b_eff = 974.033 MB/s = 162.339 * 6 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 = 6 2-dim-paterns: size = 3 * 2 3-dim-paterns: size = 3 * 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-3*2fix 1=ring-1*6fix 2=ring-1*6fix 3=ring-1*6fix 4=ring-1*6fix 5=ring-1*6fix 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: 72.826 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 4.6e-01 4.7e-03 1.7e-02 231 3.5e-01 3.6e-03 1.3e-02 238 3.6e-01 3.7e-03 1.3e-02 2 160 2.5e-01 2.5e-03 9.0e-03 160 2.4e-01 2.5e-03 8.9e-03 160 2.5e-01 2.5e-03 8.9e-03 4 158 2.4e-01 2.5e-03 9.0e-03 159 2.5e-01 2.5e-03 9.1e-03 158 2.4e-01 2.5e-03 9.0e-03 8 158 2.4e-01 2.6e-03 8.8e-03 158 2.4e-01 2.5e-03 8.8e-03 158 2.4e-01 2.5e-03 8.8e-03 16 154 2.4e-01 2.4e-03 8.7e-03 159 2.5e-01 2.5e-03 9.1e-03 158 2.5e-01 2.5e-03 8.9e-03 32 158 2.5e-01 2.6e-03 9.1e-03 157 2.5e-01 2.6e-03 9.1e-03 158 2.5e-01 2.6e-03 9.1e-03 64 153 2.5e-01 2.6e-03 9.3e-03 149 2.5e-01 2.5e-03 9.2e-03 153 2.5e-01 2.6e-03 9.3e-03 128 148 2.7e-01 2.6e-03 9.8e-03 149 2.7e-01 2.7e-03 9.8e-03 149 2.7e-01 2.7e-03 9.8e-03 256 140 2.6e-01 2.5e-03 8.8e-03 139 2.5e-01 2.5e-03 9.0e-03 135 2.4e-01 2.4e-03 8.8e-03 512 139 2.6e-01 2.7e-03 9.0e-03 140 2.6e-01 2.6e-03 9.3e-03 140 2.6e-01 2.6e-03 9.2e-03 1024 131 2.6e-01 2.6e-03 9.0e-03 134 2.7e-01 2.6e-03 9.2e-03 136 2.7e-01 2.6e-03 9.3e-03 2048 125 3.2e-01 3.3e-03 1.1e-02 126 3.2e-01 3.3e-03 1.1e-02 131 3.3e-01 3.4e-03 1.2e-02 4096 95 3.1e-01 3.2e-03 1.1e-02 94 3.1e-01 3.2e-03 1.1e-02 96 3.1e-01 3.2e-03 1.1e-02 10624 57 3.4e-01 2.9e-03 1.2e-02 57 3.4e-01 2.9e-03 1.2e-02 57 3.4e-01 3.2e-03 1.2e-02 27554 38 3.9e-01 3.1e-03 1.4e-02 37 3.7e-01 3.0e-03 1.3e-02 34 3.4e-01 2.9e-03 1.2e-02 71468 23 4.4e-01 4.0e-03 1.5e-02 23 4.4e-01 3.8e-03 1.5e-02 22 4.3e-01 3.7e-03 1.4e-02 185364 11 5.5e-01 5.3e-03 1.8e-02 11 5.5e-01 4.9e-03 1.7e-02 11 5.6e-01 4.7e-03 1.8e-02 480774 4 4.4e-01 4.0e-03 1.5e-02 4 4.5e-01 4.2e-03 1.5e-02 4 4.4e-01 4.2e-03 1.5e-02 1246974 1 2.4e-01 2.5e-03 8.3e-03 1 2.4e-01 2.5e-03 7.9e-03 1 2.4e-01 2.5e-03 8.0e-03 3234251 1 6.1e-01 6.0e-03 2.0e-02 1 6.1e-01 5.9e-03 2.0e-02 1 6.1e-01 6.1e-03 2.0e-02 8388608 1 1.5e+00 1.4e-02 5.0e-02 1 1.5e+00 1.4e-02 5.0e-02 1 1.5e+00 1.4e-02 5.0e-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 1.4e+00 2.9e-02 3.1e-02 37 1.7e-01 3.6e-03 3.8e-03 37 1.7e-01 3.6e-03 3.8e-03 2 150 7.0e-01 1.5e-02 1.5e-02 25 1.2e-01 2.4e-03 2.6e-03 25 1.2e-01 2.4e-03 2.6e-03 4 75 3.5e-01 7.3e-03 7.8e-03 25 1.2e-01 2.4e-03 2.7e-03 25 1.2e-01 2.4e-03 2.6e-03 8 37 1.7e-01 3.6e-03 3.8e-03 25 1.2e-01 2.4e-03 2.6e-03 25 1.2e-01 2.4e-03 2.6e-03 16 25 1.2e-01 2.4e-03 2.6e-03 25 1.2e-01 2.4e-03 2.6e-03 25 1.2e-01 2.4e-03 2.6e-03 32 25 1.2e-01 2.4e-03 2.7e-03 25 1.2e-01 2.4e-03 2.7e-03 25 1.2e-01 2.4e-03 2.6e-03 64 25 1.2e-01 2.5e-03 2.7e-03 25 1.2e-01 2.5e-03 2.6e-03 25 1.2e-01 2.4e-03 3.0e-03 128 25 1.2e-01 2.5e-03 2.7e-03 25 1.2e-01 2.5e-03 2.7e-03 25 1.2e-01 2.5e-03 2.7e-03 256 25 1.2e-01 2.5e-03 2.8e-03 25 1.2e-01 2.5e-03 2.8e-03 25 1.2e-01 2.5e-03 2.8e-03 512 25 1.2e-01 2.5e-03 2.7e-03 25 1.2e-01 2.5e-03 2.7e-03 25 1.2e-01 2.5e-03 2.8e-03 1024 25 1.3e-01 2.5e-03 2.8e-03 25 1.3e-01 2.5e-03 2.9e-03 25 1.2e-01 2.5e-03 2.8e-03 2048 24 1.4e-01 2.6e-03 3.4e-03 24 1.4e-01 2.6e-03 3.4e-03 25 1.5e-01 2.7e-03 3.5e-03 4096 22 1.5e-01 2.6e-03 3.7e-03 22 1.5e-01 2.6e-03 3.7e-03 22 1.5e-01 2.6e-03 3.5e-03 10624 16 1.7e-01 2.4e-03 4.8e-03 16 1.7e-01 2.4e-03 4.8e-03 16 1.7e-01 2.4e-03 5.0e-03 27554 13 2.1e-01 2.4e-03 6.6e-03 13 2.1e-01 2.5e-03 6.2e-03 12 1.9e-01 2.2e-03 6.2e-03 71468 10 2.7e-01 2.7e-03 8.9e-03 9 2.5e-01 2.4e-03 7.9e-03 10 2.8e-01 2.6e-03 9.6e-03 185364 7 4.6e-01 3.8e-03 1.6e-02 7 4.6e-01 4.0e-03 1.6e-02 7 4.7e-01 4.4e-03 1.6e-02 480774 3 4.5e-01 3.7e-03 1.4e-02 3 4.5e-01 3.5e-03 1.5e-02 3 4.5e-01 3.5e-03 1.6e-02 1246974 1 3.0e-01 2.2e-03 1.0e-02 1 3.0e-01 2.2e-03 1.0e-02 1 3.0e-01 2.2e-03 1.0e-02 3234251 1 7.8e-01 6.1e-03 2.5e-02 1 7.8e-01 6.1e-03 2.5e-02 1 7.8e-01 6.2e-03 2.5e-02 8388608 1 2.0e+00 1.6e-02 6.4e-02 1 2.0e+00 1.6e-02 6.4e-02 1 2.0e+00 1.6e-02 6.5e-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 3.2e-02 100 3.3e-01 3.6e-03 1.1e-02 102 3.4e-01 3.6e-03 1.1e-02 2 150 5.0e-01 5.4e-03 1.6e-02 70 2.3e-01 2.6e-03 7.5e-03 69 2.3e-01 2.5e-03 7.4e-03 4 75 2.6e-01 2.8e-03 8.1e-03 68 2.3e-01 2.5e-03 7.4e-03 69 2.3e-01 2.5e-03 7.4e-03 8 67 2.3e-01 2.5e-03 7.1e-03 68 2.3e-01 2.5e-03 7.2e-03 69 2.3e-01 2.5e-03 7.3e-03 16 67 2.3e-01 2.4e-03 7.1e-03 68 2.3e-01 2.5e-03 7.2e-03 70 2.3e-01 2.5e-03 7.5e-03 32 68 2.3e-01 2.5e-03 7.3e-03 68 2.3e-01 2.5e-03 7.4e-03 69 2.3e-01 2.5e-03 7.5e-03 64 68 2.4e-01 2.6e-03 7.5e-03 68 2.3e-01 2.6e-03 7.5e-03 68 2.3e-01 2.5e-03 7.5e-03 128 65 2.3e-01 2.5e-03 7.4e-03 65 2.3e-01 2.5e-03 7.4e-03 66 2.4e-01 2.5e-03 7.5e-03 256 64 2.3e-01 2.5e-03 7.2e-03 64 2.3e-01 2.5e-03 7.3e-03 64 2.4e-01 2.6e-03 7.6e-03 512 65 2.3e-01 2.5e-03 7.5e-03 65 2.4e-01 2.6e-03 7.6e-03 62 2.3e-01 2.4e-03 7.2e-03 1024 64 2.4e-01 2.6e-03 7.6e-03 62 2.3e-01 2.5e-03 7.5e-03 63 2.3e-01 2.6e-03 7.6e-03 2048 62 2.6e-01 2.8e-03 8.4e-03 63 2.6e-01 2.8e-03 8.6e-03 61 2.5e-01 2.8e-03 8.3e-03 4096 54 2.6e-01 2.8e-03 8.6e-03 55 2.7e-01 2.9e-03 8.8e-03 53 2.6e-01 2.8e-03 8.5e-03 10624 36 2.6e-01 2.7e-03 8.4e-03 36 2.6e-01 2.7e-03 8.4e-03 36 2.6e-01 2.8e-03 8.4e-03 27554 25 2.7e-01 2.6e-03 8.9e-03 26 2.8e-01 2.6e-03 9.1e-03 25 2.7e-01 2.6e-03 8.9e-03 71468 18 3.5e-01 3.3e-03 1.2e-02 19 3.7e-01 3.8e-03 1.2e-02 18 3.5e-01 3.3e-03 1.2e-02 185364 10 4.8e-01 4.4e-03 1.5e-02 9 4.3e-01 4.0e-03 1.4e-02 10 4.8e-01 4.4e-03 1.5e-02 480774 4 4.4e-01 4.1e-03 1.4e-02 4 4.4e-01 4.2e-03 1.3e-02 4 4.4e-01 4.1e-03 1.3e-02 1246974 1 2.4e-01 2.1e-03 7.8e-03 1 2.4e-01 2.1e-03 7.7e-03 1 2.4e-01 2.1e-03 7.8e-03 3234251 1 6.0e-01 6.4e-03 2.0e-02 1 6.0e-01 6.3e-03 1.9e-02 1 6.1e-01 6.4e-03 2.0e-02 8388608 1 1.5e+00 1.6e-02 5.0e-02 1 1.5e+00 1.7e-02 4.9e-02 1 1.5e+00 1.6e-02 5.0e-02 SECTION-LOOPLNGS-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 72.826 sec sum of max elapsed time per entries above = 72.427 sec difference to elapsed time = 0.399 sec = 0.5% sum based on fastest repetition = 67.892 sec difference to elapsed time = 4.934 sec = 6.8% 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-3*2fix 1 6 1.00 1.00 0 ( -1 -1 -1 ) p01 ring-1*6fix 2 12 2.00 1.00 0 ( -1 -1 -1 ) p02 ring-1*6fix 2 12 2.00 1.00 0 ( -1 -1 -1 ) p03 ring-1*6fix 2 12 2.00 1.00 0 ( -1 -1 -1 ) p04 ring-1*6fix 2 12 2.00 1.00 0 ( -1 -1 -1 ) p05 ring-1*6fix 2 12 2.00 1.00 0 ( -1 -1 -1 ) p06 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p07 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p08 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p09 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p10 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p11 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p12 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p13 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p14 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p15 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p16 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p17 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p18 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p19 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p20 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p21 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p22 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p23 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p24 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p25 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p26 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p27 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p28 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p29 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p30 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p31 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p32 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p33 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p34 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p35 random-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p36 worst-cyc-1dim 2 12 2.00 1.00 0 ( -1 -1 -1 ) p37 best bi-section 2 6 1.00 0.50 0 ( -1 -1 -1 ) p38 worst bi-section 2 6 1.00 0.50 0 ( -1 -1 -1 ) p39 one PingPong Pair 2 2 1.00 0.50 4 ( -1 -1 -1 ) p40 acyclic-2dim-all 4 14 2.33 0.58 0 ( -1 -1 -1 ) p41 acyclic-3dim-all 4 14 2.33 0.58 0 ( -1 -1 -1 ) p42 cyclic-2dim-x 2 12 2.00 1.00 0 ( -1 -1 -1 ) p43 cyclic-2dim-y 1 6 1.00 1.00 0 ( -1 -1 -1 ) p44 cyclic-2dim-all 3 18 3.00 1.00 0 ( -1 -1 -1 ) p45 cyclic-3dim-x 2 12 2.00 1.00 0 ( -1 -1 -1 ) p46 cyclic-3dim-y 1 6 1.00 1.00 0 ( -1 -1 -1 ) p47 cyclic-3dim-all 3 18 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-3*2fix : 170.474 88.455 153.352 -> 170.474 -> 1022.844 MByte/s p01 ring-1*6fix : 161.005 107.313 151.765 -> 161.005 -> 966.029 MByte/s p02 ring-1*6fix : 158.724 106.786 151.634 -> 158.724 -> 952.342 MByte/s p03 ring-1*6fix : 158.323 107.552 148.918 -> 158.323 -> 949.938 MByte/s p04 ring-1*6fix : 160.311 107.503 150.820 -> 160.311 -> 961.867 MByte/s p05 ring-1*6fix : 158.673 107.627 149.843 -> 158.673 -> 952.037 MByte/s p06 random-cyc-1dim : 158.716 107.947 148.903 -> 158.716 -> 952.293 MByte/s p07 random-cyc-1dim : 159.662 106.033 146.781 -> 159.662 -> 957.972 MByte/s p08 random-cyc-1dim : 158.942 108.152 152.277 -> 158.942 -> 953.649 MByte/s p09 random-cyc-1dim : 161.084 106.004 150.286 -> 161.084 -> 966.504 MByte/s p10 random-cyc-1dim : 159.263 107.856 150.878 -> 159.263 -> 955.578 MByte/s p11 random-cyc-1dim : 156.557 107.739 151.521 -> 156.557 -> 939.343 MByte/s p12 random-cyc-1dim : 160.264 107.917 151.667 -> 160.264 -> 961.582 MByte/s p13 random-cyc-1dim : 160.869 106.101 151.229 -> 160.869 -> 965.213 MByte/s p14 random-cyc-1dim : 159.165 106.777 152.855 -> 159.165 -> 954.993 MByte/s p15 random-cyc-1dim : 159.071 106.646 149.873 -> 159.071 -> 954.425 MByte/s p16 random-cyc-1dim : 159.287 107.938 152.866 -> 159.287 -> 955.720 MByte/s p17 random-cyc-1dim : 157.733 106.906 149.997 -> 157.733 -> 946.396 MByte/s p18 random-cyc-1dim : 160.175 106.926 150.788 -> 160.175 -> 961.053 MByte/s p19 random-cyc-1dim : 160.613 106.175 151.649 -> 160.613 -> 963.675 MByte/s p20 random-cyc-1dim : 160.484 107.538 148.185 -> 160.484 -> 962.904 MByte/s p21 random-cyc-1dim : 159.379 107.507 150.293 -> 159.379 -> 956.273 MByte/s p22 random-cyc-1dim : 159.423 105.857 149.688 -> 159.423 -> 956.539 MByte/s p23 random-cyc-1dim : 160.600 107.063 147.817 -> 160.600 -> 963.601 MByte/s p24 random-cyc-1dim : 159.179 107.052 152.174 -> 159.179 -> 955.072 MByte/s p25 random-cyc-1dim : 158.623 106.901 151.137 -> 158.623 -> 951.737 MByte/s p26 random-cyc-1dim : 158.722 107.620 149.435 -> 158.722 -> 952.332 MByte/s p27 random-cyc-1dim : 158.985 107.600 151.311 -> 158.985 -> 953.911 MByte/s p28 random-cyc-1dim : 159.572 106.065 150.550 -> 159.572 -> 957.432 MByte/s p29 random-cyc-1dim : 160.281 107.940 151.533 -> 160.281 -> 961.685 MByte/s p30 random-cyc-1dim : 158.930 107.146 147.539 -> 158.930 -> 953.582 MByte/s p31 random-cyc-1dim : 158.301 107.101 150.078 -> 158.301 -> 949.807 MByte/s p32 random-cyc-1dim : 159.921 106.695 149.003 -> 159.921 -> 959.527 MByte/s p33 random-cyc-1dim : 160.847 106.492 148.274 -> 160.847 -> 965.079 MByte/s p34 random-cyc-1dim : 158.990 107.252 150.034 -> 158.990 -> 953.938 MByte/s p35 random-cyc-1dim : 159.506 107.162 148.515 -> 159.506 -> 957.039 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 160.952 106.744 151.530 -> 160.952 -> 965.709 MByte/s p37 best bi-section : 149.648 88.825 159.042 -> 159.042 -> 954.253 MByte/s p38 worst bi-section : 152.362 136.332 157.725 -> 157.725 -> 946.349 MByte/s p39 one PingPong Pair : 53.870 0.000 0.000 -> 53.870 -> 323.221 MByte/s p40 acyclic-2dim-all : 126.114 95.890 124.927 -> 126.114 -> 756.686 MByte/s p41 acyclic-3dim-all : 126.447 95.503 125.227 -> 126.447 -> 758.683 MByte/s p42 cyclic-2dim-x : 161.143 105.340 144.083 -> 161.143 -> 966.858 MByte/s p43 cyclic-2dim-y : 171.044 89.298 153.077 -> 171.044 -> 1026.264 MByte/s p44 cyclic-2dim-all : 156.109 104.263 152.100 -> 156.109 -> 936.653 MByte/s p45 cyclic-3dim-x : 160.392 104.664 140.792 -> 160.392 -> 962.352 MByte/s p46 cyclic-3dim-y : 171.599 89.238 153.456 -> 171.599 -> 1029.592 MByte/s p47 cyclic-3dim-all : 156.298 105.053 152.780 -> 156.298 -> 937.789 MByte/s log_avg of all rings : 161.197 103.946 151.049 || 161.197 -> 967.184 MByte/s log_avg of all random : 159.435 107.068 150.230 || 159.435 -> 956.611 MByte/s log_avg(ring,random) : 160.314 105.496 150.639 ||(160.314 -> 961.883)MByte/s * size -> accumulated on all pr.: 961.883 632.973 903.832 ||(961.883)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-3*2fix : 169.580 171.813 170.612 -> 171.813 -> 1030.876 MByte/s p01 ring-1*6fix : 159.660 158.846 160.065 -> 160.065 -> 960.392 MByte/s p02 ring-1*6fix : 158.762 155.966 159.897 -> 159.897 -> 959.385 MByte/s p03 ring-1*6fix : 157.395 157.031 158.004 -> 158.004 -> 948.026 MByte/s p04 ring-1*6fix : 158.547 157.142 158.380 -> 158.547 -> 951.279 MByte/s p05 ring-1*6fix : 158.892 155.860 157.400 -> 158.892 -> 953.352 MByte/s p06 random-cyc-1dim : 154.414 156.959 156.830 -> 156.959 -> 941.754 MByte/s p07 random-cyc-1dim : 157.661 158.921 156.229 -> 158.921 -> 953.527 MByte/s p08 random-cyc-1dim : 160.698 157.641 158.622 -> 160.698 -> 964.186 MByte/s p09 random-cyc-1dim : 156.967 158.847 159.326 -> 159.326 -> 955.958 MByte/s p10 random-cyc-1dim : 157.872 157.403 157.281 -> 157.872 -> 947.233 MByte/s p11 random-cyc-1dim : 157.994 155.687 158.054 -> 158.054 -> 948.325 MByte/s p12 random-cyc-1dim : 156.071 160.835 159.967 -> 160.835 -> 965.012 MByte/s p13 random-cyc-1dim : 159.097 159.299 157.462 -> 159.299 -> 955.797 MByte/s p14 random-cyc-1dim : 156.941 161.097 156.972 -> 161.097 -> 966.581 MByte/s p15 random-cyc-1dim : 158.595 158.118 155.186 -> 158.595 -> 951.573 MByte/s p16 random-cyc-1dim : 157.099 160.701 159.858 -> 160.701 -> 964.208 MByte/s p17 random-cyc-1dim : 156.050 155.501 157.023 -> 157.023 -> 942.138 MByte/s p18 random-cyc-1dim : 158.926 158.009 159.147 -> 159.147 -> 954.882 MByte/s p19 random-cyc-1dim : 158.350 158.876 157.964 -> 158.876 -> 953.254 MByte/s p20 random-cyc-1dim : 156.508 159.532 156.610 -> 159.532 -> 957.193 MByte/s p21 random-cyc-1dim : 159.484 158.420 156.685 -> 159.484 -> 956.903 MByte/s p22 random-cyc-1dim : 156.562 157.615 158.329 -> 158.329 -> 949.975 MByte/s p23 random-cyc-1dim : 159.341 158.535 157.340 -> 159.341 -> 956.045 MByte/s p24 random-cyc-1dim : 158.968 157.060 156.849 -> 158.968 -> 953.805 MByte/s p25 random-cyc-1dim : 157.261 157.045 160.484 -> 160.484 -> 962.905 MByte/s p26 random-cyc-1dim : 157.390 156.998 158.269 -> 158.269 -> 949.614 MByte/s p27 random-cyc-1dim : 156.230 158.976 158.023 -> 158.976 -> 953.859 MByte/s p28 random-cyc-1dim : 157.068 159.349 159.527 -> 159.527 -> 957.159 MByte/s p29 random-cyc-1dim : 157.324 158.132 157.813 -> 158.132 -> 948.793 MByte/s p30 random-cyc-1dim : 155.112 159.796 157.773 -> 159.796 -> 958.775 MByte/s p31 random-cyc-1dim : 156.555 158.243 156.998 -> 158.243 -> 949.457 MByte/s p32 random-cyc-1dim : 157.816 157.746 158.063 -> 158.063 -> 948.378 MByte/s p33 random-cyc-1dim : 156.262 159.869 156.348 -> 159.869 -> 959.215 MByte/s p34 random-cyc-1dim : 157.353 157.164 157.895 -> 157.895 -> 947.373 MByte/s p35 random-cyc-1dim : 156.672 158.201 157.818 -> 158.201 -> 949.204 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 161.222 158.432 161.127 -> 161.222 -> 967.333 MByte/s p37 best bi-section : 164.432 159.011 158.765 -> 164.432 -> 986.589 MByte/s p38 worst bi-section : 162.721 162.705 162.626 -> 162.721 -> 976.323 MByte/s p39 one PingPong Pair : 52.738 53.548 52.427 -> 53.548 -> 321.291 MByte/s p40 acyclic-2dim-all : 126.187 128.202 127.079 -> 128.202 -> 769.210 MByte/s p41 acyclic-3dim-all : 128.485 128.383 127.462 -> 128.485 -> 770.907 MByte/s p42 cyclic-2dim-x : 158.674 159.427 155.119 -> 159.427 -> 956.562 MByte/s p43 cyclic-2dim-y : 169.900 170.409 170.644 -> 170.644 -> 1023.863 MByte/s p44 cyclic-2dim-all : 155.323 158.484 158.390 -> 158.484 -> 950.901 MByte/s p45 cyclic-3dim-x : 155.628 156.123 158.591 -> 158.591 -> 951.548 MByte/s p46 cyclic-3dim-y : 172.913 172.417 171.569 -> 172.913 -> 1037.479 MByte/s p47 cyclic-3dim-all : 157.469 158.667 157.813 -> 158.667 -> 952.000 MByte/s log_avg of all rings : 160.421 159.347 160.665 || 161.134 -> 966.804 MByte/s log_avg of all random : 157.416 158.347 157.820 || 159.014 -> 954.081 MByte/s log_avg(ring,random) : 158.911 158.846 159.236 ||(160.070 -> 960.421)MByte/s * size -> accumulated on all pr.: 953.467 953.078 955.417 ||(960.421)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-3*2fix p00 method 0 =Sndrcv :( 15.541) 0.064 1.003 14.346 122.364 390.467 505.185 -> 170.474 -> 1022.844 MByte/s p00 method 1 =Alltoal :( 96.946) 0.010 0.164 2.585 34.512 258.886 264.992 -> 88.455 -> 530.727 MByte/s p00 method 2 =non-blk :( 37.717) 0.027 0.428 6.256 78.117 347.560 505.033 -> 153.352 -> 920.114 MByte/s p01 ring-1*6fix p01 method 0 =Sndrcv :( 15.655) 0.064 1.000 14.164 122.502 348.874 508.092 -> 161.005 -> 966.029 MByte/s p01 method 1 =Alltoal :( 49.256) 0.020 0.322 5.000 56.906 268.587 348.032 -> 107.313 -> 643.875 MByte/s p01 method 2 =non-blk :( 36.074) 0.028 0.442 6.675 79.115 369.952 506.987 -> 151.765 -> 910.591 MByte/s p02 ring-1*6fix p02 method 0 =Sndrcv :( 15.619) 0.064 0.995 13.821 121.911 351.490 504.761 -> 158.724 -> 952.342 MByte/s p02 method 1 =Alltoal :( 49.378) 0.020 0.322 4.938 56.250 261.867 349.532 -> 106.786 -> 640.716 MByte/s p02 method 2 =non-blk :( 35.850) 0.028 0.443 6.700 80.477 369.473 507.277 -> 151.634 -> 909.803 MByte/s p03 ring-1*6fix p03 method 0 =Sndrcv :( 15.571) 0.064 1.015 13.885 122.668 345.889 503.457 -> 158.323 -> 949.938 MByte/s p03 method 1 =Alltoal :( 49.363) 0.020 0.323 5.018 57.014 268.226 348.893 -> 107.552 -> 645.314 MByte/s p03 method 2 =non-blk :( 35.941) 0.028 0.437 6.624 79.027 363.183 506.958 -> 148.918 -> 893.508 MByte/s p04 ring-1*6fix p04 method 0 =Sndrcv :( 15.750) 0.063 1.014 14.055 121.103 350.163 504.305 -> 160.311 -> 961.867 MByte/s p04 method 1 =Alltoal :( 49.420) 0.020 0.313 5.012 57.160 264.456 348.850 -> 107.503 -> 645.020 MByte/s p04 method 2 =non-blk :( 36.083) 0.028 0.441 6.587 79.446 353.952 508.107 -> 150.820 -> 904.920 MByte/s p05 ring-1*6fix p05 method 0 =Sndrcv :( 15.717) 0.064 0.999 13.854 120.358 352.737 505.047 -> 158.673 -> 952.037 MByte/s p05 method 1 =Alltoal :( 48.919) 0.020 0.323 4.963 56.409 266.053 348.806 -> 107.627 -> 645.759 MByte/s p05 method 2 =non-blk :( 36.135) 0.028 0.439 6.723 79.812 364.386 496.560 -> 149.843 -> 899.060 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 15.691) 0.064 1.005 13.766 119.592 341.398 505.035 -> 158.716 -> 952.293 MByte/s p06 method 1 =Alltoal :( 48.947) 0.020 0.324 5.008 57.360 265.158 347.937 -> 107.947 -> 647.683 MByte/s p06 method 2 =non-blk :( 36.010) 0.028 0.438 6.648 78.073 365.650 507.109 -> 148.903 -> 893.417 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 15.603) 0.064 1.009 13.969 123.070 342.980 506.130 -> 159.662 -> 957.972 MByte/s p07 method 1 =Alltoal :( 49.148) 0.020 0.322 4.992 56.908 277.255 348.523 -> 106.033 -> 636.197 MByte/s p07 method 2 =non-blk :( 36.285) 0.028 0.442 6.633 79.724 368.296 495.738 -> 146.781 -> 880.687 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 15.530) 0.064 1.002 13.777 121.940 355.165 503.638 -> 158.942 -> 953.649 MByte/s p08 method 1 =Alltoal :( 49.541) 0.020 0.322 4.925 57.765 273.140 347.787 -> 108.152 -> 648.909 MByte/s p08 method 2 =non-blk :( 36.338) 0.028 0.444 6.704 79.674 373.646 508.879 -> 152.277 -> 913.661 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 15.714) 0.064 0.994 13.657 121.100 352.526 505.597 -> 161.084 -> 966.504 MByte/s p09 method 1 =Alltoal :( 49.366) 0.020 0.325 5.017 56.179 255.652 348.205 -> 106.004 -> 636.027 MByte/s p09 method 2 =non-blk :( 36.068) 0.028 0.437 6.698 79.665 359.197 507.830 -> 150.286 -> 901.718 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 15.653) 0.064 1.012 14.046 120.360 349.294 506.804 -> 159.263 -> 955.578 MByte/s p10 method 1 =Alltoal :( 49.320) 0.020 0.325 4.988 58.025 270.294 349.350 -> 107.856 -> 647.134 MByte/s p10 method 2 =non-blk :( 35.870) 0.028 0.441 6.602 79.178 361.225 507.186 -> 150.878 -> 905.269 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 16.168) 0.062 0.975 13.494 121.083 355.660 505.018 -> 156.557 -> 939.343 MByte/s p11 method 1 =Alltoal :( 49.366) 0.020 0.321 4.850 57.469 272.651 349.315 -> 107.739 -> 646.435 MByte/s p11 method 2 =non-blk :( 36.152) 0.028 0.444 6.722 79.709 369.732 506.481 -> 151.521 -> 909.128 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 15.690) 0.064 1.003 13.783 120.638 361.910 502.808 -> 160.264 -> 961.582 MByte/s p12 method 1 =Alltoal :( 49.453) 0.020 0.322 5.051 57.305 267.975 348.581 -> 107.917 -> 647.504 MByte/s p12 method 2 =non-blk :( 35.956) 0.028 0.441 6.693 78.998 378.855 506.802 -> 151.667 -> 910.001 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 15.687) 0.064 1.002 13.894 121.460 349.773 507.554 -> 160.869 -> 965.213 MByte/s p13 method 1 =Alltoal :( 49.338) 0.020 0.325 5.010 56.887 255.877 348.039 -> 106.101 -> 636.608 MByte/s p13 method 2 =non-blk :( 35.975) 0.028 0.438 6.672 79.192 345.889 496.266 -> 151.229 -> 907.376 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 15.815) 0.063 1.008 13.660 122.345 357.971 505.123 -> 159.165 -> 954.993 MByte/s p14 method 1 =Alltoal :( 49.055) 0.020 0.325 4.826 56.996 260.656 349.067 -> 106.777 -> 640.663 MByte/s p14 method 2 =non-blk :( 36.029) 0.028 0.440 6.780 78.153 402.043 507.126 -> 152.855 -> 917.127 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 15.625) 0.064 1.000 13.776 122.212 341.828 505.308 -> 159.071 -> 954.425 MByte/s p15 method 1 =Alltoal :( 48.947) 0.020 0.323 4.992 56.604 263.780 347.635 -> 106.646 -> 639.877 MByte/s p15 method 2 =non-blk :( 35.945) 0.028 0.444 6.733 79.605 368.233 507.892 -> 149.873 -> 899.236 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 15.472) 0.065 1.001 13.967 120.896 350.827 504.790 -> 159.287 -> 955.720 MByte/s p16 method 1 =Alltoal :( 49.188) 0.020 0.325 5.000 56.870 258.809 350.357 -> 107.938 -> 647.627 MByte/s p16 method 2 =non-blk :( 36.029) 0.028 0.440 6.643 78.640 350.138 506.163 -> 152.866 -> 917.196 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 15.623) 0.064 1.014 14.040 120.030 353.872 505.764 -> 157.733 -> 946.396 MByte/s p17 method 1 =Alltoal :( 49.446) 0.020 0.321 4.863 56.426 270.519 348.255 -> 106.906 -> 641.435 MByte/s p17 method 2 =non-blk :( 35.945) 0.028 0.442 6.765 77.977 363.386 495.795 -> 149.997 -> 899.979 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 15.815) 0.063 1.006 13.710 121.392 351.581 505.445 -> 160.175 -> 961.053 MByte/s p18 method 1 =Alltoal :( 49.353) 0.020 0.322 5.012 56.250 262.638 349.264 -> 106.926 -> 641.555 MByte/s p18 method 2 =non-blk :( 36.328) 0.028 0.440 6.731 79.207 361.999 508.200 -> 150.788 -> 904.730 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 15.703) 0.064 1.001 13.857 120.924 355.044 505.628 -> 160.613 -> 963.675 MByte/s p19 method 1 =Alltoal :( 48.945) 0.020 0.322 4.998 56.355 259.925 348.508 -> 106.175 -> 637.051 MByte/s p19 method 2 =non-blk :( 36.205) 0.028 0.443 6.656 78.626 353.582 508.323 -> 151.649 -> 909.896 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 15.463) 0.065 1.003 13.964 121.554 353.258 504.928 -> 160.484 -> 962.904 MByte/s p20 method 1 =Alltoal :( 49.142) 0.020 0.323 4.969 56.782 265.482 349.089 -> 107.538 -> 645.229 MByte/s p20 method 2 =non-blk :( 36.240) 0.028 0.436 6.726 79.163 337.302 507.018 -> 148.185 -> 889.109 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 15.576) 0.064 1.012 13.601 122.917 337.139 504.850 -> 159.379 -> 956.273 MByte/s p21 method 1 =Alltoal :( 49.163) 0.020 0.324 5.014 56.496 271.423 348.508 -> 107.507 -> 645.043 MByte/s p21 method 2 =non-blk :( 36.054) 0.028 0.441 6.709 79.272 368.405 507.217 -> 150.293 -> 901.756 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 15.654) 0.064 1.009 13.896 120.435 371.774 504.275 -> 159.423 -> 956.539 MByte/s p22 method 1 =Alltoal :( 49.470) 0.020 0.322 5.012 57.050 267.288 347.917 -> 105.857 -> 635.145 MByte/s p22 method 2 =non-blk :( 35.818) 0.028 0.439 6.626 79.221 359.650 507.111 -> 149.688 -> 898.128 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 15.792) 0.063 1.010 13.990 122.346 359.359 506.283 -> 160.600 -> 963.601 MByte/s p23 method 1 =Alltoal :( 49.861) 0.020 0.321 4.934 56.407 270.913 348.675 -> 107.063 -> 642.376 MByte/s p23 method 2 =non-blk :( 35.941) 0.028 0.440 6.779 79.185 351.400 508.107 -> 147.817 -> 886.905 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 15.615) 0.064 1.015 13.954 120.415 340.176 506.099 -> 159.179 -> 955.072 MByte/s p24 method 1 =Alltoal :( 49.122) 0.020 0.322 5.016 56.744 274.265 348.444 -> 107.052 -> 642.314 MByte/s p24 method 2 =non-blk :( 35.980) 0.028 0.442 6.716 78.785 367.300 507.018 -> 152.174 -> 913.041 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 15.600) 0.064 1.008 13.802 120.491 329.508 505.933 -> 158.623 -> 951.737 MByte/s p25 method 1 =Alltoal :( 49.338) 0.020 0.323 5.014 56.727 270.462 348.566 -> 106.901 -> 641.404 MByte/s p25 method 2 =non-blk :( 36.231) 0.028 0.438 6.612 79.449 345.248 506.972 -> 151.137 -> 906.822 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 15.593) 0.064 1.000 14.023 120.196 355.938 503.987 -> 158.722 -> 952.332 MByte/s p26 method 1 =Alltoal :( 49.269) 0.020 0.323 4.973 56.638 272.794 348.546 -> 107.620 -> 645.722 MByte/s p26 method 2 =non-blk :( 36.181) 0.028 0.439 6.740 78.132 353.646 506.972 -> 149.435 -> 896.609 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 15.794) 0.063 1.002 13.741 119.846 352.309 505.628 -> 158.985 -> 953.911 MByte/s p27 method 1 =Alltoal :( 49.203) 0.020 0.325 5.008 56.763 270.127 348.364 -> 107.600 -> 645.599 MByte/s p27 method 2 =non-blk :( 36.088) 0.028 0.441 6.744 78.755 364.692 507.539 -> 151.311 -> 907.868 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 15.782) 0.063 0.988 13.715 120.358 331.545 504.638 -> 159.572 -> 957.432 MByte/s p28 method 1 =Alltoal :( 48.810) 0.020 0.325 5.014 56.676 270.237 349.016 -> 106.065 -> 636.389 MByte/s p28 method 2 =non-blk :( 36.353) 0.028 0.441 6.652 79.394 355.823 506.726 -> 150.550 -> 903.302 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 15.487) 0.065 1.002 13.802 120.104 366.395 506.697 -> 160.281 -> 961.685 MByte/s p29 method 1 =Alltoal :( 49.459) 0.020 0.325 4.898 56.872 265.184 347.700 -> 107.940 -> 647.642 MByte/s p29 method 2 =non-blk :( 36.035) 0.028 0.441 6.727 78.020 357.122 507.707 -> 151.533 -> 909.198 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 15.838) 0.063 0.994 14.149 121.295 348.696 505.475 -> 158.930 -> 953.582 MByte/s p30 method 1 =Alltoal :( 49.730) 0.020 0.322 5.024 56.763 273.655 348.487 -> 107.146 -> 642.874 MByte/s p30 method 2 =non-blk :( 36.165) 0.028 0.440 6.693 79.059 367.180 497.413 -> 147.539 -> 885.232 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 15.510) 0.064 1.009 13.714 120.859 359.106 505.781 -> 158.301 -> 949.807 MByte/s p31 method 1 =Alltoal :( 49.372) 0.020 0.325 5.010 56.657 261.628 347.527 -> 107.101 -> 642.603 MByte/s p31 method 2 =non-blk :( 36.005) 0.028 0.445 6.659 79.156 368.444 494.175 -> 150.078 -> 900.468 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 15.620) 0.064 1.003 14.193 120.227 350.134 506.572 -> 159.921 -> 959.527 MByte/s p32 method 1 =Alltoal :( 49.228) 0.020 0.324 5.008 56.746 248.145 348.581 -> 106.695 -> 640.171 MByte/s p32 method 2 =non-blk :( 36.035) 0.028 0.444 6.713 79.377 353.682 506.146 -> 149.003 -> 894.018 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 15.788) 0.063 1.004 13.930 119.955 348.547 508.032 -> 160.847 -> 965.079 MByte/s p33 method 1 =Alltoal :( 49.216) 0.020 0.323 5.037 56.729 274.524 348.306 -> 106.492 -> 638.953 MByte/s p33 method 2 =non-blk :( 36.054) 0.028 0.438 6.786 79.200 346.583 506.543 -> 148.274 -> 889.644 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 15.710) 0.064 1.003 13.806 120.084 336.857 504.154 -> 158.990 -> 953.938 MByte/s p34 method 1 =Alltoal :( 49.230) 0.020 0.325 5.021 56.657 268.392 349.562 -> 107.252 -> 643.510 MByte/s p34 method 2 =non-blk :( 35.985) 0.028 0.441 6.664 78.727 346.796 506.268 -> 150.034 -> 900.204 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 15.731) 0.064 0.985 13.841 120.376 352.280 505.871 -> 159.506 -> 957.039 MByte/s p35 method 1 =Alltoal :( 49.080) 0.020 0.322 5.017 56.640 260.525 348.755 -> 107.162 -> 642.972 MByte/s p35 method 2 =non-blk :( 36.065) 0.028 0.445 6.635 78.892 355.173 507.018 -> 148.515 -> 891.092 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 15.524) 0.064 1.017 13.813 120.065 361.493 505.337 -> 160.952 -> 965.709 MByte/s p36 method 1 =Alltoal :( 49.285) 0.020 0.323 4.967 56.996 265.023 348.596 -> 106.744 -> 640.466 MByte/s p36 method 2 =non-blk :( 36.050) 0.028 0.441 6.767 78.899 366.150 507.339 -> 151.530 -> 909.180 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 11.931) 0.042 0.641 9.126 88.775 322.524 587.562 -> 149.648 -> 897.889 MByte/s p37 method 1 =Alltoal :( 48.940) 0.010 0.162 2.556 33.928 261.656 265.774 -> 88.825 -> 532.952 MByte/s p37 method 2 =non-blk :( 17.850) 0.028 0.441 6.612 75.852 382.831 507.414 -> 159.042 -> 954.253 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 11.913) 0.042 0.645 9.122 91.902 332.622 586.944 -> 152.362 -> 914.172 MByte/s p38 method 1 =Alltoal :( 48.950) 0.010 0.165 2.558 34.499 332.020 506.159 -> 136.332 -> 817.993 MByte/s p38 method 2 =non-blk :( 17.910) 0.028 0.441 6.663 76.680 381.563 510.503 -> 157.725 -> 946.349 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 11.361) 0.015 0.221 3.151 35.346 115.063 201.950 -> 53.870 -> 323.221 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 :( 13.771) 0.042 0.661 9.537 85.955 288.361 419.985 -> 126.114 -> 756.686 MByte/s p40 method 1 =Alltoal :( 25.637) 0.023 0.362 5.372 60.699 236.458 306.827 -> 95.890 -> 575.342 MByte/s p40 method 2 =non-blk :( 23.573) 0.025 0.390 5.917 64.982 310.717 403.218 -> 124.927 -> 749.561 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 13.733) 0.042 0.662 9.466 86.126 288.238 419.788 -> 126.447 -> 758.683 MByte/s p41 method 1 =Alltoal :( 25.534) 0.023 0.361 5.519 61.069 227.195 307.420 -> 95.503 -> 573.017 MByte/s p41 method 2 =non-blk :( 23.538) 0.025 0.391 5.915 65.495 309.527 402.729 -> 125.227 -> 751.359 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 15.624) 0.064 1.020 13.922 121.410 356.312 503.457 -> 161.143 -> 966.858 MByte/s p42 method 1 =Alltoal :( 49.188) 0.020 0.322 5.000 56.056 249.986 347.060 -> 105.340 -> 632.041 MByte/s p42 method 2 =non-blk :( 35.990) 0.028 0.445 6.730 79.094 311.915 506.665 -> 144.083 -> 864.495 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 15.590) 0.064 1.014 14.295 119.955 399.804 505.523 -> 171.044 -> 1026.264 MByte/s p43 method 1 =Alltoal :( 96.431) 0.010 0.164 2.588 34.458 262.501 265.235 -> 89.298 -> 535.787 MByte/s p43 method 2 =non-blk :( 37.390) 0.027 0.426 6.486 75.980 350.625 506.312 -> 153.077 -> 918.462 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 15.880) 0.063 0.989 13.906 116.348 353.280 506.466 -> 156.109 -> 936.653 MByte/s p44 method 1 =Alltoal :( 33.198) 0.030 0.472 7.245 76.453 246.573 314.258 -> 104.263 -> 625.578 MByte/s p44 method 2 =non-blk :( 35.133) 0.028 0.454 6.822 76.809 368.832 509.141 -> 152.100 -> 912.602 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 15.632) 0.064 1.004 14.018 120.414 334.482 505.475 -> 160.392 -> 962.352 MByte/s p45 method 1 =Alltoal :( 49.122) 0.020 0.322 5.014 55.971 258.346 348.133 -> 104.664 -> 627.984 MByte/s p45 method 2 =non-blk :( 35.670) 0.028 0.445 6.726 79.248 304.649 507.032 -> 140.792 -> 844.754 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 15.588) 0.064 1.012 14.311 122.308 391.970 506.159 -> 171.599 -> 1029.592 MByte/s p46 method 1 =Alltoal :( 96.811) 0.010 0.164 2.589 34.485 261.706 265.185 -> 89.238 -> 535.430 MByte/s p46 method 2 =non-blk :( 36.961) 0.027 0.427 6.430 75.825 343.202 505.675 -> 153.456 -> 920.737 MByte/s p47 cyclic-3dim-all p47 method 0 =Sndrcv :( 15.892) 0.063 0.995 13.713 116.628 347.754 505.236 -> 156.298 -> 937.789 MByte/s p47 method 1 =Alltoal :( 33.359) 0.030 0.470 7.251 76.776 261.744 315.172 -> 105.053 -> 630.320 MByte/s p47 method 2 =non-blk :( 35.200) 0.028 0.451 6.842 77.845 382.399 509.637 -> 152.780 -> 916.681 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.064 1.004 14.020 121.815 356.290 505.139 || 161.197 -> 967.184 MByte/s - ring, method 1 = Alltoal: 0.018 0.287 4.469 52.233 264.657 333.203 || 103.946 -> 623.676 MByte/s - ring, method 2 = non-blk: 0.028 0.438 6.592 79.329 361.325 505.138 || 151.049 -> 906.292 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.064 1.003 13.850 120.947 350.301 505.460 || 159.435 -> 956.611 MByte/s - random, method 1 = Alltoal: 0.020 0.323 4.983 56.823 266.562 348.562 || 107.068 -> 642.409 MByte/s - random, method 2 = non-blk: 0.028 0.441 6.695 79.005 360.475 505.306 || 150.230 -> 901.378 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.064 1.003 13.934 121.380 353.283 505.300 || 160.314 -> 961.883 MByte/s - average, method 1 = Alltoal: 0.019 0.305 4.719 54.480 265.608 340.796 || 105.496 -> 632.973 MByte/s - average, method 2 = non-blk: 0.028 0.439 6.643 79.167 360.900 505.222 || 150.639 -> 903.832 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.383 6.021 83.606 728.279 2119.697 3031.799 || 961.883 MByte/s - accumulated, mthd 1 = Alltoal: 0.115 1.827 28.314 326.879 1593.645 2044.775 || 632.973 MByte/s - accumulated, mthd 2 = non-blk: 0.166 2.637 39.860 475.002 2165.398 3031.333 || 903.832 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 0.383 0.064 0.064 0.064 0.064 0.019 0.028 2 0.763 0.127 0.127 0.127 0.127 0.038 0.055 4 1.510 0.252 0.252 0.251 0.252 0.076 0.109 8 3.052 0.509 0.511 0.507 0.509 0.153 0.221 16 6.021 1.003 1.004 1.003 1.003 0.305 0.439 32 11.775 1.962 1.958 1.967 1.962 0.607 0.872 64 22.744 3.791 3.794 3.787 3.791 1.203 1.715 128 41.730 6.955 6.991 6.920 6.955 2.352 3.319 256 83.606 13.934 14.020 13.850 13.934 4.719 6.643 512 161.213 26.869 26.835 26.902 26.869 9.379 13.107 1024 302.989 50.498 50.981 50.020 50.498 18.437 25.498 2048 467.104 77.851 77.962 77.739 77.851 31.687 45.787 4096 728.279 121.380 121.815 120.947 121.380 54.480 79.167 10624 1054.992 175.832 177.724 173.960 175.832 92.159 136.497 27554 1642.340 273.723 280.534 267.078 273.723 162.576 237.034 71468 2176.091 362.682 364.515 360.858 361.011 248.233 342.577 185364 2192.226 365.371 368.404 362.363 353.283 265.608 360.900 480774 2540.720 423.453 426.211 420.714 411.140 301.309 420.321 1246974 2963.716 493.953 498.466 489.480 482.119 341.665 484.944 3234251 3004.344 500.724 502.267 499.186 497.826 338.010 497.446 8388608 3041.624 506.937 506.776 507.098 505.300 340.796 505.222 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-3*2fix :( 15.541) 0.064 1.003 14.346 122.364 390.467 505.185 -> 174.472 -> 1046.833 MByte/s p01 ring-1*6fix :( 15.655) 0.064 1.000 14.164 122.502 369.952 508.092 -> 163.272 -> 979.633 MByte/s p02 ring-1*6fix :( 15.619) 0.064 0.995 13.821 121.911 369.473 507.277 -> 161.933 -> 971.597 MByte/s p03 ring-1*6fix :( 15.571) 0.064 1.015 13.885 122.668 363.183 506.958 -> 159.474 -> 956.844 MByte/s p04 ring-1*6fix :( 15.750) 0.063 1.014 14.055 121.103 353.952 508.107 -> 161.848 -> 971.086 MByte/s p05 ring-1*6fix :( 15.717) 0.064 0.999 13.854 120.358 364.386 505.047 -> 160.288 -> 961.726 MByte/s p06 random-cyc-1dim :( 15.691) 0.064 1.005 13.766 119.592 365.650 507.109 -> 160.805 -> 964.832 MByte/s p07 random-cyc-1dim :( 15.603) 0.064 1.009 13.969 123.070 368.296 506.130 -> 161.330 -> 967.980 MByte/s p08 random-cyc-1dim :( 15.530) 0.064 1.002 13.777 121.940 373.646 508.879 -> 161.625 -> 969.750 MByte/s p09 random-cyc-1dim :( 15.714) 0.064 0.994 13.657 121.100 359.197 507.830 -> 161.667 -> 970.004 MByte/s p10 random-cyc-1dim :( 15.653) 0.064 1.012 14.046 120.360 361.225 507.186 -> 160.955 -> 965.728 MByte/s p11 random-cyc-1dim :( 16.168) 0.062 0.975 13.494 121.083 369.732 506.481 -> 160.918 -> 965.508 MByte/s p12 random-cyc-1dim :( 15.690) 0.064 1.003 13.783 120.638 378.855 506.802 -> 162.878 -> 977.266 MByte/s p13 random-cyc-1dim :( 15.687) 0.064 1.002 13.894 121.460 349.773 507.554 -> 161.697 -> 970.182 MByte/s p14 random-cyc-1dim :( 15.815) 0.063 1.008 13.660 122.345 402.043 507.126 -> 161.927 -> 971.559 MByte/s p15 random-cyc-1dim :( 15.625) 0.064 1.000 13.776 122.212 368.233 507.892 -> 160.899 -> 965.397 MByte/s p16 random-cyc-1dim :( 15.472) 0.065 1.001 13.967 120.896 350.827 506.163 -> 162.474 -> 974.845 MByte/s p17 random-cyc-1dim :( 15.623) 0.064 1.014 14.040 120.030 363.386 505.764 -> 159.437 -> 956.623 MByte/s p18 random-cyc-1dim :( 15.815) 0.063 1.006 13.710 121.392 361.999 508.200 -> 161.002 -> 966.011 MByte/s p19 random-cyc-1dim :( 15.703) 0.064 1.001 13.857 120.924 355.044 508.323 -> 161.717 -> 970.305 MByte/s p20 random-cyc-1dim :( 15.463) 0.065 1.003 13.964 121.554 353.258 507.018 -> 160.850 -> 965.101 MByte/s p21 random-cyc-1dim :( 15.576) 0.064 1.012 13.601 122.917 368.405 507.217 -> 161.585 -> 969.511 MByte/s p22 random-cyc-1dim :( 15.654) 0.064 1.009 13.896 120.435 371.774 507.111 -> 160.659 -> 963.954 MByte/s p23 random-cyc-1dim :( 15.792) 0.063 1.010 13.990 122.346 359.359 508.107 -> 160.885 -> 965.310 MByte/s p24 random-cyc-1dim :( 15.615) 0.064 1.015 13.954 120.415 367.300 507.018 -> 162.834 -> 977.001 MByte/s p25 random-cyc-1dim :( 15.600) 0.064 1.008 13.802 120.491 345.248 506.972 -> 161.718 -> 970.306 MByte/s p26 random-cyc-1dim :( 15.593) 0.064 1.000 14.023 120.196 355.938 506.972 -> 159.643 -> 957.858 MByte/s p27 random-cyc-1dim :( 15.794) 0.063 1.002 13.741 119.846 364.692 507.539 -> 160.545 -> 963.273 MByte/s p28 random-cyc-1dim :( 15.782) 0.063 0.988 13.715 120.358 355.823 506.726 -> 162.279 -> 973.672 MByte/s p29 random-cyc-1dim :( 15.487) 0.065 1.002 13.802 120.104 366.395 507.707 -> 161.794 -> 970.763 MByte/s p30 random-cyc-1dim :( 15.838) 0.063 0.994 14.149 121.295 367.180 505.475 -> 160.791 -> 964.746 MByte/s p31 random-cyc-1dim :( 15.510) 0.064 1.009 13.714 120.859 368.444 505.781 -> 159.893 -> 959.356 MByte/s p32 random-cyc-1dim :( 15.620) 0.064 1.003 14.193 120.227 353.682 506.572 -> 161.858 -> 971.146 MByte/s p33 random-cyc-1dim :( 15.788) 0.063 1.004 13.930 119.955 348.547 508.032 -> 161.286 -> 967.717 MByte/s p34 random-cyc-1dim :( 15.710) 0.064 1.003 13.806 120.084 346.796 506.268 -> 160.502 -> 963.009 MByte/s p35 random-cyc-1dim :( 15.731) 0.064 0.985 13.841 120.376 355.173 507.018 -> 160.003 -> 960.019 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 15.524) 0.064 1.017 13.813 120.065 366.150 507.339 -> 162.285 -> 973.707 MByte/s p37 best bi-section :( 11.931) 0.042 0.641 9.126 88.775 382.831 587.562 -> 165.280 -> 991.681 MByte/s p38 worst bi-section :( 11.913) 0.042 0.645 9.122 91.902 381.563 586.944 -> 164.575 -> 987.448 MByte/s p39 one PingPong Pair :( 11.361) 0.015 0.221 3.151 35.346 115.063 201.950 -> 53.870 -> 323.221 MByte/s p40 acyclic-2dim-all :( 13.771) 0.042 0.661 9.537 85.955 310.717 419.985 -> 128.694 -> 772.166 MByte/s p41 acyclic-3dim-all :( 13.733) 0.042 0.662 9.466 86.126 309.527 419.788 -> 129.223 -> 775.335 MByte/s p42 cyclic-2dim-x :( 15.624) 0.064 1.020 13.922 121.410 356.312 506.665 -> 162.071 -> 972.429 MByte/s p43 cyclic-2dim-y :( 15.590) 0.064 1.014 14.295 119.955 399.804 506.312 -> 174.655 -> 1047.930 MByte/s p44 cyclic-2dim-all :( 15.880) 0.063 0.989 13.906 116.348 368.832 509.141 -> 160.045 -> 960.269 MByte/s p45 cyclic-3dim-x :( 15.632) 0.064 1.004 14.018 120.414 334.482 507.032 -> 160.466 -> 962.797 MByte/s p46 cyclic-3dim-y :( 15.588) 0.064 1.012 14.311 122.308 391.970 506.159 -> 176.189 -> 1057.135 MByte/s p47 cyclic-3dim-all :( 15.892) 0.063 0.995 13.713 116.628 382.399 509.637 -> 160.824 -> 964.945 MByte/s log_avg of all rings : 0.064 1.004 14.020 121.815 368.404 506.776 || 163.473 -> 980.835 MByte/s log_avg of all random : 0.064 1.003 13.850 120.947 362.363 507.098 || 161.213 -> 967.278 MByte/s log_avg(ring,random) : 0.064 1.003 13.934 121.380 365.371 506.937 || 162.339 -> 974.033 MByte/s * size -> accumulated on all pr.: 0.383 6.021 83.606 728.279 2192.226 3041.624 || 974.033 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 974.033 MByte/s on 6 processes ( = 162.339 MByte/s * 6 processes) Ping-pong latency: 11.361 microsec Ping-pong bandwidth: 1211.698 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 6 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 17:51:39 1999 Total execution wall clock time = 74 seconds SECTION-BEFF-END b_eff = 974.033 MB/s = 162.339 * 6 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000