b_eff = 895.539 MB/s = 49.752 * 18 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 = 18 2-dim-paterns: size = 6 * 3 3-dim-paterns: size = 3 * 3 * 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-9*2fix 1=ring-4*4&+1 2=ring-2*9fix 3=ring-1*18fix 4=ring-1*18fix 5=ring-1*18fix 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: 99.275 sec SECTION-LOOP-END SECTION-LOOPLNGS-BEGIN method=0 | ------- repetition 0 --------- ------- repetition 1 --------- ------- repetition 2 --------- [sec] (= Sndrcv)| loop total per pattrn&mthd loop total per pattrn&mthd loop total per pattrn&mthd msg length| lng time minimum maximum lng time minimum maximum lng time minimum maximum ----------| ---- ------- ------- --------- ---- ------- ------- --------- ---- ------- ------- --------- 1 300 8.7e-01 8.7e-03 4.1e-02 130 3.8e-01 3.8e-03 1.8e-02 129 3.7e-01 3.7e-03 1.8e-02 2 150 4.4e-01 4.3e-03 2.1e-02 86 2.5e-01 2.5e-03 1.2e-02 86 2.5e-01 2.4e-03 1.2e-02 4 86 2.5e-01 2.5e-03 1.2e-02 87 2.6e-01 2.5e-03 1.2e-02 87 2.6e-01 2.6e-03 1.2e-02 8 85 2.5e-01 2.4e-03 1.2e-02 86 2.5e-01 2.5e-03 1.2e-02 84 2.4e-01 2.4e-03 1.2e-02 16 87 3.1e-01 2.7e-03 1.7e-02 86 2.6e-01 2.6e-03 1.3e-02 87 2.6e-01 2.6e-03 1.3e-02 32 80 3.0e-01 2.4e-03 1.4e-02 84 2.6e-01 2.5e-03 1.3e-02 85 2.6e-01 2.5e-03 1.3e-02 64 83 2.6e-01 2.5e-03 1.3e-02 84 2.6e-01 2.6e-03 1.3e-02 83 2.6e-01 2.5e-03 1.3e-02 128 81 2.6e-01 2.6e-03 1.3e-02 81 2.6e-01 2.7e-03 1.3e-02 83 2.7e-01 2.6e-03 1.3e-02 256 79 2.7e-01 2.6e-03 1.3e-02 76 2.6e-01 2.5e-03 1.2e-02 79 2.6e-01 2.5e-03 1.3e-02 512 75 2.6e-01 2.5e-03 1.3e-02 76 2.6e-01 2.7e-03 1.3e-02 78 2.6e-01 2.5e-03 1.3e-02 1024 74 2.6e-01 2.6e-03 1.3e-02 70 2.5e-01 2.4e-03 1.2e-02 77 2.7e-01 2.6e-03 1.3e-02 2048 72 4.6e-01 3.8e-03 1.9e-02 73 4.4e-01 3.8e-03 2.0e-02 75 4.5e-01 4.1e-03 2.0e-02 4096 47 3.7e-01 3.2e-03 1.6e-02 47 3.9e-01 3.2e-03 1.6e-02 46 3.5e-01 3.1e-03 1.6e-02 10624 28 5.0e-01 3.3e-03 2.2e-02 28 5.0e-01 3.1e-03 2.2e-02 28 5.0e-01 3.2e-03 2.2e-02 27554 16 5.2e-01 2.9e-03 2.2e-02 17 5.4e-01 2.9e-03 2.5e-02 16 5.1e-01 3.2e-03 2.3e-02 71468 10 7.5e-01 4.0e-03 3.1e-02 11 8.2e-01 4.2e-03 3.5e-02 9 6.6e-01 3.7e-03 2.9e-02 185364 4 5.7e-01 3.4e-03 2.5e-02 5 6.9e-01 3.9e-03 3.1e-02 4 5.6e-01 3.6e-03 2.6e-02 480774 2 6.6e-01 3.1e-03 3.0e-02 2 6.5e-01 3.2e-03 3.1e-02 2 6.5e-01 3.1e-03 2.8e-02 1246974 1 8.4e-01 3.6e-03 3.3e-02 1 7.8e-01 3.8e-03 4.1e-02 1 7.7e-01 3.6e-03 3.6e-02 3234251 1 7.9e-01 8.9e-03 8.5e-02 M 1 9.2e-01 9.0e-03 7.6e-02 M 1 9.8e-01 8.9e-03 5.8e-02 M 8388608 1 1.9e+00 2.2e-02 2.2e-01 R 1 2.3e+00 2.3e-02 1.9e-01 R 0 0.0e+00 1.0e+30 0.0e+00 R Explanation: M = only the best method is used R = only best method and only 2 repetitions method=1 | ------- repetition 0 --------- ------- repetition 1 --------- ------- repetition 2 --------- [sec] (=Alltoal)| loop total per pattrn&mthd loop total per pattrn&mthd loop total per pattrn&mthd msg length| lng time minimum maximum lng time minimum maximum lng time minimum maximum ----------| ---- ------- ------- --------- ---- ------- ------- --------- ---- ------- ------- --------- 1 300 7.0e+00 1.4e-01 1.8e-01 27 6.2e-01 1.3e-02 1.4e-02 7 1.6e-01 3.3e-03 3.7e-03 2 150 3.5e+00 7.0e-02 7.6e-02 13 3.0e-01 6.0e-03 6.6e-03 5 1.2e-01 2.3e-03 2.6e-03 4 75 1.7e+00 3.5e-02 3.8e-02 6 1.4e-01 2.8e-03 3.1e-03 5 1.2e-01 2.3e-03 2.6e-03 8 37 8.6e-01 1.7e-02 1.9e-02 5 1.2e-01 2.3e-03 2.6e-03 5 1.2e-01 2.3e-03 2.6e-03 16 18 4.5e-01 8.6e-03 1.1e-02 5 1.2e-01 2.4e-03 2.6e-03 5 1.2e-01 2.3e-03 2.6e-03 32 9 2.5e-01 4.2e-03 6.4e-03 5 1.2e-01 2.3e-03 2.6e-03 5 1.2e-01 2.3e-03 2.6e-03 64 5 1.2e-01 2.4e-03 2.7e-03 5 1.2e-01 2.4e-03 2.7e-03 5 1.2e-01 2.4e-03 2.8e-03 128 5 1.2e-01 2.4e-03 2.7e-03 5 1.2e-01 2.4e-03 2.7e-03 5 1.2e-01 2.4e-03 2.7e-03 256 5 1.2e-01 2.4e-03 2.7e-03 5 1.2e-01 2.4e-03 2.8e-03 5 1.2e-01 2.4e-03 2.7e-03 512 5 1.2e-01 2.4e-03 2.8e-03 5 1.2e-01 2.4e-03 2.7e-03 5 1.2e-01 2.4e-03 2.7e-03 1024 5 1.2e-01 2.4e-03 2.8e-03 5 1.2e-01 2.4e-03 2.9e-03 5 1.2e-01 2.4e-03 2.8e-03 2048 5 1.6e-01 2.5e-03 4.7e-03 5 1.6e-01 2.6e-03 3.8e-03 5 1.5e-01 2.5e-03 3.8e-03 4096 4 1.4e-01 2.1e-03 3.6e-03 4 1.4e-01 2.2e-03 3.8e-03 4 1.4e-01 2.1e-03 3.6e-03 10624 3 1.5e-01 2.1e-03 4.4e-03 3 1.6e-01 2.0e-03 6.6e-03 3 1.5e-01 2.0e-03 4.1e-03 27554 2 1.5e-01 2.0e-03 4.4e-03 2 1.4e-01 1.8e-03 4.2e-03 2 1.5e-01 1.9e-03 4.2e-03 71468 1 1.3e-01 1.1e-03 6.6e-03 2 2.6e-01 2.8e-03 8.6e-03 1 1.3e-01 1.1e-03 4.5e-03 185364 1 2.5e-01 1.9e-03 9.7e-03 1 2.4e-01 2.1e-03 6.9e-03 1 2.4e-01 2.5e-03 7.4e-03 480774 1 5.2e-01 4.4e-03 1.5e-02 1 5.3e-01 4.1e-03 1.7e-02 1 5.3e-01 4.1e-03 1.6e-02 1246974 1 1.1e+00 8.9e-03 4.1e-02 1 1.2e+00 8.5e-03 4.3e-02 1 1.1e+00 8.8e-03 4.1e-02 3234251 1 0.0e+00 0.0e+00 0.0e+00 M 1 0.0e+00 0.0e+00 0.0e+00 M 1 0.0e+00 0.0e+00 0.0e+00 M 8388608 1 0.0e+00 0.0e+00 0.0e+00 R 1 0.0e+00 0.0e+00 0.0e+00 R 0 0.0e+00 1.0e+30 0.0e+00 R Explanation: M = only the best method is used R = only best method and only 2 repetitions method=2 | ------- repetition 0 --------- ------- repetition 1 --------- ------- repetition 2 --------- [sec] (=non-blk)| loop total per pattrn&mthd loop total per pattrn&mthd loop total per pattrn&mthd msg length| lng time minimum maximum lng time minimum maximum lng time minimum maximum ----------| ---- ------- ------- --------- ---- ------- ------- --------- ---- ------- ------- --------- 1 300 1.5e+00 1.6e-02 6.7e-02 69 3.4e-01 3.7e-03 1.5e-02 69 3.4e-01 3.6e-03 1.5e-02 2 150 7.5e-01 8.2e-03 3.4e-02 46 2.2e-01 2.5e-03 1.0e-02 47 2.3e-01 2.5e-03 1.0e-02 4 75 3.8e-01 4.1e-03 1.7e-02 46 2.3e-01 2.5e-03 1.0e-02 46 2.3e-01 2.5e-03 1.0e-02 8 45 2.2e-01 2.4e-03 1.0e-02 46 2.2e-01 2.5e-03 1.0e-02 46 2.2e-01 2.5e-03 1.0e-02 16 46 2.5e-01 2.8e-03 1.1e-02 46 2.3e-01 2.6e-03 1.1e-02 46 2.3e-01 2.6e-03 1.1e-02 32 40 2.4e-01 2.4e-03 9.4e-03 45 2.3e-01 2.5e-03 1.0e-02 45 2.3e-01 2.5e-03 1.0e-02 64 41 2.2e-01 2.4e-03 9.7e-03 44 2.3e-01 2.5e-03 1.0e-02 44 2.3e-01 2.5e-03 1.0e-02 128 42 2.3e-01 2.5e-03 1.0e-02 43 2.3e-01 2.5e-03 1.0e-02 43 2.3e-01 2.5e-03 1.0e-02 256 42 2.4e-01 2.5e-03 1.1e-02 42 2.3e-01 2.4e-03 1.1e-02 42 2.2e-01 2.4e-03 1.0e-02 512 41 2.4e-01 2.5e-03 1.1e-02 43 2.4e-01 2.5e-03 1.1e-02 44 2.4e-01 2.5e-03 1.1e-02 1024 41 2.4e-01 2.5e-03 1.1e-02 42 2.4e-01 2.6e-03 1.1e-02 43 2.4e-01 2.5e-03 1.1e-02 2048 40 3.1e-01 3.1e-03 1.4e-02 40 3.0e-01 3.0e-03 1.4e-02 42 3.2e-01 3.2e-03 1.4e-02 4096 32 3.0e-01 3.1e-03 1.3e-02 32 3.1e-01 3.0e-03 1.4e-02 32 3.0e-01 3.1e-03 1.4e-02 10624 19 3.5e-01 2.9e-03 1.5e-02 20 3.5e-01 3.0e-03 1.6e-02 19 3.2e-01 2.7e-03 1.4e-02 27554 12 3.6e-01 2.7e-03 1.6e-02 13 3.7e-01 2.9e-03 1.7e-02 13 3.6e-01 3.0e-03 1.5e-02 71468 8 5.7e-01 3.2e-03 2.4e-02 8 5.7e-01 3.5e-03 2.4e-02 8 5.7e-01 3.3e-03 2.4e-02 185364 4 5.5e-01 4.7e-03 2.3e-02 4 5.4e-01 4.0e-03 2.3e-02 4 5.4e-01 3.8e-03 2.3e-02 480774 1 3.5e-01 2.0e-03 1.3e-02 1 3.2e-01 1.7e-03 1.3e-02 2 6.7e-01 4.1e-03 2.8e-02 1246974 1 7.9e-01 5.4e-03 4.2e-02 1 7.6e-01 5.2e-03 3.1e-02 1 7.8e-01 5.7e-03 3.5e-02 3234251 1 1.2e+00 2.5e-02 7.5e-02 M 1 9.7e-01 1.4e-02 8.9e-02 M 1 9.0e-01 2.5e-02 8.8e-02 M 8388608 1 2.8e+00 6.5e-02 1.4e-01 R 1 2.4e+00 3.3e-02 2.2e-01 R 0 0.0e+00 1.0e+30 0.0e+00 R Explanation: M = only the best method is used R = only best method and only 2 repetitions SECTION-LOOPLNGS-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 99.275 sec sum of max elapsed time per entries above = 99.141 sec difference to elapsed time = 0.134 sec = 0.1% sum based on fastest repetition = 85.630 sec difference to elapsed time = 13.645 sec = 13.7% CAUTION: A difference above is more than 5 %. There may be problems with the MPI implementation or processes weren't on dedicated processors SECTION-ELAPSED-END SECTION-PATTERN-BEGIN Pattern parameters: sendrecv total number messages/ messages/ unused best method calls of messages used node node&call nodes per repetition ---- ----------------- ----- ------------ --------- --------- ------ -------------- p00 ring-9*2fix 1 18 1.00 1.00 0 ( 2 0 0 ) p01 ring-4*4&+1 2 36 2.00 1.00 0 ( 0 2 2 ) p02 ring-2*9fix 2 36 2.00 1.00 0 ( 0 0 0 ) p03 ring-1*18fix 2 36 2.00 1.00 0 ( 2 0 0 ) p04 ring-1*18fix 2 36 2.00 1.00 0 ( 0 0 0 ) p05 ring-1*18fix 2 36 2.00 1.00 0 ( 0 0 0 ) p06 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 0 0 ) p07 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p08 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 0 0 ) p09 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p10 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 0 ) p11 random-cyc-1dim 2 36 2.00 1.00 0 ( 0 0 2 ) p12 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p13 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 0 0 ) p14 random-cyc-1dim 2 36 2.00 1.00 0 ( 0 2 0 ) p15 random-cyc-1dim 2 36 2.00 1.00 0 ( 0 0 2 ) p16 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 0 ) p17 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p18 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p19 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p20 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 0 0 ) p21 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 0 ) p22 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 0 ) p23 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 0 2 ) p24 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 0 ) p25 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 0 0 ) p26 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p27 random-cyc-1dim 2 36 2.00 1.00 0 ( 0 0 0 ) p28 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 0 ) p29 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p30 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p31 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p32 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p33 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 0 ) p34 random-cyc-1dim 2 36 2.00 1.00 0 ( 2 2 2 ) p35 random-cyc-1dim 2 36 2.00 1.00 0 ( 0 0 0 ) p36 worst-cyc-1dim 2 36 2.00 1.00 0 ( 0 0 0 ) p37 best bi-section 2 18 1.00 0.50 0 ( 0 0 0 ) p38 worst bi-section 2 18 1.00 0.50 0 ( 0 0 0 ) p39 one PingPong Pair 2 2 1.00 0.50 16 ( 0 0 0 ) p40 acyclic-2dim-all 4 54 3.00 0.75 0 ( 2 2 2 ) p41 acyclic-3dim-all 6 66 3.67 0.61 0 ( 2 0 2 ) p42 cyclic-2dim-x 2 36 2.00 1.00 0 ( 0 2 0 ) p43 cyclic-2dim-y 2 36 2.00 1.00 0 ( 0 0 2 ) p44 cyclic-2dim-all 4 72 4.00 1.00 0 ( 0 0 0 ) p45 cyclic-3dim-x 2 36 2.00 1.00 0 ( 0 0 0 ) p46 cyclic-3dim-y 2 36 2.00 1.00 0 ( 0 0 0 ) p47 cyclic-3dim-z 1 18 1.00 1.00 0 ( 0 2 2 ) p48 cyclic-3dim-all 5 90 5.00 1.00 0 ( 0 2 2 ) SECTION-PATTERN-END Printing accumulated bandwidth / number of processes = bandwidth per process (in MBytes/sec = 1e6 Bytes/sec) Additionally the accumulated value processes is printed in the last column Only the cyclic and random patterns are used to compute b_eff (except p00), the other patterns are only as information. SECTION-BY-METHODS-BEGIN 2nd analysis path, only as information, last row: for all mthd: logavg_pat ( avg_L ( max_rep ( b(L) ) ) ) || logavg_pat ( max_mthd ( avg_L ( max_rep ( b(L) ) ) ) ) pattern / methods: Sndrcv Alltoal non-blk -> best method -> accumulated p00 ring-9*2fix : 43.903 26.168 41.955 -> 43.903 -> 790.250 MByte/s p01 ring-4*4&+1 : 47.398 31.948 44.213 -> 47.398 -> 853.160 MByte/s p02 ring-2*9fix : 45.532 30.337 41.904 -> 45.532 -> 819.573 MByte/s p03 ring-1*18fix : 45.043 29.215 40.766 -> 45.043 -> 810.775 MByte/s p04 ring-1*18fix : 45.946 29.759 42.964 -> 45.946 -> 827.025 MByte/s p05 ring-1*18fix : 44.965 29.379 41.052 -> 44.965 -> 809.366 MByte/s p06 random-cyc-1dim : 44.781 28.972 42.859 -> 44.781 -> 806.066 MByte/s p07 random-cyc-1dim : 49.003 31.594 47.770 -> 49.003 -> 882.051 MByte/s p08 random-cyc-1dim : 66.138 39.649 62.637 -> 66.138 -> 1190.491 MByte/s p09 random-cyc-1dim : 46.597 30.029 44.318 -> 46.597 -> 838.747 MByte/s p10 random-cyc-1dim : 56.288 34.253 53.455 -> 56.288 -> 1013.189 MByte/s p11 random-cyc-1dim : 50.292 31.287 48.520 -> 50.292 -> 905.257 MByte/s p12 random-cyc-1dim : 50.327 31.908 48.277 -> 50.327 -> 905.884 MByte/s p13 random-cyc-1dim : 53.738 34.628 52.466 -> 53.738 -> 967.289 MByte/s p14 random-cyc-1dim : 49.016 31.450 49.142 -> 49.142 -> 884.559 MByte/s p15 random-cyc-1dim : 48.787 31.467 45.266 -> 48.787 -> 878.172 MByte/s p16 random-cyc-1dim : 58.554 35.938 56.623 -> 58.554 -> 1053.976 MByte/s p17 random-cyc-1dim : 45.566 29.921 44.158 -> 45.566 -> 820.183 MByte/s p18 random-cyc-1dim : 68.779 41.224 67.988 -> 68.779 -> 1238.015 MByte/s p19 random-cyc-1dim : 47.276 30.707 45.470 -> 47.276 -> 850.962 MByte/s p20 random-cyc-1dim : 55.125 34.201 51.474 -> 55.125 -> 992.254 MByte/s p21 random-cyc-1dim : 53.385 34.299 51.586 -> 53.385 -> 960.938 MByte/s p22 random-cyc-1dim : 59.069 36.681 58.410 -> 59.069 -> 1063.234 MByte/s p23 random-cyc-1dim : 54.968 34.125 53.227 -> 54.968 -> 989.432 MByte/s p24 random-cyc-1dim : 45.492 29.746 44.035 -> 45.492 -> 818.863 MByte/s p25 random-cyc-1dim : 61.268 37.596 58.075 -> 61.268 -> 1102.815 MByte/s p26 random-cyc-1dim : 50.559 31.586 48.029 -> 50.559 -> 910.069 MByte/s p27 random-cyc-1dim : 48.261 31.329 46.412 -> 48.261 -> 868.691 MByte/s p28 random-cyc-1dim : 59.771 36.806 55.888 -> 59.771 -> 1075.883 MByte/s p29 random-cyc-1dim : 56.282 34.575 53.015 -> 56.282 -> 1013.082 MByte/s p30 random-cyc-1dim : 53.035 33.649 50.317 -> 53.035 -> 954.629 MByte/s p31 random-cyc-1dim : 50.879 32.394 49.908 -> 50.879 -> 915.822 MByte/s p32 random-cyc-1dim : 49.749 31.812 47.306 -> 49.749 -> 895.477 MByte/s p33 random-cyc-1dim : 62.706 38.617 60.288 -> 62.706 -> 1128.705 MByte/s p34 random-cyc-1dim : 46.962 30.338 46.475 -> 46.962 -> 845.315 MByte/s p35 random-cyc-1dim : 62.544 38.558 60.389 -> 62.544 -> 1125.786 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 53.132 33.452 50.749 -> 53.132 -> 956.374 MByte/s p37 best bi-section : 46.115 28.503 44.239 -> 46.115 -> 830.065 MByte/s p38 worst bi-section : 49.464 36.739 51.226 -> 51.226 -> 922.064 MByte/s p39 one PingPong Pair : 11.030 3.922 3.922 -> 11.030 -> 198.533 MByte/s p40 acyclic-2dim-all : 64.220 47.784 67.349 -> 67.349 -> 1212.275 MByte/s p41 acyclic-3dim-all : 53.298 41.798 54.579 -> 54.579 -> 982.430 MByte/s p42 cyclic-2dim-x : 156.802 70.437 144.872 -> 156.802 -> 2822.435 MByte/s p43 cyclic-2dim-y : 45.478 30.418 41.613 -> 45.478 -> 818.602 MByte/s p44 cyclic-2dim-all : 69.279 47.805 68.422 -> 69.279 -> 1247.020 MByte/s p45 cyclic-3dim-x : 158.081 70.149 139.429 -> 158.081 -> 2845.458 MByte/s p46 cyclic-3dim-y : 45.382 31.230 41.202 -> 45.382 -> 816.872 MByte/s p47 cyclic-3dim-z : 44.043 26.380 41.987 -> 44.043 -> 792.768 MByte/s p48 cyclic-3dim-all : 61.633 48.738 60.538 -> 61.633 -> 1109.395 MByte/s log_avg of all rings : 45.452 29.416 42.126 || 45.452 -> 818.134 MByte/s log_avg of all random : 53.145 33.498 51.110 || 53.149 -> 956.691 MByte/s log_avg(ring,random) : 49.148 31.390 46.401 ||( 49.150 -> 884.704)MByte/s * size -> accumulated on all pr.: 884.666 565.029 835.220 ||(884.704)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-9*2fix : 43.081 42.818 43.610 -> 43.610 -> 784.983 MByte/s p01 ring-4*4&+1 : 43.792 44.991 47.508 -> 47.508 -> 855.152 MByte/s p02 ring-2*9fix : 42.204 44.897 44.440 -> 44.897 -> 808.152 MByte/s p03 ring-1*18fix : 39.595 43.476 44.652 -> 44.652 -> 803.734 MByte/s p04 ring-1*18fix : 45.111 44.233 45.470 -> 45.470 -> 818.457 MByte/s p05 ring-1*18fix : 43.977 44.674 44.547 -> 44.674 -> 804.123 MByte/s p06 random-cyc-1dim : 41.524 43.956 44.872 -> 44.872 -> 807.687 MByte/s p07 random-cyc-1dim : 44.664 48.889 49.805 -> 49.805 -> 896.488 MByte/s p08 random-cyc-1dim : 55.479 66.020 64.999 -> 66.020 -> 1188.364 MByte/s p09 random-cyc-1dim : 42.582 45.645 46.431 -> 46.431 -> 835.754 MByte/s p10 random-cyc-1dim : 49.900 53.533 55.673 -> 55.673 -> 1002.109 MByte/s p11 random-cyc-1dim : 45.706 50.024 49.786 -> 50.024 -> 900.425 MByte/s p12 random-cyc-1dim : 46.960 49.020 50.581 -> 50.581 -> 910.455 MByte/s p13 random-cyc-1dim : 50.477 53.374 54.907 -> 54.907 -> 988.335 MByte/s p14 random-cyc-1dim : 47.849 48.379 50.546 -> 50.546 -> 909.836 MByte/s p15 random-cyc-1dim : 45.539 48.172 47.850 -> 48.172 -> 867.097 MByte/s p16 random-cyc-1dim : 52.605 57.211 58.873 -> 58.873 -> 1059.722 MByte/s p17 random-cyc-1dim : 42.959 44.297 46.156 -> 46.156 -> 830.814 MByte/s p18 random-cyc-1dim : 65.868 68.592 70.339 -> 70.339 -> 1266.098 MByte/s p19 random-cyc-1dim : 45.580 46.757 47.019 -> 47.019 -> 846.335 MByte/s p20 random-cyc-1dim : 51.015 54.173 55.347 -> 55.347 -> 996.240 MByte/s p21 random-cyc-1dim : 50.280 53.729 53.573 -> 53.729 -> 967.116 MByte/s p22 random-cyc-1dim : 55.750 58.631 59.412 -> 59.412 -> 1069.412 MByte/s p23 random-cyc-1dim : 53.844 54.814 54.487 -> 54.814 -> 986.650 MByte/s p24 random-cyc-1dim : 43.433 45.076 44.915 -> 45.076 -> 811.363 MByte/s p25 random-cyc-1dim : 55.474 60.311 60.339 -> 60.339 -> 1086.108 MByte/s p26 random-cyc-1dim : 47.834 49.569 51.097 -> 51.097 -> 919.739 MByte/s p27 random-cyc-1dim : 46.723 47.415 47.974 -> 47.974 -> 863.538 MByte/s p28 random-cyc-1dim : 54.881 58.189 58.798 -> 58.798 -> 1058.365 MByte/s p29 random-cyc-1dim : 50.335 55.819 54.347 -> 55.819 -> 1004.737 MByte/s p30 random-cyc-1dim : 52.012 52.405 52.666 -> 52.666 -> 947.996 MByte/s p31 random-cyc-1dim : 50.477 51.215 51.639 -> 51.639 -> 929.508 MByte/s p32 random-cyc-1dim : 48.299 49.147 50.133 -> 50.133 -> 902.400 MByte/s p33 random-cyc-1dim : 57.596 61.574 62.629 -> 62.629 -> 1127.322 MByte/s p34 random-cyc-1dim : 47.064 47.576 47.870 -> 47.870 -> 861.667 MByte/s p35 random-cyc-1dim : 60.195 63.029 61.661 -> 63.029 -> 1134.530 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 51.050 51.688 53.404 -> 53.404 -> 961.273 MByte/s p37 best bi-section : 45.556 46.237 46.520 -> 46.520 -> 837.355 MByte/s p38 worst bi-section : 48.203 50.614 51.400 -> 51.400 -> 925.201 MByte/s p39 one PingPong Pair : 10.880 10.686 10.750 -> 10.880 -> 195.843 MByte/s p40 acyclic-2dim-all : 65.156 67.959 68.557 -> 68.557 -> 1234.023 MByte/s p41 acyclic-3dim-all : 52.298 53.407 55.321 -> 55.321 -> 995.771 MByte/s p42 cyclic-2dim-x : 155.214 149.244 155.240 -> 155.240 -> 2794.327 MByte/s p43 cyclic-2dim-y : 44.183 43.991 42.868 -> 44.183 -> 795.293 MByte/s p44 cyclic-2dim-all : 69.170 69.370 71.791 -> 71.791 -> 1292.231 MByte/s p45 cyclic-3dim-x : 152.889 156.382 153.793 -> 156.382 -> 2814.872 MByte/s p46 cyclic-3dim-y : 43.643 44.622 44.291 -> 44.622 -> 803.195 MByte/s p47 cyclic-3dim-z : 43.976 43.000 43.298 -> 43.976 -> 791.575 MByte/s p48 cyclic-3dim-all : 61.613 59.305 62.914 -> 62.914 -> 1132.447 MByte/s log_avg of all rings : 42.924 44.174 45.021 || 45.120 -> 812.153 MByte/s log_avg of all random : 49.808 52.517 53.142 || 53.298 -> 959.372 MByte/s log_avg(ring,random) : 46.238 48.165 48.913 ||( 49.039 -> 882.699)MByte/s * size -> accumulated on all pr.: 832.283 866.974 880.442 ||(882.699)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-9*2fix p00 method 0 =Sndrcv :( 29.411) 0.034 0.529 7.773 49.169 101.293 128.735 -> 43.903 -> 790.250 MByte/s p00 method 1 =Alltoal :(469.872) 0.002 0.034 0.519 6.533 56.478 128.735 -> 26.168 -> 471.032 MByte/s p00 method 2 =non-blk :( 56.246) 0.018 0.278 4.421 39.708 106.074 128.735 -> 41.955 -> 755.185 MByte/s p01 ring-4*4&+1 p01 method 0 =Sndrcv :( 28.777) 0.035 0.532 7.636 50.643 114.900 150.853 -> 47.398 -> 853.160 MByte/s p01 method 1 =Alltoal :(235.330) 0.004 0.067 1.025 11.093 71.515 150.853 -> 31.948 -> 575.061 MByte/s p01 method 2 =non-blk :( 49.804) 0.020 0.303 4.525 40.941 102.129 150.853 -> 44.213 -> 795.842 MByte/s p02 ring-2*9fix p02 method 0 =Sndrcv :( 29.038) 0.034 0.516 7.656 50.923 101.726 138.111 -> 45.532 -> 819.573 MByte/s p02 method 1 =Alltoal :(235.262) 0.004 0.067 1.020 10.512 63.656 138.111 -> 30.337 -> 546.073 MByte/s p02 method 2 =non-blk :( 50.218) 0.020 0.301 4.374 40.280 89.284 138.111 -> 41.904 -> 754.269 MByte/s p03 ring-1*18fix p03 method 0 =Sndrcv :( 29.623) 0.034 0.524 7.804 51.727 96.539 133.548 -> 45.043 -> 810.775 MByte/s p03 method 1 =Alltoal :(235.292) 0.004 0.066 0.977 9.735 61.799 133.548 -> 29.215 -> 525.878 MByte/s p03 method 2 =non-blk :( 50.572) 0.020 0.299 4.601 40.579 99.224 133.548 -> 40.766 -> 733.786 MByte/s p04 ring-1*18fix p04 method 0 =Sndrcv :( 29.335) 0.034 0.524 7.577 51.344 103.174 140.517 -> 45.946 -> 827.025 MByte/s p04 method 1 =Alltoal :(234.427) 0.004 0.066 1.022 9.787 60.676 140.517 -> 29.759 -> 535.654 MByte/s p04 method 2 =non-blk :( 50.623) 0.020 0.298 4.456 41.211 99.099 140.517 -> 42.964 -> 773.353 MByte/s p05 ring-1*18fix p05 method 0 =Sndrcv :( 29.292) 0.034 0.515 7.761 50.930 98.930 138.417 -> 44.965 -> 809.366 MByte/s p05 method 1 =Alltoal :(235.348) 0.004 0.067 1.022 9.945 61.277 138.417 -> 29.379 -> 528.826 MByte/s p05 method 2 =non-blk :( 51.051) 0.020 0.295 4.479 41.063 93.583 138.417 -> 41.052 -> 738.928 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 29.140) 0.034 0.530 7.687 50.057 100.078 131.990 -> 44.781 -> 806.066 MByte/s p06 method 1 =Alltoal :(236.281) 0.004 0.067 1.047 10.393 64.631 131.990 -> 28.972 -> 521.488 MByte/s p06 method 2 =non-blk :( 50.971) 0.020 0.301 4.606 41.011 105.381 131.990 -> 42.859 -> 771.470 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 28.910) 0.035 0.525 7.546 50.514 113.737 151.302 -> 49.003 -> 882.051 MByte/s p07 method 1 =Alltoal :(237.431) 0.004 0.067 1.041 10.948 68.972 151.302 -> 31.594 -> 568.691 MByte/s p07 method 2 =non-blk :( 50.762) 0.020 0.302 4.486 41.341 121.799 151.302 -> 47.770 -> 859.855 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 28.369) 0.035 0.542 8.122 54.892 157.999 213.587 -> 66.138 -> 1190.491 MByte/s p08 method 1 =Alltoal :(239.994) 0.004 0.066 1.009 12.061 75.921 213.587 -> 39.649 -> 713.681 MByte/s p08 method 2 =non-blk :( 48.102) 0.021 0.316 4.758 43.815 159.263 213.587 -> 62.637 -> 1127.464 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 28.873) 0.035 0.535 7.789 50.704 113.808 135.525 -> 46.597 -> 838.747 MByte/s p09 method 1 =Alltoal :(237.286) 0.004 0.066 1.043 10.915 69.437 135.525 -> 30.029 -> 540.515 MByte/s p09 method 2 =non-blk :( 50.204) 0.020 0.302 4.623 40.448 109.327 135.525 -> 44.318 -> 797.724 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 28.430) 0.035 0.521 7.765 52.461 130.999 172.019 -> 56.288 -> 1013.189 MByte/s p10 method 1 =Alltoal :(239.052) 0.004 0.066 1.016 11.445 75.245 172.019 -> 34.253 -> 616.562 MByte/s p10 method 2 =non-blk :( 49.638) 0.020 0.307 4.516 42.764 130.114 172.019 -> 53.455 -> 962.181 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 28.892) 0.035 0.518 7.863 51.179 118.006 155.391 -> 50.292 -> 905.257 MByte/s p11 method 1 =Alltoal :(239.202) 0.004 0.066 1.010 11.022 61.491 155.391 -> 31.287 -> 563.160 MByte/s p11 method 2 =non-blk :( 50.485) 0.020 0.300 4.642 42.275 119.589 155.391 -> 48.520 -> 873.358 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 28.843) 0.035 0.539 7.727 52.186 120.995 148.742 -> 50.327 -> 905.884 MByte/s p12 method 1 =Alltoal :(237.741) 0.004 0.067 1.039 11.358 69.204 148.742 -> 31.908 -> 574.337 MByte/s p12 method 2 =non-blk :( 49.094) 0.020 0.309 4.684 42.487 123.544 148.742 -> 48.277 -> 868.978 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 28.617) 0.035 0.524 7.709 52.440 120.147 167.898 -> 53.738 -> 967.289 MByte/s p13 method 1 =Alltoal :(244.851) 0.004 0.065 1.034 11.911 72.112 167.898 -> 34.628 -> 623.306 MByte/s p13 method 2 =non-blk :( 49.884) 0.020 0.305 4.603 42.112 131.967 167.898 -> 52.466 -> 944.382 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 28.719) 0.035 0.538 7.917 52.077 112.636 149.229 -> 49.016 -> 882.286 MByte/s p14 method 1 =Alltoal :(236.213) 0.004 0.067 1.020 11.033 66.284 149.229 -> 31.450 -> 566.093 MByte/s p14 method 2 =non-blk :( 49.812) 0.020 0.308 4.678 41.683 122.403 149.229 -> 49.142 -> 884.559 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 28.600) 0.035 0.529 7.639 51.991 110.428 152.365 -> 48.787 -> 878.172 MByte/s p15 method 1 =Alltoal :(243.000) 0.004 0.064 1.017 10.560 66.237 152.365 -> 31.467 -> 566.400 MByte/s p15 method 2 =non-blk :( 50.486) 0.020 0.303 4.544 41.902 109.456 152.365 -> 45.266 -> 814.785 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 28.388) 0.035 0.541 7.951 54.915 140.842 184.875 -> 58.554 -> 1053.976 MByte/s p16 method 1 =Alltoal :(240.999) 0.004 0.065 1.026 11.670 73.179 184.875 -> 35.938 -> 646.886 MByte/s p16 method 2 =non-blk :( 49.131) 0.020 0.303 4.594 44.244 143.430 184.875 -> 56.623 -> 1019.221 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 28.885) 0.035 0.527 7.839 50.318 106.908 134.648 -> 45.566 -> 820.183 MByte/s p17 method 1 =Alltoal :(245.214) 0.004 0.064 1.010 11.074 66.918 134.648 -> 29.921 -> 538.579 MByte/s p17 method 2 =non-blk :( 50.819) 0.020 0.304 4.642 41.696 102.945 134.648 -> 44.158 -> 794.840 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 28.415) 0.035 0.547 7.915 56.093 168.055 222.300 -> 68.779 -> 1238.015 MByte/s p18 method 1 =Alltoal :(242.130) 0.004 0.066 1.041 12.875 85.088 222.300 -> 41.224 -> 742.030 MByte/s p18 method 2 =non-blk :( 48.427) 0.021 0.320 4.758 43.815 173.968 222.300 -> 67.988 -> 1223.787 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 28.702) 0.035 0.523 7.734 51.186 114.000 144.040 -> 47.276 -> 850.962 MByte/s p19 method 1 =Alltoal :(247.163) 0.004 0.064 1.026 11.390 69.139 144.040 -> 30.707 -> 552.731 MByte/s p19 method 2 =non-blk :( 49.768) 0.020 0.298 4.534 41.380 116.986 144.040 -> 45.470 -> 818.460 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 28.388) 0.035 0.538 8.013 54.472 132.356 167.799 -> 55.125 -> 992.254 MByte/s p20 method 1 =Alltoal :(245.889) 0.004 0.064 0.987 11.587 72.337 167.799 -> 34.201 -> 615.622 MByte/s p20 method 2 =non-blk :( 48.210) 0.021 0.313 4.787 42.982 130.412 167.799 -> 51.474 -> 926.525 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 28.523) 0.035 0.522 7.721 52.941 121.010 169.407 -> 53.385 -> 960.938 MByte/s p21 method 1 =Alltoal :(242.347) 0.004 0.066 1.039 11.192 76.406 169.407 -> 34.299 -> 617.377 MByte/s p21 method 2 =non-blk :( 49.993) 0.020 0.305 4.611 42.590 131.266 169.407 -> 51.586 -> 928.556 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 28.400) 0.035 0.535 7.795 53.498 139.542 186.021 -> 59.069 -> 1063.234 MByte/s p22 method 1 =Alltoal :(246.925) 0.004 0.064 1.012 11.872 72.281 186.021 -> 36.681 -> 660.258 MByte/s p22 method 2 =non-blk :( 49.174) 0.020 0.304 4.555 42.674 142.029 186.021 -> 58.410 -> 1051.380 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 28.622) 0.035 0.541 7.965 53.543 132.602 173.182 -> 54.968 -> 989.432 MByte/s p23 method 1 =Alltoal :(242.148) 0.004 0.066 1.013 11.649 69.568 173.182 -> 34.125 -> 614.254 MByte/s p23 method 2 =non-blk :( 49.268) 0.020 0.314 4.700 42.806 134.370 173.182 -> 53.227 -> 958.085 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 29.037) 0.034 0.512 7.613 50.178 105.369 135.106 -> 45.492 -> 818.863 MByte/s p24 method 1 =Alltoal :(237.576) 0.004 0.067 1.045 10.570 67.026 135.106 -> 29.746 -> 535.426 MByte/s p24 method 2 =non-blk :( 50.312) 0.020 0.301 4.498 40.890 103.867 135.106 -> 44.035 -> 792.630 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 28.400) 0.035 0.544 8.037 55.197 139.032 199.850 -> 61.268 -> 1102.815 MByte/s p25 method 1 =Alltoal :(244.643) 0.004 0.064 0.982 11.698 71.903 199.850 -> 37.596 -> 676.728 MByte/s p25 method 2 =non-blk :( 49.798) 0.020 0.310 4.596 42.702 137.612 199.850 -> 58.075 -> 1045.343 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 28.566) 0.035 0.545 7.915 52.645 121.359 151.782 -> 50.559 -> 910.069 MByte/s p26 method 1 =Alltoal :(238.146) 0.004 0.067 1.039 11.378 68.922 151.782 -> 31.586 -> 568.553 MByte/s p26 method 2 =non-blk :( 49.514) 0.020 0.312 4.744 42.884 123.917 151.782 -> 48.029 -> 864.521 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 28.516) 0.035 0.529 7.746 51.166 112.930 148.676 -> 48.261 -> 868.691 MByte/s p27 method 1 =Alltoal :(241.242) 0.004 0.066 1.038 10.847 67.675 148.676 -> 31.329 -> 563.924 MByte/s p27 method 2 =non-blk :( 50.442) 0.020 0.298 4.551 41.199 107.817 148.676 -> 46.412 -> 835.415 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 28.244) 0.035 0.548 8.008 54.084 148.916 181.367 -> 59.771 -> 1075.883 MByte/s p28 method 1 =Alltoal :(247.110) 0.004 0.064 0.982 12.007 72.593 181.367 -> 36.806 -> 662.512 MByte/s p28 method 2 =non-blk :( 49.152) 0.020 0.308 4.592 43.038 142.001 181.367 -> 55.888 -> 1005.976 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 28.265) 0.035 0.543 7.926 54.377 131.897 173.254 -> 56.282 -> 1013.082 MByte/s p29 method 1 =Alltoal :(251.725) 0.004 0.064 1.003 11.855 74.955 173.254 -> 34.575 -> 622.349 MByte/s p29 method 2 =non-blk :( 48.377) 0.021 0.316 4.773 43.122 136.724 173.254 -> 53.015 -> 954.263 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 28.727) 0.035 0.531 7.731 53.320 127.380 165.054 -> 53.035 -> 954.629 MByte/s p30 method 1 =Alltoal :(238.282) 0.004 0.067 1.018 11.338 70.122 165.054 -> 33.649 -> 605.688 MByte/s p30 method 2 =non-blk :( 49.275) 0.020 0.301 4.525 42.918 125.150 165.054 -> 50.317 -> 905.711 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 28.595) 0.035 0.545 7.703 52.649 123.443 153.697 -> 50.879 -> 915.822 MByte/s p31 method 1 =Alltoal :(242.574) 0.004 0.063 1.019 11.330 74.533 153.697 -> 32.394 -> 583.101 MByte/s p31 method 2 =non-blk :( 49.783) 0.020 0.307 4.645 41.736 125.319 153.697 -> 49.908 -> 898.344 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 29.198) 0.034 0.517 7.579 51.869 120.186 150.352 -> 49.749 -> 895.477 MByte/s p32 method 1 =Alltoal :(238.572) 0.004 0.067 1.036 11.157 67.899 150.352 -> 31.812 -> 572.612 MByte/s p32 method 2 =non-blk :( 50.537) 0.020 0.305 4.678 37.838 120.660 150.352 -> 47.306 -> 851.504 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 28.853) 0.035 0.539 7.745 52.799 148.902 195.418 -> 62.706 -> 1128.705 MByte/s p33 method 1 =Alltoal :(247.785) 0.004 0.064 1.009 12.060 77.786 195.418 -> 38.617 -> 695.107 MByte/s p33 method 2 =non-blk :( 50.146) 0.020 0.303 4.567 42.254 146.795 195.418 -> 60.288 -> 1085.189 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 28.820) 0.035 0.532 7.953 52.316 108.814 144.165 -> 46.962 -> 845.315 MByte/s p34 method 1 =Alltoal :(242.140) 0.004 0.064 1.021 10.601 67.270 144.165 -> 30.338 -> 546.090 MByte/s p34 method 2 =non-blk :( 50.174) 0.020 0.305 4.656 41.218 111.473 144.165 -> 46.475 -> 836.551 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 28.178) 0.035 0.541 7.789 55.607 155.931 200.139 -> 62.544 -> 1125.786 MByte/s p35 method 1 =Alltoal :(245.907) 0.004 0.065 1.028 11.497 77.608 200.139 -> 38.558 -> 694.051 MByte/s p35 method 2 =non-blk :( 48.550) 0.021 0.315 4.757 44.401 146.374 200.139 -> 60.389 -> 1087.011 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 28.616) 0.035 0.535 7.792 53.520 131.885 159.059 -> 53.132 -> 956.374 MByte/s p36 method 1 =Alltoal :(233.492) 0.004 0.068 1.060 11.620 72.083 159.059 -> 33.452 -> 602.136 MByte/s p36 method 2 =non-blk :( 48.522) 0.021 0.307 4.606 43.258 128.702 159.059 -> 50.749 -> 913.491 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 25.340) 0.020 0.294 4.340 33.437 111.147 154.398 -> 46.115 -> 830.065 MByte/s p37 method 1 =Alltoal :(234.782) 0.002 0.032 0.522 6.520 55.599 154.398 -> 28.503 -> 513.046 MByte/s p37 method 2 =non-blk :( 27.430) 0.018 0.278 4.473 40.973 98.835 154.398 -> 44.239 -> 796.295 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 25.384) 0.020 0.296 4.343 34.457 130.890 159.576 -> 49.464 -> 890.355 MByte/s p38 method 1 =Alltoal :(233.216) 0.002 0.034 0.530 7.677 89.809 159.576 -> 36.739 -> 661.301 MByte/s p38 method 2 =non-blk :( 26.927) 0.019 0.283 4.465 42.104 129.763 159.576 -> 51.226 -> 922.064 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 23.185) 0.002 0.036 0.520 4.413 26.110 41.787 -> 11.030 -> 198.533 MByte/s p39 method 1 =Alltoal :(-------) 0.000 0.000 0.000 0.000 0.000 41.787 -> 3.922 -> 70.599 MByte/s p39 method 2 =non-blk :(-------) 0.000 0.000 0.000 0.000 0.000 41.787 -> 3.922 -> 70.599 MByte/s p40 acyclic-2dim-all p40 method 0 =Sndrcv :( 21.909) 0.034 0.524 7.667 54.382 155.402 204.955 -> 64.220 -> 1155.960 MByte/s p40 method 1 =Alltoal :(118.144) 0.006 0.097 1.527 16.406 112.661 204.955 -> 47.784 -> 860.104 MByte/s p40 method 2 =non-blk :( 39.373) 0.019 0.298 4.423 41.274 178.263 204.955 -> 67.349 -> 1212.275 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 22.893) 0.027 0.397 5.831 43.244 130.285 169.723 -> 53.298 -> 959.355 MByte/s p41 method 1 =Alltoal :( 79.498) 0.008 0.120 1.825 16.715 96.434 169.723 -> 41.798 -> 752.371 MByte/s p41 method 2 =non-blk :( 32.394) 0.019 0.293 4.276 40.160 147.043 169.723 -> 54.579 -> 982.430 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 15.892) 0.063 0.994 13.546 120.162 373.193 492.694 -> 156.802 -> 2822.435 MByte/s p42 method 1 =Alltoal :(232.569) 0.004 0.066 1.069 14.956 91.379 492.694 -> 70.437 -> 1267.866 MByte/s p42 method 2 =non-blk :( 35.378) 0.028 0.453 6.582 78.747 348.262 492.694 -> 144.872 -> 2607.689 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 28.838) 0.035 0.524 7.968 49.872 100.950 150.354 -> 45.478 -> 818.602 MByte/s p43 method 1 =Alltoal :(235.290) 0.004 0.065 1.008 10.601 65.628 150.354 -> 30.418 -> 547.523 MByte/s p43 method 2 =non-blk :( 49.087) 0.020 0.306 4.676 40.379 98.330 150.354 -> 41.613 -> 749.040 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 22.838) 0.044 0.667 9.764 69.864 159.719 211.773 -> 69.279 -> 1247.020 MByte/s p44 method 1 =Alltoal :(117.034) 0.009 0.132 2.030 20.340 108.894 211.773 -> 47.805 -> 860.484 MByte/s p44 method 2 =non-blk :( 43.112) 0.023 0.357 5.352 51.945 174.379 211.773 -> 68.422 -> 1231.605 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 15.767) 0.063 0.972 13.813 116.815 350.400 488.008 -> 158.081 -> 2845.458 MByte/s p45 method 1 =Alltoal :(233.855) 0.004 0.068 1.072 14.861 90.312 488.008 -> 70.149 -> 1262.674 MByte/s p45 method 2 =non-blk :( 35.203) 0.028 0.451 6.866 79.293 324.564 488.008 -> 139.429 -> 2509.727 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 29.097) 0.034 0.517 7.658 50.075 98.399 142.298 -> 45.382 -> 816.872 MByte/s p46 method 1 =Alltoal :(235.257) 0.004 0.067 1.026 11.108 75.428 142.298 -> 31.230 -> 562.140 MByte/s p46 method 2 =non-blk :( 49.493) 0.020 0.298 4.530 41.577 89.721 142.298 -> 41.202 -> 741.642 MByte/s p47 cyclic-3dim-z p47 method 0 =Sndrcv :( 29.107) 0.034 0.532 7.912 46.998 99.418 129.346 -> 44.043 -> 792.768 MByte/s p47 method 1 =Alltoal :(464.712) 0.002 0.034 0.528 6.473 57.601 129.346 -> 26.380 -> 474.843 MByte/s p47 method 2 =non-blk :( 53.755) 0.019 0.273 4.392 41.140 103.847 129.346 -> 41.987 -> 755.773 MByte/s p48 cyclic-3dim-all p48 method 0 =Sndrcv :( 24.319) 0.041 0.613 8.977 61.427 146.681 188.029 -> 61.633 -> 1109.395 MByte/s p48 method 1 =Alltoal :( 94.793) 0.011 0.164 2.483 22.985 121.423 188.029 -> 48.738 -> 877.289 MByte/s p48 method 2 =non-blk :( 44.180) 0.023 0.347 5.229 48.491 147.460 188.029 -> 60.538 -> 1089.684 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.034 0.523 7.701 50.783 102.602 138.199 || 45.452 -> 818.134 MByte/s - ring, method 1 = Alltoal: 0.004 0.059 0.906 9.471 62.407 138.199 || 29.416 -> 529.480 MByte/s - ring, method 2 = non-blk: 0.019 0.296 4.475 40.627 98.078 138.199 || 42.126 -> 758.274 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.035 0.533 7.813 52.696 125.547 163.696 || 53.145 -> 956.609 MByte/s - random, method 1 = Alltoal: 0.004 0.065 1.021 11.364 70.939 163.696 || 33.498 -> 602.964 MByte/s - random, method 2 = non-blk: 0.020 0.306 4.629 42.188 126.843 163.696 || 51.110 -> 919.974 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.035 0.528 7.757 51.731 113.496 150.408 || 49.148 -> 884.666 MByte/s - average, method 1 = Alltoal: 0.004 0.062 0.962 10.374 66.537 150.408 || 31.390 -> 565.029 MByte/s - average, method 2 = non-blk: 0.020 0.301 4.552 41.400 111.537 150.408 || 46.401 -> 835.220 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.622 9.510 139.624 931.156 2042.930 2707.348 || 884.666 MByte/s - accumulated, mthd 1 = Alltoal: 0.071 1.123 17.317 186.740 1197.660 2707.348 || 565.029 MByte/s - accumulated, mthd 2 = non-blk: 0.356 5.417 81.931 745.204 2007.664 2707.348 || 835.220 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 0.622 0.035 0.034 0.035 0.035 0.004 0.020 2 1.242 0.069 0.068 0.070 0.069 0.008 0.040 4 2.433 0.135 0.133 0.137 0.135 0.016 0.078 8 4.980 0.277 0.274 0.279 0.277 0.032 0.159 16 9.510 0.528 0.523 0.533 0.528 0.062 0.301 32 18.723 1.040 1.030 1.050 1.040 0.123 0.594 64 37.079 2.060 2.040 2.080 2.060 0.246 1.178 128 71.239 3.958 3.931 3.984 3.958 0.484 2.309 256 139.624 7.757 7.701 7.813 7.757 0.962 4.552 512 275.363 15.298 15.239 15.358 15.298 1.914 8.948 1024 533.425 29.635 29.524 29.746 29.635 3.789 17.554 2048 605.604 33.645 33.144 34.153 33.645 5.886 26.068 4096 931.156 51.731 50.783 52.696 51.731 10.374 41.400 10624 1008.883 56.049 51.199 61.358 54.510 18.409 55.065 27554 1500.679 83.371 74.594 93.180 76.963 33.890 83.371 71468 1529.684 84.982 75.778 95.305 83.986 48.538 82.776 185364 2077.193 115.400 103.867 128.212 113.496 66.537 111.537 480774 2124.418 118.023 104.309 133.541 117.110 81.668 108.074 1246974 2533.185 140.732 129.668 152.741 139.905 86.818 129.478 3234251 2664.233 148.013 138.709 157.941 148.013 148.013 148.013 8388608 2707.348 150.408 138.199 163.696 150.408 150.408 150.408 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-9*2fix :( 29.411) 0.034 0.529 7.773 49.169 106.074 128.735 -> 44.389 -> 798.997 MByte/s p01 ring-4*4&+1 :( 28.777) 0.035 0.532 7.636 50.643 114.900 150.853 -> 47.632 -> 857.372 MByte/s p02 ring-2*9fix :( 29.038) 0.034 0.516 7.656 50.923 101.726 138.111 -> 45.824 -> 824.829 MByte/s p03 ring-1*18fix :( 29.623) 0.034 0.524 7.804 51.727 99.224 133.548 -> 45.442 -> 817.960 MByte/s p04 ring-1*18fix :( 29.335) 0.034 0.524 7.577 51.344 103.174 140.517 -> 46.334 -> 834.008 MByte/s p05 ring-1*18fix :( 29.292) 0.034 0.515 7.761 50.930 98.930 138.417 -> 45.164 -> 812.956 MByte/s p06 random-cyc-1dim :( 29.140) 0.034 0.530 7.687 50.057 105.381 131.990 -> 45.321 -> 815.779 MByte/s p07 random-cyc-1dim :( 28.910) 0.035 0.525 7.546 50.514 121.799 151.302 -> 50.098 -> 901.759 MByte/s p08 random-cyc-1dim :( 28.369) 0.035 0.542 8.122 54.892 159.263 213.587 -> 66.689 -> 1200.397 MByte/s p09 random-cyc-1dim :( 28.873) 0.035 0.535 7.789 50.704 113.808 135.525 -> 46.951 -> 845.124 MByte/s p10 random-cyc-1dim :( 28.430) 0.035 0.521 7.765 52.461 130.999 172.019 -> 56.503 -> 1017.049 MByte/s p11 random-cyc-1dim :( 28.892) 0.035 0.518 7.863 51.179 119.589 155.391 -> 50.801 -> 914.425 MByte/s p12 random-cyc-1dim :( 28.843) 0.035 0.539 7.727 52.186 123.544 148.742 -> 50.950 -> 917.092 MByte/s p13 random-cyc-1dim :( 28.617) 0.035 0.524 7.709 52.440 131.967 167.898 -> 55.379 -> 996.818 MByte/s p14 random-cyc-1dim :( 28.719) 0.035 0.538 7.917 52.077 122.403 149.229 -> 51.189 -> 921.400 MByte/s p15 random-cyc-1dim :( 28.600) 0.035 0.529 7.639 51.991 110.428 152.365 -> 49.168 -> 885.030 MByte/s p16 random-cyc-1dim :( 28.388) 0.035 0.541 7.951 54.915 143.430 184.875 -> 59.775 -> 1075.948 MByte/s p17 random-cyc-1dim :( 28.885) 0.035 0.527 7.839 50.318 106.908 134.648 -> 46.233 -> 832.197 MByte/s p18 random-cyc-1dim :( 28.415) 0.035 0.547 7.915 56.093 173.968 222.300 -> 70.744 -> 1273.388 MByte/s p19 random-cyc-1dim :( 28.702) 0.035 0.523 7.734 51.186 116.986 144.040 -> 47.845 -> 861.211 MByte/s p20 random-cyc-1dim :( 28.388) 0.035 0.538 8.013 54.472 132.356 167.799 -> 55.849 -> 1005.279 MByte/s p21 random-cyc-1dim :( 28.523) 0.035 0.522 7.721 52.941 131.266 169.407 -> 54.783 -> 986.088 MByte/s p22 random-cyc-1dim :( 28.400) 0.035 0.535 7.795 53.498 142.029 186.021 -> 60.484 -> 1088.720 MByte/s p23 random-cyc-1dim :( 28.622) 0.035 0.541 7.965 53.543 134.370 173.182 -> 55.910 -> 1006.385 MByte/s p24 random-cyc-1dim :( 29.037) 0.034 0.512 7.613 50.178 105.369 135.106 -> 46.438 -> 835.887 MByte/s p25 random-cyc-1dim :( 28.400) 0.035 0.544 8.037 55.197 139.032 199.850 -> 62.011 -> 1116.203 MByte/s p26 random-cyc-1dim :( 28.566) 0.035 0.545 7.915 52.645 123.917 151.782 -> 51.228 -> 922.103 MByte/s p27 random-cyc-1dim :( 28.516) 0.035 0.529 7.746 51.166 112.930 148.676 -> 48.732 -> 877.167 MByte/s p28 random-cyc-1dim :( 28.244) 0.035 0.548 8.008 54.084 148.916 181.367 -> 60.623 -> 1091.214 MByte/s p29 random-cyc-1dim :( 28.265) 0.035 0.543 7.926 54.377 136.724 173.254 -> 57.221 -> 1029.977 MByte/s p30 random-cyc-1dim :( 28.727) 0.035 0.531 7.731 53.320 127.380 165.054 -> 53.680 -> 966.232 MByte/s p31 random-cyc-1dim :( 28.595) 0.035 0.545 7.703 52.649 125.319 153.697 -> 52.396 -> 943.127 MByte/s p32 random-cyc-1dim :( 29.198) 0.034 0.517 7.579 51.869 120.660 150.352 -> 50.567 -> 910.199 MByte/s p33 random-cyc-1dim :( 28.853) 0.035 0.539 7.745 52.799 148.902 195.418 -> 63.115 -> 1136.071 MByte/s p34 random-cyc-1dim :( 28.820) 0.035 0.532 7.953 52.316 111.473 144.165 -> 48.525 -> 873.452 MByte/s p35 random-cyc-1dim :( 28.178) 0.035 0.541 7.789 55.607 155.931 200.139 -> 63.653 -> 1145.756 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 28.616) 0.035 0.535 7.792 53.520 131.885 159.059 -> 54.039 -> 972.709 MByte/s p37 best bi-section :( 25.340) 0.020 0.294 4.473 40.973 111.147 154.398 -> 47.429 -> 853.717 MByte/s p38 worst bi-section :( 25.384) 0.020 0.296 4.465 42.104 130.890 159.576 -> 51.744 -> 931.396 MByte/s p39 one PingPong Pair :( 23.185) 0.002 0.036 0.520 4.413 26.110 41.787 -> 11.030 -> 198.533 MByte/s p40 acyclic-2dim-all :( 21.909) 0.034 0.524 7.667 54.382 178.263 204.955 -> 69.677 -> 1254.183 MByte/s p41 acyclic-3dim-all :( 22.893) 0.027 0.397 5.831 43.244 147.043 169.723 -> 55.762 -> 1003.714 MByte/s p42 cyclic-2dim-x :( 15.892) 0.063 0.994 13.546 120.162 373.193 492.694 -> 156.802 -> 2822.435 MByte/s p43 cyclic-2dim-y :( 28.838) 0.035 0.524 7.968 49.872 100.950 150.354 -> 45.691 -> 822.441 MByte/s p44 cyclic-2dim-all :( 22.838) 0.044 0.667 9.764 69.864 174.379 211.773 -> 72.135 -> 1298.434 MByte/s p45 cyclic-3dim-x :( 15.767) 0.063 0.972 13.813 116.815 350.400 488.008 -> 158.081 -> 2845.458 MByte/s p46 cyclic-3dim-y :( 29.097) 0.034 0.517 7.658 50.075 98.399 142.298 -> 45.574 -> 820.332 MByte/s p47 cyclic-3dim-z :( 29.107) 0.034 0.532 7.912 46.998 103.847 129.346 -> 44.494 -> 800.896 MByte/s p48 cyclic-3dim-all :( 24.319) 0.041 0.613 8.977 61.427 147.460 188.029 -> 63.137 -> 1136.470 MByte/s log_avg of all rings : 0.034 0.523 7.701 50.783 103.867 138.199 || 45.786 -> 824.153 MByte/s log_avg of all random : 0.035 0.533 7.813 52.696 128.212 163.696 || 54.062 -> 973.107 MByte/s log_avg(ring,random) : 0.035 0.528 7.757 51.731 115.400 150.408 || 49.752 -> 895.539 MByte/s * size -> accumulated on all pr.: 0.622 9.510 139.624 931.156 2077.193 2707.348 || 895.539 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 895.539 MByte/s on 18 processes ( = 49.752 MByte/s * 18 processes) Ping-pong latency: 23.185 microsec Ping-pong bandwidth: 752.172 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 18 nodes, 1024 MB/node system name : HI-UX/MPP hostname : himiko OS release : 03-00 OS version : ad2b0 machine : SR8000 Date of measurement: Mon Nov 29 13:56:35 1999 Total execution wall clock time = 101 seconds SECTION-BEFF-END b_eff = 895.539 MB/s = 49.752 * 18 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000