b_eff = 1118.625 MB/s = 159.804 * 7 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 = 7 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*2&+1 1=ring-2*4&-1 2=ring-1*7fix 3=ring-1*7fix 4=ring-1*7fix 5=ring-1*7fix 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: 78.361 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 1.6e-02 235 3.6e-01 3.7e-03 1.3e-02 238 3.7e-01 3.8e-03 1.3e-02 2 158 2.5e-01 2.6e-03 1.1e-02 158 2.5e-01 2.5e-03 8.7e-03 158 2.5e-01 2.5e-03 8.7e-03 4 154 2.4e-01 2.5e-03 8.7e-03 159 2.5e-01 2.5e-03 9.0e-03 159 2.5e-01 2.5e-03 9.0e-03 8 155 2.4e-01 2.5e-03 8.8e-03 157 2.4e-01 2.5e-03 8.7e-03 157 2.4e-01 2.5e-03 8.7e-03 16 157 2.5e-01 2.5e-03 9.0e-03 159 2.5e-01 2.6e-03 8.9e-03 157 2.5e-01 2.5e-03 8.9e-03 32 156 2.5e-01 2.6e-03 8.9e-03 155 2.5e-01 2.5e-03 8.9e-03 155 2.5e-01 2.5e-03 9.0e-03 64 148 2.5e-01 2.5e-03 8.9e-03 152 2.5e-01 2.6e-03 9.2e-03 153 2.6e-01 2.6e-03 9.2e-03 128 147 2.6e-01 2.7e-03 9.9e-03 148 2.7e-01 2.7e-03 9.6e-03 149 2.7e-01 2.7e-03 9.7e-03 256 137 2.5e-01 2.5e-03 8.5e-03 138 2.5e-01 2.5e-03 8.7e-03 139 2.5e-01 2.6e-03 8.9e-03 512 137 2.6e-01 2.6e-03 8.7e-03 139 2.7e-01 2.6e-03 9.1e-03 135 2.6e-01 2.6e-03 8.9e-03 1024 132 2.7e-01 2.7e-03 9.1e-03 134 2.7e-01 2.8e-03 9.3e-03 128 2.6e-01 2.6e-03 8.8e-03 2048 120 3.2e-01 3.3e-03 1.1e-02 120 3.1e-01 3.2e-03 1.1e-02 122 3.2e-01 3.3e-03 1.1e-02 4096 92 3.1e-01 3.1e-03 1.0e-02 93 3.1e-01 3.2e-03 1.0e-02 93 3.1e-01 3.1e-03 1.0e-02 10624 56 3.3e-01 3.1e-03 1.2e-02 56 3.4e-01 3.0e-03 1.1e-02 57 3.4e-01 3.0e-03 1.2e-02 27554 35 3.4e-01 3.0e-03 1.2e-02 36 3.6e-01 2.9e-03 1.3e-02 36 3.7e-01 3.2e-03 1.3e-02 71468 22 4.2e-01 3.9e-03 1.4e-02 23 4.4e-01 3.6e-03 1.7e-02 21 4.1e-01 3.6e-03 1.3e-02 185364 10 4.5e-01 4.1e-03 1.4e-02 12 5.4e-01 4.8e-03 1.7e-02 11 5.7e-01 4.3e-03 8.4e-02 480774 4 4.3e-01 4.0e-03 1.4e-02 4 4.3e-01 4.0e-03 1.5e-02 4 4.4e-01 4.1e-03 1.6e-02 1246974 1 2.7e-01 2.6e-03 1.1e-02 1 2.7e-01 2.5e-03 8.9e-03 1 2.7e-01 2.5e-03 1.1e-02 3234251 1 6.4e-01 6.0e-03 2.0e-02 1 6.3e-01 6.2e-03 2.0e-02 1 6.4e-01 6.2e-03 2.2e-02 8388608 1 1.6e+00 1.4e-02 5.0e-02 1 1.7e+00 1.4e-02 1.1e-01 1 1.6e+00 1.4e-02 5.3e-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 1.5e+00 2.8e-02 3.4e-02 39 2.0e-01 3.6e-03 4.6e-03 40 2.0e-01 3.6e-03 4.6e-03 2 150 7.6e-01 1.4e-02 1.8e-02 27 1.4e-01 2.5e-03 3.4e-03 27 1.4e-01 2.5e-03 3.1e-03 4 75 3.8e-01 6.8e-03 8.8e-03 26 1.3e-01 2.4e-03 3.0e-03 27 1.4e-01 2.4e-03 3.3e-03 8 37 1.9e-01 3.5e-03 4.3e-03 27 1.4e-01 2.5e-03 3.1e-03 27 1.4e-01 2.5e-03 3.1e-03 16 26 1.3e-01 2.4e-03 3.1e-03 27 1.4e-01 2.5e-03 3.1e-03 26 1.3e-01 2.4e-03 3.0e-03 32 27 1.4e-01 2.5e-03 3.3e-03 26 1.3e-01 2.4e-03 3.1e-03 27 1.4e-01 2.5e-03 3.1e-03 64 27 1.4e-01 2.6e-03 3.2e-03 27 1.4e-01 2.6e-03 3.5e-03 27 1.4e-01 2.6e-03 3.1e-03 128 26 1.4e-01 2.5e-03 3.1e-03 26 1.4e-01 2.4e-03 3.2e-03 26 1.4e-01 2.4e-03 3.1e-03 256 25 1.3e-01 2.3e-03 3.0e-03 26 1.4e-01 2.4e-03 3.3e-03 26 1.4e-01 2.5e-03 3.4e-03 512 26 1.4e-01 2.4e-03 3.5e-03 26 1.4e-01 2.4e-03 3.2e-03 25 1.3e-01 2.3e-03 3.0e-03 1024 26 1.4e-01 2.5e-03 3.7e-03 26 1.4e-01 2.5e-03 3.2e-03 26 1.4e-01 2.6e-03 3.3e-03 2048 26 1.7e-01 2.7e-03 4.0e-03 26 1.7e-01 2.7e-03 3.8e-03 25 1.6e-01 2.6e-03 4.6e-03 4096 23 1.7e-01 2.6e-03 4.5e-03 24 1.8e-01 2.8e-03 4.4e-03 24 1.8e-01 2.7e-03 4.7e-03 10624 16 1.9e-01 2.4e-03 4.6e-03 16 1.9e-01 2.4e-03 4.8e-03 17 2.0e-01 2.6e-03 5.1e-03 27554 12 2.1e-01 2.4e-03 5.6e-03 12 2.1e-01 2.3e-03 5.4e-03 12 2.1e-01 2.5e-03 5.6e-03 71468 9 2.7e-01 2.7e-03 7.1e-03 10 3.1e-01 3.0e-03 9.3e-03 9 2.8e-01 2.4e-03 7.7e-03 185364 6 3.9e-01 3.5e-03 1.2e-02 6 3.9e-01 3.2e-03 1.2e-02 7 4.6e-01 3.8e-03 1.4e-02 480774 3 4.8e-01 3.5e-03 1.6e-02 3 4.8e-01 3.2e-03 1.5e-02 3 4.8e-01 3.3e-03 1.4e-02 1246974 1 3.7e-01 2.2e-03 1.5e-02 1 3.9e-01 2.3e-03 1.4e-02 1 3.9e-01 2.2e-03 1.8e-02 3234251 1 9.2e-01 6.3e-03 2.6e-02 1 9.2e-01 6.3e-03 3.3e-02 1 9.4e-01 6.4e-03 3.8e-02 8388608 1 2.3e+00 1.6e-02 6.6e-02 1 2.4e+00 1.6e-02 6.9e-02 1 2.4e+00 1.6e-02 6.6e-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-02 102 3.5e-01 3.6e-03 1.1e-02 102 3.5e-01 3.8e-03 1.1e-02 2 150 5.1e-01 5.5e-03 1.6e-02 70 2.4e-01 2.5e-03 7.5e-03 67 2.3e-01 2.5e-03 7.4e-03 4 75 2.6e-01 2.7e-03 8.1e-03 69 2.4e-01 2.5e-03 7.4e-03 67 2.3e-01 2.5e-03 7.9e-03 8 68 2.3e-01 2.5e-03 7.6e-03 68 2.3e-01 2.5e-03 7.4e-03 68 2.3e-01 2.4e-03 7.2e-03 16 68 2.3e-01 2.5e-03 8.1e-03 68 2.3e-01 2.5e-03 7.3e-03 70 2.4e-01 2.6e-03 7.5e-03 32 68 2.3e-01 2.5e-03 7.3e-03 69 2.4e-01 2.5e-03 7.4e-03 68 2.4e-01 2.6e-03 8.8e-03 64 67 2.3e-01 2.6e-03 7.3e-03 68 2.4e-01 2.6e-03 7.6e-03 66 2.3e-01 2.5e-03 7.2e-03 128 65 2.4e-01 2.6e-03 7.4e-03 65 2.3e-01 2.5e-03 7.5e-03 65 2.4e-01 2.6e-03 7.5e-03 256 62 2.2e-01 2.4e-03 7.0e-03 63 2.4e-01 2.5e-03 7.2e-03 63 2.4e-01 2.6e-03 7.6e-03 512 65 2.4e-01 2.5e-03 8.2e-03 63 2.4e-01 2.6e-03 7.4e-03 59 2.3e-01 2.4e-03 7.1e-03 1024 64 2.4e-01 2.6e-03 8.6e-03 61 2.4e-01 2.5e-03 7.3e-03 60 2.3e-01 2.5e-03 7.2e-03 2048 61 2.6e-01 2.8e-03 8.3e-03 60 2.6e-01 2.8e-03 8.2e-03 60 2.6e-01 2.8e-03 8.2e-03 4096 54 2.7e-01 2.9e-03 8.6e-03 53 2.7e-01 3.0e-03 8.5e-03 54 2.7e-01 2.9e-03 8.6e-03 10624 35 2.6e-01 2.7e-03 7.9e-03 34 2.5e-01 2.6e-03 7.6e-03 36 2.6e-01 2.7e-03 8.1e-03 27554 25 2.7e-01 2.7e-03 8.5e-03 25 2.7e-01 2.7e-03 8.7e-03 25 2.7e-01 2.8e-03 8.6e-03 71468 18 3.5e-01 3.4e-03 1.1e-02 17 3.3e-01 3.1e-03 1.1e-02 17 3.4e-01 3.2e-03 1.1e-02 185364 10 4.5e-01 4.4e-03 1.4e-02 10 4.5e-01 4.2e-03 1.5e-02 10 4.6e-01 4.0e-03 1.4e-02 480774 4 4.4e-01 4.1e-03 1.5e-02 4 4.4e-01 4.2e-03 1.5e-02 4 4.4e-01 3.9e-03 1.4e-02 1246974 1 2.6e-01 2.2e-03 1.1e-02 1 2.6e-01 2.3e-03 8.5e-03 1 2.5e-01 2.2e-03 9.8e-03 3234251 1 6.3e-01 6.5e-03 2.0e-02 1 6.4e-01 6.5e-03 2.2e-02 1 6.5e-01 6.5e-03 2.2e-02 8388608 1 1.6e+00 1.7e-02 5.2e-02 1 1.6e+00 1.7e-02 5.3e-02 1 1.6e+00 1.6e-02 5.1e-02 SECTION-LOOPLNGS-END SECTION-ELAPSED-BEGIN measurment loop: elapsed time = 78.361 sec sum of max elapsed time per entries above = 77.493 sec difference to elapsed time = 0.868 sec = 1.1% sum based on fastest repetition = 71.669 sec difference to elapsed time = 6.693 sec = 8.5% 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*2&+1 1 7 1.00 1.00 0 ( -1 -1 -1 ) p01 ring-2*4&-1 2 14 2.00 1.00 0 ( -1 -1 -1 ) p02 ring-1*7fix 2 14 2.00 1.00 0 ( -1 -1 -1 ) p03 ring-1*7fix 2 14 2.00 1.00 0 ( -1 -1 -1 ) p04 ring-1*7fix 2 14 2.00 1.00 0 ( -1 -1 -1 ) p05 ring-1*7fix 2 14 2.00 1.00 0 ( -1 -1 -1 ) p06 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p07 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p08 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p09 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p10 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p11 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p12 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p13 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p14 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p15 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p16 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p17 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p18 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p19 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p20 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p21 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p22 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p23 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p24 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p25 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p26 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p27 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p28 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p29 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p30 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p31 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p32 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p33 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p34 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p35 random-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p36 worst-cyc-1dim 2 14 2.00 1.00 0 ( -1 -1 -1 ) p37 best bi-section 2 6 1.00 0.50 1 ( -1 -1 -1 ) p38 worst bi-section 2 6 1.00 0.50 1 ( -1 -1 -1 ) p39 one PingPong Pair 2 2 1.00 0.50 5 ( -1 -1 -1 ) p40 acyclic-2dim-all 4 14 2.33 0.58 1 ( -1 -1 -1 ) p41 acyclic-3dim-all 4 14 2.33 0.58 1 ( -1 -1 -1 ) p42 cyclic-2dim-x 2 12 2.00 1.00 1 ( -1 -1 -1 ) p43 cyclic-2dim-y 1 6 1.00 1.00 1 ( -1 -1 -1 ) p44 cyclic-2dim-all 3 18 3.00 1.00 1 ( -1 -1 -1 ) p45 cyclic-3dim-x 2 12 2.00 1.00 1 ( -1 -1 -1 ) p46 cyclic-3dim-y 1 6 1.00 1.00 1 ( -1 -1 -1 ) p47 cyclic-3dim-all 3 18 3.00 1.00 1 ( -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*2&+1 : 167.090 55.574 144.039 -> 167.090 -> 1169.633 MByte/s p01 ring-2*4&-1 : 162.336 106.404 144.299 -> 162.336 -> 1136.355 MByte/s p02 ring-1*7fix : 157.101 90.524 143.669 -> 157.101 -> 1099.710 MByte/s p03 ring-1*7fix : 157.715 90.107 146.301 -> 157.715 -> 1104.002 MByte/s p04 ring-1*7fix : 158.916 89.709 144.271 -> 158.916 -> 1112.409 MByte/s p05 ring-1*7fix : 157.337 89.099 141.700 -> 157.337 -> 1101.358 MByte/s p06 random-cyc-1dim : 159.660 89.387 142.179 -> 159.660 -> 1117.618 MByte/s p07 random-cyc-1dim : 156.849 90.632 146.816 -> 156.849 -> 1097.945 MByte/s p08 random-cyc-1dim : 159.540 88.605 149.991 -> 159.540 -> 1116.781 MByte/s p09 random-cyc-1dim : 159.116 89.940 146.062 -> 159.116 -> 1113.812 MByte/s p10 random-cyc-1dim : 159.225 89.950 147.956 -> 159.225 -> 1114.575 MByte/s p11 random-cyc-1dim : 157.704 88.752 147.020 -> 157.704 -> 1103.925 MByte/s p12 random-cyc-1dim : 159.470 89.979 147.968 -> 159.470 -> 1116.289 MByte/s p13 random-cyc-1dim : 158.587 89.190 151.157 -> 158.587 -> 1110.112 MByte/s p14 random-cyc-1dim : 158.029 87.523 147.040 -> 158.029 -> 1106.204 MByte/s p15 random-cyc-1dim : 159.049 89.754 147.201 -> 159.049 -> 1113.340 MByte/s p16 random-cyc-1dim : 159.898 90.568 144.255 -> 159.898 -> 1119.287 MByte/s p17 random-cyc-1dim : 159.236 88.870 147.763 -> 159.236 -> 1114.650 MByte/s p18 random-cyc-1dim : 158.124 89.737 146.058 -> 158.124 -> 1106.868 MByte/s p19 random-cyc-1dim : 158.571 89.841 150.018 -> 158.571 -> 1109.997 MByte/s p20 random-cyc-1dim : 158.184 89.981 148.312 -> 158.184 -> 1107.287 MByte/s p21 random-cyc-1dim : 153.658 88.869 146.656 -> 153.658 -> 1075.604 MByte/s p22 random-cyc-1dim : 159.461 89.545 147.332 -> 159.461 -> 1116.224 MByte/s p23 random-cyc-1dim : 160.186 90.461 147.511 -> 160.186 -> 1121.304 MByte/s p24 random-cyc-1dim : 155.994 88.770 147.466 -> 155.994 -> 1091.959 MByte/s p25 random-cyc-1dim : 158.265 88.598 146.564 -> 158.265 -> 1107.853 MByte/s p26 random-cyc-1dim : 159.457 89.039 144.443 -> 159.457 -> 1116.196 MByte/s p27 random-cyc-1dim : 159.156 88.834 143.306 -> 159.156 -> 1114.094 MByte/s p28 random-cyc-1dim : 159.583 88.898 146.899 -> 159.583 -> 1117.079 MByte/s p29 random-cyc-1dim : 156.945 88.527 146.552 -> 156.945 -> 1098.612 MByte/s p30 random-cyc-1dim : 159.396 89.231 145.334 -> 159.396 -> 1115.772 MByte/s p31 random-cyc-1dim : 157.207 90.611 145.606 -> 157.207 -> 1100.451 MByte/s p32 random-cyc-1dim : 158.773 88.775 146.129 -> 158.773 -> 1111.411 MByte/s p33 random-cyc-1dim : 158.628 90.655 146.797 -> 158.628 -> 1110.398 MByte/s p34 random-cyc-1dim : 159.887 87.898 146.539 -> 159.887 -> 1119.206 MByte/s p35 random-cyc-1dim : 156.418 89.526 147.110 -> 156.418 -> 1094.926 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 159.205 90.078 147.344 -> 159.205 -> 1114.438 MByte/s p37 best bi-section : 131.778 75.911 135.361 -> 135.361 -> 947.526 MByte/s p38 worst bi-section : 132.284 117.474 135.314 -> 135.314 -> 947.199 MByte/s p39 one PingPong Pair : 46.565 0.000 0.000 -> 46.565 -> 325.952 MByte/s p40 acyclic-2dim-all : 109.155 84.814 109.070 -> 109.155 -> 764.082 MByte/s p41 acyclic-3dim-all : 109.192 85.319 109.164 -> 109.192 -> 764.346 MByte/s p42 cyclic-2dim-x : 141.745 93.454 125.640 -> 141.745 -> 992.213 MByte/s p43 cyclic-2dim-y : 147.644 80.064 130.635 -> 147.644 -> 1033.505 MByte/s p44 cyclic-2dim-all : 137.270 92.596 129.254 -> 137.270 -> 960.892 MByte/s p45 cyclic-3dim-x : 141.429 92.342 125.550 -> 141.429 -> 990.002 MByte/s p46 cyclic-3dim-y : 147.696 77.894 134.658 -> 147.696 -> 1033.872 MByte/s p47 cyclic-3dim-all : 137.046 93.271 128.605 -> 137.046 -> 959.324 MByte/s log_avg of all rings : 160.043 85.312 144.040 || 160.043 -> 1120.299 MByte/s log_avg of all random : 158.469 89.361 146.790 || 158.469 -> 1109.283 MByte/s log_avg(ring,random) : 159.254 87.313 145.409 ||(159.254 -> 1114.777)MByte/s * size -> accumulated on all pr.: 1114.777 611.193 1017.860 ||(1114.777)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*2&+1 : 162.954 164.304 162.189 -> 164.304 -> 1150.127 MByte/s p01 ring-2*4&-1 : 154.902 155.617 153.493 -> 155.617 -> 1089.317 MByte/s p02 ring-1*7fix : 154.334 151.065 152.317 -> 154.334 -> 1080.340 MByte/s p03 ring-1*7fix : 156.557 149.340 152.226 -> 156.557 -> 1095.899 MByte/s p04 ring-1*7fix : 149.570 156.008 154.217 -> 156.008 -> 1092.054 MByte/s p05 ring-1*7fix : 155.308 153.735 152.529 -> 155.308 -> 1087.153 MByte/s p06 random-cyc-1dim : 155.176 157.860 152.762 -> 157.860 -> 1105.019 MByte/s p07 random-cyc-1dim : 155.431 154.446 152.926 -> 155.431 -> 1088.017 MByte/s p08 random-cyc-1dim : 159.730 156.904 154.825 -> 159.730 -> 1118.107 MByte/s p09 random-cyc-1dim : 156.232 156.234 154.074 -> 156.234 -> 1093.635 MByte/s p10 random-cyc-1dim : 155.179 156.528 154.154 -> 156.528 -> 1095.696 MByte/s p11 random-cyc-1dim : 155.960 155.911 151.191 -> 155.960 -> 1091.719 MByte/s p12 random-cyc-1dim : 157.450 154.575 157.285 -> 157.450 -> 1102.148 MByte/s p13 random-cyc-1dim : 154.839 158.566 158.206 -> 158.566 -> 1109.962 MByte/s p14 random-cyc-1dim : 156.925 153.266 153.354 -> 156.925 -> 1098.478 MByte/s p15 random-cyc-1dim : 154.999 153.263 157.064 -> 157.064 -> 1099.448 MByte/s p16 random-cyc-1dim : 153.347 157.403 157.306 -> 157.403 -> 1101.822 MByte/s p17 random-cyc-1dim : 158.264 158.473 157.354 -> 158.473 -> 1109.310 MByte/s p18 random-cyc-1dim : 155.021 157.023 153.668 -> 157.023 -> 1099.158 MByte/s p19 random-cyc-1dim : 158.374 158.328 154.431 -> 158.374 -> 1108.615 MByte/s p20 random-cyc-1dim : 156.618 158.156 152.423 -> 158.156 -> 1107.094 MByte/s p21 random-cyc-1dim : 157.440 157.146 156.448 -> 157.440 -> 1102.078 MByte/s p22 random-cyc-1dim : 156.782 155.470 156.561 -> 156.782 -> 1097.473 MByte/s p23 random-cyc-1dim : 158.800 152.420 156.793 -> 158.800 -> 1111.601 MByte/s p24 random-cyc-1dim : 148.106 156.205 154.864 -> 156.205 -> 1093.432 MByte/s p25 random-cyc-1dim : 154.726 157.111 155.932 -> 157.111 -> 1099.780 MByte/s p26 random-cyc-1dim : 157.388 155.307 156.462 -> 157.388 -> 1101.715 MByte/s p27 random-cyc-1dim : 154.904 154.314 157.360 -> 157.360 -> 1101.517 MByte/s p28 random-cyc-1dim : 155.686 157.185 154.334 -> 157.185 -> 1100.297 MByte/s p29 random-cyc-1dim : 155.790 154.881 155.184 -> 155.790 -> 1090.529 MByte/s p30 random-cyc-1dim : 153.024 158.442 153.531 -> 158.442 -> 1109.094 MByte/s p31 random-cyc-1dim : 155.549 155.404 152.426 -> 155.549 -> 1088.841 MByte/s p32 random-cyc-1dim : 155.761 155.044 153.401 -> 155.761 -> 1090.328 MByte/s p33 random-cyc-1dim : 156.243 155.424 155.498 -> 156.243 -> 1093.702 MByte/s p34 random-cyc-1dim : 157.642 156.047 152.794 -> 157.642 -> 1103.495 MByte/s p35 random-cyc-1dim : 156.714 154.087 150.266 -> 156.714 -> 1096.998 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim : 157.616 154.023 156.744 -> 157.616 -> 1103.309 MByte/s p37 best bi-section : 138.972 137.518 138.222 -> 138.972 -> 972.803 MByte/s p38 worst bi-section : 140.260 139.226 136.590 -> 140.260 -> 981.822 MByte/s p39 one PingPong Pair : 42.621 45.927 44.421 -> 45.927 -> 321.491 MByte/s p40 acyclic-2dim-all : 111.020 111.263 110.515 -> 111.263 -> 778.840 MByte/s p41 acyclic-3dim-all : 109.347 109.003 110.412 -> 110.412 -> 772.884 MByte/s p42 cyclic-2dim-x : 140.422 136.777 137.365 -> 140.422 -> 982.953 MByte/s p43 cyclic-2dim-y : 145.861 143.840 148.801 -> 148.801 -> 1041.606 MByte/s p44 cyclic-2dim-all : 135.862 134.491 134.104 -> 135.862 -> 951.037 MByte/s p45 cyclic-3dim-x : 139.361 137.940 135.765 -> 139.361 -> 975.525 MByte/s p46 cyclic-3dim-y : 149.070 144.662 144.683 -> 149.070 -> 1043.487 MByte/s p47 cyclic-3dim-all : 135.683 131.891 135.862 -> 135.862 -> 951.034 MByte/s log_avg of all rings : 155.554 154.939 154.456 || 156.987 -> 1098.907 MByte/s log_avg of all random : 155.923 156.039 154.749 || 157.183 -> 1100.280 MByte/s log_avg(ring,random) : 155.738 155.488 154.603 ||(157.085 -> 1099.593)MByte/s * size -> accumulated on all pr.: 1090.169 1088.415 1082.219 ||(1099.593)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*2&+1 p00 method 0 =Sndrcv :( 15.734) 0.064 0.991 13.663 115.748 424.651 494.729 -> 167.090 -> 1169.633 MByte/s p00 method 1 =Alltoal :(107.710) 0.009 0.149 2.289 28.811 159.820 174.045 -> 55.574 -> 389.017 MByte/s p00 method 2 =non-blk :( 38.373) 0.026 0.416 6.195 73.489 356.133 492.809 -> 144.039 -> 1008.274 MByte/s p01 ring-2*4&-1 p01 method 0 =Sndrcv :( 15.885) 0.063 0.997 13.652 114.836 414.779 486.860 -> 162.336 -> 1136.355 MByte/s p01 method 1 =Alltoal :( 54.888) 0.018 0.289 4.463 54.313 269.956 341.118 -> 106.404 -> 744.831 MByte/s p01 method 2 =non-blk :( 36.725) 0.027 0.438 6.408 76.778 348.198 488.263 -> 144.299 -> 1010.091 MByte/s p02 ring-1*7fix p02 method 0 =Sndrcv :( 15.851) 0.063 0.979 13.873 119.207 369.953 487.624 -> 157.101 -> 1099.710 MByte/s p02 method 1 =Alltoal :( 54.742) 0.018 0.291 4.496 50.387 272.594 260.568 -> 90.524 -> 633.665 MByte/s p02 method 2 =non-blk :( 36.515) 0.027 0.436 6.406 77.459 360.037 480.090 -> 143.669 -> 1005.680 MByte/s p03 ring-1*7fix p03 method 0 =Sndrcv :( 16.073) 0.062 0.999 13.843 115.660 390.953 490.246 -> 157.715 -> 1104.002 MByte/s p03 method 1 =Alltoal :( 54.707) 0.018 0.295 4.510 50.960 279.478 260.633 -> 90.107 -> 630.752 MByte/s p03 method 2 =non-blk :( 36.525) 0.027 0.435 6.697 76.226 385.011 484.638 -> 146.301 -> 1024.107 MByte/s p04 ring-1*7fix p04 method 0 =Sndrcv :( 16.030) 0.062 0.989 13.914 116.686 409.234 488.179 -> 158.916 -> 1112.409 MByte/s p04 method 1 =Alltoal :( 54.912) 0.018 0.290 4.501 50.392 265.882 261.221 -> 89.709 -> 627.965 MByte/s p04 method 2 =non-blk :( 36.608) 0.027 0.436 6.433 76.736 388.766 477.588 -> 144.271 -> 1009.897 MByte/s p05 ring-1*7fix p05 method 0 =Sndrcv :( 15.992) 0.063 0.978 13.873 117.517 390.351 480.297 -> 157.337 -> 1101.358 MByte/s p05 method 1 =Alltoal :( 55.088) 0.018 0.293 4.493 50.309 272.161 256.344 -> 89.099 -> 623.695 MByte/s p05 method 2 =non-blk :( 36.505) 0.027 0.438 6.578 75.955 370.027 482.993 -> 141.700 -> 991.897 MByte/s p06 random-cyc-1dim p06 method 0 =Sndrcv :( 15.868) 0.063 0.993 13.489 115.537 393.219 478.148 -> 159.660 -> 1117.618 MByte/s p06 method 1 =Alltoal :( 55.000) 0.018 0.289 4.478 50.143 262.029 259.991 -> 89.387 -> 625.710 MByte/s p06 method 2 =non-blk :( 36.833) 0.027 0.441 6.617 76.774 387.951 484.093 -> 142.179 -> 995.255 MByte/s p07 random-cyc-1dim p07 method 0 =Sndrcv :( 15.764) 0.063 1.000 13.771 117.372 366.906 484.610 -> 156.849 -> 1097.945 MByte/s p07 method 1 =Alltoal :( 55.277) 0.018 0.294 4.529 51.053 268.673 260.698 -> 90.632 -> 634.426 MByte/s p07 method 2 =non-blk :( 36.652) 0.027 0.436 6.521 76.774 378.719 480.407 -> 146.816 -> 1027.711 MByte/s p08 random-cyc-1dim p08 method 0 =Sndrcv :( 16.010) 0.062 0.986 13.356 119.376 386.106 488.847 -> 159.540 -> 1116.781 MByte/s p08 method 1 =Alltoal :( 55.282) 0.018 0.292 4.480 49.812 268.905 260.917 -> 88.605 -> 620.238 MByte/s p08 method 2 =non-blk :( 36.405) 0.027 0.437 6.569 77.364 380.820 490.175 -> 149.991 -> 1049.939 MByte/s p09 random-cyc-1dim p09 method 0 =Sndrcv :( 16.099) 0.062 0.998 14.008 117.497 420.182 489.130 -> 159.116 -> 1113.812 MByte/s p09 method 1 =Alltoal :( 55.172) 0.018 0.290 4.478 49.523 268.515 259.955 -> 89.940 -> 629.582 MByte/s p09 method 2 =non-blk :( 36.370) 0.027 0.434 6.641 77.364 389.994 479.856 -> 146.062 -> 1022.433 MByte/s p10 random-cyc-1dim p10 method 0 =Sndrcv :( 15.870) 0.063 0.980 13.581 116.332 401.831 487.497 -> 159.225 -> 1114.575 MByte/s p10 method 1 =Alltoal :( 54.848) 0.018 0.294 4.525 50.830 260.292 260.933 -> 89.950 -> 629.649 MByte/s p10 method 2 =non-blk :( 36.181) 0.028 0.437 6.518 76.179 400.223 488.960 -> 147.956 -> 1035.689 MByte/s p11 random-cyc-1dim p11 method 0 =Sndrcv :( 16.132) 0.062 0.973 13.805 119.752 392.094 489.304 -> 157.704 -> 1103.925 MByte/s p11 method 1 =Alltoal :( 54.851) 0.018 0.292 4.469 49.015 257.630 260.852 -> 88.752 -> 621.262 MByte/s p11 method 2 =non-blk :( 36.478) 0.027 0.438 6.518 75.786 395.696 475.760 -> 147.020 -> 1029.142 MByte/s p12 random-cyc-1dim p12 method 0 =Sndrcv :( 15.740) 0.064 0.996 13.854 118.228 389.625 485.959 -> 159.470 -> 1116.289 MByte/s p12 method 1 =Alltoal :( 54.625) 0.018 0.293 4.366 50.335 266.806 260.326 -> 89.979 -> 629.853 MByte/s p12 method 2 =non-blk :( 36.196) 0.028 0.438 6.617 76.114 395.319 493.767 -> 147.968 -> 1035.774 MByte/s p13 random-cyc-1dim p13 method 0 =Sndrcv :( 15.860) 0.063 0.999 13.446 115.696 394.937 487.725 -> 158.587 -> 1110.112 MByte/s p13 method 1 =Alltoal :( 55.083) 0.018 0.293 4.513 50.321 263.677 259.677 -> 89.190 -> 624.327 MByte/s p13 method 2 =non-blk :( 36.299) 0.028 0.431 6.560 76.960 392.015 490.404 -> 151.157 -> 1058.100 MByte/s p14 random-cyc-1dim p14 method 0 =Sndrcv :( 15.817) 0.063 1.000 13.710 118.374 401.225 485.466 -> 158.029 -> 1106.204 MByte/s p14 method 1 =Alltoal :( 54.710) 0.018 0.292 4.491 50.947 255.615 260.056 -> 87.523 -> 612.664 MByte/s p14 method 2 =non-blk :( 36.270) 0.028 0.437 6.563 75.985 386.255 477.805 -> 147.040 -> 1029.282 MByte/s p15 random-cyc-1dim p15 method 0 =Sndrcv :( 15.735) 0.064 1.006 13.987 117.497 374.441 487.242 -> 159.049 -> 1113.340 MByte/s p15 method 1 =Alltoal :( 54.738) 0.018 0.292 4.472 50.460 269.422 260.140 -> 89.754 -> 628.280 MByte/s p15 method 2 =non-blk :( 36.340) 0.028 0.439 6.670 76.801 374.776 481.923 -> 147.201 -> 1030.409 MByte/s p16 random-cyc-1dim p16 method 0 =Sndrcv :( 15.982) 0.063 0.987 13.663 117.861 400.068 485.831 -> 159.898 -> 1119.287 MByte/s p16 method 1 =Alltoal :( 54.735) 0.018 0.291 4.522 51.240 264.555 260.670 -> 90.568 -> 633.977 MByte/s p16 method 2 =non-blk :( 36.302) 0.028 0.436 6.589 76.112 389.501 482.354 -> 144.255 -> 1009.786 MByte/s p17 random-cyc-1dim p17 method 0 =Sndrcv :( 16.018) 0.062 0.993 14.028 116.313 390.614 486.873 -> 159.236 -> 1114.650 MByte/s p17 method 1 =Alltoal :( 54.892) 0.018 0.293 4.525 51.602 251.542 261.287 -> 88.870 -> 622.091 MByte/s p17 method 2 =non-blk :( 36.270) 0.028 0.437 6.524 76.468 393.259 480.764 -> 147.763 -> 1034.343 MByte/s p18 random-cyc-1dim p18 method 0 =Sndrcv :( 15.823) 0.063 0.996 13.644 119.508 391.785 485.565 -> 158.124 -> 1106.868 MByte/s p18 method 1 =Alltoal :( 54.850) 0.018 0.293 4.508 50.257 270.539 258.573 -> 89.737 -> 628.158 MByte/s p18 method 2 =non-blk :( 36.853) 0.027 0.435 6.630 76.441 378.715 478.870 -> 146.058 -> 1022.409 MByte/s p19 random-cyc-1dim p19 method 0 =Sndrcv :( 16.251) 0.062 0.971 13.805 117.515 377.075 480.613 -> 158.571 -> 1109.997 MByte/s p19 method 1 =Alltoal :( 55.237) 0.018 0.292 4.498 50.988 271.828 255.287 -> 89.841 -> 628.888 MByte/s p19 method 2 =non-blk :( 36.314) 0.028 0.438 6.518 77.000 371.468 474.776 -> 150.018 -> 1050.125 MByte/s p20 random-cyc-1dim p20 method 0 =Sndrcv :( 15.904) 0.063 1.001 13.873 116.013 373.565 486.241 -> 158.184 -> 1107.287 MByte/s p20 method 1 =Alltoal :( 54.963) 0.018 0.291 4.505 50.790 264.334 260.322 -> 89.981 -> 629.865 MByte/s p20 method 2 =non-blk :( 36.068) 0.028 0.437 6.602 76.198 383.857 491.078 -> 148.312 -> 1038.184 MByte/s p21 random-cyc-1dim p21 method 0 =Sndrcv :( 15.781) 0.063 0.989 13.373 116.797 376.898 487.426 -> 153.658 -> 1075.604 MByte/s p21 method 1 =Alltoal :( 55.207) 0.018 0.294 4.534 49.805 264.591 259.745 -> 88.869 -> 622.081 MByte/s p21 method 2 =non-blk :( 36.142) 0.028 0.439 6.701 78.184 369.913 489.861 -> 146.656 -> 1026.590 MByte/s p22 random-cyc-1dim p22 method 0 =Sndrcv :( 15.903) 0.063 0.991 13.665 115.679 404.164 482.216 -> 159.461 -> 1116.224 MByte/s p22 method 1 =Alltoal :( 54.564) 0.018 0.290 4.515 51.454 254.572 260.326 -> 89.545 -> 626.812 MByte/s p22 method 2 =non-blk :( 36.505) 0.027 0.437 6.537 75.654 386.942 489.660 -> 147.332 -> 1031.321 MByte/s p23 random-cyc-1dim p23 method 0 =Sndrcv :( 16.007) 0.062 0.986 13.512 115.221 395.701 488.234 -> 160.186 -> 1121.304 MByte/s p23 method 1 =Alltoal :( 54.460) 0.018 0.293 4.499 51.280 268.445 260.605 -> 90.461 -> 633.228 MByte/s p23 method 2 =non-blk :( 36.322) 0.028 0.436 6.658 75.168 378.332 482.159 -> 147.511 -> 1032.576 MByte/s p24 random-cyc-1dim p24 method 0 =Sndrcv :( 15.830) 0.063 0.988 13.701 117.463 399.662 488.263 -> 155.994 -> 1091.959 MByte/s p24 method 1 =Alltoal :( 54.654) 0.018 0.294 4.529 50.044 255.271 260.459 -> 88.770 -> 621.390 MByte/s p24 method 2 =non-blk :( 36.435) 0.027 0.438 6.641 76.900 382.154 489.204 -> 147.466 -> 1032.261 MByte/s p25 random-cyc-1dim p25 method 0 =Sndrcv :( 15.989) 0.063 0.985 13.827 120.834 373.781 483.953 -> 158.265 -> 1107.853 MByte/s p25 method 1 =Alltoal :( 54.486) 0.018 0.292 4.523 50.817 277.255 259.677 -> 88.598 -> 620.188 MByte/s p25 method 2 =non-blk :( 36.515) 0.027 0.437 6.563 76.933 362.395 474.400 -> 146.564 -> 1025.945 MByte/s p26 random-cyc-1dim p26 method 0 =Sndrcv :( 15.962) 0.063 0.992 13.590 115.751 382.337 483.702 -> 159.457 -> 1116.196 MByte/s p26 method 1 =Alltoal :( 54.424) 0.018 0.291 4.519 50.594 267.353 259.348 -> 89.039 -> 623.275 MByte/s p26 method 2 =non-blk :( 36.390) 0.027 0.438 6.538 75.246 366.365 482.381 -> 144.443 -> 1011.099 MByte/s p27 random-cyc-1dim p27 method 0 =Sndrcv :( 15.993) 0.063 0.975 13.997 116.510 393.214 484.428 -> 159.156 -> 1114.094 MByte/s p27 method 1 =Alltoal :( 54.398) 0.018 0.292 4.510 51.226 256.116 260.767 -> 88.834 -> 621.836 MByte/s p27 method 2 =non-blk :( 36.603) 0.027 0.434 6.663 76.641 382.469 477.560 -> 143.306 -> 1003.144 MByte/s p28 random-cyc-1dim p28 method 0 =Sndrcv :( 16.181) 0.062 0.982 13.731 118.614 405.700 482.992 -> 159.583 -> 1117.079 MByte/s p28 method 1 =Alltoal :( 54.730) 0.018 0.290 4.505 50.182 249.370 260.310 -> 88.898 -> 622.288 MByte/s p28 method 2 =non-blk :( 36.248) 0.028 0.438 6.548 78.323 394.686 478.146 -> 146.899 -> 1028.296 MByte/s p29 random-cyc-1dim p29 method 0 =Sndrcv :( 16.068) 0.062 1.001 13.562 115.765 388.231 487.003 -> 156.945 -> 1098.612 MByte/s p29 method 1 =Alltoal :( 54.922) 0.018 0.291 4.496 51.427 256.173 260.747 -> 88.527 -> 619.692 MByte/s p29 method 2 =non-blk :( 36.510) 0.027 0.439 6.654 75.747 362.750 486.988 -> 146.552 -> 1025.863 MByte/s p30 random-cyc-1dim p30 method 0 =Sndrcv :( 15.860) 0.063 0.987 13.738 117.389 398.704 482.244 -> 159.396 -> 1115.772 MByte/s p30 method 1 =Alltoal :( 54.385) 0.018 0.292 4.541 50.750 261.321 258.330 -> 89.231 -> 624.619 MByte/s p30 method 2 =non-blk :( 36.450) 0.027 0.433 6.700 77.050 376.564 490.103 -> 145.334 -> 1017.341 MByte/s p31 random-cyc-1dim p31 method 0 =Sndrcv :( 15.907) 0.063 0.991 13.607 116.829 355.136 488.334 -> 157.207 -> 1100.451 MByte/s p31 method 1 =Alltoal :( 54.243) 0.018 0.293 4.541 51.161 271.298 260.310 -> 90.611 -> 634.278 MByte/s p31 method 2 =non-blk :( 36.363) 0.028 0.438 6.574 76.922 368.043 488.575 -> 145.606 -> 1019.245 MByte/s p32 random-cyc-1dim p32 method 0 =Sndrcv :( 15.687) 0.064 1.004 13.911 116.635 405.947 486.367 -> 158.773 -> 1111.411 MByte/s p32 method 1 =Alltoal :( 54.693) 0.018 0.291 4.528 50.555 267.127 261.421 -> 88.775 -> 621.423 MByte/s p32 method 2 =non-blk :( 36.697) 0.027 0.436 6.647 75.399 381.292 473.492 -> 146.129 -> 1022.904 MByte/s p33 random-cyc-1dim p33 method 0 =Sndrcv :( 15.905) 0.063 0.983 13.678 115.169 407.636 483.757 -> 158.628 -> 1110.398 MByte/s p33 method 1 =Alltoal :( 54.564) 0.018 0.291 4.529 50.759 270.308 260.759 -> 90.655 -> 634.582 MByte/s p33 method 2 =non-blk :( 36.554) 0.027 0.431 6.663 76.987 394.937 478.391 -> 146.797 -> 1027.580 MByte/s p34 random-cyc-1dim p34 method 0 =Sndrcv :( 16.013) 0.062 0.989 13.520 117.279 408.703 488.462 -> 159.887 -> 1119.206 MByte/s p34 method 1 =Alltoal :( 54.257) 0.018 0.285 4.491 50.935 265.977 259.228 -> 87.898 -> 615.283 MByte/s p34 method 2 =non-blk :( 36.471) 0.027 0.439 6.550 77.229 387.632 480.598 -> 146.539 -> 1025.770 MByte/s p35 random-cyc-1dim p35 method 0 =Sndrcv :( 15.719) 0.064 0.992 13.873 119.300 376.969 483.202 -> 156.418 -> 1094.926 MByte/s p35 method 1 =Alltoal :( 54.450) 0.018 0.291 4.354 50.478 258.254 260.088 -> 89.526 -> 626.682 MByte/s p35 method 2 =non-blk :( 36.897) 0.027 0.433 6.703 77.786 378.719 471.402 -> 147.110 -> 1029.767 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim p36 method 0 =Sndrcv :( 15.823) 0.063 0.982 13.451 116.387 391.847 482.090 -> 159.205 -> 1114.438 MByte/s p36 method 1 =Alltoal :( 54.077) 0.018 0.292 4.493 50.935 264.107 261.984 -> 90.078 -> 630.547 MByte/s p36 method 2 =non-blk :( 36.617) 0.027 0.431 6.656 77.146 399.016 482.075 -> 147.344 -> 1031.410 MByte/s p37 best bi-section p37 method 0 =Sndrcv :( 12.098) 0.035 0.552 7.563 75.187 318.302 493.666 -> 131.778 -> 922.444 MByte/s p37 method 1 =Alltoal :( 54.630) 0.008 0.123 1.994 27.155 230.490 226.258 -> 75.911 -> 531.378 MByte/s p37 method 2 =non-blk :( 17.936) 0.024 0.378 5.671 65.195 349.727 425.684 -> 135.361 -> 947.526 MByte/s p38 worst bi-section p38 method 0 =Sndrcv :( 12.025) 0.036 0.547 7.614 74.853 325.179 497.559 -> 132.284 -> 925.986 MByte/s p38 method 1 =Alltoal :( 54.380) 0.008 0.126 1.979 27.269 288.576 430.811 -> 117.474 -> 822.318 MByte/s p38 method 2 =non-blk :( 18.055) 0.024 0.375 5.638 64.030 364.325 429.345 -> 135.314 -> 947.199 MByte/s p39 one PingPong Pair p39 method 0 =Sndrcv :( 11.528) 0.012 0.189 2.598 28.259 114.159 172.501 -> 46.565 -> 325.952 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 :( 13.595) 0.037 0.571 8.250 76.653 267.060 353.912 -> 109.155 -> 764.082 MByte/s p40 method 1 =Alltoal :( 23.859) 0.021 0.330 5.049 55.981 232.916 258.704 -> 84.814 -> 593.698 MByte/s p40 method 2 =non-blk :( 23.408) 0.021 0.337 5.091 57.153 278.116 340.274 -> 109.070 -> 763.493 MByte/s p41 acyclic-3dim-all p41 method 0 =Sndrcv :( 13.598) 0.037 0.574 8.247 75.973 277.473 355.593 -> 109.192 -> 764.346 MByte/s p41 method 1 =Alltoal :( 23.989) 0.021 0.331 4.954 55.304 234.267 257.430 -> 85.319 -> 597.235 MByte/s p41 method 2 =non-blk :( 23.521) 0.021 0.337 5.130 56.815 293.993 341.626 -> 109.164 -> 764.145 MByte/s p42 cyclic-2dim-x p42 method 0 =Sndrcv :( 15.713) 0.055 0.858 12.115 101.190 355.623 428.436 -> 141.745 -> 992.213 MByte/s p42 method 1 =Alltoal :( 46.308) 0.019 0.286 4.530 49.375 260.435 295.688 -> 93.454 -> 654.175 MByte/s p42 method 2 =non-blk :( 35.605) 0.024 0.382 5.664 66.444 306.165 428.424 -> 125.640 -> 879.479 MByte/s p43 cyclic-2dim-y p43 method 0 =Sndrcv :( 15.749) 0.054 0.859 12.171 104.584 385.732 426.899 -> 147.644 -> 1033.505 MByte/s p43 method 1 =Alltoal :( 90.802) 0.009 0.149 2.352 31.346 256.540 224.499 -> 80.064 -> 560.446 MByte/s p43 method 2 =non-blk :( 37.210) 0.023 0.362 5.569 63.386 321.105 426.772 -> 130.635 -> 914.447 MByte/s p44 cyclic-2dim-all p44 method 0 =Sndrcv :( 15.714) 0.055 0.851 12.045 101.758 339.232 426.484 -> 137.270 -> 960.892 MByte/s p44 method 1 =Alltoal :( 31.205) 0.027 0.433 6.556 67.843 246.201 266.971 -> 92.596 -> 648.172 MByte/s p44 method 2 =non-blk :( 35.104) 0.024 0.386 5.868 66.654 337.452 422.914 -> 129.254 -> 904.778 MByte/s p45 cyclic-3dim-x p45 method 0 =Sndrcv :( 15.775) 0.054 0.858 12.161 103.793 373.328 427.507 -> 141.429 -> 990.002 MByte/s p45 method 1 =Alltoal :( 46.743) 0.018 0.295 4.554 49.480 262.545 295.021 -> 92.342 -> 646.393 MByte/s p45 method 2 =non-blk :( 35.655) 0.024 0.385 5.821 65.646 301.975 427.760 -> 125.550 -> 878.852 MByte/s p46 cyclic-3dim-y p46 method 0 =Sndrcv :( 15.903) 0.054 0.847 12.270 102.832 383.874 429.421 -> 147.696 -> 1033.872 MByte/s p46 method 1 =Alltoal :( 91.256) 0.009 0.146 2.354 31.208 252.602 223.848 -> 77.894 -> 545.258 MByte/s p46 method 2 =non-blk :( 37.220) 0.023 0.356 5.587 63.791 351.739 428.859 -> 134.658 -> 942.603 MByte/s p47 cyclic-3dim-all p47 method 0 =Sndrcv :( 15.776) 0.054 0.850 12.112 101.265 332.497 425.080 -> 137.046 -> 959.324 MByte/s p47 method 1 =Alltoal :( 31.393) 0.027 0.432 6.520 67.573 256.332 266.542 -> 93.271 -> 652.900 MByte/s p47 method 2 =non-blk :( 35.050) 0.024 0.385 5.879 65.882 328.249 420.785 -> 128.605 -> 900.234 MByte/s log_avg of all rings - ring, method 0 = Sndrcv : 0.063 0.989 13.803 116.600 399.569 487.970 || 160.043 -> 1120.299 MByte/s - ring, method 1 = Alltoal: 0.016 0.261 4.015 46.559 248.915 254.229 || 85.312 -> 597.185 MByte/s - ring, method 2 = non-blk: 0.027 0.433 6.451 76.097 367.731 484.371 || 144.040 -> 1008.280 MByte/s log_avg of all random - random, method 0 = Sndrcv : 0.063 0.990 13.709 117.261 390.624 485.647 || 158.469 -> 1109.283 MByte/s - random, method 1 = Alltoal: 0.018 0.292 4.499 50.623 263.508 260.058 || 89.361 -> 625.529 MByte/s - random, method 2 = non-blk: 0.027 0.437 6.600 76.612 382.258 482.759 || 146.790 -> 1027.532 MByte/s log_avg(ring,random) - average, method 0 = Sndrcv : 0.063 0.990 13.756 116.930 395.071 486.807 || 159.254 -> 1114.777 MByte/s - average, method 1 = Alltoal: 0.017 0.276 4.250 48.548 256.107 257.127 || 87.313 -> 611.193 MByte/s - average, method 2 = non-blk: 0.027 0.435 6.525 76.354 374.924 483.564 || 145.409 -> 1017.860 MByte/s * size -> accumulated on all processes: - accumulated, mthd 0 = Sndrcv : 0.440 6.928 96.290 818.512 2765.497 3407.650 || 1114.777 MByte/s - accumulated, mthd 1 = Alltoal: 0.121 1.930 29.749 339.838 1792.751 1799.886 || 611.193 MByte/s - accumulated, mthd 2 = non-blk: 0.191 3.044 45.674 534.478 2624.467 3384.948 || 1017.860 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 0.440 0.063 0.063 0.063 0.063 0.017 0.027 2 0.874 0.125 0.124 0.125 0.125 0.035 0.054 4 1.725 0.246 0.246 0.246 0.246 0.069 0.108 8 3.508 0.501 0.501 0.501 0.501 0.138 0.219 16 6.928 0.990 0.989 0.990 0.990 0.276 0.435 32 13.494 1.928 1.926 1.930 1.928 0.546 0.856 64 26.314 3.759 3.769 3.750 3.759 1.085 1.690 128 48.848 6.978 7.033 6.924 6.978 2.128 3.266 256 96.290 13.756 13.803 13.709 13.756 4.250 6.525 512 182.613 26.088 25.990 26.186 26.088 8.415 12.831 1024 341.175 48.739 48.660 48.819 48.739 16.450 24.996 2048 528.330 75.476 75.842 75.112 75.476 28.050 44.659 4096 818.512 116.930 116.600 117.261 116.930 48.548 76.354 10624 1222.062 174.580 178.047 171.181 174.580 80.775 135.845 27554 1885.207 269.315 273.152 265.533 269.315 142.507 232.992 71468 2458.985 351.284 350.538 352.030 350.909 207.846 334.771 185364 2771.518 395.931 399.569 392.327 395.071 256.107 374.924 480774 3030.014 432.859 432.095 433.625 430.782 268.557 406.618 1246974 3270.487 467.212 464.636 469.803 461.747 255.796 441.012 3234251 3362.103 480.300 479.942 480.659 478.213 253.771 470.018 8388608 3415.079 487.868 488.660 487.078 486.807 257.127 483.564 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*2&+1 :( 15.734) 0.064 0.991 13.663 115.748 424.651 494.729 -> 167.417 -> 1171.922 MByte/s p01 ring-2*4&-1 :( 15.885) 0.063 0.997 13.652 114.836 414.779 488.263 -> 162.567 -> 1137.969 MByte/s p02 ring-1*7fix :( 15.851) 0.063 0.979 13.873 119.207 369.953 487.624 -> 157.101 -> 1099.710 MByte/s p03 ring-1*7fix :( 16.073) 0.062 0.999 13.843 115.660 390.953 490.246 -> 157.735 -> 1104.144 MByte/s p04 ring-1*7fix :( 16.030) 0.062 0.989 13.914 116.686 409.234 488.179 -> 158.916 -> 1112.409 MByte/s p05 ring-1*7fix :( 15.992) 0.063 0.978 13.873 117.517 390.351 482.993 -> 157.465 -> 1102.257 MByte/s p06 random-cyc-1dim :( 15.868) 0.063 0.993 13.489 115.537 393.219 484.093 -> 159.943 -> 1119.600 MByte/s p07 random-cyc-1dim :( 15.764) 0.063 1.000 13.771 117.372 378.719 484.610 -> 158.000 -> 1105.997 MByte/s p08 random-cyc-1dim :( 16.010) 0.062 0.986 13.356 119.376 386.106 490.175 -> 160.836 -> 1125.852 MByte/s p09 random-cyc-1dim :( 16.099) 0.062 0.998 14.008 117.497 420.182 489.130 -> 159.116 -> 1113.812 MByte/s p10 random-cyc-1dim :( 15.870) 0.063 0.980 13.581 116.332 401.831 488.960 -> 159.739 -> 1118.171 MByte/s p11 random-cyc-1dim :( 16.132) 0.062 0.973 13.805 119.752 395.696 489.304 -> 157.887 -> 1105.212 MByte/s p12 random-cyc-1dim :( 15.740) 0.064 0.996 13.854 118.228 395.319 493.767 -> 160.113 -> 1120.790 MByte/s p13 random-cyc-1dim :( 15.860) 0.063 0.999 13.446 115.696 394.937 490.404 -> 160.806 -> 1125.639 MByte/s p14 random-cyc-1dim :( 15.817) 0.063 1.000 13.710 118.374 401.225 485.466 -> 160.031 -> 1120.215 MByte/s p15 random-cyc-1dim :( 15.735) 0.064 1.006 13.987 117.497 374.776 487.242 -> 159.578 -> 1117.043 MByte/s p16 random-cyc-1dim :( 15.982) 0.063 0.987 13.663 117.861 400.068 485.831 -> 160.292 -> 1122.042 MByte/s p17 random-cyc-1dim :( 16.018) 0.062 0.993 14.028 116.313 393.259 486.873 -> 160.188 -> 1121.318 MByte/s p18 random-cyc-1dim :( 15.823) 0.063 0.996 13.644 119.508 391.785 485.565 -> 158.854 -> 1111.978 MByte/s p19 random-cyc-1dim :( 16.251) 0.062 0.971 13.805 117.515 377.075 480.613 -> 160.169 -> 1121.181 MByte/s p20 random-cyc-1dim :( 15.904) 0.063 1.001 13.873 116.013 383.857 491.078 -> 159.002 -> 1113.016 MByte/s p21 random-cyc-1dim :( 15.781) 0.063 0.989 13.373 116.797 376.898 489.861 -> 160.563 -> 1123.943 MByte/s p22 random-cyc-1dim :( 15.903) 0.063 0.991 13.665 115.679 404.164 489.660 -> 160.009 -> 1120.060 MByte/s p23 random-cyc-1dim :( 16.007) 0.062 0.986 13.512 115.221 395.701 488.234 -> 160.901 -> 1126.305 MByte/s p24 random-cyc-1dim :( 15.830) 0.063 0.988 13.701 117.463 399.662 489.204 -> 157.999 -> 1105.996 MByte/s p25 random-cyc-1dim :( 15.989) 0.063 0.985 13.827 120.834 373.781 483.953 -> 158.879 -> 1112.155 MByte/s p26 random-cyc-1dim :( 15.962) 0.063 0.992 13.590 115.751 382.337 483.702 -> 159.457 -> 1116.196 MByte/s p27 random-cyc-1dim :( 15.993) 0.063 0.975 13.997 116.510 393.214 484.428 -> 159.399 -> 1115.793 MByte/s p28 random-cyc-1dim :( 16.181) 0.062 0.982 13.731 118.614 405.700 482.992 -> 159.583 -> 1117.079 MByte/s p29 random-cyc-1dim :( 16.068) 0.062 1.001 13.562 115.765 388.231 487.003 -> 158.560 -> 1109.918 MByte/s p30 random-cyc-1dim :( 15.860) 0.063 0.987 13.738 117.389 398.704 490.103 -> 159.770 -> 1118.392 MByte/s p31 random-cyc-1dim :( 15.907) 0.063 0.991 13.607 116.829 368.043 488.575 -> 157.995 -> 1105.965 MByte/s p32 random-cyc-1dim :( 15.687) 0.064 1.004 13.911 116.635 405.947 486.367 -> 159.490 -> 1116.429 MByte/s p33 random-cyc-1dim :( 15.905) 0.063 0.983 13.678 115.169 407.636 483.757 -> 158.849 -> 1111.943 MByte/s p34 random-cyc-1dim :( 16.013) 0.062 0.989 13.520 117.279 408.703 488.462 -> 159.887 -> 1119.206 MByte/s p35 random-cyc-1dim :( 15.719) 0.064 0.992 13.873 119.300 378.719 483.202 -> 157.684 -> 1103.786 MByte/s -- additional patterns that are not used to compute b_eff: p36 worst-cyc-1dim :( 15.823) 0.063 0.982 13.451 116.387 399.016 482.090 -> 159.706 -> 1117.939 MByte/s p37 best bi-section :( 12.098) 0.035 0.552 7.563 75.187 349.727 493.666 -> 140.955 -> 986.682 MByte/s p38 worst bi-section :( 12.025) 0.036 0.547 7.614 74.853 364.325 497.559 -> 141.506 -> 990.545 MByte/s p39 one PingPong Pair :( 11.528) 0.012 0.189 2.598 28.259 114.159 172.501 -> 46.565 -> 325.952 MByte/s p40 acyclic-2dim-all :( 13.595) 0.037 0.571 8.250 76.653 278.116 353.912 -> 112.437 -> 787.061 MByte/s p41 acyclic-3dim-all :( 13.598) 0.037 0.574 8.247 75.973 293.993 355.593 -> 112.648 -> 788.534 MByte/s p42 cyclic-2dim-x :( 15.713) 0.055 0.858 12.115 101.190 355.623 428.436 -> 142.198 -> 995.385 MByte/s p43 cyclic-2dim-y :( 15.749) 0.054 0.859 12.171 104.584 385.732 426.899 -> 151.133 -> 1057.934 MByte/s p44 cyclic-2dim-all :( 15.714) 0.055 0.851 12.045 101.758 339.232 426.484 -> 137.894 -> 965.257 MByte/s p45 cyclic-3dim-x :( 15.775) 0.054 0.858 12.161 103.793 373.328 427.760 -> 141.899 -> 993.293 MByte/s p46 cyclic-3dim-y :( 15.903) 0.054 0.847 12.270 102.832 383.874 429.421 -> 151.631 -> 1061.420 MByte/s p47 cyclic-3dim-all :( 15.776) 0.054 0.850 12.112 101.265 332.497 425.080 -> 137.483 -> 962.383 MByte/s log_avg of all rings : 0.063 0.989 13.803 116.600 399.569 488.660 || 160.158 -> 1121.106 MByte/s log_avg of all random : 0.063 0.990 13.709 117.261 392.327 487.078 || 159.450 -> 1116.150 MByte/s log_avg(ring,random) : 0.063 0.990 13.756 116.930 395.931 487.868 || 159.804 -> 1118.625 MByte/s * size -> accumulated on all pr.: 0.440 6.928 96.290 818.512 2771.518 3415.079 || 1118.625 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 1118.625 MByte/s on 7 processes ( = 159.804 MByte/s * 7 processes) Ping-pong latency: 11.528 microsec Ping-pong bandwidth: 1207.508 MByte/s at Lmax= 8.000 MByte (MByte/s=1e6 Byte/s) (MByte=2**20 Byte) system parameters : 7 nodes, 1024 MB/node system name : HI-UX/MPP hostname : himiko OS release : 03-00 OS version : ad2b0 machine : SR8000 Date of measurement: Mon Nov 29 18:00:36 1999 Total execution wall clock time = 80 seconds SECTION-BEFF-END b_eff = 1118.625 MB/s = 159.804 * 7 PEs with 1024 MB/PE on HI-UX/MPP himiko 03-00 ad2b0 SR8000