b_eff = 410.553 MB/s = 205.276 * 2 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 = 2 2-dim-paterns: size = 2 * 1 3-dim-paterns: size = 2 * 1 * 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-1*2fix 1=ring-1*2fix 2=ring-1*2fix 3=ring-1*2fix 4=ring-1*2fix 5=ring-1*2fix 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-all 44=cyclic-3dim-x 45=cyclic-3dim-all SECTION-HEAD-END SECTION-LOOP-BEGIN measurment loop: 34.904 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 2.2e-01 4.5e-03 7.0e-03 246 1.8e-01 3.7e-03 5.7e-03 246 1.8e-01 3.7e-03 5.7e-03 2 166 1.2e-01 2.5e-03 3.9e-03 166 1.2e-01 2.5e-03 3.9e-03 165 1.2e-01 2.5e-03 3.9e-03 4 164 1.2e-01 2.5e-03 3.9e-03 164 1.2e-01 2.5e-03 3.9e-03 164 1.2e-01 2.5e-03 3.9e-03 8 163 1.2e-01 2.5e-03 3.9e-03 162 1.2e-01 2.5e-03 3.8e-03 163 1.2e-01 2.5e-03 3.9e-03 16 164 1.2e-01 2.5e-03 4.0e-03 164 1.2e-01 2.5e-03 4.1e-03 164 1.2e-01 2.5e-03 4.0e-03 32 162 1.3e-01 2.5e-03 4.2e-03 162 1.3e-01 2.5e-03 4.2e-03 162 1.3e-01 2.5e-03 4.2e-03 64 160 1.3e-01 2.6e-03 4.3e-03 159 1.3e-01 2.6e-03 4.3e-03 160 1.3e-01 2.6e-03 4.3e-03 128 154 1.3e-01 2.6e-03 4.4e-03 154 1.3e-01 2.7e-03 4.5e-03 154 1.3e-01 2.6e-03 4.5e-03 256 145 1.2e-01 2.5e-03 4.0e-03 145 1.2e-01 2.4e-03 4.0e-03 145 1.2e-01 2.5e-03 4.0e-03 512 147 1.3e-01 2.6e-03 4.2e-03 149 1.3e-01 2.6e-03 4.3e-03 146 1.3e-01 2.5e-03 4.2e-03 1024 143 1.3e-01 2.6e-03 4.3e-03 143 1.3e-01 2.6e-03 4.3e-03 143 1.3e-01 2.6e-03 4.3e-03 2048 136 1.6e-01 3.3e-03 4.6e-03 136 1.6e-01 3.3e-03 4.6e-03 137 1.6e-01 3.3e-03 4.7e-03 4096 102 1.5e-01 3.1e-03 4.2e-03 102 1.5e-01 3.1e-03 4.2e-03 102 1.5e-01 3.1e-03 4.2e-03 10624 62 1.4e-01 2.9e-03 4.7e-03 63 1.5e-01 2.9e-03 4.7e-03 63 1.5e-01 2.9e-03 4.8e-03 27554 41 1.4e-01 2.9e-03 5.0e-03 41 1.5e-01 2.8e-03 5.0e-03 41 1.5e-01 2.9e-03 5.0e-03 71468 27 2.0e-01 3.9e-03 5.6e-03 27 2.0e-01 4.0e-03 5.4e-03 27 2.0e-01 3.9e-03 5.6e-03 185364 13 2.1e-01 4.1e-03 6.0e-03 13 2.2e-01 4.1e-03 6.3e-03 13 2.2e-01 4.2e-03 6.1e-03 480774 6 2.4e-01 4.6e-03 7.7e-03 6 2.3e-01 4.6e-03 6.7e-03 5 1.9e-01 3.9e-03 6.0e-03 1246974 2 2.0e-01 4.0e-03 6.4e-03 2 2.1e-01 4.0e-03 8.4e-03 2 2.0e-01 4.0e-03 6.9e-03 3234251 1 2.9e-01 5.9e-03 1.2e-02 1 3.2e-01 5.7e-03 1.2e-02 1 2.7e-01 5.7e-03 6.1e-03 8388608 1 7.0e-01 1.4e-02 1.8e-02 1 6.9e-01 1.4e-02 1.5e-02 1 7.1e-01 1.4e-02 2.9e-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 4.2e-01 9.2e-03 9.5e-03 121 1.7e-01 3.7e-03 3.8e-03 120 1.7e-01 3.7e-03 3.8e-03 2 150 2.1e-01 4.6e-03 4.8e-03 81 1.1e-01 2.5e-03 2.6e-03 81 1.1e-01 2.5e-03 2.6e-03 4 81 1.1e-01 2.5e-03 2.6e-03 81 1.1e-01 2.5e-03 2.6e-03 80 1.1e-01 2.5e-03 2.6e-03 8 80 1.1e-01 2.5e-03 2.5e-03 80 1.1e-01 2.5e-03 2.5e-03 80 1.1e-01 2.5e-03 2.5e-03 16 81 1.1e-01 2.5e-03 2.6e-03 80 1.1e-01 2.5e-03 2.6e-03 80 1.1e-01 2.5e-03 2.5e-03 32 80 1.1e-01 2.5e-03 2.6e-03 80 1.1e-01 2.5e-03 2.6e-03 80 1.1e-01 2.5e-03 2.6e-03 64 79 1.1e-01 2.5e-03 2.6e-03 79 1.1e-01 2.5e-03 2.6e-03 79 1.1e-01 2.5e-03 2.6e-03 128 78 1.2e-01 2.6e-03 2.7e-03 78 1.2e-01 2.6e-03 2.7e-03 78 1.2e-01 2.6e-03 2.7e-03 256 75 1.1e-01 2.5e-03 2.5e-03 75 1.1e-01 2.4e-03 2.5e-03 75 1.1e-01 2.5e-03 2.6e-03 512 76 1.1e-01 2.5e-03 2.7e-03 77 1.2e-01 2.6e-03 2.7e-03 76 1.1e-01 2.5e-03 2.6e-03 1024 75 1.2e-01 2.6e-03 2.7e-03 75 1.2e-01 2.5e-03 2.6e-03 75 1.2e-01 2.5e-03 2.7e-03 2048 73 1.3e-01 2.9e-03 3.0e-03 73 1.3e-01 2.9e-03 3.0e-03 73 1.3e-01 2.9e-03 3.0e-03 4096 62 1.3e-01 2.9e-03 3.0e-03 62 1.3e-01 2.9e-03 3.0e-03 62 1.3e-01 2.9e-03 3.0e-03 10624 41 1.2e-01 2.6e-03 2.8e-03 41 1.2e-01 2.6e-03 2.8e-03 41 1.2e-01 2.6e-03 2.8e-03 27554 30 1.2e-01 2.6e-03 2.9e-03 30 1.2e-01 2.6e-03 2.9e-03 30 1.2e-01 2.6e-03 2.9e-03 71468 22 1.7e-01 3.6e-03 4.3e-03 22 1.7e-01 3.6e-03 4.1e-03 22 1.7e-01 3.6e-03 4.2e-03 185364 11 1.8e-01 3.7e-03 4.5e-03 11 1.8e-01 3.7e-03 4.6e-03 11 1.8e-01 3.7e-03 4.7e-03 480774 5 1.9e-01 4.0e-03 5.6e-03 5 1.9e-01 4.0e-03 7.0e-03 5 1.9e-01 4.0e-03 6.7e-03 1246974 2 2.0e-01 4.1e-03 6.3e-03 2 1.9e-01 4.0e-03 6.1e-03 2 1.9e-01 4.0e-03 6.3e-03 3234251 1 2.7e-01 5.8e-03 6.2e-03 1 2.7e-01 5.7e-03 1.2e-02 1 2.7e-01 5.7e-03 1.0e-02 8388608 1 6.9e-01 1.5e-02 1.8e-02 1 6.8e-01 1.5e-02 1.5e-02 1 7.0e-01 1.5e-02 2.9e-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 4.8e-01 1.0e-02 1.1e-02 106 1.7e-01 3.6e-03 3.8e-03 108 1.7e-01 3.7e-03 3.9e-03 2 150 2.4e-01 5.2e-03 5.5e-03 72 1.2e-01 2.5e-03 2.6e-03 72 1.2e-01 2.5e-03 2.6e-03 4 75 1.2e-01 2.6e-03 2.8e-03 72 1.2e-01 2.5e-03 2.6e-03 72 1.2e-01 2.5e-03 2.6e-03 8 71 1.2e-01 2.5e-03 2.6e-03 71 1.1e-01 2.5e-03 2.6e-03 71 1.1e-01 2.5e-03 2.6e-03 16 71 1.2e-01 2.5e-03 2.6e-03 72 1.2e-01 2.5e-03 2.6e-03 72 1.2e-01 2.5e-03 2.6e-03 32 71 1.2e-01 2.5e-03 2.7e-03 71 1.2e-01 2.5e-03 2.6e-03 71 1.2e-01 2.5e-03 2.6e-03 64 70 1.2e-01 2.5e-03 2.7e-03 70 1.2e-01 2.5e-03 2.6e-03 70 1.2e-01 2.5e-03 2.6e-03 128 69 1.2e-01 2.6e-03 2.7e-03 69 1.2e-01 2.6e-03 2.7e-03 69 1.2e-01 2.6e-03 2.7e-03 256 67 1.1e-01 2.5e-03 2.6e-03 67 1.1e-01 2.4e-03 2.6e-03 67 1.1e-01 2.5e-03 2.6e-03 512 68 1.2e-01 2.5e-03 2.7e-03 68 1.2e-01 2.5e-03 2.7e-03 68 1.2e-01 2.5e-03 2.7e-03 1024 67 1.2e-01 2.5e-03 2.7e-03 67 1.2e-01 2.5e-03 2.7e-03 67 1.2e-01 2.5e-03 2.7e-03 2048 66 1.3e-01 2.8e-03 3.0e-03 66 1.3e-01 2.8e-03 3.0e-03 66 1.3e-01 2.8e-03 3.0e-03 4096 58 1.3e-01 2.9e-03 3.0e-03 58 1.3e-01 2.8e-03 3.0e-03 58 1.3e-01 2.9e-03 3.0e-03 10624 39 1.2e-01 2.6e-03 3.0e-03 39 1.2e-01 2.6e-03 3.1e-03 39 1.3e-01 2.6e-03 3.1e-03 27554 29 1.3e-01 2.6e-03 3.5e-03 29 1.3e-01 2.5e-03 3.6e-03 29 1.3e-01 2.6e-03 3.6e-03 71468 21 1.8e-01 3.5e-03 4.8e-03 22 1.9e-01 3.7e-03 4.9e-03 21 1.8e-01 3.5e-03 4.7e-03 185364 11 1.9e-01 3.7e-03 4.9e-03 11 2.0e-01 3.7e-03 5.7e-03 11 2.0e-01 3.7e-03 5.5e-03 480774 5 1.9e-01 4.0e-03 6.2e-03 5 2.0e-01 4.0e-03 6.9e-03 5 2.0e-01 4.0e-03 6.1e-03 1246974 2 2.0e-01 4.1e-03 7.9e-03 2 2.0e-01 4.0e-03 6.5e-03 2 2.0e-01 4.1e-03 7.3e-03 3234251 1 3.1e-01 5.9e-03 1.2e-02 1 2.7e-01 5.9e-03 6.1e-03 1 3.1e-01 5.9e-03 1.2e-02 8388608 1 6.9e-01 1.5e-02 1.8e-02 1 6.9e-01 1.5e-02 1.5e-02 1 7.0e-01 1.5e-02 2.9e-02 SECTION-LOOPLNGS-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 34.904 sec sum of max elapsed time per entries above = 34.679 sec difference to elapsed time = 0.225 sec = 0.6% sum based on fastest repetition = 32.964 sec difference to elapsed time = 1.940 sec = 5.6% 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-1*2fix 1 2 1.00 1.00 0 ( -1 -1 -1 ) p01 ring-1*2fix 1 2 1.00 1.00 0 ( -1 -1 -1 ) p02 ring-1*2fix 1 2 1.00 1.00 0 ( -1 -1 -1 ) p03 ring-1*2fix 1 2 1.00 1.00 0 ( -1 -1 -1 ) p04 ring-1*2fix 1 2 1.00 1.00 0 ( -1 -1 -1 ) p05 ring-1*2fix 1 2 1.00 1.00 0 ( -1 -1 -1 ) p06 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p07 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p08 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p09 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p10 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p11 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p12 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p13 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p14 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p15 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p16 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p17 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p18 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p19 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p20 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p21 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p22 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p23 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p24 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p25 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p26 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p27 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p28 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p29 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p30 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p31 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p32 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p33 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p34 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p35 random-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p36 worst-cyc-1dim 1 2 1.00 1.00 0 ( -1 -1 -1 ) p37 best bi-section 2 2 1.00 0.50 0 ( -1 -1 -1 ) p38 worst bi-section 2 2 1.00 0.50 0 ( -1 -1 -1 ) p39 one PingPong Pair 2 2 1.00 0.50 0 ( -1 -1 -1 ) p40 acyclic-2dim-all 2 2 1.00 0.50 0 ( -1 -1 -1 ) p41 acyclic-3dim-all 2 2 1.00 0.50 0 ( -1 -1 -1 ) p42 cyclic-2dim-x 1 2 1.00 1.00 0 ( -1 -1 -1 ) p43 cyclic-2dim-all 1 2 1.00 1.00 0 ( -1 -1 -1 ) p44 cyclic-3dim-x 1 2 1.00 1.00 0 ( -1 -1 -1 ) p45 cyclic-3dim-all 1 2 1.00 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-1*2fix : 203.732 187.567 179.339 -> 203.732 -> 407.464 MByte/s p01 ring-1*2fix : 204.498 186.595 185.180 -> 204.498 -> 408.996 MByte/s p02 ring-1*2fix : 204.485 187.613 177.975 -> 204.485 -> 408.970 MByte/s p03 ring-1*2fix : 205.547 187.071 181.049 -> 205.547 -> 411.093 MByte/s p04 ring-1*2fix : 204.673 186.704 180.537 -> 204.673 -> 409.347 MByte/s p05 ring-1*2fix : 205.808 187.846 180.203 -> 205.808 -> 411.615 MByte/s p06 random-cyc-1dim : 202.552 186.310 179.696 -> 202.552 -> 405.104 MByte/s p07 random-cyc-1dim : 205.169 188.653 183.513 -> 205.169 -> 410.338 MByte/s p08 random-cyc-1dim : 204.418 187.944 183.039 -> 204.418 -> 408.837 MByte/s p09 random-cyc-1dim : 204.034 188.722 182.861 -> 204.034 -> 408.067 MByte/s p10 random-cyc-1dim : 205.921 186.267 182.212 -> 205.921 -> 411.843 MByte/s p11 random-cyc-1dim : 203.759 188.656 179.262 -> 203.759 -> 407.518 MByte/s p12 random-cyc-1dim : 203.492 186.650 183.096 -> 203.492 -> 406.985 MByte/s p13 random-cyc-1dim : 201.965 186.962 176.574 -> 201.965 -> 403.929 MByte/s p14 random-cyc-1dim : 204.657 185.174 179.174 -> 204.657 -> 409.313 MByte/s p15 random-cyc-1dim : 205.451 188.097 183.142 -> 205.451 -> 410.902 MByte/s p16 random-cyc-1dim : 205.309 186.804 183.742 -> 205.309 -> 410.618 MByte/s p17 random-cyc-1dim : 204.793 186.605 181.745 -> 204.793 -> 409.587 MByte/s p18 random-cyc-1dim : 203.427 187.433 179.830 -> 203.427 -> 406.855 MByte/s p19 random-cyc-1dim : 206.477 187.339 177.542 -> 206.477 -> 412.955 MByte/s p20 random-cyc-1dim : 201.759 188.581 183.710 -> 201.759 -> 403.517 MByte/s p21 random-cyc-1dim : 204.811 186.247 179.641 -> 204.811 -> 409.623 MByte/s p22 random-cyc-1dim : 205.496 186.893 179.320 -> 205.496 -> 410.993 MByte/s p23 random-cyc-1dim : 203.091 188.202 181.589 -> 203.091 -> 406.183 MByte/s p24 random-cyc-1dim : 203.392 187.569 183.781 -> 203.392 -> 406.784 MByte/s p25 random-cyc-1dim : 205.608 186.547 181.974 -> 205.608 -> 411.215 MByte/s p26 random-cyc-1dim : 206.179 187.235 178.728 -> 206.179 -> 412.358 MByte/s p27 random-cyc-1dim : 206.373 187.092 183.753 -> 206.373 -> 412.745 MByte/s p28 random-cyc-1dim : 205.073 187.906 184.942 -> 205.073 -> 410.147 MByte/s p29 random-cyc-1dim : 205.241 187.850 184.108 -> 205.241 -> 410.481 MByte/s p30 random-cyc-1dim : 205.636 187.392 184.476 -> 205.636 -> 411.272 MByte/s p31 random-cyc-1dim : 204.768 187.298 182.431 -> 204.768 -> 409.536 MByte/s p32 random-cyc-1dim : 202.440 186.689 183.518 -> 202.440 -> 404.881 MByte/s p33 random-cyc-1dim : 201.930 187.592 184.357 -> 201.930 -> 403.859 MByte/s p34 random-cyc-1dim : 205.599 188.051 179.451 -> 205.599 -> 411.199 MByte/s p35 random-cyc-1dim : 204.689 186.536 185.489 -> 204.689 -> 409.377 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 204.347 186.621 182.294 -> 204.347 -> 408.695 MByte/s p37 best bi-section : 173.676 183.913 180.517 -> 183.913 -> 367.826 MByte/s p38 worst bi-section : 173.792 186.025 180.462 -> 186.025 -> 372.050 MByte/s p39 one PingPong Pair : 173.964 0.000 0.000 -> 173.964 -> 347.929 MByte/s p40 acyclic-2dim-all : 173.102 185.989 181.128 -> 185.989 -> 371.978 MByte/s p41 acyclic-3dim-all : 173.980 186.403 181.957 -> 186.403 -> 372.805 MByte/s p42 cyclic-2dim-x : 204.598 187.333 177.325 -> 204.598 -> 409.197 MByte/s p43 cyclic-2dim-all : 203.162 186.681 180.391 -> 203.162 -> 406.323 MByte/s p44 cyclic-3dim-x : 205.802 187.200 182.943 -> 205.802 -> 411.604 MByte/s p45 cyclic-3dim-all : 201.879 188.307 183.912 -> 201.879 -> 403.758 MByte/s log_avg of all rings : 204.789 187.232 180.700 || 204.789 -> 409.578 MByte/s log_avg of all random : 204.446 187.308 181.875 || 204.446 -> 408.892 MByte/s log_avg(ring,random) : 204.617 187.270 181.287 ||(204.617 -> 409.235)MByte/s * size -> accumulated on all pr.: 409.235 374.540 362.573 ||(409.235)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-1*2fix : 199.290 204.416 190.191 -> 204.416 -> 408.831 MByte/s p01 ring-1*2fix : 199.297 202.060 202.126 -> 202.126 -> 404.251 MByte/s p02 ring-1*2fix : 199.892 202.292 201.809 -> 202.292 -> 404.584 MByte/s p03 ring-1*2fix : 200.424 204.165 203.646 -> 204.165 -> 408.331 MByte/s p04 ring-1*2fix : 201.247 201.869 202.277 -> 202.277 -> 404.554 MByte/s p05 ring-1*2fix : 202.750 203.436 203.175 -> 203.436 -> 406.872 MByte/s p06 random-cyc-1dim : 201.771 201.384 200.867 -> 201.771 -> 403.541 MByte/s p07 random-cyc-1dim : 202.102 202.629 201.150 -> 202.629 -> 405.257 MByte/s p08 random-cyc-1dim : 202.732 201.947 201.944 -> 202.732 -> 405.464 MByte/s p09 random-cyc-1dim : 201.827 201.935 202.053 -> 202.053 -> 404.107 MByte/s p10 random-cyc-1dim : 204.227 201.093 202.649 -> 204.227 -> 408.454 MByte/s p11 random-cyc-1dim : 202.885 203.428 203.122 -> 203.428 -> 406.855 MByte/s p12 random-cyc-1dim : 200.383 200.730 201.680 -> 201.680 -> 403.360 MByte/s p13 random-cyc-1dim : 200.195 199.771 202.499 -> 202.499 -> 404.997 MByte/s p14 random-cyc-1dim : 202.583 202.014 198.927 -> 202.583 -> 405.165 MByte/s p15 random-cyc-1dim : 200.814 200.748 204.054 -> 204.054 -> 408.108 MByte/s p16 random-cyc-1dim : 202.523 204.768 201.695 -> 204.768 -> 409.537 MByte/s p17 random-cyc-1dim : 202.548 200.940 202.508 -> 202.548 -> 405.096 MByte/s p18 random-cyc-1dim : 201.361 200.674 202.029 -> 202.029 -> 404.059 MByte/s p19 random-cyc-1dim : 199.924 200.333 205.237 -> 205.237 -> 410.474 MByte/s p20 random-cyc-1dim : 202.290 204.215 199.578 -> 204.215 -> 408.430 MByte/s p21 random-cyc-1dim : 202.222 202.460 200.479 -> 202.460 -> 404.920 MByte/s p22 random-cyc-1dim : 201.092 203.989 202.680 -> 203.989 -> 407.979 MByte/s p23 random-cyc-1dim : 201.184 202.606 203.743 -> 203.743 -> 407.487 MByte/s p24 random-cyc-1dim : 200.650 202.536 203.090 -> 203.090 -> 406.179 MByte/s p25 random-cyc-1dim : 204.192 201.620 201.510 -> 204.192 -> 408.383 MByte/s p26 random-cyc-1dim : 199.552 203.423 203.040 -> 203.423 -> 406.847 MByte/s p27 random-cyc-1dim : 204.345 202.725 205.007 -> 205.007 -> 410.013 MByte/s p28 random-cyc-1dim : 203.515 203.658 202.528 -> 203.658 -> 407.316 MByte/s p29 random-cyc-1dim : 202.460 202.709 204.653 -> 204.653 -> 409.306 MByte/s p30 random-cyc-1dim : 202.086 201.120 204.969 -> 204.969 -> 409.939 MByte/s p31 random-cyc-1dim : 201.340 201.443 204.101 -> 204.101 -> 408.201 MByte/s p32 random-cyc-1dim : 201.568 201.866 202.127 -> 202.127 -> 404.255 MByte/s p33 random-cyc-1dim : 201.298 200.905 199.909 -> 201.298 -> 402.597 MByte/s p34 random-cyc-1dim : 202.824 202.113 201.639 -> 202.824 -> 405.649 MByte/s p35 random-cyc-1dim : 203.802 201.010 202.348 -> 203.802 -> 407.604 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 202.800 202.636 202.358 -> 202.800 -> 405.599 MByte/s p37 best bi-section : 186.115 188.671 186.991 -> 188.671 -> 377.342 MByte/s p38 worst bi-section : 187.735 187.287 189.971 -> 189.971 -> 379.941 MByte/s p39 one PingPong Pair : 170.382 171.031 163.436 -> 171.031 -> 342.062 MByte/s p40 acyclic-2dim-all : 187.590 189.151 189.687 -> 189.687 -> 379.373 MByte/s p41 acyclic-3dim-all : 188.080 188.608 188.319 -> 188.608 -> 377.216 MByte/s p42 cyclic-2dim-x : 201.998 204.430 202.539 -> 204.430 -> 408.861 MByte/s p43 cyclic-2dim-all : 202.149 200.753 200.750 -> 202.149 -> 404.297 MByte/s p44 cyclic-3dim-x : 201.158 203.467 202.985 -> 203.467 -> 406.933 MByte/s p45 cyclic-3dim-all : 200.447 201.312 201.304 -> 201.312 -> 402.623 MByte/s log_avg of all rings : 200.480 203.037 200.481 || 203.116 -> 406.233 MByte/s log_avg of all random : 202.006 202.023 202.388 || 203.323 -> 406.647 MByte/s log_avg(ring,random) : 201.241 202.529 201.432 ||(203.220 -> 406.440)MByte/s * size -> accumulated on all pr.: 402.483 405.059 402.865 ||(406.440)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-1*2fix p00 method 0 =Sndrcv :( 15.114) 0.066 1.030 15.010 132.678 543.585 549.966 -> 203.732 -> 407.464 MByte/s p00 method 1 =Alltoal :( 30.792) 0.032 0.514 7.885 88.394 524.160 552.501 -> 187.567 -> 375.135 MByte/s p00 method 2 =non-blk :( 35.584) 0.028 0.446 6.863 81.358 519.228 549.782 -> 179.339 -> 358.678 MByte/s p01 ring-1*2fix p01 method 0 =Sndrcv :( 15.277) 0.065 1.038 15.084 134.558 571.833 552.575 -> 204.498 -> 408.996 MByte/s p01 method 1 =Alltoal :( 30.750) 0.033 0.511 7.808 84.822 522.831 552.570 -> 186.595 -> 373.190 MByte/s p01 method 2 =non-blk :( 35.566) 0.028 0.447 6.858 81.806 521.746 551.704 -> 185.180 -> 370.361 MByte/s p02 ring-1*2fix p02 method 0 =Sndrcv :( 15.103) 0.066 1.039 15.151 134.166 557.036 552.063 -> 204.485 -> 408.970 MByte/s p02 method 1 =Alltoal :( 30.743) 0.033 0.513 7.882 86.293 547.516 552.388 -> 187.613 -> 375.225 MByte/s p02 method 2 =non-blk :( 35.557) 0.028 0.443 6.702 81.836 533.063 551.881 -> 177.975 -> 355.950 MByte/s p03 ring-1*2fix p03 method 0 =Sndrcv :( 15.130) 0.066 1.037 15.108 134.682 544.332 552.610 -> 205.547 -> 411.093 MByte/s p03 method 1 =Alltoal :( 30.769) 0.033 0.513 7.888 86.820 527.003 552.172 -> 187.071 -> 374.143 MByte/s p03 method 2 =non-blk :( 35.713) 0.028 0.447 6.869 81.611 510.900 551.773 -> 181.049 -> 362.097 MByte/s p04 ring-1*2fix p04 method 0 =Sndrcv :( 15.077) 0.066 1.036 14.937 134.553 548.288 552.788 -> 204.673 -> 409.347 MByte/s p04 method 1 =Alltoal :( 30.892) 0.032 0.513 7.888 87.058 527.556 550.543 -> 186.704 -> 373.409 MByte/s p04 method 2 =non-blk :( 35.380) 0.028 0.446 6.858 80.998 467.346 551.955 -> 180.537 -> 361.075 MByte/s p05 ring-1*2fix p05 method 0 =Sndrcv :( 15.081) 0.066 1.029 15.114 132.970 587.745 550.435 -> 205.808 -> 411.615 MByte/s p05 method 1 =Alltoal :( 30.897) 0.032 0.515 7.795 88.516 527.133 552.718 -> 187.846 -> 375.691 MByte/s p05 method 2 =non-blk :( 35.481) 0.028 0.447 6.858 80.070 497.077 550.001 -> 180.203 -> 360.407 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 15.094) 0.066 1.037 15.170 134.594 518.555 552.683 -> 202.552 -> 405.104 MByte/s p06 method 1 =Alltoal :( 30.864) 0.032 0.514 7.885 88.391 523.888 550.651 -> 186.310 -> 372.620 MByte/s p06 method 2 =non-blk :( 35.471) 0.028 0.445 6.820 79.641 490.857 552.423 -> 179.696 -> 359.393 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 15.203) 0.066 1.032 15.151 134.336 561.836 550.035 -> 205.169 -> 410.338 MByte/s p07 method 1 =Alltoal :( 30.841) 0.032 0.515 7.879 88.241 552.718 552.792 -> 188.653 -> 377.306 MByte/s p07 method 2 =non-blk :( 35.472) 0.028 0.439 6.858 81.471 545.334 552.172 -> 183.513 -> 367.027 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 15.107) 0.066 1.036 14.980 134.599 571.041 552.575 -> 204.418 -> 408.837 MByte/s p08 method 1 =Alltoal :( 30.801) 0.032 0.513 7.875 88.578 530.567 552.610 -> 187.944 -> 375.888 MByte/s p08 method 2 =non-blk :( 35.528) 0.028 0.446 6.872 81.920 528.648 552.098 -> 183.039 -> 366.078 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 15.102) 0.066 1.033 15.127 133.137 550.543 552.792 -> 204.034 -> 408.067 MByte/s p09 method 1 =Alltoal :( 30.752) 0.033 0.514 7.798 88.361 536.003 552.792 -> 188.722 -> 377.444 MByte/s p09 method 2 =non-blk :( 35.538) 0.028 0.447 6.877 81.836 541.279 551.920 -> 182.861 -> 365.722 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 15.094) 0.066 1.038 15.175 131.178 571.025 552.683 -> 205.921 -> 411.843 MByte/s p10 method 1 =Alltoal :( 30.784) 0.032 0.513 7.879 88.149 526.047 552.900 -> 186.267 -> 372.535 MByte/s p10 method 2 =non-blk :( 35.871) 0.028 0.447 6.806 81.083 513.337 549.893 -> 182.212 -> 364.424 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 15.110) 0.066 1.038 15.126 131.257 551.174 552.718 -> 203.759 -> 407.518 MByte/s p11 method 1 =Alltoal :( 30.740) 0.033 0.511 7.850 88.303 545.926 550.254 -> 188.656 -> 377.311 MByte/s p11 method 2 =non-blk :( 35.425) 0.028 0.447 6.869 81.471 443.740 552.172 -> 179.262 -> 358.525 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 15.130) 0.066 1.039 14.980 131.134 565.008 550.685 -> 203.492 -> 406.985 MByte/s p12 method 1 =Alltoal :( 31.037) 0.032 0.513 7.888 88.424 524.032 552.427 -> 186.650 -> 373.299 MByte/s p12 method 2 =non-blk :( 35.425) 0.028 0.446 6.855 81.920 545.334 550.216 -> 183.096 -> 366.191 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 15.107) 0.066 1.037 15.095 133.522 511.728 552.792 -> 201.965 -> 403.929 MByte/s p13 method 1 =Alltoal :( 30.953) 0.032 0.512 7.795 87.721 512.568 550.362 -> 186.962 -> 373.924 MByte/s p13 method 2 =non-blk :( 35.435) 0.028 0.446 6.847 81.748 440.019 552.102 -> 176.574 -> 353.147 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 15.204) 0.066 1.038 15.170 133.736 548.288 550.397 -> 204.657 -> 409.313 MByte/s p14 method 1 =Alltoal :( 30.792) 0.032 0.513 7.888 86.261 522.687 552.644 -> 185.174 -> 370.349 MByte/s p14 method 2 =non-blk :( 35.454) 0.028 0.446 6.823 81.554 451.804 552.280 -> 179.174 -> 358.349 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 15.150) 0.066 1.038 15.307 134.729 548.407 552.718 -> 205.451 -> 410.902 MByte/s p15 method 1 =Alltoal :( 30.817) 0.032 0.512 7.840 86.468 541.416 552.649 -> 188.097 -> 376.194 MByte/s p15 method 2 =non-blk :( 35.538) 0.028 0.447 6.869 81.554 545.334 552.063 -> 183.142 -> 366.283 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 15.106) 0.066 1.036 14.992 133.477 558.854 552.935 -> 205.309 -> 410.618 MByte/s p16 method 1 =Alltoal :( 30.785) 0.032 0.513 7.885 85.678 523.215 552.427 -> 186.804 -> 373.608 MByte/s p16 method 2 =non-blk :( 35.528) 0.028 0.439 6.875 81.695 543.446 551.557 -> 183.742 -> 367.484 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 15.093) 0.066 1.040 15.145 134.770 573.472 552.388 -> 204.793 -> 409.587 MByte/s p17 method 1 =Alltoal :( 30.784) 0.032 0.514 7.850 88.208 505.838 552.792 -> 186.605 -> 373.211 MByte/s p17 method 2 =non-blk :( 35.852) 0.028 0.446 6.864 81.245 443.361 549.859 -> 181.745 -> 363.490 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 15.097) 0.066 1.037 15.213 133.309 542.986 553.122 -> 203.427 -> 406.855 MByte/s p18 method 1 =Alltoal :( 31.033) 0.032 0.513 7.647 87.750 526.468 550.435 -> 187.433 -> 374.865 MByte/s p18 method 2 =non-blk :( 35.203) 0.028 0.447 6.869 79.964 535.299 552.354 -> 179.830 -> 359.661 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 15.081) 0.066 1.040 15.213 133.309 569.947 550.220 -> 206.477 -> 412.955 MByte/s p19 method 1 =Alltoal :( 30.963) 0.032 0.511 7.833 88.146 523.888 552.718 -> 187.339 -> 374.677 MByte/s p19 method 2 =non-blk :( 35.333) 0.028 0.446 6.809 80.041 449.607 549.962 -> 177.542 -> 355.083 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 15.094) 0.066 1.038 15.170 134.120 508.382 552.683 -> 201.759 -> 403.517 MByte/s p20 method 1 =Alltoal :( 30.910) 0.032 0.513 7.885 88.424 551.969 552.536 -> 188.581 -> 377.163 MByte/s p20 method 2 =non-blk :( 35.389) 0.028 0.446 6.864 79.935 546.956 552.393 -> 183.710 -> 367.419 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 15.070) 0.066 1.038 14.986 134.424 552.817 552.427 -> 204.811 -> 409.623 MByte/s p21 method 1 =Alltoal :( 30.817) 0.032 0.515 7.821 88.424 537.570 552.683 -> 186.247 -> 372.494 MByte/s p21 method 2 =non-blk :( 35.528) 0.028 0.446 6.916 81.695 484.434 551.665 -> 179.641 -> 359.282 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 15.217) 0.066 1.037 15.120 133.436 555.995 552.718 -> 205.496 -> 410.993 MByte/s p22 method 1 =Alltoal :( 30.769) 0.033 0.515 7.792 88.453 527.019 552.206 -> 186.893 -> 373.786 MByte/s p22 method 2 =non-blk :( 35.632) 0.028 0.446 6.861 81.752 437.845 552.462 -> 179.320 -> 358.641 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 15.057) 0.066 1.031 15.182 130.806 565.008 552.753 -> 203.091 -> 406.183 MByte/s p23 method 1 =Alltoal :( 30.817) 0.032 0.515 7.837 88.149 536.440 552.644 -> 188.202 -> 376.404 MByte/s p23 method 2 =non-blk :( 35.548) 0.028 0.446 6.825 81.863 546.641 552.245 -> 181.589 -> 363.178 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 15.114) 0.066 1.039 15.120 130.928 566.195 550.362 -> 203.392 -> 406.784 MByte/s p24 method 1 =Alltoal :( 30.784) 0.032 0.512 7.879 88.055 535.735 552.427 -> 187.569 -> 375.137 MByte/s p24 method 2 =non-blk :( 35.769) 0.028 0.446 6.872 81.528 546.799 550.147 -> 183.781 -> 367.562 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 15.077) 0.066 1.035 14.992 131.012 585.023 552.935 -> 205.608 -> 411.215 MByte/s p25 method 1 =Alltoal :( 30.818) 0.032 0.512 7.875 87.297 537.705 549.928 -> 186.547 -> 373.095 MByte/s p25 method 2 =non-blk :( 35.481) 0.028 0.438 6.902 81.415 543.601 552.358 -> 181.974 -> 363.947 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 15.106) 0.066 1.037 15.071 133.736 559.116 550.508 -> 206.179 -> 412.358 MByte/s p26 method 1 =Alltoal :( 30.946) 0.032 0.515 7.789 86.997 517.249 552.974 -> 187.235 -> 374.470 MByte/s p26 method 2 =non-blk :( 35.333) 0.028 0.447 6.877 82.316 455.741 549.820 -> 178.728 -> 357.457 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 15.069) 0.066 1.032 15.245 134.553 565.926 552.718 -> 206.373 -> 412.745 MByte/s p27 method 1 =Alltoal :( 30.863) 0.032 0.513 7.799 86.555 536.727 552.900 -> 187.092 -> 374.183 MByte/s p27 method 2 =non-blk :( 35.547) 0.028 0.446 6.820 81.866 548.271 551.773 -> 183.753 -> 367.505 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 15.065) 0.066 1.038 15.114 134.166 559.101 552.501 -> 205.073 -> 410.147 MByte/s p28 method 1 =Alltoal :( 30.891) 0.032 0.512 7.882 86.496 540.424 552.388 -> 187.906 -> 375.812 MByte/s p28 method 2 =non-blk :( 35.287) 0.028 0.446 6.875 81.638 545.039 552.137 -> 184.942 -> 369.884 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 15.080) 0.066 1.040 14.986 134.377 573.195 550.582 -> 205.241 -> 410.481 MByte/s p29 method 1 =Alltoal :( 30.800) 0.032 0.514 7.827 86.408 536.440 552.718 -> 187.850 -> 375.701 MByte/s p29 method 2 =non-blk :( 35.567) 0.028 0.445 6.886 81.471 547.832 549.679 -> 184.108 -> 368.216 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 15.098) 0.066 1.040 15.078 133.609 569.690 552.866 -> 205.636 -> 411.272 MByte/s p30 method 1 =Alltoal :( 30.801) 0.032 0.515 7.798 88.549 522.160 550.543 -> 187.392 -> 374.784 MByte/s p30 method 2 =non-blk :( 35.557) 0.028 0.446 6.877 81.608 521.889 552.098 -> 184.476 -> 368.952 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 15.102) 0.066 1.038 15.170 133.609 528.796 550.470 -> 204.768 -> 409.536 MByte/s p31 method 1 =Alltoal :( 30.833) 0.032 0.514 7.875 88.116 536.861 552.866 -> 187.298 -> 374.596 MByte/s p31 method 2 =non-blk :( 35.825) 0.028 0.447 6.839 80.125 532.085 549.855 -> 182.431 -> 364.863 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 15.101) 0.066 1.036 15.238 134.213 552.817 552.427 -> 202.440 -> 404.881 MByte/s p32 method 1 =Alltoal :( 30.837) 0.032 0.514 7.879 88.641 515.286 550.470 -> 186.689 -> 373.377 MByte/s p32 method 2 =non-blk :( 35.500) 0.028 0.447 6.864 79.562 533.479 552.358 -> 183.518 -> 367.037 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 15.093) 0.066 1.038 14.998 133.823 523.063 550.508 -> 201.930 -> 403.859 MByte/s p33 method 1 =Alltoal :( 30.793) 0.032 0.512 7.827 88.457 525.513 553.157 -> 187.592 -> 375.183 MByte/s p33 method 2 =non-blk :( 35.426) 0.028 0.446 6.902 79.884 537.857 551.445 -> 184.357 -> 368.713 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 15.073) 0.066 1.040 15.089 132.759 547.160 552.501 -> 205.599 -> 411.199 MByte/s p34 method 1 =Alltoal :( 30.863) 0.032 0.514 7.801 88.270 526.338 552.683 -> 188.051 -> 376.102 MByte/s p34 method 2 =non-blk :( 35.333) 0.028 0.439 6.869 81.863 523.503 550.220 -> 179.451 -> 358.903 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 15.103) 0.066 1.040 15.170 133.355 555.628 552.757 -> 204.689 -> 409.377 MByte/s p35 method 1 =Alltoal :( 30.866) 0.032 0.515 7.802 88.424 526.873 550.181 -> 186.536 -> 373.072 MByte/s p35 method 2 =non-blk :( 35.399) 0.028 0.447 6.815 81.554 548.411 552.280 -> 185.489 -> 370.977 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 15.057) 0.066 1.040 15.084 131.711 552.424 550.685 -> 204.347 -> 408.695 MByte/s p36 method 1 =Alltoal :( 30.833) 0.032 0.516 7.872 88.424 537.148 552.245 -> 186.621 -> 373.241 MByte/s p36 method 2 =non-blk :( 35.613) 0.028 0.447 6.869 81.722 531.407 549.425 -> 182.294 -> 364.589 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 11.496) 0.043 0.667 9.386 100.600 433.644 614.999 -> 173.676 -> 347.351 MByte/s p37 method 1 =Alltoal :( 15.702) 0.032 0.503 7.646 86.969 515.814 558.420 -> 183.913 -> 367.826 MByte/s p37 method 2 =non-blk :( 17.259) 0.029 0.459 6.990 83.474 501.728 554.543 -> 180.517 -> 361.034 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 11.496) 0.043 0.662 9.479 100.817 434.035 615.267 -> 173.792 -> 347.584 MByte/s p38 method 1 =Alltoal :( 15.767) 0.032 0.503 7.646 87.268 530.847 552.497 -> 186.025 -> 372.050 MByte/s p38 method 2 =non-blk :( 17.171) 0.029 0.458 6.992 83.621 487.097 549.713 -> 180.462 -> 360.924 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 11.462) 0.044 0.667 9.369 100.623 433.012 615.133 -> 173.964 -> 347.929 MByte/s p39 method 1 =Alltoal :(-------) 0.000 0.000 0.000 0.000 0.000 0.000 -> 0.000 -> 0.000 MByte/s p39 method 2 =non-blk :(-------) 0.000 0.000 0.000 0.000 0.000 0.000 -> 0.000 -> 0.000 MByte/s p40 acyclic-2dim-all p40 method 0 =Sndrcv :( 11.490) 0.044 0.656 9.506 102.127 430.458 614.461 -> 173.102 -> 346.203 MByte/s p40 method 1 =Alltoal :( 15.777) 0.032 0.503 7.649 87.300 520.952 549.460 -> 185.989 -> 371.978 MByte/s p40 method 2 =non-blk :( 17.170) 0.029 0.459 6.972 83.387 513.985 552.610 -> 181.128 -> 362.255 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 11.256) 0.044 0.665 9.547 102.175 433.793 611.588 -> 173.980 -> 347.960 MByte/s p41 method 1 =Alltoal :( 15.713) 0.032 0.503 7.646 86.672 507.851 552.137 -> 186.403 -> 372.805 MByte/s p41 method 2 =non-blk :( 17.180) 0.029 0.460 6.995 83.359 490.970 544.894 -> 181.957 -> 363.913 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 15.103) 0.066 1.034 15.010 134.511 536.687 552.393 -> 204.598 -> 409.197 MByte/s p42 method 1 =Alltoal :( 30.801) 0.032 0.514 7.875 88.391 536.575 550.143 -> 187.333 -> 374.666 MByte/s p42 method 2 =non-blk :( 35.575) 0.028 0.445 6.866 79.587 452.809 552.137 -> 177.325 -> 354.649 MByte/s p43 cyclic-2dim-all p43 method 0 =Sndrcv :( 15.094) 0.066 1.033 14.998 134.687 540.186 550.401 -> 203.162 -> 406.323 MByte/s p43 method 1 =Alltoal :( 30.909) 0.032 0.513 7.865 88.116 527.279 552.683 -> 186.681 -> 373.363 MByte/s p43 method 2 =non-blk :( 35.671) 0.028 0.448 6.861 79.964 488.265 551.592 -> 180.391 -> 360.782 MByte/s p44 cyclic-3dim-x p44 method 0 =Sndrcv :( 15.077) 0.066 1.034 15.157 134.207 571.041 552.570 -> 205.802 -> 411.604 MByte/s p44 method 1 =Alltoal :( 30.918) 0.032 0.515 7.798 88.332 545.334 552.679 -> 187.200 -> 374.399 MByte/s p44 method 2 =non-blk :( 35.389) 0.028 0.442 6.888 79.801 509.499 551.630 -> 182.943 -> 365.886 MByte/s p45 cyclic-3dim-all p45 method 0 =Sndrcv :( 15.094) 0.066 1.034 15.083 133.263 499.118 552.610 -> 201.879 -> 403.758 MByte/s p45 method 1 =Alltoal :( 30.827) 0.032 0.513 7.837 88.453 538.281 550.358 -> 188.307 -> 376.614 MByte/s p45 method 2 =non-blk :( 35.426) 0.028 0.447 6.855 81.554 516.079 552.137 -> 183.912 -> 367.824 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.066 1.035 15.067 133.932 558.573 551.738 || 204.789 -> 409.578 MByte/s - ring, method 1 = Alltoal: 0.032 0.513 7.858 86.975 529.302 552.148 || 187.232 -> 374.464 MByte/s - ring, method 2 = non-blk: 0.028 0.446 6.835 81.277 507.768 551.182 || 180.700 -> 361.401 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.066 1.037 15.119 133.328 553.371 552.014 || 204.446 -> 408.892 MByte/s - random, method 1 = Alltoal: 0.032 0.513 7.838 87.809 530.077 552.058 || 187.308 -> 374.616 MByte/s - random, method 2 = non-blk: 0.028 0.445 6.859 81.237 512.244 551.466 || 181.875 -> 363.750 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.066 1.036 15.093 133.630 555.966 551.876 || 204.617 -> 409.235 MByte/s - average, method 1 = Alltoal: 0.032 0.513 7.848 87.391 529.689 552.103 || 187.270 -> 374.540 MByte/s - average, method 2 = non-blk: 0.028 0.446 6.847 81.257 510.001 551.324 || 181.287 -> 362.573 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.132 2.072 30.186 267.259 1111.932 1103.753 || 409.235 MByte/s - accumulated, mthd 1 = Alltoal: 0.065 1.027 15.696 174.782 1059.379 1104.206 || 374.540 MByte/s - accumulated, mthd 2 = non-blk: 0.056 0.891 13.694 162.514 1020.002 1102.648 || 362.573 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 0.132 0.066 0.066 0.066 0.066 0.032 0.028 2 0.263 0.131 0.131 0.131 0.131 0.065 0.056 4 0.520 0.260 0.260 0.260 0.260 0.129 0.111 8 1.046 0.523 0.522 0.524 0.523 0.258 0.224 16 2.072 1.036 1.035 1.037 1.036 0.513 0.446 32 4.068 2.034 2.032 2.037 2.034 1.018 0.888 64 7.898 3.949 3.949 3.949 3.949 2.008 1.754 128 14.865 7.432 7.431 7.434 7.432 3.884 3.413 256 30.186 15.093 15.067 15.119 15.093 7.848 6.847 512 58.486 29.243 29.270 29.216 29.243 15.383 13.508 1024 111.590 55.795 55.731 55.860 55.795 29.995 26.392 2048 166.299 83.149 82.951 83.348 83.149 50.668 46.660 4096 267.259 133.630 133.932 133.328 133.630 87.391 81.257 10624 450.990 225.495 225.052 225.939 225.495 164.889 157.613 27554 775.791 387.896 385.328 390.480 387.896 311.761 293.324 71468 956.320 478.160 480.588 475.744 478.160 420.360 382.059 185364 1114.477 557.239 558.573 555.907 555.966 529.689 510.001 480774 1214.783 607.392 606.861 607.923 604.403 593.729 590.365 1246974 1233.241 616.621 617.308 615.934 609.787 612.345 591.425 3234251 1105.018 552.509 554.497 550.528 550.409 548.312 546.181 8388608 1105.353 552.676 552.597 552.756 551.876 552.103 551.324 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-1*2fix :( 15.114) 0.066 1.030 15.010 132.678 543.585 552.501 -> 205.084 -> 410.167 MByte/s p01 ring-1*2fix :( 15.277) 0.065 1.038 15.084 134.558 571.833 552.575 -> 205.045 -> 410.090 MByte/s p02 ring-1*2fix :( 15.103) 0.066 1.039 15.151 134.166 557.036 552.388 -> 205.418 -> 410.837 MByte/s p03 ring-1*2fix :( 15.130) 0.066 1.037 15.108 134.682 544.332 552.610 -> 205.547 -> 411.093 MByte/s p04 ring-1*2fix :( 15.077) 0.066 1.036 14.937 134.553 548.288 552.788 -> 204.723 -> 409.445 MByte/s p05 ring-1*2fix :( 15.081) 0.066 1.029 15.114 132.970 587.745 552.718 -> 206.672 -> 413.345 MByte/s p06 random-cyc-1dim :( 15.094) 0.066 1.037 15.170 134.594 523.888 552.683 -> 202.919 -> 405.837 MByte/s p07 random-cyc-1dim :( 15.203) 0.066 1.032 15.151 134.336 561.836 552.792 -> 205.300 -> 410.601 MByte/s p08 random-cyc-1dim :( 15.107) 0.066 1.036 14.980 134.599 571.041 552.610 -> 205.188 -> 410.377 MByte/s p09 random-cyc-1dim :( 15.102) 0.066 1.033 15.127 133.137 550.543 552.792 -> 205.271 -> 410.543 MByte/s p10 random-cyc-1dim :( 15.094) 0.066 1.038 15.175 131.178 571.025 552.900 -> 206.202 -> 412.404 MByte/s p11 random-cyc-1dim :( 15.110) 0.066 1.038 15.126 131.257 551.174 552.718 -> 204.616 -> 409.232 MByte/s p12 random-cyc-1dim :( 15.130) 0.066 1.039 14.980 131.134 565.008 552.427 -> 203.575 -> 407.151 MByte/s p13 random-cyc-1dim :( 15.107) 0.066 1.037 15.095 133.522 512.568 552.792 -> 202.750 -> 405.499 MByte/s p14 random-cyc-1dim :( 15.204) 0.066 1.038 15.170 133.736 548.288 552.644 -> 205.205 -> 410.410 MByte/s p15 random-cyc-1dim :( 15.150) 0.066 1.038 15.307 134.729 548.407 552.718 -> 205.451 -> 410.902 MByte/s p16 random-cyc-1dim :( 15.106) 0.066 1.036 14.992 133.477 558.854 552.935 -> 205.772 -> 411.544 MByte/s p17 random-cyc-1dim :( 15.093) 0.066 1.040 15.145 134.770 573.472 552.792 -> 206.142 -> 412.285 MByte/s p18 random-cyc-1dim :( 15.097) 0.066 1.037 15.213 133.309 542.986 553.122 -> 204.551 -> 409.103 MByte/s p19 random-cyc-1dim :( 15.081) 0.066 1.040 15.213 133.309 569.947 552.718 -> 206.830 -> 413.661 MByte/s p20 random-cyc-1dim :( 15.094) 0.066 1.038 15.170 134.120 551.969 552.683 -> 204.672 -> 409.343 MByte/s p21 random-cyc-1dim :( 15.070) 0.066 1.038 14.986 134.424 552.817 552.683 -> 204.824 -> 409.647 MByte/s p22 random-cyc-1dim :( 15.217) 0.066 1.037 15.120 133.436 555.995 552.718 -> 205.496 -> 410.993 MByte/s p23 random-cyc-1dim :( 15.057) 0.066 1.031 15.182 130.806 565.008 552.753 -> 204.987 -> 409.973 MByte/s p24 random-cyc-1dim :( 15.114) 0.066 1.039 15.120 130.928 566.195 552.427 -> 204.973 -> 409.946 MByte/s p25 random-cyc-1dim :( 15.077) 0.066 1.035 14.992 131.012 585.023 552.935 -> 205.817 -> 411.634 MByte/s p26 random-cyc-1dim :( 15.106) 0.066 1.037 15.071 133.736 559.116 552.974 -> 206.383 -> 412.766 MByte/s p27 random-cyc-1dim :( 15.069) 0.066 1.032 15.245 134.553 565.926 552.900 -> 206.743 -> 413.485 MByte/s p28 random-cyc-1dim :( 15.065) 0.066 1.038 15.114 134.166 559.101 552.501 -> 205.781 -> 411.563 MByte/s p29 random-cyc-1dim :( 15.080) 0.066 1.040 14.986 134.377 573.195 552.718 -> 205.643 -> 411.287 MByte/s p30 random-cyc-1dim :( 15.098) 0.066 1.040 15.078 133.609 569.690 552.866 -> 206.301 -> 412.601 MByte/s p31 random-cyc-1dim :( 15.102) 0.066 1.038 15.170 133.609 536.861 552.866 -> 205.454 -> 410.909 MByte/s p32 random-cyc-1dim :( 15.101) 0.066 1.036 15.238 134.213 552.817 552.427 -> 203.518 -> 407.037 MByte/s p33 random-cyc-1dim :( 15.093) 0.066 1.038 14.998 133.823 537.857 553.157 -> 202.990 -> 405.980 MByte/s p34 random-cyc-1dim :( 15.073) 0.066 1.040 15.089 132.759 547.160 552.683 -> 205.608 -> 411.216 MByte/s p35 random-cyc-1dim :( 15.103) 0.066 1.040 15.170 133.355 555.628 552.757 -> 205.286 -> 410.571 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 15.057) 0.066 1.040 15.084 131.711 552.424 552.245 -> 205.310 -> 410.621 MByte/s p37 best bi-section :( 11.496) 0.043 0.667 9.386 100.600 515.814 614.999 -> 189.367 -> 378.735 MByte/s p38 worst bi-section :( 11.496) 0.043 0.662 9.479 100.817 530.847 615.267 -> 190.788 -> 381.575 MByte/s p39 one PingPong Pair :( 11.462) 0.044 0.667 9.369 100.623 433.012 615.133 -> 173.964 -> 347.929 MByte/s p40 acyclic-2dim-all :( 11.490) 0.044 0.656 9.506 102.127 520.952 614.461 -> 191.329 -> 382.659 MByte/s p41 acyclic-3dim-all :( 11.256) 0.044 0.665 9.547 102.175 507.851 611.588 -> 191.057 -> 382.114 MByte/s p42 cyclic-2dim-x :( 15.103) 0.066 1.034 15.010 134.511 536.687 552.393 -> 205.045 -> 410.089 MByte/s p43 cyclic-2dim-all :( 15.094) 0.066 1.033 14.998 134.687 540.186 552.683 -> 203.901 -> 407.801 MByte/s p44 cyclic-3dim-x :( 15.077) 0.066 1.034 15.157 134.207 571.041 552.679 -> 206.061 -> 412.122 MByte/s p45 cyclic-3dim-all :( 15.094) 0.066 1.034 15.083 133.263 538.281 552.610 -> 204.363 -> 408.727 MByte/s log_avg of all rings : 0.066 1.035 15.067 133.932 558.573 552.597 || 205.414 -> 410.828 MByte/s log_avg of all random : 0.066 1.037 15.119 133.328 555.907 552.756 || 205.139 -> 410.278 MByte/s log_avg(ring,random) : 0.066 1.036 15.093 133.630 557.239 552.676 || 205.276 -> 410.553 MByte/s * size -> accumulated on all pr.: 0.132 2.072 30.186 267.259 1114.477 1105.353 || 410.553 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 410.553 MByte/s on 2 processes ( = 205.276 MByte/s * 2 processes) Ping-pong latency: 11.462 microsec Ping-pong bandwidth: 1230.266 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 2 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 17:38:28 1999 Total execution wall clock time = 36 seconds SECTION-BEFF-END b_eff = 410.553 MB/s = 205.276 * 2 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000