b_eff = 1218.994 MB/s = 152.374 * 8 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 = 8 2-dim-paterns: size = 4 * 2 3-dim-paterns: size = 2 * 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-4*2fix 1=ring-2*4fix 2=ring-1*8fix 3=ring-1*8fix 4=ring-1*8fix 5=ring-1*8fix 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: 90.022 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 5.1e-01 4.8e-03 2.2e-02 228 3.9e-01 3.7e-03 1.9e-02 231 4.4e-01 3.7e-03 2.8e-02 2 156 2.5e-01 2.5e-03 1.2e-02 152 2.5e-01 2.5e-03 1.1e-02 154 2.7e-01 2.5e-03 1.2e-02 4 155 2.6e-01 2.5e-03 1.5e-02 153 2.6e-01 2.5e-03 1.3e-02 153 2.9e-01 2.5e-03 2.0e-02 8 152 2.6e-01 2.5e-03 1.6e-02 150 2.8e-01 2.4e-03 2.4e-02 151 2.6e-01 2.5e-03 1.1e-02 16 152 2.7e-01 2.5e-03 1.6e-02 154 2.6e-01 2.6e-03 1.2e-02 152 5.1e-01 2.5e-03 2.3e-01 32 151 4.0e-01 2.5e-03 1.3e-01 150 2.5e-01 2.6e-03 1.2e-02 152 3.3e-01 2.6e-03 7.1e-02 64 152 3.1e-01 2.6e-03 2.3e-02 146 2.6e-01 2.6e-03 1.2e-02 146 2.6e-01 2.6e-03 1.2e-02 128 143 2.8e-01 2.7e-03 1.8e-02 140 2.8e-01 2.6e-03 1.3e-02 141 2.9e-01 2.7e-03 2.5e-02 256 134 3.7e-01 2.7e-03 6.5e-02 133 3.1e-01 2.6e-03 1.6e-02 131 2.7e-01 2.5e-03 1.7e-02 512 124 2.7e-01 2.5e-03 1.1e-02 128 2.8e-01 2.7e-03 1.2e-02 130 2.8e-01 2.6e-03 1.4e-02 1024 122 3.1e-01 2.7e-03 1.5e-02 117 2.6e-01 2.5e-03 1.1e-02 126 2.7e-01 2.8e-03 1.2e-02 2048 113 3.2e-01 2.9e-03 1.5e-02 114 3.3e-01 3.1e-03 1.3e-02 113 3.1e-01 3.1e-03 1.3e-02 4096 96 3.5e-01 3.5e-03 1.8e-02 91 3.6e-01 3.2e-03 2.0e-02 90 3.1e-01 3.3e-03 1.3e-02 10624 53 4.5e-01 2.9e-03 1.2e-01 55 3.4e-01 2.9e-03 1.5e-02 52 3.2e-01 2.9e-03 1.3e-02 27554 35 3.6e-01 2.9e-03 1.7e-02 36 3.7e-01 3.3e-03 1.6e-02 34 3.5e-01 3.0e-03 1.5e-02 71468 23 4.7e-01 4.1e-03 1.6e-02 21 4.1e-01 3.7e-03 1.6e-02 21 4.2e-01 3.6e-03 1.5e-02 185364 10 5.4e-01 3.8e-03 6.8e-02 10 4.6e-01 4.0e-03 1.5e-02 11 9.1e-01 4.2e-03 2.4e-01 480774 5 5.5e-01 5.0e-03 2.3e-02 4 4.5e-01 4.1e-03 1.5e-02 5 6.4e-01 5.1e-03 7.7e-02 1246974 1 2.7e-01 2.7e-03 9.2e-03 1 2.7e-01 2.8e-03 1.0e-02 1 3.0e-01 2.7e-03 9.6e-03 3234251 1 7.5e-01 6.6e-03 3.2e-02 1 7.4e-01 6.8e-03 2.5e-02 1 7.9e-01 6.8e-03 4.6e-02 8388608 1 1.8e+00 1.5e-02 5.6e-02 1 1.8e+00 1.7e-02 6.8e-02 1 1.8e+00 1.7e-02 5.6e-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 1.9e+00 3.7e-02 5.7e-02 30 2.0e-01 3.7e-03 1.2e-02 30 2.1e-01 3.7e-03 1.0e-02 2 150 9.2e-01 1.9e-02 2.2e-02 20 1.9e-01 2.5e-03 4.1e-02 20 1.3e-01 2.5e-03 7.7e-03 4 75 4.9e-01 9.4e-03 1.8e-02 20 2.1e-01 2.5e-03 7.5e-02 20 1.3e-01 2.5e-03 4.5e-03 8 37 2.3e-01 4.6e-03 6.9e-03 20 1.4e-01 2.5e-03 1.2e-02 20 1.4e-01 2.5e-03 6.5e-03 16 20 1.2e-01 2.5e-03 2.8e-03 20 1.3e-01 2.5e-03 7.2e-03 20 1.2e-01 2.5e-03 2.9e-03 32 20 1.5e-01 2.5e-03 1.6e-02 20 1.9e-01 2.5e-03 6.4e-02 20 1.4e-01 2.5e-03 1.7e-02 64 20 1.3e-01 2.5e-03 3.0e-03 19 1.2e-01 2.4e-03 2.7e-03 20 1.3e-01 2.5e-03 5.0e-03 128 19 1.2e-01 2.4e-03 2.8e-03 19 1.5e-01 2.4e-03 1.7e-02 19 1.3e-01 2.4e-03 7.0e-03 256 19 1.3e-01 2.4e-03 9.4e-03 19 1.3e-01 2.4e-03 6.7e-03 19 1.7e-01 2.4e-03 4.3e-02 512 19 1.2e-01 2.4e-03 3.0e-03 19 1.4e-01 2.4e-03 9.8e-03 19 1.3e-01 2.4e-03 5.7e-03 1024 19 1.4e-01 2.5e-03 1.2e-02 19 1.3e-01 2.4e-03 2.9e-03 19 1.3e-01 2.5e-03 3.0e-03 2048 19 1.5e-01 2.6e-03 3.6e-03 19 1.5e-01 2.6e-03 6.5e-03 19 1.5e-01 2.7e-03 3.5e-03 4096 18 1.7e-01 2.7e-03 1.2e-02 18 1.7e-01 2.7e-03 1.0e-02 17 1.6e-01 2.5e-03 7.6e-03 10624 12 1.7e-01 2.1e-03 8.5e-03 12 1.7e-01 2.2e-03 5.5e-03 13 1.8e-01 2.3e-03 4.7e-03 27554 11 2.3e-01 2.4e-03 7.5e-03 10 2.1e-01 2.1e-03 6.0e-03 10 2.1e-01 2.3e-03 6.0e-03 71468 8 2.9e-01 2.4e-03 9.4e-03 9 3.2e-01 3.0e-03 9.4e-03 8 2.9e-01 2.5e-03 9.3e-03 185364 6 5.0e-01 3.4e-03 1.9e-02 5 4.0e-01 2.9e-03 1.4e-02 6 5.3e-01 4.2e-03 5.1e-02 480774 3 7.0e-01 4.0e-03 1.1e-01 3 5.8e-01 3.8e-03 1.8e-02 2 4.1e-01 2.9e-03 1.5e-02 1246974 1 4.3e-01 2.5e-03 1.7e-02 1 4.2e-01 2.5e-03 1.5e-02 1 4.2e-01 2.5e-03 1.7e-02 3234251 1 1.2e+00 7.0e-03 4.9e-02 1 1.4e+00 6.6e-03 2.3e-01 1 1.3e+00 6.7e-03 1.9e-01 8388608 1 2.8e+00 1.7e-02 1.0e-01 1 2.8e+00 1.9e-02 1.0e-01 1 2.8e+00 2.0e-02 9.9e-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 1.0e+00 1.1e-02 3.3e-02 102 3.6e-01 3.8e-03 1.7e-02 102 4.1e-01 3.9e-03 2.1e-02 2 150 5.2e-01 5.5e-03 1.7e-02 66 2.3e-01 2.5e-03 7.4e-03 66 2.4e-01 2.4e-03 1.1e-02 4 75 2.7e-01 2.8e-03 1.1e-02 65 2.3e-01 2.5e-03 7.5e-03 67 2.5e-01 2.5e-03 1.1e-02 8 67 2.3e-01 2.5e-03 7.4e-03 65 2.4e-01 2.4e-03 1.3e-02 66 2.4e-01 2.5e-03 1.0e-02 16 68 2.4e-01 2.5e-03 7.6e-03 68 2.4e-01 2.6e-03 7.7e-03 66 4.1e-01 2.4e-03 1.9e-01 32 67 2.6e-01 2.6e-03 1.7e-02 64 2.3e-01 2.4e-03 7.6e-03 67 2.5e-01 2.5e-03 1.2e-02 64 64 2.4e-01 2.6e-03 1.1e-02 65 2.5e-01 2.6e-03 1.0e-02 65 2.4e-01 2.5e-03 7.5e-03 128 62 2.4e-01 2.5e-03 1.1e-02 63 2.5e-01 2.6e-03 1.1e-02 63 2.5e-01 2.5e-03 1.2e-02 256 61 2.8e-01 2.6e-03 1.4e-02 61 2.5e-01 2.6e-03 1.4e-02 62 2.3e-01 2.5e-03 7.9e-03 512 58 2.5e-01 2.5e-03 1.1e-02 59 2.5e-01 2.5e-03 7.7e-03 61 2.4e-01 2.5e-03 1.0e-02 1024 57 2.4e-01 2.5e-03 1.3e-02 59 2.4e-01 2.4e-03 7.5e-03 61 2.4e-01 2.6e-03 7.9e-03 2048 56 2.4e-01 2.6e-03 9.2e-03 61 2.7e-01 2.9e-03 1.4e-02 59 2.6e-01 2.8e-03 8.6e-03 4096 53 2.9e-01 2.9e-03 1.2e-02 51 2.6e-01 2.8e-03 8.5e-03 52 2.8e-01 2.9e-03 1.3e-02 10624 35 2.7e-01 2.8e-03 8.2e-03 34 2.5e-01 2.7e-03 9.0e-03 34 2.5e-01 2.7e-03 7.8e-03 27554 23 2.7e-01 2.7e-03 1.8e-02 24 2.7e-01 2.8e-03 1.1e-02 24 2.7e-01 2.6e-03 1.0e-02 71468 16 3.3e-01 3.2e-03 1.0e-02 16 3.2e-01 3.1e-03 9.9e-03 17 3.6e-01 3.7e-03 1.9e-02 185364 9 4.3e-01 3.7e-03 1.9e-02 10 4.7e-01 4.4e-03 1.5e-02 8 4.2e-01 3.3e-03 3.9e-02 480774 4 4.5e-01 3.9e-03 1.5e-02 4 4.5e-01 4.1e-03 1.7e-02 4 4.5e-01 3.7e-03 1.5e-02 1246974 1 2.6e-01 2.3e-03 1.1e-02 1 2.7e-01 2.4e-03 8.4e-03 2 5.4e-01 4.8e-03 1.8e-02 3234251 1 7.0e-01 6.4e-03 2.9e-02 1 7.0e-01 7.0e-03 2.6e-02 1 7.2e-01 6.7e-03 2.6e-02 8388608 1 1.7e+00 1.6e-02 5.5e-02 1 1.8e+00 1.8e-02 9.6e-02 1 1.7e+00 1.7e-02 5.7e-02 SECTION-LOOPLNGS-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 90.022 sec sum of max elapsed time per entries above = 89.646 sec difference to elapsed time = 0.376 sec = 0.4% sum based on fastest repetition = 74.548 sec difference to elapsed time = 15.474 sec = 17.2% 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-4*2fix 1 8 1.00 1.00 0 ( -1 -1 -1 ) p01 ring-2*4fix 2 16 2.00 1.00 0 ( -1 -1 -1 ) p02 ring-1*8fix 2 16 2.00 1.00 0 ( -1 -1 -1 ) p03 ring-1*8fix 2 16 2.00 1.00 0 ( -1 -1 -1 ) p04 ring-1*8fix 2 16 2.00 1.00 0 ( -1 -1 -1 ) p05 ring-1*8fix 2 16 2.00 1.00 0 ( -1 -1 -1 ) p06 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p07 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p08 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p09 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p10 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p11 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p12 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p13 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p14 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p15 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p16 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p17 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p18 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p19 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p20 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p21 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p22 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p23 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p24 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p25 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p26 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p27 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p28 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p29 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p30 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p31 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p32 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p33 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p34 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p35 random-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p36 worst-cyc-1dim 2 16 2.00 1.00 0 ( -1 -1 -1 ) p37 best bi-section 2 8 1.00 0.50 0 ( -1 -1 -1 ) p38 worst bi-section 2 8 1.00 0.50 0 ( -1 -1 -1 ) p39 one PingPong Pair 2 2 1.00 0.50 6 ( -1 -1 -1 ) p40 acyclic-2dim-all 4 20 2.50 0.63 0 ( -1 -1 -1 ) p41 acyclic-3dim-all 6 24 3.00 0.50 0 ( -1 -1 -1 ) p42 cyclic-2dim-x 2 16 2.00 1.00 0 ( -1 -1 -1 ) p43 cyclic-2dim-y 1 8 1.00 1.00 0 ( -1 -1 -1 ) p44 cyclic-2dim-all 3 24 3.00 1.00 0 ( -1 -1 -1 ) p45 cyclic-3dim-x 1 8 1.00 1.00 0 ( -1 -1 -1 ) p46 cyclic-3dim-y 1 8 1.00 1.00 0 ( -1 -1 -1 ) p47 cyclic-3dim-z 1 8 1.00 1.00 0 ( -1 -1 -1 ) p48 cyclic-3dim-all 3 24 3.00 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-4*2fix : 149.633 77.662 125.752 -> 149.633 -> 1197.066 MByte/s p01 ring-2*4fix : 153.423 102.830 139.381 -> 153.423 -> 1227.385 MByte/s p02 ring-1*8fix : 150.774 79.151 138.505 -> 150.774 -> 1206.192 MByte/s p03 ring-1*8fix : 149.468 79.850 141.281 -> 149.468 -> 1195.745 MByte/s p04 ring-1*8fix : 145.165 79.474 138.848 -> 145.165 -> 1161.322 MByte/s p05 ring-1*8fix : 150.979 80.797 138.868 -> 150.979 -> 1207.831 MByte/s p06 random-cyc-1dim : 153.044 80.839 139.476 -> 153.044 -> 1224.353 MByte/s p07 random-cyc-1dim : 148.469 79.534 142.854 -> 148.469 -> 1187.748 MByte/s p08 random-cyc-1dim : 147.366 76.909 143.424 -> 147.366 -> 1178.926 MByte/s p09 random-cyc-1dim : 153.886 78.649 143.173 -> 153.886 -> 1231.089 MByte/s p10 random-cyc-1dim : 149.937 71.549 139.804 -> 149.937 -> 1199.493 MByte/s p11 random-cyc-1dim : 148.061 74.307 139.060 -> 148.061 -> 1184.485 MByte/s p12 random-cyc-1dim : 148.609 76.309 139.578 -> 148.609 -> 1188.875 MByte/s p13 random-cyc-1dim : 150.356 80.711 141.822 -> 150.356 -> 1202.845 MByte/s p14 random-cyc-1dim : 148.817 81.375 140.139 -> 148.817 -> 1190.540 MByte/s p15 random-cyc-1dim : 144.427 79.534 141.909 -> 144.427 -> 1155.419 MByte/s p16 random-cyc-1dim : 148.288 81.095 140.875 -> 148.288 -> 1186.303 MByte/s p17 random-cyc-1dim : 151.734 73.568 142.554 -> 151.734 -> 1213.873 MByte/s p18 random-cyc-1dim : 150.772 73.692 138.681 -> 150.772 -> 1206.172 MByte/s p19 random-cyc-1dim : 147.998 79.761 134.669 -> 147.998 -> 1183.981 MByte/s p20 random-cyc-1dim : 149.678 80.524 135.436 -> 149.678 -> 1197.423 MByte/s p21 random-cyc-1dim : 153.643 81.109 141.984 -> 153.643 -> 1229.144 MByte/s p22 random-cyc-1dim : 151.209 81.681 140.615 -> 151.209 -> 1209.674 MByte/s p23 random-cyc-1dim : 149.672 79.294 139.272 -> 149.672 -> 1197.380 MByte/s p24 random-cyc-1dim : 148.127 79.938 142.580 -> 148.127 -> 1185.013 MByte/s p25 random-cyc-1dim : 152.300 79.186 139.477 -> 152.300 -> 1218.398 MByte/s p26 random-cyc-1dim : 152.947 78.980 140.667 -> 152.947 -> 1223.576 MByte/s p27 random-cyc-1dim : 149.865 81.802 141.075 -> 149.865 -> 1198.916 MByte/s p28 random-cyc-1dim : 151.289 80.163 143.430 -> 151.289 -> 1210.311 MByte/s p29 random-cyc-1dim : 150.372 80.776 141.408 -> 150.372 -> 1202.972 MByte/s p30 random-cyc-1dim : 150.160 78.936 139.770 -> 150.160 -> 1201.284 MByte/s p31 random-cyc-1dim : 146.186 77.565 141.714 -> 146.186 -> 1169.490 MByte/s p32 random-cyc-1dim : 151.713 79.938 140.697 -> 151.713 -> 1213.701 MByte/s p33 random-cyc-1dim : 153.273 79.152 140.589 -> 153.273 -> 1226.182 MByte/s p34 random-cyc-1dim : 151.390 72.945 138.721 -> 151.390 -> 1211.118 MByte/s p35 random-cyc-1dim : 148.977 81.594 143.262 -> 148.977 -> 1191.818 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 152.983 80.084 141.655 -> 152.983 -> 1223.862 MByte/s p37 best bi-section : 133.110 77.267 135.129 -> 135.129 -> 1081.031 MByte/s p38 worst bi-section : 141.197 123.622 149.904 -> 149.904 -> 1199.229 MByte/s p39 one PingPong Pair : 35.902 0.000 0.000 -> 35.902 -> 287.216 MByte/s p40 acyclic-2dim-all : 127.345 82.529 124.678 -> 127.345 -> 1018.759 MByte/s p41 acyclic-3dim-all : 142.196 110.843 138.773 -> 142.196 -> 1137.570 MByte/s p42 cyclic-2dim-x : 151.275 80.373 144.499 -> 151.275 -> 1210.197 MByte/s p43 cyclic-2dim-y : 150.453 77.895 135.411 -> 150.453 -> 1203.627 MByte/s p44 cyclic-2dim-all : 150.970 83.235 137.164 -> 150.970 -> 1207.762 MByte/s p45 cyclic-3dim-x : 151.663 37.346 132.216 -> 151.663 -> 1213.307 MByte/s p46 cyclic-3dim-y : 152.778 75.634 132.638 -> 152.778 -> 1222.224 MByte/s p47 cyclic-3dim-z : 148.989 78.393 141.004 -> 148.989 -> 1191.909 MByte/s p48 cyclic-3dim-all : 150.365 111.344 143.878 -> 150.365 -> 1202.921 MByte/s log_avg of all rings : 149.886 82.879 137.005 || 149.886 -> 1199.091 MByte/s log_avg of all random : 150.069 78.662 140.609 || 150.069 -> 1200.552 MByte/s log_avg(ring,random) : 149.978 80.743 138.795 ||(149.978 -> 1199.821)MByte/s * size -> accumulated on all pr.: 1199.821 645.947 1110.359 ||(1199.821)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-4*2fix : 148.199 142.322 148.292 -> 148.292 -> 1186.334 MByte/s p01 ring-2*4fix : 145.403 145.917 146.857 -> 146.857 -> 1174.855 MByte/s p02 ring-1*8fix : 145.682 146.885 144.717 -> 146.885 -> 1175.081 MByte/s p03 ring-1*8fix : 146.540 147.843 143.143 -> 147.843 -> 1182.744 MByte/s p04 ring-1*8fix : 140.158 143.373 144.859 -> 144.859 -> 1158.872 MByte/s p05 ring-1*8fix : 149.610 145.326 146.647 -> 149.610 -> 1196.882 MByte/s p06 random-cyc-1dim : 146.109 139.651 150.289 -> 150.289 -> 1202.311 MByte/s p07 random-cyc-1dim : 141.627 146.507 138.914 -> 146.507 -> 1172.060 MByte/s p08 random-cyc-1dim : 143.690 146.473 144.671 -> 146.473 -> 1171.783 MByte/s p09 random-cyc-1dim : 147.508 150.332 150.079 -> 150.332 -> 1202.655 MByte/s p10 random-cyc-1dim : 144.956 147.762 147.238 -> 147.762 -> 1182.095 MByte/s p11 random-cyc-1dim : 148.830 142.101 142.587 -> 148.830 -> 1190.641 MByte/s p12 random-cyc-1dim : 150.687 144.969 142.779 -> 150.687 -> 1205.498 MByte/s p13 random-cyc-1dim : 146.362 149.051 149.243 -> 149.243 -> 1193.943 MByte/s p14 random-cyc-1dim : 144.245 148.972 145.981 -> 148.972 -> 1191.776 MByte/s p15 random-cyc-1dim : 145.585 147.228 143.521 -> 147.228 -> 1177.827 MByte/s p16 random-cyc-1dim : 145.182 139.187 144.816 -> 145.182 -> 1161.455 MByte/s p17 random-cyc-1dim : 145.872 149.642 138.494 -> 149.642 -> 1197.134 MByte/s p18 random-cyc-1dim : 143.655 147.805 148.561 -> 148.561 -> 1188.489 MByte/s p19 random-cyc-1dim : 136.567 141.451 142.649 -> 142.649 -> 1141.195 MByte/s p20 random-cyc-1dim : 138.043 145.062 144.187 -> 145.062 -> 1160.494 MByte/s p21 random-cyc-1dim : 149.236 142.427 148.457 -> 149.236 -> 1193.887 MByte/s p22 random-cyc-1dim : 149.833 148.658 140.318 -> 149.833 -> 1198.667 MByte/s p23 random-cyc-1dim : 143.780 144.954 145.436 -> 145.436 -> 1163.489 MByte/s p24 random-cyc-1dim : 146.401 147.015 144.164 -> 147.015 -> 1176.118 MByte/s p25 random-cyc-1dim : 150.436 147.138 145.684 -> 150.436 -> 1203.490 MByte/s p26 random-cyc-1dim : 149.755 140.956 151.019 -> 151.019 -> 1208.153 MByte/s p27 random-cyc-1dim : 144.120 144.193 144.335 -> 144.335 -> 1154.680 MByte/s p28 random-cyc-1dim : 149.839 144.341 152.919 -> 152.919 -> 1223.350 MByte/s p29 random-cyc-1dim : 140.572 143.186 148.246 -> 148.246 -> 1185.965 MByte/s p30 random-cyc-1dim : 140.070 150.383 146.881 -> 150.383 -> 1203.066 MByte/s p31 random-cyc-1dim : 141.272 143.361 143.168 -> 143.361 -> 1146.885 MByte/s p32 random-cyc-1dim : 148.519 148.373 138.534 -> 148.519 -> 1188.154 MByte/s p33 random-cyc-1dim : 148.308 143.098 148.467 -> 148.467 -> 1187.738 MByte/s p34 random-cyc-1dim : 148.052 145.349 141.454 -> 148.052 -> 1184.419 MByte/s p35 random-cyc-1dim : 151.643 139.915 145.838 -> 151.643 -> 1213.141 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 146.631 135.249 145.469 -> 146.631 -> 1173.052 MByte/s p37 best bi-section : 142.206 136.950 130.052 -> 142.206 -> 1137.646 MByte/s p38 worst bi-section : 139.529 147.090 149.367 -> 149.367 -> 1194.938 MByte/s p39 one PingPong Pair : 33.330 31.428 33.593 -> 33.593 -> 268.744 MByte/s p40 acyclic-2dim-all : 122.526 129.758 121.036 -> 129.758 -> 1038.064 MByte/s p41 acyclic-3dim-all : 139.986 136.716 139.131 -> 139.986 -> 1119.887 MByte/s p42 cyclic-2dim-x : 148.363 144.184 148.546 -> 148.546 -> 1188.372 MByte/s p43 cyclic-2dim-y : 151.227 143.193 143.296 -> 151.227 -> 1209.819 MByte/s p44 cyclic-2dim-all : 147.174 145.443 146.572 -> 147.174 -> 1177.389 MByte/s p45 cyclic-3dim-x : 147.718 150.398 144.986 -> 150.398 -> 1203.184 MByte/s p46 cyclic-3dim-y : 154.194 139.385 140.795 -> 154.194 -> 1233.549 MByte/s p47 cyclic-3dim-z : 149.382 148.529 154.351 -> 154.351 -> 1234.804 MByte/s p48 cyclic-3dim-all : 149.466 145.360 150.429 -> 150.429 -> 1203.434 MByte/s log_avg of all rings : 145.902 145.265 145.743 || 147.384 -> 1179.070 MByte/s log_avg of all random : 145.642 145.282 145.251 || 148.190 -> 1185.523 MByte/s log_avg(ring,random) : 145.772 145.274 145.497 ||(147.786 -> 1182.292)MByte/s * size -> accumulated on all pr.: 1166.173 1162.190 1163.972 ||(1182.292)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-4*2fix p00 method 0 =Sndrcv :( 16.443) 0.061 0.959 12.579 112.371 208.060 471.138 -> 149.633 -> 1197.066 MByte/s p00 method 1 =Alltoal :(124.200) 0.008 0.128 2.009 27.247 226.328 253.318 -> 77.662 -> 621.295 MByte/s p00 method 2 =non-blk :( 39.713) 0.025 0.411 5.976 71.104 156.983 459.776 -> 125.752 -> 1006.018 MByte/s p01 ring-2*4fix p01 method 0 =Sndrcv :( 16.385) 0.061 0.944 13.046 112.728 353.413 454.730 -> 153.423 -> 1227.385 MByte/s p01 method 1 =Alltoal :( 63.183) 0.016 0.253 3.876 47.814 289.705 327.290 -> 102.830 -> 822.638 MByte/s p01 method 2 =non-blk :( 37.502) 0.027 0.428 6.287 76.117 369.863 387.383 -> 139.381 -> 1115.047 MByte/s p02 ring-1*8fix p02 method 0 =Sndrcv :( 16.642) 0.060 0.937 12.481 113.380 379.276 452.083 -> 150.774 -> 1206.192 MByte/s p02 method 1 =Alltoal :( 63.167) 0.016 0.251 3.806 44.308 206.860 253.958 -> 79.151 -> 633.206 MByte/s p02 method 2 =non-blk :( 36.848) 0.027 0.433 6.427 75.907 371.389 439.713 -> 138.505 -> 1108.043 MByte/s p03 ring-1*8fix p03 method 0 =Sndrcv :( 16.615) 0.060 0.954 12.971 115.506 337.423 453.255 -> 149.468 -> 1195.745 MByte/s p03 method 1 =Alltoal :( 63.066) 0.016 0.251 3.916 43.394 218.719 253.658 -> 79.850 -> 638.802 MByte/s p03 method 2 =non-blk :( 37.029) 0.027 0.431 6.530 77.084 354.610 446.239 -> 141.281 -> 1130.247 MByte/s p04 ring-1*8fix p04 method 0 =Sndrcv :( 16.719) 0.060 0.933 12.537 113.794 340.057 384.367 -> 145.165 -> 1161.322 MByte/s p04 method 1 =Alltoal :( 63.550) 0.016 0.250 3.874 44.440 202.916 251.370 -> 79.474 -> 635.794 MByte/s p04 method 2 =non-blk :( 36.975) 0.027 0.432 6.431 76.011 354.493 449.249 -> 138.848 -> 1110.783 MByte/s p05 ring-1*8fix p05 method 0 =Sndrcv :( 16.649) 0.060 0.948 12.790 113.638 363.916 453.328 -> 150.979 -> 1207.831 MByte/s p05 method 1 =Alltoal :( 63.099) 0.016 0.254 3.901 44.029 216.483 243.011 -> 80.797 -> 646.378 MByte/s p05 method 2 =non-blk :( 36.755) 0.027 0.433 6.387 77.296 358.957 382.447 -> 138.868 -> 1110.944 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 16.390) 0.061 0.956 12.713 113.518 383.163 452.681 -> 153.044 -> 1224.353 MByte/s p06 method 1 =Alltoal :( 62.766) 0.016 0.253 3.885 43.678 227.052 246.858 -> 80.839 -> 646.711 MByte/s p06 method 2 =non-blk :( 36.496) 0.027 0.433 6.342 77.426 342.386 431.847 -> 139.476 -> 1115.805 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 16.745) 0.060 0.953 12.224 113.959 367.057 432.157 -> 148.469 -> 1187.748 MByte/s p07 method 1 =Alltoal :( 63.201) 0.016 0.253 3.891 44.308 212.127 247.909 -> 79.534 -> 636.271 MByte/s p07 method 2 =non-blk :( 36.422) 0.027 0.429 6.166 76.373 361.826 442.448 -> 142.854 -> 1142.834 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 16.842) 0.059 0.944 12.027 115.990 332.342 444.135 -> 147.366 -> 1178.926 MByte/s p08 method 1 =Alltoal :( 63.000) 0.016 0.252 3.884 43.834 222.995 249.888 -> 76.909 -> 615.274 MByte/s p08 method 2 =non-blk :( 36.534) 0.027 0.433 6.334 77.153 364.573 448.913 -> 143.424 -> 1147.393 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 16.831) 0.059 0.940 12.217 113.596 393.473 451.510 -> 153.886 -> 1231.089 MByte/s p09 method 1 =Alltoal :( 63.266) 0.016 0.253 3.845 44.029 182.761 252.745 -> 78.649 -> 629.194 MByte/s p09 method 2 =non-blk :( 36.514) 0.027 0.428 6.248 75.919 361.815 450.807 -> 143.173 -> 1145.388 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 16.983) 0.059 0.940 12.465 113.636 365.905 453.658 -> 149.937 -> 1199.493 MByte/s p10 method 1 =Alltoal :( 63.767) 0.016 0.252 3.896 44.016 206.244 225.425 -> 71.549 -> 572.389 MByte/s p10 method 2 =non-blk :( 36.569) 0.027 0.431 6.327 74.656 338.875 400.095 -> 139.804 -> 1118.436 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 16.737) 0.060 0.953 12.469 115.061 309.809 451.218 -> 148.061 -> 1184.485 MByte/s p11 method 1 =Alltoal :( 63.793) 0.016 0.249 3.853 43.601 199.192 211.695 -> 74.307 -> 594.456 MByte/s p11 method 2 =non-blk :( 36.706) 0.027 0.432 5.889 77.240 371.357 423.870 -> 139.060 -> 1112.476 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 15.956) 0.063 0.961 12.775 113.531 395.812 423.026 -> 148.609 -> 1188.875 MByte/s p12 method 1 =Alltoal :( 63.510) 0.016 0.251 3.893 43.547 214.890 222.224 -> 76.309 -> 610.474 MByte/s p12 method 2 =non-blk :( 36.553) 0.027 0.428 6.400 76.804 375.466 413.496 -> 139.578 -> 1116.623 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 16.572) 0.060 0.958 12.677 113.934 364.139 427.902 -> 150.356 -> 1202.845 MByte/s p13 method 1 =Alltoal :( 63.217) 0.016 0.251 3.888 44.467 203.786 253.248 -> 80.711 -> 645.688 MByte/s p13 method 2 =non-blk :( 36.681) 0.027 0.430 6.484 75.422 369.247 456.250 -> 141.822 -> 1134.574 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 16.596) 0.060 0.955 12.462 112.624 308.145 453.108 -> 148.817 -> 1190.540 MByte/s p14 method 1 =Alltoal :( 63.384) 0.016 0.250 3.873 44.096 226.031 254.204 -> 81.375 -> 650.998 MByte/s p14 method 2 =non-blk :( 36.486) 0.027 0.436 6.354 75.866 364.139 432.928 -> 140.139 -> 1121.115 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 16.076) 0.062 0.962 12.820 115.346 336.887 437.693 -> 144.427 -> 1155.419 MByte/s p15 method 1 =Alltoal :( 63.235) 0.016 0.251 3.896 42.877 226.000 240.820 -> 79.534 -> 636.271 MByte/s p15 method 2 =non-blk :( 36.780) 0.027 0.419 6.494 76.729 381.114 441.657 -> 141.909 -> 1135.271 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 15.901) 0.063 0.977 12.805 111.505 345.893 427.881 -> 148.288 -> 1186.303 MByte/s p16 method 1 =Alltoal :( 63.334) 0.016 0.251 3.867 44.161 222.928 252.627 -> 81.095 -> 648.758 MByte/s p16 method 2 =non-blk :( 36.780) 0.027 0.426 6.526 75.537 369.214 428.143 -> 140.875 -> 1126.999 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 16.487) 0.061 0.942 12.248 112.746 360.421 449.201 -> 151.734 -> 1213.873 MByte/s p17 method 1 =Alltoal :( 63.467) 0.016 0.250 3.879 43.873 219.951 214.564 -> 73.568 -> 588.541 MByte/s p17 method 2 =non-blk :( 37.187) 0.027 0.425 6.543 75.563 376.332 438.299 -> 142.554 -> 1140.430 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 16.708) 0.060 0.947 12.267 115.936 370.827 429.074 -> 150.772 -> 1206.172 MByte/s p18 method 1 =Alltoal :( 63.183) 0.016 0.250 3.734 43.078 205.808 223.678 -> 73.692 -> 589.538 MByte/s p18 method 2 =non-blk :( 36.649) 0.027 0.429 6.538 77.013 378.586 405.933 -> 138.681 -> 1109.450 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 16.478) 0.061 0.970 12.891 114.715 377.561 430.605 -> 147.998 -> 1183.981 MByte/s p19 method 1 =Alltoal :( 63.258) 0.016 0.252 3.905 44.254 226.553 252.452 -> 79.761 -> 638.088 MByte/s p19 method 2 =non-blk :( 36.737) 0.027 0.428 6.430 75.971 356.302 441.936 -> 134.669 -> 1077.351 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 16.756) 0.060 0.944 12.874 112.854 373.153 445.079 -> 149.678 -> 1197.423 MByte/s p20 method 1 =Alltoal :( 63.550) 0.016 0.252 3.880 44.267 230.124 245.439 -> 80.524 -> 644.189 MByte/s p20 method 2 =non-blk :( 37.147) 0.027 0.434 6.422 76.378 367.309 411.782 -> 135.436 -> 1083.491 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 16.518) 0.061 0.964 12.638 114.954 380.732 452.179 -> 153.643 -> 1229.144 MByte/s p21 method 1 =Alltoal :( 63.350) 0.016 0.247 3.902 44.507 220.758 250.167 -> 81.109 -> 648.872 MByte/s p21 method 2 =non-blk :( 36.932) 0.027 0.427 6.449 76.743 382.838 424.427 -> 141.984 -> 1135.869 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 16.138) 0.062 0.951 12.908 113.140 368.444 447.416 -> 151.209 -> 1209.674 MByte/s p22 method 1 =Alltoal :( 64.166) 0.016 0.248 3.924 44.002 218.588 254.593 -> 81.681 -> 653.444 MByte/s p22 method 2 =non-blk :( 36.887) 0.027 0.426 6.435 75.734 382.238 422.270 -> 140.615 -> 1124.923 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 16.557) 0.060 0.960 12.336 114.338 367.782 443.291 -> 149.672 -> 1197.380 MByte/s p23 method 1 =Alltoal :( 64.417) 0.016 0.248 3.916 43.963 203.674 248.331 -> 79.294 -> 634.353 MByte/s p23 method 2 =non-blk :( 36.968) 0.027 0.433 6.172 75.591 376.140 434.170 -> 139.272 -> 1114.179 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 16.487) 0.061 0.947 12.588 112.605 356.811 440.856 -> 148.127 -> 1185.013 MByte/s p24 method 1 =Alltoal :( 64.983) 0.015 0.251 3.886 44.099 220.644 253.119 -> 79.938 -> 639.506 MByte/s p24 method 2 =non-blk :( 36.691) 0.027 0.428 6.367 77.240 376.136 452.631 -> 142.580 -> 1140.638 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 16.736) 0.060 0.950 12.329 113.322 358.018 445.456 -> 152.300 -> 1218.398 MByte/s p25 method 1 =Alltoal :( 63.820) 0.016 0.252 3.910 44.307 201.081 242.379 -> 79.186 -> 633.487 MByte/s p25 method 2 =non-blk :( 36.588) 0.027 0.425 6.434 75.234 349.815 431.192 -> 139.477 -> 1115.814 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 16.615) 0.060 0.967 12.729 113.259 362.534 449.081 -> 152.947 -> 1223.576 MByte/s p26 method 1 =Alltoal :( 64.143) 0.016 0.249 3.923 44.096 222.555 251.081 -> 78.980 -> 631.837 MByte/s p26 method 2 =non-blk :( 36.804) 0.027 0.427 6.372 75.342 368.801 453.843 -> 140.667 -> 1125.336 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 18.331) 0.055 0.855 11.260 114.108 376.062 433.196 -> 149.865 -> 1198.916 MByte/s p27 method 1 =Alltoal :( 64.362) 0.016 0.249 3.857 43.669 219.263 252.005 -> 81.802 -> 654.415 MByte/s p27 method 2 =non-blk :( 36.784) 0.027 0.425 6.448 75.430 370.357 446.308 -> 141.075 -> 1128.599 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 16.540) 0.060 0.945 12.462 117.119 369.578 449.058 -> 151.289 -> 1210.311 MByte/s p28 method 1 =Alltoal :( 63.316) 0.016 0.252 3.885 43.241 229.011 254.008 -> 80.163 -> 641.303 MByte/s p28 method 2 =non-blk :( 36.922) 0.027 0.424 6.171 76.518 358.990 458.682 -> 143.430 -> 1147.443 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 16.560) 0.060 0.960 12.539 113.656 356.541 456.572 -> 150.372 -> 1202.972 MByte/s p29 method 1 =Alltoal :( 63.235) 0.016 0.249 3.877 44.227 226.952 242.916 -> 80.776 -> 646.206 MByte/s p29 method 2 =non-blk :( 36.490) 0.027 0.431 6.453 76.602 359.539 450.359 -> 141.408 -> 1131.265 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 16.063) 0.062 0.973 12.888 115.023 351.400 450.576 -> 150.160 -> 1201.284 MByte/s p30 method 1 =Alltoal :( 63.000) 0.016 0.252 3.929 43.678 219.315 250.029 -> 78.936 -> 631.485 MByte/s p30 method 2 =non-blk :( 36.773) 0.027 0.432 6.427 77.254 333.254 440.636 -> 139.770 -> 1118.161 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 16.707) 0.060 0.951 12.710 113.604 388.970 447.523 -> 146.186 -> 1169.490 MByte/s p31 method 1 =Alltoal :( 63.084) 0.016 0.251 3.893 43.951 222.954 253.253 -> 77.565 -> 620.518 MByte/s p31 method 2 =non-blk :( 36.809) 0.027 0.426 6.258 75.812 371.957 453.230 -> 141.714 -> 1133.711 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 16.438) 0.061 0.948 12.839 113.416 362.462 455.964 -> 151.713 -> 1213.701 MByte/s p32 method 1 =Alltoal :( 63.467) 0.016 0.253 3.872 43.821 216.210 253.122 -> 79.938 -> 639.501 MByte/s p32 method 2 =non-blk :( 36.640) 0.027 0.428 6.371 76.132 354.828 446.488 -> 140.697 -> 1125.574 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 15.955) 0.063 0.986 12.589 115.112 382.394 453.219 -> 153.273 -> 1226.182 MByte/s p33 method 1 =Alltoal :( 63.183) 0.016 0.248 3.863 43.664 194.233 253.012 -> 79.152 -> 633.213 MByte/s p33 method 2 =non-blk :( 36.793) 0.027 0.432 6.334 74.939 367.964 460.735 -> 140.589 -> 1124.712 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 16.010) 0.062 0.963 13.247 117.174 355.380 453.427 -> 151.390 -> 1211.118 MByte/s p34 method 1 =Alltoal :( 64.617) 0.015 0.251 3.897 43.873 225.938 208.773 -> 72.945 -> 583.561 MByte/s p34 method 2 =non-blk :( 36.490) 0.027 0.431 6.238 77.040 354.309 431.181 -> 138.721 -> 1109.766 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 16.545) 0.060 0.945 12.667 112.682 375.990 448.889 -> 148.977 -> 1191.818 MByte/s p35 method 1 =Alltoal :( 64.649) 0.015 0.246 3.819 43.484 231.923 250.657 -> 81.594 -> 652.751 MByte/s p35 method 2 =non-blk :( 36.475) 0.027 0.426 6.320 77.198 363.976 462.628 -> 143.262 -> 1146.098 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 16.240) 0.062 0.978 13.006 112.592 395.194 446.976 -> 152.983 -> 1223.862 MByte/s p36 method 1 =Alltoal :( 63.200) 0.016 0.251 3.806 44.136 219.235 250.881 -> 80.084 -> 640.670 MByte/s p36 method 2 =non-blk :( 36.708) 0.027 0.432 6.345 74.847 372.119 445.775 -> 141.655 -> 1133.242 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 12.277) 0.041 0.611 8.441 84.648 179.650 514.290 -> 133.110 -> 1064.877 MByte/s p37 method 1 =Alltoal :( 63.185) 0.008 0.127 1.983 26.741 220.367 252.350 -> 77.267 -> 618.139 MByte/s p37 method 2 =non-blk :( 18.517) 0.027 0.426 6.015 72.486 195.884 452.238 -> 135.129 -> 1081.031 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 12.366) 0.040 0.610 8.523 86.661 322.883 498.609 -> 141.197 -> 1129.572 MByte/s p38 method 1 =Alltoal :( 63.350) 0.008 0.126 1.972 27.763 322.469 446.179 -> 123.622 -> 988.977 MByte/s p38 method 2 =non-blk :( 18.613) 0.027 0.425 6.181 72.911 398.845 457.371 -> 149.904 -> 1199.229 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 11.570) 0.011 0.163 2.231 24.724 91.010 114.605 -> 35.902 -> 287.216 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 :( 13.901) 0.045 0.696 10.065 88.744 315.933 415.467 -> 127.345 -> 1018.759 MByte/s p40 method 1 =Alltoal :( 33.124) 0.019 0.299 4.549 50.903 224.176 247.937 -> 82.529 -> 660.229 MByte/s p40 method 2 =non-blk :( 25.201) 0.025 0.394 5.908 65.950 339.099 394.127 -> 124.678 -> 997.424 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 12.337) 0.041 0.628 8.732 88.550 362.250 503.145 -> 142.196 -> 1137.570 MByte/s p41 method 1 =Alltoal :( 23.117) 0.022 0.341 5.152 59.616 292.834 359.604 -> 110.843 -> 886.742 MByte/s p41 method 2 =non-blk :( 17.542) 0.029 0.454 6.533 74.873 365.804 445.311 -> 138.773 -> 1110.182 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 16.156) 0.062 0.955 12.637 113.795 360.948 458.306 -> 151.275 -> 1210.197 MByte/s p42 method 1 =Alltoal :( 63.167) 0.016 0.250 3.845 44.693 216.874 246.901 -> 80.373 -> 642.987 MByte/s p42 method 2 =non-blk :( 37.343) 0.027 0.417 6.386 75.743 380.668 459.223 -> 144.499 -> 1155.993 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 16.113) 0.062 0.961 12.926 116.443 207.437 458.596 -> 150.453 -> 1203.627 MByte/s p43 method 1 =Alltoal :(124.602) 0.008 0.129 1.993 26.977 220.409 251.736 -> 77.895 -> 623.157 MByte/s p43 method 2 =non-blk :( 38.402) 0.026 0.408 6.107 70.429 227.691 459.548 -> 135.411 -> 1083.289 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 16.541) 0.060 0.940 12.244 113.057 362.935 445.879 -> 150.970 -> 1207.762 MByte/s p44 method 1 =Alltoal :( 43.203) 0.023 0.367 5.550 59.633 222.544 247.383 -> 83.235 -> 665.880 MByte/s p44 method 2 =non-blk :( 36.391) 0.027 0.433 6.384 75.332 367.860 455.070 -> 137.164 -> 1097.313 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 16.518) 0.061 0.958 13.377 112.187 245.369 463.510 -> 151.663 -> 1213.307 MByte/s p45 method 1 =Alltoal :(125.627) 0.008 0.128 2.014 23.638 67.229 118.923 -> 37.346 -> 298.765 MByte/s p45 method 2 =non-blk :( 38.695) 0.026 0.410 5.761 72.170 191.953 447.061 -> 132.216 -> 1057.730 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 15.957) 0.063 0.972 12.790 111.876 273.397 455.632 -> 152.778 -> 1222.224 MByte/s p46 method 1 =Alltoal :(124.534) 0.008 0.128 2.006 26.426 194.097 253.004 -> 75.634 -> 605.071 MByte/s p46 method 2 =non-blk :( 38.402) 0.026 0.411 6.140 71.789 268.757 450.879 -> 132.638 -> 1061.105 MByte/s p47 cyclic-3dim-z p47 method 0 =Sndrcv :( 16.255) 0.062 0.958 12.287 111.997 233.779 456.895 -> 148.989 -> 1191.909 MByte/s p47 method 1 =Alltoal :(124.133) 0.008 0.129 2.023 26.802 225.721 251.088 -> 78.393 -> 627.145 MByte/s p47 method 2 =non-blk :( 38.977) 0.026 0.410 6.135 72.076 381.898 460.254 -> 141.004 -> 1128.030 MByte/s p48 cyclic-3dim-all p48 method 0 =Sndrcv :( 16.574) 0.060 0.944 12.444 111.953 378.292 451.226 -> 150.365 -> 1202.921 MByte/s p48 method 1 =Alltoal :( 43.256) 0.023 0.366 5.619 62.728 301.948 359.892 -> 111.344 -> 890.755 MByte/s p48 method 2 =non-blk :( 36.759) 0.027 0.426 6.005 73.859 393.346 446.162 -> 143.878 -> 1151.023 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.060 0.946 12.732 113.565 324.359 443.885 || 149.886 -> 1199.091 MByte/s - ring, method 1 = Alltoal: 0.014 0.225 3.473 41.215 225.164 262.376 || 82.879 -> 663.035 MByte/s - ring, method 2 = non-blk: 0.027 0.428 6.337 75.557 314.790 426.331 || 137.005 -> 1096.037 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.060 0.952 12.550 114.075 362.649 444.417 || 150.069 -> 1200.552 MByte/s - random, method 1 = Alltoal: 0.016 0.251 3.881 43.887 216.319 243.297 || 78.662 -> 629.299 MByte/s - random, method 2 = non-blk: 0.027 0.429 6.357 76.225 364.778 437.602 || 140.609 -> 1124.868 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.060 0.949 12.641 113.820 342.970 444.151 || 149.978 -> 1199.821 MByte/s - average, method 1 = Alltoal: 0.015 0.237 3.671 42.530 220.697 252.657 || 80.743 -> 645.947 MByte/s - average, method 2 = non-blk: 0.027 0.428 6.347 75.890 338.863 431.930 || 138.795 -> 1110.359 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.483 7.591 101.127 910.556 2743.758 3553.207 || 1199.821 MByte/s - accumulated, mthd 1 = Alltoal: 0.119 1.899 29.368 340.240 1765.580 2021.253 || 645.947 MByte/s - accumulated, mthd 2 = non-blk: 0.216 3.426 50.776 607.122 2710.907 3455.439 || 1110.359 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 0.483 0.060 0.060 0.060 0.060 0.015 0.027 2 0.963 0.120 0.120 0.121 0.120 0.030 0.054 4 1.904 0.238 0.237 0.239 0.238 0.059 0.106 8 3.872 0.484 0.486 0.482 0.484 0.119 0.216 16 7.591 0.949 0.946 0.952 0.949 0.237 0.428 32 14.923 1.865 1.868 1.863 1.865 0.472 0.843 64 28.970 3.621 3.621 3.622 3.621 0.935 1.658 128 54.078 6.760 6.815 6.705 6.760 1.829 3.197 256 101.127 12.641 12.732 12.550 12.641 3.671 6.347 512 198.682 24.835 24.836 24.834 24.835 7.212 12.098 1024 372.456 46.557 46.296 46.819 46.557 14.215 23.838 2048 605.399 75.675 77.067 74.308 75.675 24.857 44.464 4096 910.556 113.820 113.565 114.075 113.820 42.530 75.890 10624 1373.124 171.640 173.255 170.041 171.640 73.026 134.214 27554 2160.212 270.026 274.767 265.367 270.026 125.960 231.180 71468 2774.663 346.833 346.593 347.073 346.421 188.032 329.603 185364 2834.618 354.327 336.524 373.073 342.970 220.697 338.863 480774 3238.510 404.814 408.983 400.687 397.384 235.247 380.231 1246974 3602.991 450.374 451.705 449.047 436.411 252.024 440.995 3234251 3659.681 457.460 459.076 455.850 446.774 248.753 447.945 8388608 3616.603 452.075 455.575 448.602 444.151 252.657 431.930 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-4*2fix :( 16.443) 0.061 0.959 12.579 112.371 226.328 471.138 -> 154.259 -> 1234.072 MByte/s p01 ring-2*4fix :( 16.385) 0.061 0.944 13.046 112.728 369.863 454.730 -> 154.450 -> 1235.603 MByte/s p02 ring-1*8fix :( 16.642) 0.060 0.937 12.481 113.380 379.276 452.083 -> 151.081 -> 1208.645 MByte/s p03 ring-1*8fix :( 16.615) 0.060 0.954 12.971 115.506 354.610 453.255 -> 151.008 -> 1208.067 MByte/s p04 ring-1*8fix :( 16.719) 0.060 0.933 12.537 113.794 354.493 449.249 -> 149.756 -> 1198.049 MByte/s p05 ring-1*8fix :( 16.649) 0.060 0.948 12.790 113.638 363.916 453.328 -> 154.490 -> 1235.924 MByte/s p06 random-cyc-1dim :( 16.390) 0.061 0.956 12.713 113.518 383.163 452.681 -> 153.318 -> 1226.546 MByte/s p07 random-cyc-1dim :( 16.745) 0.060 0.953 12.224 113.959 367.057 442.448 -> 152.412 -> 1219.298 MByte/s p08 random-cyc-1dim :( 16.842) 0.059 0.944 12.027 115.990 364.573 448.913 -> 152.095 -> 1216.759 MByte/s p09 random-cyc-1dim :( 16.831) 0.059 0.940 12.217 113.596 393.473 451.510 -> 154.267 -> 1234.132 MByte/s p10 random-cyc-1dim :( 16.983) 0.059 0.940 12.465 113.636 365.905 453.658 -> 152.669 -> 1221.349 MByte/s p11 random-cyc-1dim :( 16.737) 0.060 0.953 12.469 115.061 371.357 451.218 -> 151.344 -> 1210.752 MByte/s p12 random-cyc-1dim :( 15.956) 0.063 0.961 12.775 113.531 395.812 423.026 -> 152.801 -> 1222.407 MByte/s p13 random-cyc-1dim :( 16.572) 0.060 0.958 12.677 113.934 369.247 456.250 -> 152.464 -> 1219.713 MByte/s p14 random-cyc-1dim :( 16.596) 0.060 0.955 12.462 112.624 364.139 453.108 -> 151.664 -> 1213.308 MByte/s p15 random-cyc-1dim :( 16.076) 0.062 0.962 12.820 115.346 381.114 441.657 -> 153.258 -> 1226.063 MByte/s p16 random-cyc-1dim :( 15.901) 0.063 0.977 12.805 111.505 369.214 428.143 -> 150.961 -> 1207.687 MByte/s p17 random-cyc-1dim :( 16.487) 0.061 0.942 12.248 112.746 376.332 449.201 -> 153.027 -> 1224.215 MByte/s p18 random-cyc-1dim :( 16.708) 0.060 0.947 12.267 115.936 378.586 429.074 -> 151.141 -> 1209.128 MByte/s p19 random-cyc-1dim :( 16.478) 0.061 0.970 12.891 114.715 377.561 441.936 -> 148.677 -> 1189.418 MByte/s p20 random-cyc-1dim :( 16.756) 0.060 0.944 12.874 112.854 373.153 445.079 -> 150.968 -> 1207.743 MByte/s p21 random-cyc-1dim :( 16.518) 0.061 0.964 12.638 114.954 382.838 452.179 -> 154.132 -> 1233.056 MByte/s p22 random-cyc-1dim :( 16.138) 0.062 0.951 12.908 113.140 382.238 447.416 -> 152.732 -> 1221.854 MByte/s p23 random-cyc-1dim :( 16.557) 0.060 0.960 12.336 114.338 376.140 443.291 -> 151.165 -> 1209.316 MByte/s p24 random-cyc-1dim :( 16.487) 0.061 0.947 12.588 112.605 376.136 452.631 -> 151.553 -> 1212.420 MByte/s p25 random-cyc-1dim :( 16.736) 0.060 0.950 12.329 113.322 358.018 445.456 -> 152.889 -> 1223.115 MByte/s p26 random-cyc-1dim :( 16.615) 0.060 0.967 12.729 113.259 368.801 453.843 -> 153.472 -> 1227.778 MByte/s p27 random-cyc-1dim :( 18.331) 0.055 0.855 11.260 114.108 376.062 446.308 -> 151.554 -> 1212.435 MByte/s p28 random-cyc-1dim :( 16.540) 0.060 0.945 12.462 117.119 369.578 458.682 -> 154.188 -> 1233.506 MByte/s p29 random-cyc-1dim :( 16.560) 0.060 0.960 12.539 113.656 359.539 456.572 -> 150.928 -> 1207.425 MByte/s p30 random-cyc-1dim :( 16.063) 0.062 0.973 12.888 115.023 351.400 450.576 -> 151.198 -> 1209.587 MByte/s p31 random-cyc-1dim :( 16.707) 0.060 0.951 12.710 113.604 388.970 453.230 -> 151.757 -> 1214.056 MByte/s p32 random-cyc-1dim :( 16.438) 0.061 0.948 12.839 113.416 362.462 455.964 -> 152.686 -> 1221.486 MByte/s p33 random-cyc-1dim :( 15.955) 0.063 0.986 12.589 115.112 382.394 460.735 -> 153.631 -> 1229.046 MByte/s p34 random-cyc-1dim :( 16.010) 0.062 0.963 13.247 117.174 355.380 453.427 -> 151.390 -> 1211.118 MByte/s p35 random-cyc-1dim :( 16.545) 0.060 0.945 12.667 112.682 375.990 462.628 -> 153.413 -> 1227.306 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 16.240) 0.062 0.978 13.006 112.592 395.194 446.976 -> 155.187 -> 1241.497 MByte/s p37 best bi-section :( 12.277) 0.041 0.611 8.441 84.648 220.367 514.290 -> 143.018 -> 1144.144 MByte/s p38 worst bi-section :( 12.366) 0.040 0.610 8.523 86.661 398.845 498.609 -> 153.867 -> 1230.937 MByte/s p39 one PingPong Pair :( 11.570) 0.011 0.163 2.231 24.724 91.010 114.605 -> 35.902 -> 287.216 MByte/s p40 acyclic-2dim-all :( 13.901) 0.045 0.696 10.065 88.744 339.099 415.467 -> 130.912 -> 1047.294 MByte/s p41 acyclic-3dim-all :( 12.337) 0.041 0.628 8.732 88.550 365.804 503.145 -> 147.170 -> 1177.358 MByte/s p42 cyclic-2dim-x :( 16.156) 0.062 0.955 12.637 113.795 380.668 459.223 -> 154.333 -> 1234.668 MByte/s p43 cyclic-2dim-y :( 16.113) 0.062 0.961 12.926 116.443 227.691 459.548 -> 155.700 -> 1245.602 MByte/s p44 cyclic-2dim-all :( 16.541) 0.060 0.940 12.244 113.057 367.860 455.070 -> 152.108 -> 1216.861 MByte/s p45 cyclic-3dim-x :( 16.518) 0.061 0.958 13.377 112.187 245.369 463.510 -> 155.424 -> 1243.394 MByte/s p46 cyclic-3dim-y :( 15.957) 0.063 0.972 12.790 111.876 273.397 455.632 -> 156.630 -> 1253.040 MByte/s p47 cyclic-3dim-z :( 16.255) 0.062 0.958 12.287 111.997 381.898 460.254 -> 160.829 -> 1286.632 MByte/s p48 cyclic-3dim-all :( 16.574) 0.060 0.944 12.444 111.953 393.346 451.226 -> 151.989 -> 1215.911 MByte/s log_avg of all rings : 0.060 0.946 12.732 113.565 336.524 455.575 || 152.495 -> 1219.961 MByte/s log_avg of all random : 0.060 0.952 12.550 114.075 373.073 448.602 || 152.254 -> 1218.028 MByte/s log_avg(ring,random) : 0.060 0.949 12.641 113.820 354.327 452.075 || 152.374 -> 1218.994 MByte/s * size -> accumulated on all pr.: 0.483 7.591 101.127 910.556 2834.618 3616.603 || 1218.994 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 1218.994 MByte/s on 8 processes ( = 152.374 MByte/s * 8 processes) Ping-pong latency: 11.570 microsec Ping-pong bandwidth: 916.839 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 8 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 18:02:57 1999 Total execution wall clock time = 91 seconds SECTION-BEFF-END b_eff = 1218.994 MB/s = 152.374 * 8 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000