b_eff = 3364.445 MB/s = 50.216 * 67 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 = 67 1-dim-paterns: size = 67 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 = 158.927 sec sum of max elapsed time per entries above = 160.778 sec difference = -1.851 sec = 1.2% The difference is less than 5 % SECTION-LOOP-END SECTION-PATTERN-BEGIN Pattern parameters: p00 ring-33*2&+1 => 1 sendrecv_calls with 67 messages, i.e. msgs/used node, all nodes are used p01 ring-17*4&-1 => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p02 ring-8*8&+1 => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p03 ring-4*16&+1 => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p04 ring-2*34&-1 => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p05 ring-1*67fix => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p06 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p07 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p08 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p09 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p10 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p11 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p12 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p13 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p14 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p15 random-cyc-1dim => 2 sendrecv_calls with 134 messages, i.e. msgs/used node, all nodes are used p16 worst-cyc-1dim => 2 sendrecv_calls with 134 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, 1 nodes are UNUSED p18 worst bi-section => 2 sendrecv_calls with 66 messages, i.e. msgs/used node, 1 nodes are UNUSED p19 acyclic-1dim-all => 2 sendrecv_calls with 132 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, 1 nodes are UNUSED p21 acyclic-3dim-all => 6 sendrecv_calls with 274 messages, i.e. msgs/used node, 1 nodes are UNUSED p22 cyclic-1dim-all => 2 sendrecv_calls with 134 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, 1 nodes are UNUSED p24 cyclic-3dim-all => 5 sendrecv_calls with 330 messages, i.e. msgs/used node, 1 nodes are UNUSED 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*2&+1 : 67.091 69.519 49.512 -> 69.519 -> 4657.785 MByte/s p01 ring-17*4&-1 : 58.219 74.364 45.018 -> 74.364 -> 4982.393 MByte/s p02 ring-8*8&+1 : 53.552 66.449 44.704 -> 66.449 -> 4452.083 MByte/s p03 ring-4*16&+1 : 51.614 66.306 44.574 -> 66.306 -> 4442.492 MByte/s p04 ring-2*34&-1 : 55.011 76.781 46.233 -> 76.781 -> 5144.357 MByte/s p05 ring-1*67fix : 54.271 72.380 45.535 -> 72.380 -> 4849.428 MByte/s p06 random-cyc-1dim : 30.357 30.326 27.178 -> 30.357 -> 2033.899 MByte/s p07 random-cyc-1dim : 35.912 37.664 30.073 -> 37.664 -> 2523.513 MByte/s p08 random-cyc-1dim : 38.804 41.793 34.168 -> 41.793 -> 2800.116 MByte/s p09 random-cyc-1dim : 26.944 27.457 24.070 -> 27.457 -> 1839.640 MByte/s p10 random-cyc-1dim : 36.583 37.758 31.979 -> 37.758 -> 2529.767 MByte/s p11 random-cyc-1dim : 25.448 26.523 23.075 -> 26.523 -> 1777.044 MByte/s p12 random-cyc-1dim : 36.904 37.661 32.100 -> 37.661 -> 2523.305 MByte/s p13 random-cyc-1dim : 35.745 36.138 30.410 -> 36.138 -> 2421.236 MByte/s p14 random-cyc-1dim : 29.516 31.556 27.314 -> 31.556 -> 2114.271 MByte/s p15 random-cyc-1dim : 27.468 27.616 24.811 -> 27.616 -> 1850.245 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 20.804 21.018 19.557 -> 21.018 -> 1408.187 MByte/s p17 best bi-section : 50.719 68.413 48.352 -> 68.413 -> 4583.684 MByte/s p18 worst bi-section : 18.797 22.660 18.433 -> 22.660 -> 1518.232 MByte/s p19 acyclic-1dim-all : 54.206 65.214 45.383 -> 65.214 -> 4369.357 MByte/s p20 acyclic-2dim-all : 42.617 48.286 35.212 -> 48.286 -> 3235.185 MByte/s p21 acyclic-3dim-all : 40.829 46.745 34.953 -> 46.745 -> 3131.946 MByte/s p22 cyclic-1dim-all : 54.579 72.353 45.909 -> 72.353 -> 4847.648 MByte/s p23 cyclic-2dim-all : 42.566 46.574 36.491 -> 46.574 -> 3120.457 MByte/s p24 cyclic-3dim-all : 41.571 48.206 36.980 -> 48.206 -> 3229.816 MByte/s log_avg of all rings : 56.414 70.859 45.899 || 70.859 -> 4747.571 MByte/s log_avg of all random : 32.026 33.054 28.288 || 33.057 -> 2214.838 MByte/s log_avg(ring,random) : 42.505 48.396 36.033 ||( 48.398 -> 3242.699)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*2&+1 : 71.572 71.378 71.686 -> 71.686 -> 4802.933 MByte/s p01 ring-17*4&-1 : 72.862 72.125 72.197 -> 72.862 -> 4881.738 MByte/s p02 ring-8*8&+1 : 65.906 66.176 66.427 -> 66.427 -> 4450.623 MByte/s p03 ring-4*16&+1 : 64.958 65.290 64.172 -> 65.290 -> 4374.428 MByte/s p04 ring-2*34&-1 : 75.084 76.214 75.371 -> 76.214 -> 5106.360 MByte/s p05 ring-1*67fix : 70.069 71.385 71.281 -> 71.385 -> 4782.798 MByte/s p06 random-cyc-1dim : 32.854 32.863 32.179 -> 32.863 -> 2201.812 MByte/s p07 random-cyc-1dim : 38.409 38.573 39.486 -> 39.486 -> 2645.542 MByte/s p08 random-cyc-1dim : 43.643 43.817 43.247 -> 43.817 -> 2935.762 MByte/s p09 random-cyc-1dim : 28.100 28.171 28.578 -> 28.578 -> 1914.712 MByte/s p10 random-cyc-1dim : 39.760 39.212 40.122 -> 40.122 -> 2688.171 MByte/s p11 random-cyc-1dim : 27.121 27.242 27.024 -> 27.242 -> 1825.215 MByte/s p12 random-cyc-1dim : 40.180 39.476 39.908 -> 40.180 -> 2692.055 MByte/s p13 random-cyc-1dim : 38.186 38.461 37.581 -> 38.461 -> 2576.917 MByte/s p14 random-cyc-1dim : 31.889 31.895 32.603 -> 32.603 -> 2184.379 MByte/s p15 random-cyc-1dim : 29.034 29.288 29.317 -> 29.317 -> 1964.233 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 22.127 22.189 22.008 -> 22.189 -> 1486.652 MByte/s p17 best bi-section : 67.592 67.819 68.387 -> 68.387 -> 4581.914 MByte/s p18 worst bi-section : 22.443 22.601 22.679 -> 22.679 -> 1519.463 MByte/s p19 acyclic-1dim-all : 64.602 64.450 64.972 -> 64.972 -> 4353.100 MByte/s p20 acyclic-2dim-all : 50.577 50.268 50.306 -> 50.577 -> 3388.654 MByte/s p21 acyclic-3dim-all : 49.071 49.303 49.218 -> 49.303 -> 3303.327 MByte/s p22 cyclic-1dim-all : 70.814 71.407 70.932 -> 71.407 -> 4784.253 MByte/s p23 cyclic-2dim-all : 48.811 48.930 49.660 -> 49.660 -> 3327.229 MByte/s p24 cyclic-3dim-all : 50.064 49.304 49.318 -> 50.064 -> 3354.276 MByte/s log_avg of all rings : 69.981 70.330 70.087 || 70.544 -> 4726.461 MByte/s log_avg of all random : 34.474 34.474 34.574 || 34.824 -> 2333.241 MByte/s log_avg(ring,random) : 49.117 49.240 49.226 ||( 49.565 -> 3320.839)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*2&+1 p00 method 0 : 0.055 0.872 10.074 51.213 179.784 130.803 -> 67.091 -> 4495.106 MByte/s p00 method 1 : 0.016 0.274 4.239 53.368 177.580 207.985 -> 69.519 -> 4657.785 MByte/s p00 method 2 : 0.025 0.391 5.001 26.490 122.313 119.541 -> 49.512 -> 3317.313 MByte/s p01 ring-17*4&-1 p01 method 0 : 0.053 0.846 9.992 50.320 157.503 129.639 -> 58.219 -> 3900.703 MByte/s p01 method 1 : 0.027 0.473 7.062 76.516 183.523 196.952 -> 74.364 -> 4982.393 MByte/s p01 method 2 : 0.021 0.354 4.693 29.550 119.022 107.175 -> 45.018 -> 3016.234 MByte/s p02 ring-8*8&+1 p02 method 0 : 0.051 0.828 9.296 48.572 134.051 130.946 -> 53.552 -> 3588.017 MByte/s p02 method 1 : 0.027 0.470 7.030 73.536 154.464 183.346 -> 66.449 -> 4452.083 MByte/s p02 method 2 : 0.021 0.341 4.460 30.020 117.919 119.907 -> 44.704 -> 2995.156 MByte/s p03 ring-4*16&+1 p03 method 0 : 0.047 0.754 8.512 41.975 131.711 130.117 -> 51.614 -> 3458.120 MByte/s p03 method 1 : 0.027 0.468 6.993 73.923 151.387 172.432 -> 66.306 -> 4442.492 MByte/s p03 method 2 : 0.022 0.340 4.411 29.910 118.382 115.194 -> 44.574 -> 2986.487 MByte/s p04 ring-2*34&-1 p04 method 0 : 0.048 0.768 8.491 40.231 144.582 138.062 -> 55.011 -> 3685.752 MByte/s p04 method 1 : 0.027 0.470 6.963 75.279 188.676 211.967 -> 76.781 -> 5144.357 MByte/s p04 method 2 : 0.022 0.342 4.503 30.162 124.445 108.030 -> 46.233 -> 3097.637 MByte/s p05 ring-1*67fix p05 method 0 : 0.048 0.769 8.401 38.047 141.434 133.699 -> 54.271 -> 3636.165 MByte/s p05 method 1 : 0.027 0.467 6.974 73.688 178.335 197.074 -> 72.380 -> 4849.428 MByte/s p05 method 2 : 0.022 0.344 4.471 30.018 122.561 103.610 -> 45.535 -> 3050.864 MByte/s p06 random-cyc-1dim p06 method 0 : 0.044 0.704 7.751 36.600 69.450 57.774 -> 30.357 -> 2033.899 MByte/s p06 method 1 : 0.027 0.462 6.990 60.954 65.272 38.008 -> 30.326 -> 2031.868 MByte/s p06 method 2 : 0.021 0.335 4.284 29.054 67.532 55.694 -> 27.178 -> 1820.910 MByte/s p07 random-cyc-1dim p07 method 0 : 0.045 0.708 7.957 37.312 85.632 83.772 -> 35.912 -> 2406.110 MByte/s p07 method 1 : 0.027 0.465 7.031 63.722 81.153 73.420 -> 37.664 -> 2523.513 MByte/s p07 method 2 : 0.021 0.334 4.301 29.209 74.979 58.677 -> 30.073 -> 2014.887 MByte/s p08 random-cyc-1dim p08 method 0 : 0.044 0.699 7.743 36.430 98.158 80.833 -> 38.804 -> 2599.885 MByte/s p08 method 1 : 0.026 0.454 6.890 69.287 100.527 69.007 -> 41.793 -> 2800.116 MByte/s p08 method 2 : 0.021 0.333 4.345 29.387 89.120 85.267 -> 34.168 -> 2289.243 MByte/s p09 random-cyc-1dim p09 method 0 : 0.044 0.704 7.657 34.784 59.837 58.632 -> 26.944 -> 1805.256 MByte/s p09 method 1 : 0.027 0.463 6.977 47.854 57.723 47.708 -> 27.457 -> 1839.640 MByte/s p09 method 2 : 0.021 0.336 4.310 28.581 54.274 56.243 -> 24.070 -> 1612.687 MByte/s p10 random-cyc-1dim p10 method 0 : 0.044 0.693 7.795 37.410 89.025 78.675 -> 36.583 -> 2451.043 MByte/s p10 method 1 : 0.027 0.459 6.917 64.781 82.996 69.853 -> 37.758 -> 2529.767 MByte/s p10 method 2 : 0.021 0.335 4.313 29.194 77.262 77.705 -> 31.979 -> 2142.617 MByte/s p11 random-cyc-1dim p11 method 0 : 0.044 0.688 7.730 35.251 57.032 45.302 -> 25.448 -> 1705.049 MByte/s p11 method 1 : 0.027 0.459 6.909 53.215 53.775 39.269 -> 26.523 -> 1777.044 MByte/s p11 method 2 : 0.021 0.332 4.346 28.813 53.799 47.789 -> 23.075 -> 1546.012 MByte/s p12 random-cyc-1dim p12 method 0 : 0.044 0.713 7.718 37.527 88.126 82.571 -> 36.904 -> 2472.592 MByte/s p12 method 1 : 0.027 0.457 6.893 65.781 85.340 69.772 -> 37.661 -> 2523.305 MByte/s p12 method 2 : 0.021 0.334 4.348 29.348 80.982 71.849 -> 32.100 -> 2150.701 MByte/s p13 random-cyc-1dim p13 method 0 : 0.045 0.706 7.734 37.165 84.829 77.608 -> 35.745 -> 2394.947 MByte/s p13 method 1 : 0.027 0.461 6.895 63.792 81.554 63.935 -> 36.138 -> 2421.236 MByte/s p13 method 2 : 0.021 0.336 4.356 29.038 74.109 68.495 -> 30.410 -> 2037.494 MByte/s p14 random-cyc-1dim p14 method 0 : 0.043 0.689 7.680 35.941 67.879 53.418 -> 29.516 -> 1977.596 MByte/s p14 method 1 : 0.027 0.458 6.924 59.614 65.815 52.935 -> 31.556 -> 2114.271 MByte/s p14 method 2 : 0.021 0.333 4.311 29.052 62.814 70.153 -> 27.314 -> 1830.063 MByte/s p15 random-cyc-1dim p15 method 0 : 0.044 0.702 7.720 36.299 63.492 51.914 -> 27.468 -> 1840.369 MByte/s p15 method 1 : 0.027 0.463 6.962 57.217 58.445 35.793 -> 27.616 -> 1850.245 MByte/s p15 method 2 : 0.021 0.333 4.289 29.066 60.400 49.463 -> 24.811 -> 1662.346 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim p16 method 0 : 0.044 0.680 7.677 31.673 43.716 37.134 -> 20.804 -> 1393.856 MByte/s p16 method 1 : 0.027 0.463 6.986 40.991 41.575 35.610 -> 21.018 -> 1408.187 MByte/s p16 method 2 : 0.021 0.333 4.273 27.533 41.872 41.775 -> 19.557 -> 1310.347 MByte/s p17 best bi-section p17 method 0 : 0.032 0.485 5.351 27.773 127.760 158.842 -> 50.719 -> 3398.153 MByte/s p17 method 1 : 0.016 0.267 4.100 51.427 174.433 205.084 -> 68.413 -> 4583.684 MByte/s p17 method 2 : 0.015 0.237 3.275 27.065 123.099 158.923 -> 48.352 -> 3239.611 MByte/s p18 worst bi-section p18 method 0 : 0.023 0.367 4.561 25.593 42.110 34.290 -> 18.797 -> 1259.427 MByte/s p18 method 1 : 0.016 0.263 4.037 34.625 46.360 55.858 -> 22.660 -> 1518.232 MByte/s p18 method 2 : 0.015 0.237 3.248 25.336 43.527 34.239 -> 18.433 -> 1235.043 MByte/s p19 acyclic-1dim-all p19 method 0 : 0.047 0.756 8.318 39.316 141.075 134.543 -> 54.206 -> 3631.774 MByte/s p19 method 1 : 0.027 0.463 6.944 73.434 164.081 145.207 -> 65.214 -> 4369.357 MByte/s p19 method 2 : 0.021 0.335 4.401 29.588 123.437 104.306 -> 45.383 -> 3040.642 MByte/s p20 acyclic-2dim-all p20 method 0 : 0.035 0.549 6.018 28.215 110.950 109.078 -> 42.617 -> 2855.332 MByte/s p20 method 1 : 0.038 0.656 9.478 76.071 108.918 92.630 -> 48.286 -> 3235.185 MByte/s p20 method 2 : 0.018 0.293 3.768 25.653 93.564 76.241 -> 35.212 -> 2359.233 MByte/s p21 acyclic-3dim-all p21 method 0 : 0.031 0.489 5.559 26.981 105.081 109.739 -> 40.829 -> 2735.559 MByte/s p21 method 1 : 0.040 0.706 10.009 77.019 101.840 91.961 -> 46.745 -> 3131.946 MByte/s p21 method 2 : 0.016 0.254 3.288 23.186 94.026 82.577 -> 34.953 -> 2341.818 MByte/s p22 cyclic-1dim-all p22 method 0 : 0.048 0.776 8.344 38.596 141.633 133.383 -> 54.579 -> 3656.763 MByte/s p22 method 1 : 0.027 0.458 6.837 73.426 175.394 195.066 -> 72.353 -> 4847.648 MByte/s p22 method 2 : 0.022 0.345 4.438 29.937 123.876 107.760 -> 45.909 -> 3075.912 MByte/s p23 cyclic-2dim-all p23 method 0 : 0.039 0.588 6.695 31.804 109.363 108.473 -> 42.566 -> 2851.922 MByte/s p23 method 1 : 0.040 0.695 10.169 76.195 104.759 73.956 -> 46.574 -> 3120.457 MByte/s p23 method 2 : 0.021 0.334 4.312 29.147 96.530 82.410 -> 36.491 -> 2444.872 MByte/s p24 cyclic-3dim-all p24 method 0 : 0.038 0.589 6.495 30.403 105.428 110.406 -> 41.571 -> 2785.232 MByte/s p24 method 1 : 0.045 0.792 11.364 78.660 104.037 91.142 -> 48.206 -> 3229.816 MByte/s p24 method 2 : 0.021 0.330 4.293 28.805 96.835 79.122 -> 36.980 -> 2477.658 MByte/s log_avg of all rings - ring, method 0 : 0.050 0.805 9.100 44.761 147.322 132.179 || 56.414 -> 3779.705 MByte/s - ring, method 1 : 0.025 0.429 6.442 70.534 171.722 194.475 || 70.859 -> 4747.571 MByte/s - ring, method 2 : 0.022 0.352 4.585 29.328 120.749 112.066 || 45.899 -> 3075.253 MByte/s log_avg of all random - random, method 0 : 0.044 0.701 7.748 36.461 75.109 65.497 || 32.026 -> 2145.713 MByte/s - random, method 1 : 0.027 0.460 6.939 60.299 71.862 54.055 || 33.054 -> 2214.616 MByte/s - random, method 2 : 0.021 0.334 4.320 29.073 68.630 63.057 || 28.288 -> 1895.310 MByte/s log_avg(ring,random) - average, method 0 : 0.047 0.751 8.397 40.398 105.191 93.045 || 42.505 -> 2847.835 MByte/s - average, method 1 : 0.026 0.445 6.686 65.216 111.087 102.530 || 48.396 -> 3242.537 MByte/s - average, method 2 : 0.022 0.343 4.451 29.201 91.033 84.062 || 36.033 -> 2414.241 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 3.155 0.047 0.050 0.044 0.047 0.026 0.022 2 6.341 0.095 0.101 0.089 0.095 0.052 0.043 4 12.683 0.189 0.202 0.177 0.189 0.113 0.086 8 25.354 0.378 0.404 0.354 0.378 0.225 0.172 16 50.316 0.751 0.805 0.701 0.751 0.445 0.343 32 77.263 1.153 1.277 1.042 1.153 0.877 0.595 64 139.912 2.088 2.286 1.908 2.088 1.690 1.129 128 303.738 4.533 4.979 4.128 4.533 3.483 2.337 256 562.613 8.397 9.100 7.748 8.397 6.686 4.451 512 997.608 14.890 16.009 13.849 14.890 12.841 8.119 1024 1723.541 25.724 26.642 24.839 23.005 24.194 13.943 2048 2882.363 43.020 44.086 41.980 31.453 42.169 21.502 4096 4369.455 65.216 70.534 60.299 40.398 65.216 29.201 8192 5701.844 85.102 104.157 69.533 62.539 84.984 59.502 16384 6659.210 99.391 134.737 73.318 83.089 99.161 76.317 32768 7235.030 107.986 157.767 73.912 96.955 107.116 87.253 65536 7626.037 113.821 172.075 75.289 105.191 111.087 91.033 131072 7886.828 117.714 182.254 76.029 108.179 112.678 93.809 262144 7843.511 117.067 186.599 73.445 106.991 110.854 90.573 524288 7826.115 116.808 192.625 70.832 102.478 107.512 87.659 1048576 7706.462 115.022 194.475 68.030 93.045 102.530 84.062 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*2&+1 : 0.055 0.872 10.074 53.368 179.784 207.985 -> 72.139 -> 4833.318 MByte/s p01 ring-17*4&-1 : 0.053 0.846 9.992 76.516 183.523 196.952 -> 74.977 -> 5023.480 MByte/s p02 ring-8*8&+1 : 0.051 0.828 9.296 73.536 154.464 183.346 -> 66.951 -> 4485.709 MByte/s p03 ring-4*16&+1 : 0.047 0.754 8.512 73.923 151.387 172.432 -> 66.542 -> 4458.328 MByte/s p04 ring-2*34&-1 : 0.048 0.768 8.491 75.279 188.676 211.967 -> 77.029 -> 5160.938 MByte/s p05 ring-1*67fix : 0.048 0.769 8.401 73.688 178.335 197.074 -> 72.618 -> 4865.411 MByte/s p06 random-cyc-1dim : 0.044 0.704 7.751 60.954 69.450 57.774 -> 33.258 -> 2228.255 MByte/s p07 random-cyc-1dim : 0.045 0.708 7.957 63.722 85.632 83.772 -> 39.756 -> 2663.674 MByte/s p08 random-cyc-1dim : 0.044 0.699 7.743 69.287 100.527 85.267 -> 44.290 -> 2967.456 MByte/s p09 random-cyc-1dim : 0.044 0.704 7.657 47.854 59.837 58.632 -> 28.715 -> 1923.895 MByte/s p10 random-cyc-1dim : 0.044 0.693 7.795 64.781 89.025 78.675 -> 40.662 -> 2724.351 MByte/s p11 random-cyc-1dim : 0.044 0.688 7.730 53.215 57.032 47.789 -> 27.548 -> 1845.736 MByte/s p12 random-cyc-1dim : 0.044 0.713 7.718 65.781 88.126 82.571 -> 40.593 -> 2719.755 MByte/s p13 random-cyc-1dim : 0.045 0.706 7.734 63.792 84.829 77.608 -> 38.899 -> 2606.210 MByte/s p14 random-cyc-1dim : 0.043 0.689 7.680 59.614 67.879 70.153 -> 33.055 -> 2214.662 MByte/s p15 random-cyc-1dim : 0.044 0.702 7.720 57.217 63.492 51.914 -> 29.836 -> 1998.980 MByte/s -- additional patterns that are not used to compute b_eff: p16 worst-cyc-1dim : 0.044 0.680 7.677 40.991 43.716 41.775 -> 22.491 -> 1506.867 MByte/s p17 best bi-section : 0.032 0.485 5.351 51.427 174.433 205.084 -> 68.642 -> 4599.017 MByte/s p18 worst bi-section : 0.023 0.367 4.561 34.625 46.360 55.858 -> 22.743 -> 1523.788 MByte/s p19 acyclic-1dim-all : 0.047 0.756 8.318 73.434 164.081 145.207 -> 65.449 -> 4385.065 MByte/s p20 acyclic-2dim-all : 0.038 0.656 9.478 76.071 110.950 109.078 -> 51.018 -> 3418.204 MByte/s p21 acyclic-3dim-all : 0.040 0.706 10.009 77.019 105.081 109.739 -> 49.727 -> 3331.691 MByte/s p22 cyclic-1dim-all : 0.048 0.776 8.344 73.426 175.394 195.066 -> 72.616 -> 4865.299 MByte/s p23 cyclic-2dim-all : 0.040 0.695 10.169 76.195 109.363 108.473 -> 50.082 -> 3355.491 MByte/s p24 cyclic-3dim-all : 0.045 0.792 11.364 78.660 105.428 110.406 -> 50.271 -> 3368.138 MByte/s log_avg of all rings : 0.050 0.805 9.100 70.534 172.075 194.475 || 71.605 -> 4797.521 MByte/s log_avg of all random : 0.044 0.701 7.748 60.299 75.289 68.030 || 35.216 -> 2359.445 MByte/s log_avg(ring,random) : 0.047 0.751 8.397 65.216 113.821 115.022 || 50.216 -> 3364.445 MByte/s SECTION-BY-PATTERN-MSGLNG-END SECTION-BEFF-BEGIN The effective bandwidth is b_eff = 3364.445 MByte/s on 67 processes ( = 50.216 MByte/s * 67 processes) system parameters : 67 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 = 3364.445 MB/s = 50.216 * 67 PEs with 128 MB/PE on sn6715 hwwt3e 2.0.4.71 unicosmk CRAY T3E