14.649 124.668 428.379 525.387 -> 175.203 -> 700.814 MByte/s p04 ring-1*4fix :( 15.422) 0.065 1.021 14.872 124.668 428.933 526.726 -> 176.219 -> 704.874 MByte/s p05 ring-1*4fix :( 15.430) 0.065 1.019 14.694 124.608 437.264 526.377 -> 176.509 -> 706.037 MByte/s p06 random-cyc-1dim :( 15.359) 0.065 1.029 14.748 125.850 431.078 525.585 -> 177.386 -> 709.544 MByte/s p07 random-cyc-1dim :( 15.516) 0.064 1.020 14.652 125.994 422.722 525.685 -> 174.781 -> 699.124 MByte/s p08 random-cyc-1dim :( 15.436) 0.065 1.019 14.900 124.218 432.488 526.029 -> 174.759 -> 699.035 MByte/s p09 random-cyc-1dim :( 15.285) 0.065 1.026 14.971 126.714 460.785 525.882 -> 178.357 -> 713.429 MByte/s p10 random-cyc-1dim :( 15.354) 0.065 1.020 14.682 127.941 430.078 525.717 -> 175.643 -> 702.571 MByte/s p11 random-cyc-1dim :( 15.359) 0.065 1.013 14.733 125.220 430.291 525.931 -> 175.207 -> 700.828 MByte/s p12 random-cyc-1dim :( 15.413) 0.065 1.020 14.860 126.754 431.480 525.356 -> 176.600 -> 706.401 MByte/s p13 random-cyc-1dim :( 15.488) 0.065 1.016 14.757 126.311 437.465 526.460 -> 176.711 -> 706.843 MByte/s p14 random-cyc-1dim :( 15.425) 0.065 1.024 14.688 126.613 436.265 526.757 -> 176.229 -> 704.916 MByte/s p15 random-cyc-1dim :( 15.397) 0.065 1.015 14.623 127.007 425.799 526.460 -> 175.973 -> 703.892 MByte/s p16 random-cyc-1dim :( 15.500) 0.065 1.022 14.827 125.294 425.087 526.228 -> 175.267 -> 701.068 MByte/s p17 random-cyc-1dim :( 15.419) 0.065 1.018 14.808 128.261 427.477 525.899 -> 175.969 -> 703.875 MByte/s p18 random-cyc-1dim :( 15.358) 0.065 1.022 14.703 126.910 434.444 526.178 -> 176.421 -> 705.683 MByte/s p19 random-cyc-1dim :( 15.263) 0.066 1.028 14.745 124.473 429.471 527.122 -> 175.387 -> 701.550 MByte/s p20 random-cyc-1dim :( 15.348) 0.065 1.023 14.854 125.858 433.749 526.478 -> 175.683 -> 702.734 MByte/s p21 random-cyc-1dim :( 15.390) 0.065 1.024 14.709 124.481 420.614 524.780 -> 176.691 -> 706.764 MByte/s p22 random-cyc-1dim :( 15.415) 0.065 1.026 14.775 126.948 421.680 525.289 -> 176.959 -> 707.837 MByte/s p23 random-cyc-1dim :( 15.370) 0.065 1.021 14.561 126.265 420.445 525.964 -> 174.864 -> 699.457 MByte/s p24 random-cyc-1dim :( 15.503) 0.065 1.023 14.922 125.533 417.963 524.353 -> 175.996 -> 703.985 MByte/s p25 random-cyc-1dim :( 15.337) 0.065 1.016 14.775 124.529 432.584 525.505 -> 175.468 -> 701.874 MByte/s p26 random-cyc-1dim :( 15.451) 0.065 1.024 14.703 126.323 440.065 524.418 -> 176.029 -> 704.117 MByte/s p27 random-cyc-1dim :( 15.372) 0.065 1.021 14.745 125.913 428.877 526.295 -> 175.637 -> 702.546 MByte/s p28 random-cyc-1dim :( 15.263) 0.066 1.026 14.867 127.145 431.031 525.436 -> 178.009 -> 712.036 MByte/s p29 random-cyc-1dim :( 15.413) 0.065 1.018 14.715 124.233 433.710 525.436 -> 175.161 -> 700.644 MByte/s p30 random-cyc-1dim :( 15.345) 0.065 1.027 14.679 127.322 433.878 523.667 -> 177.451 -> 709.804 MByte/s p31 random-cyc-1dim :( 15.455) 0.065 1.022 14.857 125.770 427.994 525.884 -> 175.485 -> 701.938 MByte/s p32 random-cyc-1dim :( 15.471) 0.065 1.021 14.882 127.166 424.902 525.256 -> 175.432 -> 701.730 MByte/s p33 random-cyc-1dim :( 15.333) 0.065 1.020 14.572 124.902 435.168 524.615 -> 174.879 -> 699.515 MByte/s p34 random-cyc-1dim :( 15.417) 0.065 1.025 14.727 127.148 427.379 524.764 -> 175.145 -> 700.578 MByte/s p35 random-cyc-1dim :( 15.274) 0.065 1.028 14.944 126.576 435.078 524.518 -> 175.970 -> 703.882 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 15.243) 0.066 1.029 14.906 125.816 427.941 525.191 -> 176.964 -> 707.855 MByte/s p37 best bi-section :( 11.688) 0.043 0.657 9.203 95.611 450.018 593.969 -> 173.172 -> 692.689 MByte/s p38 worst bi-section :( 11.658) 0.043 0.657 9.206 93.902 469.503 589.580 -> 176.081 -> 704.323 MByte/s p39 one PingPong Pair :( 11.521) 0.022 0.332 4.665 50.122 212.943 301.445 -> 83.932 -> 335.729 MByte/s p40 acyclic-2dim-all :( 11.709) 0.043 0.653 9.345 96.946 432.085 592.771 -> 169.679 -> 678.714 MByte/s p41 acyclic-3dim-all :( 11.684) 0.043 0.655 9.350 96.993 426.615 594.685 -> 169.837 -> 679.347 MByte/s p42 cyclic-2dim-x :( 15.585) 0.064 1.022 14.661 127.561 442.931 528.183 -> 183.455 -> 733.820 MByte/s p43 cyclic-2dim-y :( 15.572) 0.064 1.008 14.703 124.763 452.019 524.486 -> 182.908 -> 731.632 MByte/s p44 cyclic-2dim-all :( 15.288) 0.065 1.022 14.910 126.265 438.600 525.964 -> 178.381 -> 713.522 MByte/s p45 cyclic-3dim-x :( 15.398) 0.065 1.017 14.626 125.837 442.836 527.055 -> 184.058 -> 736.233 MByte/s p46 cyclic-3dim-y :( 15.577) 0.064 1.005 14.643 124.537 455.162 524.877 -> 184.780 -> 739.118 MByte/s p47 cyclic-3dim-all :( 15.352) 0.065 1.024 14.772 126.167 434.914 523.863 -> 176.633 -> 706.531 MByte/s log_avg of all rings : 0.065 1.017 14.648 125.047 433.752 526.974 || 177.421 -> 709.683 MByte/s log_avg of all random : 0.065 1.022 14.766 126.118 430.600 525.598 || 175.983 -> 703.930 MByte/s log_avg(ring,random) : 0.065 1.019 14.707 125.581 432.173 526.285 || 176.700 -> 706.801 MByte/s * size -> accumulated on all pr.: 0.260 4.078 58.828 502.325 1728.693 2105.141 || 706.801 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 706.801 MByte/s on 4 processes ( = 176.700 MByte/s * 4 processes) Ping-pong latency: 11.521 microsec Ping-pong bandwidth: 1205.780 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 4 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 14:34:57 1999 Total execution wall clock time = 66 seconds SECTION-BEFF-END b_eff = 706.801 MB/s = 176.700 * 4 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000