b_eff = 3134.033 MB/s = 47.485 * 66 PEs with 128 MB/PE on sn6715 hwwt3e 2.0.4.71 unicosmk CRAY T3E SECTION-HEAD-BEGIN b_eff.c, Revision 3.2 from Nov. 07, 1999 MEMORY_PER_PROCESSOR = 128 MBytes [1M = 1024*1024] 1-dim-paterns: size = 66 1-dim-paterns: size = 66 2-dim-paterns: size = 11 * 6 3-dim-paterns: size = 11 * 3 * 2 Used message lengths (and used loop length for each message lengths): msglng= 1 (300), 2 (300), 4 (300), 8 (300), 16 (300), 32 (300), 64 (300), 128 (300), 256 (300), 512 (300), 1024 (300), 2048 (300), 4096 (256), 8192 (128), 16384 (64), 32768 (32), 65536 (16), 131072 (8), 262144 (4), 524288 (2), 1048576 (1), SECTION-HEAD-END SECTION-LOOP-BEGIN measurment loop: elapsed time = 160.260 sec sum of max elapsed time per entries above = 165.261 sec difference = -5.001 sec = 3.1% The difference is less than 5 % SECTION-LOOP-END SECTION-PATTERN-BEGIN Pattern parameters: p00 ring-33*2fix => 1 sendrecv_calls with 66 messages, i.e. msgs/used node, all nodes are used p01 ring-16*4&+1 => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p02 ring-8*8&+1 => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p03 ring-4*16&+1 => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p04 ring-2*33fix => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p05 ring-1*66fix => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p06 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p07 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p08 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p09 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p10 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p11 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p12 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p13 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p14 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p15 random-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p16 worst-cyc-1dim => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p17 best bi-section => 2 sendrecv_calls with 66 messages, i.e. msgs/used node, all nodes are used p18 worst bi-section => 2 sendrecv_calls with 66 messages, i.e. msgs/used node, all nodes are used p19 acyclic-1dim-all => 2 sendrecv_calls with 130 messages, i.e. msgs/used node, all nodes are used p20 acyclic-2dim-all => 4 sendrecv_calls with 230 messages, i.e. msgs/used node, all nodes are used p21 acyclic-3dim-all => 6 sendrecv_calls with 274 messages, i.e. msgs/used node, all nodes are used p22 cyclic-1dim-all => 2 sendrecv_calls with 132 messages, i.e. msgs/used node, all nodes are used p23 cyclic-2dim-all => 4 sendrecv_calls with 264 messages, i.e. msgs/used node, all nodes are used p24 cyclic-3dim-all => 5 sendrecv_calls with 330 messages, i.e. msgs/used node, all nodes are used 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-33*2fix : 72.125 69.254 59.531 -> 72.125 -> 4760.226 MByte/s p01 ring-16*4&+1 : 55.959 71.751 45.587 -> 71.751 -> 4735.567 MByte/s p02 ring-8*8&+1 : 53.656 65.049 43.630 -> 65.049 -> 4293.243 MByte/s p03 ring-4*16&+1 : 52.126 64.655 43.376 -> 64.655 -> 4267.199 MByte/s p04 ring-2*33fix : 55.220 76.083 45.426 -> 76.083 -> 5021.503 MByte/s p05 ring-1*66fix : 54.686 75.958 45.714 -> 75.958 -> 5013.208 MByte/s p06 random-cyc-1dim : 24.209 24.544 21.407 -> 24.544 -> 1619.896 MByte/s p07 random-cyc-1dim : 30.013 29.666 26.681 -> 30.013 -> 1980.857 MByte/s p08 random-cyc-1dim : 28.563 27.889 26.249 -> 28.563 -> 1885.135 MByte/s p09 random-cyc-1dim : 30.971 34.358 28.992 -> 34.358 -> 2267.634 MByte/s p10 random-cyc-1dim : 27.066 26.344 23.551 -> 27.066 -> 1786.338 MByte/s p11 random-cyc-1dim : 33.986 35.782 30.439 -> 35.782 -> 2361.614 MByte/s p12 random-cyc-1dim : 31.952 32.902 29.846 -> 32.902 -> 2171.530 MByte/s p13 random-cyc-1dim : 26.736 27.022 24.062 -> 27.022 -> 1783.420 MByte/s p14 random-cyc-1dim : 26.374 27.135 22.282 -> 27.135 -> 1790.913 MByte/s p15 random-cyc-1dim : 29.626 31.759 27.659 -> 31.759 -> 2096.071 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 20.360 21.318 19.072 -> 21.318 -> 1406.983 MByte/s p17 best bi-section : 51.401 69.248 48.932 -> 69.248 -> 4570.377 MByte/s p18 worst bi-section : 19.028 23.004 19.208 -> 23.004 -> 1518.237 MByte/s p19 acyclic-1dim-all : 53.992 65.165 44.957 -> 65.165 -> 4300.891 MByte/s p20 acyclic-2dim-all : 43.007 48.978 35.956 -> 48.978 -> 3232.572 MByte/s p21 acyclic-3dim-all : 41.227 47.567 35.292 -> 47.567 -> 3139.416 MByte/s p22 cyclic-1dim-all : 54.498 75.720 45.434 -> 75.720 -> 4997.506 MByte/s p23 cyclic-2dim-all : 43.608 47.729 37.318 -> 47.729 -> 3150.134 MByte/s p24 cyclic-3dim-all : 41.566 48.816 37.545 -> 48.816 -> 3221.868 MByte/s log_avg of all rings : 56.942 70.307 46.917 || 70.784 -> 4671.750 MByte/s log_avg of all random : 28.815 29.528 25.940 || 29.713 -> 1961.069 MByte/s log_avg(ring,random) : 40.507 45.563 34.886 ||( 45.861 -> 3026.817)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-33*2fix : 72.024 71.679 71.531 -> 72.024 -> 4753.600 MByte/s p01 ring-16*4&+1 : 71.769 70.797 69.614 -> 71.769 -> 4736.753 MByte/s p02 ring-8*8&+1 : 64.303 64.699 64.282 -> 64.699 -> 4270.152 MByte/s p03 ring-4*16&+1 : 62.914 63.631 64.012 -> 64.012 -> 4224.788 MByte/s p04 ring-2*33fix : 74.839 74.704 75.036 -> 75.036 -> 4952.391 MByte/s p05 ring-1*66fix : 75.372 74.886 74.450 -> 75.372 -> 4974.525 MByte/s p06 random-cyc-1dim : 25.901 25.799 25.774 -> 25.901 -> 1709.438 MByte/s p07 random-cyc-1dim : 31.827 31.011 32.132 -> 32.132 -> 2120.690 MByte/s p08 random-cyc-1dim : 30.472 31.084 30.797 -> 31.084 -> 2051.543 MByte/s p09 random-cyc-1dim : 33.964 35.070 34.330 -> 35.070 -> 2314.651 MByte/s p10 random-cyc-1dim : 28.323 28.262 28.574 -> 28.574 -> 1885.855 MByte/s p11 random-cyc-1dim : 36.963 36.203 37.272 -> 37.272 -> 2459.943 MByte/s p12 random-cyc-1dim : 35.168 34.981 34.434 -> 35.168 -> 2321.073 MByte/s p13 random-cyc-1dim : 28.844 28.699 28.547 -> 28.844 -> 1903.733 MByte/s p14 random-cyc-1dim : 28.363 28.405 28.132 -> 28.405 -> 1874.697 MByte/s p15 random-cyc-1dim : 32.163 32.281 32.424 -> 32.424 -> 2140.014 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 21.761 21.787 21.850 -> 21.850 -> 1442.092 MByte/s p17 best bi-section : 68.816 68.790 68.771 -> 68.816 -> 4541.853 MByte/s p18 worst bi-section : 23.029 22.988 22.806 -> 23.029 -> 1519.898 MByte/s p19 acyclic-1dim-all : 65.046 64.676 64.079 -> 65.046 -> 4293.053 MByte/s p20 acyclic-2dim-all : 51.240 51.131 51.105 -> 51.240 -> 3381.832 MByte/s p21 acyclic-3dim-all : 50.212 49.882 49.605 -> 50.212 -> 3313.992 MByte/s p22 cyclic-1dim-all : 74.600 74.343 74.876 -> 74.876 -> 4941.822 MByte/s p23 cyclic-2dim-all : 50.534 50.349 50.527 -> 50.534 -> 3335.217 MByte/s p24 cyclic-3dim-all : 49.908 49.858 49.289 -> 49.908 -> 3293.899 MByte/s log_avg of all rings : 70.031 69.923 69.681 || 70.336 -> 4642.156 MByte/s log_avg of all random : 31.026 31.007 31.062 || 31.301 -> 2065.843 MByte/s log_avg(ring,random) : 46.613 46.563 46.523 ||( 46.921 -> 3096.767)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 65536 1048576 -> average -> accumulated p00 ring-33*2fix p00 method 0 : 0.056 0.870 10.425 51.255 179.637 207.372 -> 72.125 -> 4760.226 MByte/s p00 method 1 : 0.016 0.271 4.189 52.230 177.030 207.011 -> 69.254 -> 4570.789 MByte/s p00 method 2 : 0.025 0.395 5.306 26.691 166.956 163.539 -> 59.531 -> 3929.022 MByte/s p01 ring-16*4&+1 p01 method 0 : 0.053 0.839 9.756 49.665 139.637 132.686 -> 55.959 -> 3693.323 MByte/s p01 method 1 : 0.027 0.465 7.033 76.669 179.258 178.275 -> 71.751 -> 4735.567 MByte/s p01 method 2 : 0.021 0.352 4.487 29.672 121.484 108.318 -> 45.587 -> 3008.759 MByte/s p02 ring-8*8&+1 p02 method 0 : 0.052 0.821 9.271 47.671 135.161 137.051 -> 53.656 -> 3541.329 MByte/s p02 method 1 : 0.027 0.466 7.039 75.509 152.345 180.126 -> 65.049 -> 4293.243 MByte/s p02 method 2 : 0.021 0.343 4.478 29.911 116.396 105.665 -> 43.630 -> 2879.605 MByte/s p03 ring-4*16&+1 p03 method 0 : 0.048 0.774 8.623 41.578 134.598 133.730 -> 52.126 -> 3440.335 MByte/s p03 method 1 : 0.027 0.465 7.025 75.658 140.220 173.419 -> 64.655 -> 4267.199 MByte/s p03 method 2 : 0.022 0.327 4.445 29.996 115.475 100.488 -> 43.376 -> 2862.797 MByte/s p04 ring-2*33fix p04 method 0 : 0.047 0.771 8.745 39.088 141.831 144.465 -> 55.220 -> 3644.552 MByte/s p04 method 1 : 0.027 0.463 7.039 73.224 189.381 209.981 -> 76.083 -> 5021.503 MByte/s p04 method 2 : 0.022 0.342 4.481 30.121 126.482 100.985 -> 45.426 -> 2998.115 MByte/s p05 ring-1*66fix p05 method 0 : 0.048 0.759 8.430 40.027 144.937 135.301 -> 54.686 -> 3609.270 MByte/s p05 method 1 : 0.027 0.465 7.019 73.370 188.496 207.850 -> 75.958 -> 5013.208 MByte/s p05 method 2 : 0.022 0.345 4.497 29.960 127.220 102.299 -> 45.714 -> 3017.115 MByte/s p06 random-cyc-1dim p06 method 0 : 0.044 0.681 7.685 34.951 53.858 38.301 -> 24.209 -> 1597.769 MByte/s p06 method 1 : 0.027 0.461 6.926 50.212 47.223 40.634 -> 24.544 -> 1619.896 MByte/s p06 method 2 : 0.021 0.331 4.275 28.914 49.872 33.428 -> 21.407 -> 1412.878 MByte/s p07 random-cyc-1dim p07 method 0 : 0.044 0.701 7.757 36.006 70.315 56.941 -> 30.013 -> 1980.857 MByte/s p07 method 1 : 0.026 0.451 6.822 60.919 64.716 43.942 -> 29.666 -> 1957.969 MByte/s p07 method 2 : 0.021 0.330 4.261 29.039 65.224 55.214 -> 26.681 -> 1760.948 MByte/s p08 random-cyc-1dim p08 method 0 : 0.043 0.695 7.690 36.740 64.033 51.470 -> 28.563 -> 1885.135 MByte/s p08 method 1 : 0.026 0.454 6.877 57.955 59.665 32.033 -> 27.889 -> 1840.666 MByte/s p08 method 2 : 0.021 0.334 4.295 29.045 58.766 65.298 -> 26.249 -> 1732.431 MByte/s p09 random-cyc-1dim p09 method 0 : 0.045 0.722 7.751 36.505 75.589 54.034 -> 30.971 -> 2044.108 MByte/s p09 method 1 : 0.027 0.461 6.946 61.998 75.208 64.155 -> 34.358 -> 2267.634 MByte/s p09 method 2 : 0.021 0.337 4.356 29.108 72.016 65.771 -> 28.992 -> 1913.474 MByte/s p10 random-cyc-1dim p10 method 0 : 0.044 0.694 7.772 36.394 63.171 46.252 -> 27.066 -> 1786.338 MByte/s p10 method 1 : 0.027 0.462 6.982 52.130 55.462 35.422 -> 26.344 -> 1738.706 MByte/s p10 method 2 : 0.021 0.334 4.289 28.349 56.373 51.067 -> 23.551 -> 1554.337 MByte/s p11 random-cyc-1dim p11 method 0 : 0.046 0.713 7.771 36.839 78.470 81.420 -> 33.986 -> 2243.046 MByte/s p11 method 1 : 0.027 0.461 6.924 64.068 82.213 50.571 -> 35.782 -> 2361.614 MByte/s p11 method 2 : 0.021 0.336 4.338 29.348 75.501 59.587 -> 30.439 -> 2008.999 MByte/s p12 random-cyc-1dim p12 method 0 : 0.044 0.699 7.627 35.817 75.649 65.116 -> 31.952 -> 2108.820 MByte/s p12 method 1 : 0.027 0.458 6.899 63.578 69.693 51.767 -> 32.902 -> 2171.530 MByte/s p12 method 2 : 0.021 0.333 4.210 29.136 71.179 69.065 -> 29.846 -> 1969.861 MByte/s p13 random-cyc-1dim p13 method 0 : 0.044 0.690 7.316 36.068 60.555 48.311 -> 26.736 -> 1764.605 MByte/s p13 method 1 : 0.027 0.454 6.822 56.179 55.634 35.268 -> 27.022 -> 1783.420 MByte/s p13 method 2 : 0.021 0.335 4.348 28.888 55.697 44.708 -> 24.062 -> 1588.112 MByte/s p14 random-cyc-1dim p14 method 0 : 0.044 0.685 7.695 36.128 61.760 39.737 -> 26.374 -> 1740.656 MByte/s p14 method 1 : 0.027 0.459 6.888 55.947 58.341 33.103 -> 27.135 -> 1790.913 MByte/s p14 method 2 : 0.021 0.331 4.264 28.817 54.280 32.781 -> 22.282 -> 1470.639 MByte/s p15 random-cyc-1dim p15 method 0 : 0.044 0.710 7.674 36.339 71.741 53.379 -> 29.626 -> 1955.291 MByte/s p15 method 1 : 0.027 0.462 6.991 59.436 68.656 45.836 -> 31.759 -> 2096.071 MByte/s p15 method 2 : 0.021 0.331 4.319 29.225 67.159 55.440 -> 27.659 -> 1825.517 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim p16 method 0 : 0.044 0.690 7.596 32.654 42.762 31.819 -> 20.360 -> 1343.789 MByte/s p16 method 1 : 0.027 0.461 6.966 41.113 43.255 29.111 -> 21.318 -> 1406.983 MByte/s p16 method 2 : 0.021 0.315 4.263 27.994 42.409 35.232 -> 19.072 -> 1258.768 MByte/s p17 best bi-section p17 method 0 : 0.033 0.488 5.580 27.855 129.899 162.632 -> 51.401 -> 3392.475 MByte/s p17 method 1 : 0.016 0.269 4.165 52.347 175.574 208.354 -> 69.248 -> 4570.377 MByte/s p17 method 2 : 0.015 0.243 3.360 27.217 125.755 159.775 -> 48.932 -> 3229.493 MByte/s p18 worst bi-section p18 method 0 : 0.023 0.371 4.652 25.913 43.495 35.028 -> 19.028 -> 1255.871 MByte/s p18 method 1 : 0.016 0.266 4.097 34.536 47.113 56.735 -> 23.004 -> 1518.237 MByte/s p18 method 2 : 0.015 0.241 3.415 25.441 44.587 42.696 -> 19.208 -> 1267.707 MByte/s p19 acyclic-1dim-all p19 method 0 : 0.047 0.757 8.484 38.476 140.253 128.820 -> 53.992 -> 3563.454 MByte/s p19 method 1 : 0.027 0.460 6.932 74.027 165.732 134.180 -> 65.165 -> 4300.891 MByte/s p19 method 2 : 0.021 0.334 4.330 29.914 123.985 105.650 -> 44.957 -> 2967.181 MByte/s p20 acyclic-2dim-all p20 method 0 : 0.035 0.554 6.065 28.489 112.132 110.608 -> 43.007 -> 2838.468 MByte/s p20 method 1 : 0.038 0.660 9.665 76.905 111.166 94.414 -> 48.978 -> 3232.572 MByte/s p20 method 2 : 0.019 0.296 3.816 26.249 96.095 78.687 -> 35.956 -> 2373.093 MByte/s p21 acyclic-3dim-all p21 method 0 : 0.031 0.495 5.372 27.286 105.469 108.992 -> 41.227 -> 2720.991 MByte/s p21 method 1 : 0.041 0.718 10.164 77.896 103.148 95.344 -> 47.567 -> 3139.416 MByte/s p21 method 2 : 0.016 0.258 3.327 23.503 94.706 77.504 -> 35.292 -> 2329.283 MByte/s p22 cyclic-1dim-all p22 method 0 : 0.048 0.766 8.462 39.676 142.920 130.401 -> 54.498 -> 3596.838 MByte/s p22 method 1 : 0.027 0.453 6.800 73.880 188.410 204.456 -> 75.720 -> 4997.506 MByte/s p22 method 2 : 0.022 0.347 4.496 29.946 124.905 102.742 -> 45.434 -> 2998.626 MByte/s p23 cyclic-2dim-all p23 method 0 : 0.040 0.620 6.575 32.528 109.933 111.979 -> 43.608 -> 2878.157 MByte/s p23 method 1 : 0.041 0.706 10.167 77.904 109.738 76.559 -> 47.729 -> 3150.134 MByte/s p23 method 2 : 0.021 0.339 4.380 29.684 98.146 82.405 -> 37.318 -> 2462.984 MByte/s p24 cyclic-3dim-all p24 method 0 : 0.038 0.605 6.607 31.432 104.958 103.327 -> 41.566 -> 2743.386 MByte/s p24 method 1 : 0.046 0.805 11.529 79.827 103.436 92.639 -> 48.816 -> 3221.868 MByte/s p24 method 2 : 0.021 0.338 4.359 29.408 98.348 84.634 -> 37.545 -> 2477.937 MByte/s log_avg of all rings - ring, method 0 : 0.050 0.805 9.182 44.622 145.224 146.428 || 56.942 -> 3758.194 MByte/s - ring, method 1 : 0.025 0.425 6.450 70.512 170.072 192.139 || 70.307 -> 4640.237 MByte/s - ring, method 2 : 0.022 0.350 4.606 29.366 127.945 111.708 || 46.917 -> 3096.511 MByte/s log_avg of all random - random, method 0 : 0.044 0.699 7.673 36.175 67.078 52.276 || 28.815 -> 1901.790 MByte/s - random, method 1 : 0.027 0.458 6.908 58.069 62.911 42.269 || 29.528 -> 1948.846 MByte/s - random, method 2 : 0.021 0.333 4.295 28.986 62.055 51.659 || 25.940 -> 1712.010 MByte/s log_avg(ring,random) - average, method 0 : 0.047 0.750 8.394 40.177 98.698 87.491 || 40.507 -> 2673.443 MByte/s - average, method 1 : 0.026 0.441 6.675 63.989 103.438 90.120 || 45.563 -> 3007.176 MByte/s - average, method 2 : 0.022 0.342 4.448 29.175 89.104 75.965 || 34.886 -> 2302.446 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: msg length| effective| average rings random methd_1 methd_2 methd_3 | bandwidth| crt,rnd only only Sendrcv Alltoall non-blk 1 3.112 0.047 0.050 0.044 0.047 0.026 0.022 2 6.237 0.094 0.101 0.088 0.094 0.052 0.043 4 12.424 0.188 0.202 0.176 0.188 0.112 0.086 8 25.023 0.379 0.407 0.353 0.379 0.224 0.172 16 49.493 0.750 0.805 0.699 0.750 0.441 0.342 32 76.188 1.154 1.285 1.037 1.154 0.878 0.592 64 138.331 2.096 2.294 1.915 2.096 1.685 1.132 128 299.573 4.539 4.982 4.135 4.539 3.474 2.349 256 553.979 8.394 9.182 7.673 8.394 6.675 4.448 512 980.496 14.856 16.102 13.706 14.847 12.806 8.097 1024 1686.962 25.560 26.346 24.797 22.801 24.121 13.988 2048 2834.519 42.947 44.181 41.748 31.159 42.014 21.427 4096 4223.265 63.989 70.512 58.069 40.177 63.989 29.175 8192 5357.868 81.180 104.321 63.172 61.501 80.854 58.260 16384 6180.562 93.645 134.612 65.145 79.192 92.780 74.284 32768 6786.290 102.823 158.380 66.754 91.596 100.660 83.791 65536 7074.449 107.189 170.487 67.392 98.698 103.438 89.104 131072 7143.627 108.237 177.825 65.880 100.223 104.210 89.583 262144 7184.111 108.850 184.109 64.355 100.254 102.367 87.204 524288 7162.385 108.521 190.926 61.683 95.424 99.198 85.477 1048576 6847.568 103.751 192.194 56.007 87.491 90.120 75.965 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 65536 1048576 -> average -> accumulated p00 ring-33*2fix : 0.056 0.870 10.425 52.230 179.637 207.372 -> 72.183 -> 4764.048 MByte/s p01 ring-16*4&+1 : 0.053 0.839 9.756 76.669 179.258 178.275 -> 72.313 -> 4772.670 MByte/s p02 ring-8*8&+1 : 0.052 0.821 9.271 75.509 152.345 180.126 -> 65.511 -> 4323.719 MByte/s p03 ring-4*16&+1 : 0.048 0.774 8.623 75.658 140.220 173.419 -> 64.922 -> 4284.851 MByte/s p04 ring-2*33fix : 0.047 0.771 8.745 73.224 189.381 209.981 -> 76.340 -> 5038.461 MByte/s p05 ring-1*66fix : 0.048 0.759 8.430 73.370 188.496 207.850 -> 76.186 -> 5028.304 MByte/s p06 random-cyc-1dim : 0.044 0.681 7.685 50.212 53.858 40.634 -> 26.154 -> 1726.156 MByte/s p07 random-cyc-1dim : 0.044 0.701 7.757 60.919 70.315 56.941 -> 32.434 -> 2140.675 MByte/s p08 random-cyc-1dim : 0.043 0.695 7.690 57.955 64.033 65.298 -> 31.854 -> 2102.393 MByte/s p09 random-cyc-1dim : 0.045 0.722 7.751 61.998 75.589 65.771 -> 35.145 -> 2319.585 MByte/s p10 random-cyc-1dim : 0.044 0.694 7.772 52.130 63.171 51.067 -> 29.018 -> 1915.192 MByte/s p11 random-cyc-1dim : 0.046 0.713 7.771 64.068 82.213 81.420 -> 38.003 -> 2508.212 MByte/s p12 random-cyc-1dim : 0.044 0.699 7.627 63.578 75.649 69.065 -> 35.485 -> 2342.023 MByte/s p13 random-cyc-1dim : 0.044 0.690 7.316 56.179 60.555 48.311 -> 29.205 -> 1927.504 MByte/s p14 random-cyc-1dim : 0.044 0.685 7.695 55.947 61.760 39.737 -> 28.806 -> 1901.195 MByte/s p15 random-cyc-1dim : 0.044 0.710 7.674 59.436 71.741 55.440 -> 32.948 -> 2174.583 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 0.044 0.690 7.596 41.113 43.255 35.232 -> 21.994 -> 1451.575 MByte/s p17 best bi-section : 0.033 0.488 5.580 52.347 175.574 208.354 -> 69.477 -> 4585.495 MByte/s p18 worst bi-section : 0.023 0.371 4.652 34.536 47.113 56.735 -> 23.093 -> 1524.162 MByte/s p19 acyclic-1dim-all : 0.047 0.757 8.484 74.027 165.732 134.180 -> 65.399 -> 4316.343 MByte/s p20 acyclic-2dim-all : 0.038 0.660 9.665 76.905 112.132 110.608 -> 51.645 -> 3408.552 MByte/s p21 acyclic-3dim-all : 0.041 0.718 10.164 77.896 105.469 108.992 -> 50.439 -> 3328.997 MByte/s p22 cyclic-1dim-all : 0.048 0.766 8.462 73.880 188.410 204.456 -> 76.004 -> 5016.286 MByte/s p23 cyclic-2dim-all : 0.041 0.706 10.167 77.904 109.933 111.979 -> 51.426 -> 3394.135 MByte/s p24 cyclic-3dim-all : 0.046 0.805 11.529 79.827 104.958 103.327 -> 50.274 -> 3318.099 MByte/s log_avg of all rings : 0.050 0.805 9.182 70.512 170.487 192.194 || 71.094 -> 4692.184 MByte/s log_avg of all random : 0.044 0.699 7.673 58.069 67.392 56.007 || 31.717 -> 2093.303 MByte/s log_avg(ring,random) : 0.047 0.750 8.394 63.989 107.189 103.751 || 47.485 -> 3134.033 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 3134.033 MByte/s on 66 processes ( = 47.485 MByte/s * 66 processes) system parameters : 66 nodes, 128 MB/node system name: sn6715 hostname : hwwt3e OS release : 2.0.4.71 OS version : unicosmk machine : CRAY T3E SECTION-BEFF-END b_eff = 3134.033 MB/s = 47.485 * 66 PEs with 128 MB/PE on sn6715 hwwt3e 2.0.4.71 unicosmk CRAY T3E