Open-MX 0.5.0 (--disable-mx-wire --disable-endian OMX_RCACHE=1 dmaengine=1) MPICH-MX 1.2.7..5 Dual quad-core Xeon (E5345, 2.33GHz, C1E sleeping disabled) Myri-10G NICs (rx-usecs=1, myri10ge 1.4.1), no switch No IRQ or Process binding #--------------------------------------------------- # Intel (R) MPI Benchmark Suite V2.3, MPI-1 part #--------------------------------------------------- # Date : Tue Apr 29 20:47:40 2008 # Machine : x86_64# System : Linux # Release : 2.6.23-1-amd64 # Version : #1 SMP Fri Nov 30 12:19:15 UTC 2007 # # Minimum message length in bytes: 0 # Maximum message length in bytes: 4194304 # # MPI_Datatype : MPI_BYTE # MPI_Datatype for reductions : MPI_FLOAT # MPI_Op : MPI_SUM # # # List of Benchmarks to run: # PingPong # PingPing # Sendrecv # Exchange # Allreduce # Reduce # Reduce_scatter # Allgather # Allgatherv # Alltoall # Bcast # Barrier #--------------------------------------------------- # Benchmarking PingPong # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 9.05 0.00 1 1000 9.09 0.10 2 1000 9.10 0.21 4 1000 9.21 0.41 8 1000 9.19 0.83 16 1000 9.14 1.67 32 1000 9.21 3.32 64 1000 9.56 6.39 128 1000 9.86 12.38 256 1000 11.24 21.72 512 1000 12.25 39.86 1024 1000 14.24 68.58 2048 1000 17.99 108.57 4096 1000 25.87 150.97 8192 1000 36.51 213.97 16384 1000 51.96 300.72 32768 1000 81.67 382.63 65536 640 200.57 311.61 131072 320 207.78 601.60 262144 160 346.34 721.84 524288 80 580.61 861.16 1048576 40 1024.51 976.07 2097152 20 1879.17 1064.30 4194304 10 3600.49 1110.96 #--------------------------------------------------- # Benchmarking PingPing # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 10.06 0.00 1 1000 10.19 0.09 2 1000 10.14 0.19 4 1000 10.25 0.37 8 1000 10.32 0.74 16 1000 10.28 1.48 32 1000 10.21 2.99 64 1000 10.66 5.73 128 1000 10.99 11.11 256 1000 12.21 19.99 512 1000 13.29 36.75 1024 1000 15.18 64.33 2048 1000 18.87 103.51 4096 1000 27.86 140.19 8192 1000 40.65 192.20 16384 1000 60.66 257.58 32768 1000 94.18 331.80 65536 640 151.57 412.35 131072 320 229.29 545.15 262144 160 380.85 656.43 524288 80 690.99 723.60 1048576 40 1236.58 808.68 2097152 20 2360.56 847.26 4194304 10 4631.81 863.59 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 10.13 10.13 10.13 0.00 1 1000 10.43 10.44 10.43 0.18 2 1000 10.19 10.20 10.19 0.37 4 1000 10.31 10.32 10.32 0.74 8 1000 10.45 10.46 10.46 1.46 16 1000 10.40 10.40 10.40 2.93 32 1000 10.34 10.36 10.35 5.89 64 1000 10.81 10.81 10.81 11.30 128 1000 11.03 11.05 11.04 22.10 256 1000 12.68 12.69 12.69 38.47 512 1000 13.63 13.63 13.63 71.64 1024 1000 15.18 15.18 15.18 128.63 2048 1000 19.22 19.23 19.22 203.16 4096 1000 27.57 27.57 27.57 283.41 8192 1000 40.72 40.72 40.72 383.69 16384 1000 60.07 60.11 60.09 519.90 32768 1000 95.10 95.11 95.10 657.16 65536 640 153.36 153.38 153.37 814.99 131072 320 233.08 233.09 233.09 1072.53 262144 160 383.79 383.91 383.85 1302.38 524288 80 712.00 712.03 712.01 1404.44 1048576 40 1264.85 1265.35 1265.10 1580.59 2097152 20 2429.65 2429.65 2429.65 1646.33 4194304 10 4696.39 4698.99 4697.69 1702.49 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 15.15 15.17 15.16 0.00 1 1000 15.08 15.10 15.09 0.13 2 1000 15.16 15.19 15.17 0.25 4 1000 15.32 15.35 15.33 0.50 8 1000 15.12 15.16 15.14 1.01 16 1000 15.11 15.14 15.12 2.02 32 1000 15.17 15.19 15.18 4.02 64 1000 15.45 15.48 15.46 7.88 128 1000 15.74 15.77 15.76 15.48 256 1000 17.99 18.02 18.00 27.10 512 1000 18.73 18.76 18.75 52.06 1024 1000 20.46 20.47 20.47 95.41 2048 1000 24.22 24.25 24.24 161.06 4096 1000 33.45 33.50 33.47 233.23 8192 1000 49.32 49.40 49.36 316.30 16384 1000 74.16 74.27 74.21 420.79 32768 1000 131.96 132.06 132.02 473.29 65536 640 311.56 311.63 311.59 401.11 131072 320 546.43 546.72 546.59 457.27 262144 160 814.19 814.54 814.43 613.84 524288 80 1512.69 1518.35 1516.83 658.61 1048576 40 2469.77 2470.77 2470.23 809.46 2097152 20 4441.75 4468.75 4455.71 895.10 4194304 10 8088.71 8093.91 8091.28 988.40 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 19.17 19.22 19.20 0.00 1 1000 19.42 19.49 19.46 0.10 2 1000 19.45 19.51 19.48 0.20 4 1000 19.63 19.69 19.66 0.39 8 1000 19.58 19.64 19.61 0.78 16 1000 19.45 19.48 19.47 1.57 32 1000 19.42 19.49 19.47 3.13 64 1000 19.91 20.01 19.96 6.10 128 1000 20.37 20.41 20.39 11.96 256 1000 23.20 23.28 23.24 20.98 512 1000 24.60 24.65 24.63 39.62 1024 1000 26.62 26.69 26.66 73.19 2048 1000 32.35 32.39 32.37 120.61 4096 1000 45.25 45.40 45.36 172.07 8192 1000 71.67 71.82 71.75 217.56 16384 1000 130.84 131.17 131.03 238.24 32768 1000 232.93 233.55 233.32 267.60 65536 640 511.60 512.19 511.92 244.05 131072 320 894.20 896.61 895.90 278.83 262144 160 1576.64 1577.24 1577.00 317.01 524288 80 3203.51 3208.86 3207.74 311.64 1048576 40 4631.32 4632.17 4631.71 431.76 2097152 20 8195.51 8205.15 8202.62 487.50 4194304 10 15094.61 15135.79 15116.63 528.55 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 16 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 27.66 27.86 27.79 0.00 1 1000 27.84 27.95 27.90 0.07 2 1000 26.85 27.02 26.95 0.14 4 1000 26.43 26.54 26.49 0.29 8 1000 26.30 26.42 26.36 0.58 16 1000 26.35 26.53 26.45 1.15 32 1000 26.59 26.70 26.66 2.29 64 1000 27.33 27.49 27.41 4.44 128 1000 27.58 27.77 27.67 8.79 256 1000 33.05 33.17 33.12 14.72 512 1000 34.15 34.26 34.21 28.50 1024 1000 38.19 38.40 38.31 50.86 2048 1000 51.24 51.58 51.44 75.72 4096 1000 76.22 76.83 76.57 101.69 8192 1000 140.18 141.22 140.73 110.64 16384 1000 273.47 275.25 274.51 113.53 32768 1000 532.48 536.56 535.02 116.48 65536 640 801.03 801.98 801.57 155.86 131072 320 1430.62 1436.91 1434.44 173.98 262144 160 2697.13 2714.49 2709.38 184.20 524288 80 5658.34 5699.77 5683.38 175.45 1048576 40 8454.45 8489.50 8482.70 235.59 2097152 20 15648.65 15941.30 15807.30 250.92 4194304 10 30074.21 30424.81 30316.02 262.94 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 16.66 16.67 16.66 0.00 1 1000 16.88 16.89 16.88 0.23 2 1000 16.72 16.74 16.73 0.46 4 1000 16.82 16.83 16.82 0.91 8 1000 16.78 16.78 16.78 1.82 16 1000 16.66 16.66 16.66 3.66 32 1000 16.95 16.96 16.95 7.20 64 1000 17.25 17.26 17.26 14.14 128 1000 17.49 17.51 17.50 27.89 256 1000 19.23 19.25 19.24 50.73 512 1000 20.66 20.67 20.67 94.50 1024 1000 22.86 22.88 22.87 170.76 2048 1000 29.11 29.13 29.12 268.18 4096 1000 40.72 40.73 40.72 383.62 8192 1000 61.70 61.73 61.71 506.25 16384 1000 96.02 96.03 96.02 650.85 32768 1000 160.04 160.12 160.08 780.67 65536 640 303.55 303.57 303.56 823.54 131072 320 492.83 492.91 492.87 1014.38 262144 160 821.31 821.37 821.34 1217.48 524288 80 1426.37 1426.43 1426.40 1402.11 1048576 40 2569.92 2570.22 2570.07 1556.28 2097152 20 4923.80 4923.81 4923.80 1624.76 4194304 10 9532.28 9532.59 9532.44 1678.45 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 21.43 21.45 21.44 0.00 1 1000 21.10 21.11 21.11 0.18 2 1000 21.24 21.26 21.25 0.36 4 1000 21.30 21.33 21.32 0.72 8 1000 21.67 21.69 21.68 1.41 16 1000 21.77 21.78 21.77 2.80 32 1000 21.80 21.83 21.81 5.59 64 1000 22.50 22.52 22.51 10.84 128 1000 22.97 23.01 22.99 21.22 256 1000 26.54 26.55 26.54 36.78 512 1000 28.48 28.50 28.49 68.54 1024 1000 31.70 31.71 31.71 123.18 2048 1000 39.23 39.24 39.23 199.11 4096 1000 55.30 55.31 55.31 282.49 8192 1000 88.58 88.65 88.61 352.50 16384 1000 143.78 143.82 143.80 434.56 32768 1000 261.37 261.52 261.44 477.98 65536 640 516.10 516.47 516.34 484.06 131072 320 881.65 882.00 881.89 566.89 262144 160 1603.72 1603.91 1603.85 623.48 524288 80 2972.15 2977.30 2975.79 671.75 1048576 40 5106.75 5116.67 5112.28 781.76 2097152 20 8818.26 8843.45 8832.64 904.62 4194304 10 17035.20 17058.90 17047.17 937.93 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 28.75 28.76 28.75 0.00 1 1000 28.33 28.37 28.35 0.13 2 1000 27.40 27.42 27.42 0.28 4 1000 27.85 27.90 27.88 0.55 8 1000 27.58 27.60 27.59 1.11 16 1000 28.21 28.24 28.23 2.16 32 1000 29.12 29.17 29.14 4.19 64 1000 29.99 30.02 30.01 8.13 128 1000 30.85 30.88 30.86 15.81 256 1000 35.29 35.32 35.31 27.65 512 1000 37.49 37.51 37.50 52.07 1024 1000 42.55 42.59 42.56 91.72 2048 1000 51.94 52.05 52.00 150.10 4096 1000 76.53 76.62 76.58 203.94 8192 1000 128.06 128.13 128.10 243.89 16384 1000 235.84 236.08 235.97 264.74 32768 1000 458.83 459.15 459.00 272.24 65536 640 843.91 844.22 844.05 296.13 131072 320 1500.55 1502.73 1501.80 332.73 262144 160 2763.93 2768.24 2766.82 361.24 524288 80 5910.85 5936.65 5930.32 336.89 1048576 40 9951.77 9952.60 9952.12 401.90 2097152 20 16851.35 17069.60 17011.66 468.67 4194304 10 31607.10 31616.40 31612.84 506.07 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 16 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 43.94 43.99 43.96 0.00 1 1000 44.34 44.40 44.38 0.09 2 1000 44.42 44.46 44.44 0.17 4 1000 44.28 44.38 44.33 0.34 8 1000 42.14 42.22 42.18 0.72 16 1000 41.22 41.29 41.26 1.48 32 1000 41.68 41.78 41.74 2.92 64 1000 43.17 43.28 43.22 5.64 128 1000 44.67 44.76 44.72 10.91 256 1000 55.86 55.92 55.90 17.46 512 1000 58.54 58.71 58.66 33.27 1024 1000 64.59 64.79 64.71 60.29 2048 1000 89.93 90.12 90.03 86.69 4096 1000 133.22 133.68 133.56 116.88 8192 1000 250.68 251.17 250.95 124.42 16384 1000 484.68 485.40 485.08 128.76 32768 1000 944.20 946.78 946.01 132.03 65536 640 1440.83 1441.76 1441.46 173.40 131072 320 2639.70 2644.38 2642.82 189.08 262144 160 4928.59 4950.06 4941.67 202.02 524288 80 11001.50 11076.09 11066.15 180.57 1048576 40 19042.05 19163.60 19131.98 208.73 2097152 20 33076.39 33880.85 33618.95 236.12 4194304 10 62766.89 63108.30 63048.16 253.53 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 11.92 11.93 11.92 8 1000 11.49 11.49 11.49 16 1000 11.37 11.38 11.38 32 1000 11.53 11.54 11.54 64 1000 11.64 11.65 11.65 128 1000 12.35 12.35 12.35 256 1000 14.11 14.11 14.11 512 1000 15.13 15.13 15.13 1024 1000 16.92 16.94 16.93 2048 1000 21.29 21.31 21.30 4096 1000 40.67 40.68 40.68 8192 1000 59.31 59.34 59.32 16384 1000 89.48 89.51 89.49 32768 1000 134.84 134.95 134.89 65536 640 219.74 219.75 219.74 131072 320 534.95 535.03 534.99 262144 160 923.26 923.27 923.26 524288 80 1613.94 1614.05 1613.99 1048576 40 3348.45 3348.50 3348.48 2097152 20 5684.54 5685.35 5684.95 4194304 10 9414.20 9415.51 9414.85 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 20.32 20.34 20.33 8 1000 20.40 20.41 20.41 16 1000 20.34 20.35 20.35 32 1000 20.45 20.46 20.45 64 1000 21.11 21.12 21.11 128 1000 21.64 21.65 21.65 256 1000 23.97 23.99 23.98 512 1000 25.79 25.80 25.80 1024 1000 29.39 29.42 29.40 2048 1000 36.20 36.21 36.20 4096 1000 63.62 63.65 63.64 8192 1000 88.57 88.59 88.58 16384 1000 137.45 137.47 137.46 32768 1000 223.56 223.59 223.58 65536 640 390.37 390.40 390.38 131072 320 825.09 825.14 825.11 262144 160 1388.96 1389.07 1389.03 524288 80 2933.59 2936.14 2934.88 1048576 40 5581.07 5581.55 5581.21 2097152 20 10125.26 10126.60 10125.81 4194304 10 18503.59 18507.29 18505.27 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 29.64 29.67 29.66 8 1000 29.36 29.39 29.38 16 1000 29.41 29.43 29.42 32 1000 29.66 29.68 29.67 64 1000 31.20 31.20 31.20 128 1000 32.22 32.23 32.22 256 1000 37.05 37.08 37.06 512 1000 39.21 39.23 39.22 1024 1000 44.27 44.28 44.28 2048 1000 54.81 54.84 54.83 4096 1000 93.82 93.87 93.85 8192 1000 131.07 131.09 131.08 16384 1000 217.05 217.11 217.08 32768 1000 375.78 375.92 375.86 65536 640 702.07 702.19 702.13 131072 320 1281.99 1282.06 1282.03 262144 160 2459.74 2462.82 2462.03 524288 80 4643.15 4648.74 4647.28 1048576 40 8940.45 8941.45 8940.87 2097152 20 16776.70 16784.60 16779.38 4194304 10 32084.18 32110.50 32102.31 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 16 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 48.25 48.28 48.27 8 1000 48.47 48.50 48.49 16 1000 48.19 48.20 48.19 32 1000 48.78 48.86 48.82 64 1000 51.20 51.21 51.21 128 1000 52.99 53.00 53.00 256 1000 59.44 59.47 59.45 512 1000 64.12 64.15 64.13 1024 1000 72.15 72.18 72.16 2048 1000 90.38 90.40 90.40 4096 1000 154.82 154.87 154.84 8192 1000 222.03 222.21 222.11 16384 1000 386.83 387.01 386.90 32768 1000 698.03 698.28 698.12 65536 640 1301.94 1302.50 1302.18 131072 320 2187.41 2188.73 2188.17 262144 160 4048.03 4055.61 4053.60 524288 80 8036.59 8045.05 8039.54 1048576 40 15913.87 15927.62 15924.43 2097152 20 31507.15 31514.60 31511.45 4194304 10 63110.09 63121.80 63115.28 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.04 0.03 4 1000 10.39 10.42 10.41 8 1000 10.28 10.30 10.29 16 1000 10.36 10.37 10.36 32 1000 10.40 10.42 10.41 64 1000 10.76 10.78 10.77 128 1000 11.28 11.30 11.29 256 1000 12.56 12.57 12.56 512 1000 13.60 13.63 13.62 1024 1000 15.95 15.97 15.96 2048 1000 19.86 19.88 19.87 4096 1000 30.64 30.68 30.66 8192 1000 42.96 42.99 42.98 16384 1000 65.87 65.91 65.89 32768 1000 104.96 105.00 104.98 65536 640 177.86 177.94 177.90 131072 320 573.15 573.15 573.15 262144 160 1004.92 1004.99 1004.96 524288 80 1787.36 1787.37 1787.37 1048576 40 2856.80 2856.80 2856.80 2097152 20 4528.34 4528.55 4528.45 4194304 10 10538.01 10539.29 10538.65 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 19.04 19.07 19.05 8 1000 18.85 18.88 18.87 16 1000 18.77 18.79 18.78 32 1000 18.94 18.97 18.96 64 1000 20.11 20.14 20.13 128 1000 20.20 20.24 20.22 256 1000 21.40 21.43 21.42 512 1000 23.49 23.52 23.50 1024 1000 27.45 27.48 27.47 2048 1000 33.93 33.97 33.95 4096 1000 42.71 42.74 42.72 8192 1000 58.79 58.83 58.81 16384 1000 89.03 89.09 89.06 32768 1000 149.22 149.29 149.25 65536 640 269.13 269.29 269.19 131072 320 681.12 681.57 681.34 262144 160 1262.87 1264.76 1263.86 524288 80 2329.98 2335.01 2332.69 1048576 40 4078.22 4097.30 4088.53 2097152 20 7284.15 7355.70 7324.92 4194304 10 15764.50 15935.90 15855.80 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 23.78 23.80 23.79 8 1000 24.23 24.26 24.24 16 1000 24.44 24.46 24.45 32 1000 24.44 24.53 24.51 64 1000 25.23 25.24 25.24 128 1000 26.45 26.47 26.46 256 1000 29.00 29.02 29.01 512 1000 31.16 31.19 31.18 1024 1000 34.79 34.82 34.81 2048 1000 42.66 42.71 42.69 4096 1000 61.63 61.64 61.64 8192 1000 87.06 87.10 87.07 16384 1000 137.84 137.90 137.86 32768 1000 235.23 235.35 235.27 65536 640 429.46 429.60 429.49 131072 320 869.49 870.09 869.67 262144 160 1576.44 1578.23 1577.05 524288 80 2979.79 2985.62 2981.67 1048576 40 5680.23 5703.25 5688.05 2097152 20 11489.20 11596.31 11534.07 4194304 10 23921.70 24216.91 24041.14 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 16 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 4 1000 32.75 32.80 32.77 8 1000 32.81 32.87 32.84 16 1000 32.86 32.92 32.90 32 1000 33.06 33.12 33.10 64 1000 33.97 34.04 34.00 128 1000 35.29 35.37 35.33 256 1000 39.26 39.34 39.30 512 1000 42.09 42.17 42.12 1024 1000 47.14 47.22 47.18 2048 1000 58.19 58.29 58.24 4096 1000 93.19 93.24 93.21 8192 1000 132.59 132.65 132.61 16384 1000 224.71 224.78 224.73 32768 1000 384.01 384.10 384.04 65536 640 758.79 759.01 758.82 131072 320 1334.58 1335.26 1334.73 262144 160 2400.32 2402.64 2400.97 524288 80 4720.35 4728.04 4722.29 1048576 40 9964.67 9995.65 9973.88 2097152 20 21179.51 21312.20 21222.62 4194304 10 45547.41 46032.91 45725.07 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.09 4 1000 3.55 3.56 3.55 8 1000 12.11 12.12 12.11 16 1000 12.16 12.16 12.16 32 1000 12.08 12.10 12.09 64 1000 12.20 12.21 12.21 128 1000 12.81 12.81 12.81 256 1000 13.26 13.27 13.27 512 1000 14.76 14.78 14.77 1024 1000 16.82 16.85 16.84 2048 1000 18.69 18.71 18.70 4096 1000 23.02 23.04 23.03 8192 1000 33.34 33.37 33.35 16384 1000 50.92 50.94 50.93 32768 1000 81.77 81.78 81.78 65536 640 132.71 132.79 132.75 131072 320 381.07 381.10 381.09 262144 160 668.85 668.89 668.87 524288 80 565.99 565.99 565.99 1048576 40 1238.98 1239.05 1239.01 2097152 20 2209.00 2209.81 2209.40 4194304 10 4837.99 4838.99 4838.49 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.10 4 1000 2.41 16.43 7.17 8 1000 2.21 23.62 12.95 16 1000 21.79 21.80 21.79 32 1000 21.65 21.68 21.67 64 1000 21.69 21.70 21.70 128 1000 22.17 22.18 22.17 256 1000 23.05 23.06 23.06 512 1000 24.13 24.16 24.15 1024 1000 26.72 26.74 26.73 2048 1000 28.67 28.68 28.68 4096 1000 33.37 33.39 33.38 8192 1000 43.15 43.16 43.16 16384 1000 65.26 65.30 65.28 32768 1000 102.33 102.38 102.35 65536 640 171.60 171.71 171.65 131072 320 340.61 340.67 340.64 262144 160 856.86 857.24 857.07 524288 80 1206.85 1207.09 1206.98 1048576 40 2380.47 2382.28 2381.73 2097152 20 4908.96 4912.10 4910.48 4194304 10 8724.71 8742.59 8732.97 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.12 0.11 4 1000 2.59 26.52 7.75 8 1000 2.46 37.36 12.12 16 1000 2.26 38.13 20.26 32 1000 30.84 30.86 30.85 64 1000 31.01 31.03 31.02 128 1000 31.71 31.73 31.72 256 1000 32.62 32.65 32.64 512 1000 34.49 34.51 34.50 1024 1000 35.98 36.01 36.00 2048 1000 40.73 40.76 40.74 4096 1000 45.28 45.32 45.30 8192 1000 54.03 54.06 54.04 16384 1000 74.38 74.42 74.40 32768 1000 120.78 120.81 120.79 65536 640 208.28 208.51 208.39 131072 320 416.11 416.43 416.27 262144 160 752.13 752.79 752.50 524288 80 2286.64 2289.15 2288.27 1048576 40 4159.90 4169.12 4166.12 2097152 20 8179.45 8196.81 8190.15 4194304 10 15609.79 15631.01 15619.58 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 16 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.12 0.16 0.14 4 1000 2.45 40.70 8.20 8 1000 2.34 50.95 10.85 16 1000 2.35 56.19 16.90 32 1000 2.41 51.20 26.89 64 1000 49.95 49.98 49.96 128 1000 51.03 51.07 51.05 256 1000 51.62 51.67 51.64 512 1000 53.70 53.73 53.71 1024 1000 56.73 56.79 56.75 2048 1000 59.55 59.59 59.57 4096 1000 68.34 68.39 68.36 8192 1000 79.22 79.31 79.23 16384 1000 103.71 103.75 103.73 32768 1000 159.36 159.43 159.39 65536 640 284.78 284.94 284.85 131072 320 531.47 531.95 531.68 262144 160 963.41 965.22 964.23 524288 80 5219.38 5229.50 5224.87 1048576 40 7521.40 7538.03 7531.07 2097152 20 14259.90 14271.15 14266.74 4194304 10 27518.11 27606.80 27572.85 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 1 1000 11.12 11.13 11.13 2 1000 11.22 11.24 11.23 4 1000 11.21 11.22 11.21 8 1000 11.31 11.32 11.31 16 1000 11.32 11.33 11.32 32 1000 11.33 11.34 11.34 64 1000 11.52 11.52 11.52 128 1000 12.04 12.05 12.04 256 1000 13.36 13.36 13.36 512 1000 14.95 14.95 14.95 1024 1000 16.14 16.15 16.15 2048 1000 20.80 20.82 20.81 4096 1000 29.18 29.19 29.19 8192 1000 43.65 43.67 43.66 16384 1000 65.26 65.27 65.26 32768 1000 106.25 106.28 106.26 65536 640 172.78 172.78 172.78 131072 320 274.42 274.47 274.44 262144 160 446.90 446.92 446.91 524288 80 853.88 854.02 853.95 1048576 40 1615.95 1616.30 1616.12 2097152 20 3366.01 3366.85 3366.43 4194304 10 7304.00 7306.00 7305.00 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.04 0.03 1 1000 19.61 19.61 19.61 2 1000 19.76 19.76 19.76 4 1000 19.81 19.82 19.82 8 1000 19.78 19.80 19.79 16 1000 19.95 19.95 19.95 32 1000 20.29 20.30 20.30 64 1000 21.12 21.14 21.13 128 1000 21.80 21.82 21.81 256 1000 23.97 23.98 23.98 512 1000 25.86 25.89 25.87 1024 1000 29.05 29.07 29.06 2048 1000 36.43 36.46 36.44 4096 1000 56.59 56.61 56.60 8192 1000 87.80 87.84 87.82 16384 1000 149.52 149.56 149.54 32768 1000 204.04 204.10 204.07 65536 640 350.54 350.57 350.55 131072 320 1586.16 1586.99 1586.65 262144 160 2638.37 2640.87 2639.85 524288 80 4500.09 4505.88 4504.32 1048576 40 7892.20 7893.43 7893.07 2097152 20 15274.55 15291.05 15285.49 4194304 10 28852.58 28852.92 28852.77 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.04 0.03 1 1000 28.36 28.44 28.40 2 1000 28.59 28.63 28.62 4 1000 28.93 28.94 28.93 8 1000 29.00 29.01 29.01 16 1000 29.63 29.66 29.65 32 1000 30.37 30.37 30.37 64 1000 31.84 31.84 31.84 128 1000 33.16 33.19 33.17 256 1000 37.75 37.76 37.76 512 1000 41.19 41.21 41.20 1024 1000 48.23 48.23 48.23 2048 1000 64.73 64.74 64.74 4096 1000 103.20 103.21 103.20 8192 1000 181.79 181.80 181.80 16384 1000 266.33 266.43 266.38 32768 1000 436.77 436.85 436.81 65536 640 3590.44 3591.10 3590.83 131072 320 6165.15 6165.81 6165.33 262144 160 11330.09 11339.22 11335.65 524288 80 21236.76 21263.96 21257.85 1048576 40 33966.58 33967.58 33966.93 2097152 20 60433.20 60434.15 60433.66 4194304 10 113322.50 113323.90 113323.09 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 16 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.05 0.03 1 1000 46.79 46.82 46.80 2 1000 46.84 46.86 46.85 4 1000 47.28 47.29 47.29 8 1000 47.76 47.78 47.77 16 1000 48.40 48.40 48.40 32 1000 50.66 50.69 50.67 64 1000 52.28 52.30 52.30 128 1000 55.40 55.41 55.41 256 1000 64.01 64.02 64.01 512 1000 74.33 74.34 74.33 1024 1000 94.60 94.66 94.63 2048 1000 146.51 146.52 146.51 4096 1000 261.26 261.32 261.28 8192 1000 340.08 340.13 340.11 16384 1000 593.26 593.35 593.31 32768 1000 8120.95 8124.00 8123.09 65536 640 12126.67 12128.50 12127.82 131072 320 21913.24 21917.12 21915.62 262144 160 41405.94 41418.33 41412.17 524288 80 82349.14 82363.61 82360.76 1048576 40 130504.30 130660.35 130644.73 2097152 20 240991.90 241085.95 241051.40 4194304 10 459693.91 460092.21 459991.71 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.04 0.03 1 1000 12.77 12.77 12.77 2 1000 12.69 12.70 12.69 4 1000 12.45 12.46 12.46 8 1000 12.38 12.39 12.39 16 1000 12.67 12.68 12.67 32 1000 12.53 12.53 12.53 64 1000 13.10 13.11 13.11 128 1000 13.40 13.41 13.40 256 1000 14.71 14.72 14.71 512 1000 16.25 16.27 16.26 1024 1000 17.94 17.94 17.94 2048 1000 22.29 22.29 22.29 4096 1000 31.11 31.12 31.12 8192 1000 45.74 45.76 45.75 16384 1000 69.68 69.72 69.70 32768 1000 119.35 119.38 119.36 65536 640 330.83 330.83 330.83 131072 320 621.00 621.04 621.02 262144 160 470.61 470.66 470.63 524288 80 848.64 848.73 848.68 1048576 40 1620.02 1620.27 1620.15 2097152 20 3445.15 3445.90 3445.52 4194304 10 6956.10 6957.29 6956.70 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 1 1000 22.15 22.15 22.15 2 1000 22.26 22.28 22.26 4 1000 22.38 22.40 22.39 8 1000 22.40 22.42 22.41 16 1000 22.33 22.37 22.35 32 1000 22.82 22.83 22.83 64 1000 23.58 23.59 23.59 128 1000 24.46 24.47 24.47 256 1000 26.90 26.91 26.90 512 1000 28.57 28.57 28.57 1024 1000 32.04 32.04 32.04 2048 1000 39.84 39.86 39.85 4096 1000 58.48 58.53 58.51 8192 1000 93.83 93.85 93.84 16384 1000 159.90 159.92 159.91 32768 1000 303.20 303.25 303.23 65536 640 747.83 748.07 747.95 131072 320 1659.00 1659.83 1659.50 262144 160 2724.17 2724.29 2724.22 524288 80 4454.70 4454.99 4454.83 1048576 40 7875.53 7876.78 7876.21 2097152 20 14854.05 14872.00 14866.28 4194304 10 28687.31 28695.51 28692.59 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 1 1000 33.71 33.71 33.71 2 1000 33.84 33.87 33.86 4 1000 33.96 33.97 33.96 8 1000 34.03 34.04 34.03 16 1000 34.39 34.41 34.40 32 1000 35.37 35.38 35.37 64 1000 36.99 37.02 37.00 128 1000 38.16 38.19 38.18 256 1000 42.90 42.90 42.90 512 1000 46.35 46.37 46.36 1024 1000 53.62 53.63 53.62 2048 1000 71.32 71.36 71.33 4096 1000 112.11 112.16 112.13 8192 1000 194.85 194.88 194.86 16384 1000 340.57 340.63 340.60 32768 1000 555.21 555.25 555.23 65536 640 3583.16 3583.65 3583.40 131072 320 6287.07 6288.96 6288.25 262144 160 11384.55 11387.86 11387.31 524288 80 21373.56 21390.29 21383.83 1048576 40 33733.55 33778.10 33758.64 2097152 20 60477.24 60735.34 60669.74 4194304 10 113811.61 113869.00 113852.67 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 16 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.05 0.06 0.05 1 1000 56.51 56.55 56.53 2 1000 56.49 56.51 56.50 4 1000 56.66 56.71 56.69 8 1000 57.10 57.13 57.12 16 1000 57.75 57.76 57.76 32 1000 58.82 58.85 58.83 64 1000 61.96 61.97 61.96 128 1000 64.10 64.11 64.11 256 1000 71.79 71.86 71.83 512 1000 82.24 82.28 82.26 1024 1000 104.89 104.91 104.90 2048 1000 159.16 159.23 159.19 4096 1000 276.14 276.20 276.17 8192 1000 520.95 521.04 521.01 16384 1000 729.01 729.25 729.13 32768 1000 8113.09 8116.14 8115.14 65536 640 12125.29 12126.33 12126.07 131072 320 21842.18 21844.51 21843.00 262144 160 41251.51 41270.96 41263.70 524288 80 81890.73 81962.77 81941.30 1048576 40 130673.40 130739.07 130720.87 2097152 20 240843.90 240988.95 240943.09 4194304 10 460667.11 461073.71 460874.99 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 1 1000 11.02 11.02 11.02 2 1000 11.17 11.17 11.17 4 1000 11.31 11.31 11.31 8 1000 11.17 11.19 11.18 16 1000 11.18 11.18 11.18 32 1000 11.24 11.25 11.25 64 1000 11.28 11.29 11.28 128 1000 11.79 11.80 11.80 256 1000 13.17 13.18 13.18 512 1000 14.56 14.57 14.56 1024 1000 16.23 16.24 16.24 2048 1000 19.89 19.91 19.90 4096 1000 29.24 29.26 29.25 8192 1000 42.99 43.01 43.00 16384 1000 63.70 63.72 63.71 32768 1000 99.58 99.60 99.59 65536 640 171.22 171.22 171.22 131072 320 269.71 269.71 269.71 262144 160 525.34 525.35 525.34 524288 80 1177.41 1177.53 1177.47 1048576 40 1798.80 1798.80 1798.80 2097152 20 3498.24 3498.51 3498.38 4194304 10 7158.90 7160.28 7159.59 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.04 0.03 1 1000 23.91 23.91 23.91 2 1000 24.06 24.10 24.08 4 1000 24.11 24.15 24.13 8 1000 24.10 24.11 24.11 16 1000 23.95 23.96 23.96 32 1000 24.07 24.09 24.08 64 1000 24.89 24.90 24.90 128 1000 25.59 25.60 25.60 256 1000 29.17 29.18 29.17 512 1000 30.91 30.91 30.91 1024 1000 34.56 34.59 34.57 2048 1000 42.74 42.78 42.76 4096 1000 59.97 59.98 59.97 8192 1000 94.36 94.39 94.38 16384 1000 159.52 159.56 159.54 32768 1000 288.72 288.82 288.77 65536 640 621.51 621.53 621.52 131072 320 1016.61 1016.71 1016.66 262144 160 1784.41 1784.82 1784.70 524288 80 3722.41 3722.56 3722.48 1048576 40 7307.67 7308.40 7308.01 2097152 20 13277.79 13279.90 13278.85 4194304 10 25974.11 25975.49 25974.79 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.03 0.03 1 1000 41.61 41.63 41.62 2 1000 41.04 41.06 41.05 4 1000 40.41 40.44 40.42 8 1000 41.77 41.78 41.78 16 1000 42.77 42.80 42.79 32 1000 45.05 45.08 45.06 64 1000 49.38 49.41 49.39 128 1000 52.48 52.50 52.49 256 1000 57.58 57.61 57.60 512 1000 76.33 76.37 76.35 1024 1000 85.72 85.80 85.75 2048 1000 111.02 111.05 111.03 4096 1000 165.50 165.54 165.52 8192 1000 289.90 289.99 289.94 16384 1000 555.26 555.52 555.46 32768 1000 1151.67 1152.06 1151.89 65536 640 1981.31 1981.50 1981.43 131072 320 3522.22 3522.40 3522.34 262144 160 7478.62 7481.82 7480.78 524288 80 15586.98 15588.31 15587.73 1048576 40 27505.50 27506.92 27506.04 2097152 20 45108.26 45120.60 45115.61 4194304 10 84496.69 84541.20 84528.38 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 16 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.03 0.04 0.03 1 1000 66.69 66.74 66.71 2 1000 66.24 66.25 66.25 4 1000 67.66 67.68 67.67 8 1000 69.67 69.68 69.68 16 1000 72.29 72.31 72.30 32 1000 79.64 79.67 79.64 64 1000 84.57 84.59 84.58 128 1000 93.00 93.11 93.05 256 1000 113.82 113.84 113.83 512 1000 251.15 251.31 251.22 1024 1000 297.27 297.38 297.33 2048 1000 409.39 409.55 409.50 4096 1000 653.92 654.12 654.01 8192 1000 1289.23 1289.41 1289.33 16384 1000 2657.36 2657.65 2657.52 32768 1000 5745.59 5746.27 5745.94 65536 640 7295.01 7296.10 7295.61 131072 320 13706.11 13709.63 13708.92 262144 160 27408.46 27420.75 27417.43 524288 80 53420.28 53454.41 53444.07 1048576 40 95793.45 95815.60 95809.55 2097152 20 167910.44 167987.64 167937.30 4194304 10 323603.58 323849.49 323766.19 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.02 0.02 0.02 1 1000 9.40 9.40 9.40 2 1000 9.28 9.28 9.28 4 1000 9.41 9.42 9.42 8 1000 9.44 9.44 9.44 16 1000 9.41 9.41 9.41 32 1000 9.36 9.37 9.36 64 1000 9.66 9.67 9.67 128 1000 10.05 10.06 10.06 256 1000 11.42 11.42 11.42 512 1000 12.50 12.50 12.50 1024 1000 14.46 14.46 14.46 2048 1000 18.32 18.34 18.33 4096 1000 26.14 26.16 26.15 8192 1000 37.05 37.07 37.06 16384 1000 52.34 52.37 52.36 32768 1000 82.81 82.85 82.83 65536 640 138.48 138.52 138.50 131072 320 209.35 209.39 209.37 262144 160 348.67 348.71 348.69 524288 80 584.66 584.85 584.76 1048576 40 1033.25 1033.60 1033.43 2097152 20 1901.45 1901.65 1901.55 4194304 10 3637.19 3638.41 3637.80 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.02 0.02 0.02 1 1000 13.38 13.38 13.38 2 1000 13.25 13.32 13.30 4 1000 13.51 13.53 13.52 8 1000 13.32 13.34 13.33 16 1000 13.80 13.81 13.81 32 1000 13.31 13.32 13.31 64 1000 13.72 13.73 13.72 128 1000 14.23 14.23 14.23 256 1000 15.79 15.82 15.81 512 1000 16.95 16.96 16.96 1024 1000 19.69 19.71 19.70 2048 1000 24.80 24.83 24.81 4096 1000 35.10 35.14 35.12 8192 1000 60.10 60.15 60.13 16384 1000 99.76 99.81 99.78 32768 1000 174.34 174.42 174.38 65536 640 232.13 232.23 232.18 131072 320 389.07 389.41 389.24 262144 160 692.06 692.97 692.51 524288 80 1260.81 1261.05 1260.91 1048576 40 2434.90 2435.70 2435.26 2097152 20 4452.10 4455.70 4453.90 4194304 10 8677.20 8686.09 8681.64 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.02 0.02 0.02 1 1000 17.45 17.54 17.48 2 1000 17.50 17.56 17.53 4 1000 17.83 17.87 17.85 8 1000 17.75 17.78 17.76 16 1000 17.82 17.87 17.85 32 1000 17.72 17.76 17.74 64 1000 18.15 18.19 18.17 128 1000 18.51 18.55 18.52 256 1000 21.53 21.58 21.55 512 1000 22.60 22.65 22.63 1024 1000 24.90 24.96 24.93 2048 1000 30.38 30.41 30.39 4096 1000 42.41 42.48 42.45 8192 1000 70.69 70.78 70.73 16384 1000 95.00 95.01 95.00 32768 1000 153.24 153.25 153.25 65536 640 286.34 286.37 286.35 131072 320 461.75 461.92 461.85 262144 160 866.41 866.92 866.75 524288 80 4086.49 4090.39 4089.55 1048576 40 7248.07 7266.50 7260.52 2097152 20 13090.90 13149.31 13134.16 4194304 10 25192.19 25408.79 25338.85 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 16 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.02 0.03 0.02 1 1000 23.16 23.29 23.20 2 1000 22.77 22.83 22.79 4 1000 23.04 23.11 23.07 8 1000 23.13 23.17 23.14 16 1000 22.77 22.85 22.81 32 1000 23.06 23.11 23.09 64 1000 23.20 23.24 23.22 128 1000 24.17 24.22 24.19 256 1000 27.93 27.97 27.95 512 1000 29.79 29.87 29.82 1024 1000 32.68 32.76 32.72 2048 1000 40.22 40.32 40.26 4096 1000 56.03 56.14 56.09 8192 1000 99.74 99.91 99.83 16384 1000 147.91 147.92 147.92 32768 1000 219.32 219.34 219.33 65536 640 381.43 381.47 381.45 131072 320 599.39 599.61 599.43 262144 160 1125.79 1127.48 1126.59 524288 80 8717.63 8755.74 8740.93 1048576 40 13261.50 13271.93 13270.04 2097152 20 23805.61 23913.94 23886.18 4194304 10 45120.91 45405.60 45328.36 #--------------------------------------------------- # Benchmarking Barrier # #processes = 2 # ( 14 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 10.51 10.51 10.51 #--------------------------------------------------- # Benchmarking Barrier # #processes = 4 # ( 12 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 19.08 19.08 19.08 #--------------------------------------------------- # Benchmarking Barrier # #processes = 8 # ( 8 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 28.21 28.21 28.21 #--------------------------------------------------- # Benchmarking Barrier # #processes = 16 #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 46.72 46.74 46.73