#--------------------------------------------------- # PALLAS MPI Benchmark Suite V2.2, MPI-1 part #--------------------------------------------------- # Date : Wed Sep 17 08:07:59 2003 # Machine : i686# System : Linux # Release : 2.4.21 # Version : #2 SMP Sun Jul 13 19:21:19 EDT 2003 # # 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 6.48 0.00 1 1000 6.57 0.15 2 1000 6.56 0.29 4 1000 6.60 0.58 8 1000 6.63 1.15 16 1000 6.73 2.27 32 1000 6.80 4.49 64 1000 7.01 8.71 128 1000 8.05 15.16 256 1000 10.19 23.96 512 1000 12.28 39.75 1024 1000 15.54 62.83 2048 1000 22.41 87.16 4096 1000 32.61 119.79 8192 1000 53.37 146.38 16384 1000 100.10 156.09 32768 1000 169.28 184.60 65536 640 306.16 204.14 131072 320 581.90 214.81 262144 160 1134.93 220.28 524288 80 2235.44 223.67 1048576 40 4440.34 225.21 2097152 20 8678.35 230.46 4194304 10 17172.35 232.93 #--------------------------------------------------- # Benchmarking PingPing # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 9.81 0.00 1 1000 9.86 0.10 2 1000 9.80 0.19 4 1000 9.85 0.39 8 1000 9.87 0.77 16 1000 9.94 1.53 32 1000 10.03 3.04 64 1000 10.17 6.00 128 1000 10.92 11.18 256 1000 13.85 17.63 512 1000 14.68 33.26 1024 1000 18.38 53.13 2048 1000 25.45 76.75 4096 1000 38.44 101.63 8192 1000 58.91 132.62 16384 1000 114.42 136.55 32768 1000 180.88 172.77 65536 640 318.72 196.10 131072 320 594.34 210.32 262144 160 1164.88 214.61 524288 80 2279.66 219.33 1048576 40 4492.60 222.59 2097152 20 8773.35 227.96 4194304 10 17379.70 230.15 #----------------------------------------------------------------------------- # 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 9.81 9.82 9.82 0.00 1 1000 9.78 9.79 9.79 0.19 2 1000 9.82 9.82 9.82 0.39 4 1000 9.77 9.77 9.77 0.78 8 1000 10.02 10.02 10.02 1.52 16 1000 9.89 9.90 9.90 3.08 32 1000 10.04 10.04 10.04 6.08 64 1000 10.24 10.25 10.24 11.92 128 1000 11.91 11.92 11.92 20.49 256 1000 13.60 13.62 13.61 35.86 512 1000 15.44 15.45 15.45 63.20 1024 1000 17.75 17.76 17.75 109.99 2048 1000 25.79 25.80 25.79 151.40 4096 1000 37.86 37.87 37.87 206.29 8192 1000 60.36 60.38 60.37 258.76 16384 1000 114.67 114.68 114.68 272.49 32768 1000 180.75 180.75 180.75 345.78 65536 640 319.56 319.56 319.56 391.16 131072 320 593.05 593.08 593.06 421.53 262144 160 1153.64 1153.64 1153.64 433.41 524288 80 2258.63 2258.66 2258.64 442.74 1048576 40 4483.45 4483.48 4483.46 446.08 2097152 20 8777.70 8777.75 8777.73 455.70 4194304 10 17480.60 17481.91 17481.26 457.62 #----------------------------------------------------------------------------- # 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 10.52 10.52 10.52 0.00 1 1000 10.71 10.71 10.71 0.18 2 1000 10.63 10.63 10.63 0.36 4 1000 10.91 10.91 10.91 0.70 8 1000 11.12 11.12 11.12 1.37 16 1000 11.52 11.52 11.52 2.65 32 1000 11.47 11.48 11.48 5.32 64 1000 11.76 11.76 11.76 10.38 128 1000 12.22 12.22 12.22 19.97 256 1000 14.59 14.59 14.59 33.46 512 1000 15.86 15.88 15.87 61.50 1024 1000 18.72 18.73 18.72 104.30 2048 1000 27.57 27.60 27.59 141.52 4096 1000 42.90 42.95 42.92 181.91 8192 1000 62.23 62.26 62.24 250.97 16384 1000 145.57 145.64 145.61 214.58 32768 1000 260.79 260.85 260.83 239.60 65536 640 381.34 381.50 381.44 327.66 131072 320 643.70 643.72 643.70 388.37 262144 160 1194.22 1194.84 1194.57 418.47 524288 80 2312.03 2312.49 2312.22 432.43 1048576 40 4563.53 4565.03 4564.28 438.11 2097152 20 8867.90 8871.30 8869.89 450.89 4194304 10 17756.61 17802.30 17779.77 449.38 #----------------------------------------------------------------------------- # 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 10.71 10.72 10.72 0.00 1 1000 10.75 10.75 10.75 0.18 2 1000 10.75 10.76 10.75 0.35 4 1000 10.81 10.81 10.81 0.71 8 1000 10.79 10.80 10.80 1.41 16 1000 11.27 11.28 11.28 2.70 32 1000 11.41 11.42 11.42 5.34 64 1000 11.42 11.43 11.42 10.68 128 1000 12.15 12.16 12.15 20.08 256 1000 14.36 14.38 14.37 33.96 512 1000 15.97 15.99 15.98 61.09 1024 1000 18.63 18.65 18.64 104.72 2048 1000 28.86 28.89 28.88 135.21 4096 1000 45.32 45.44 45.38 171.95 8192 1000 64.16 64.29 64.23 243.05 16384 1000 163.88 163.98 163.94 190.58 32768 1000 264.08 264.32 264.21 236.45 65536 640 431.38 431.50 431.47 289.68 131072 320 740.67 741.40 741.26 337.20 262144 160 1341.99 1342.73 1342.47 372.38 524288 80 2565.35 2567.11 2566.37 389.54 1048576 40 4999.52 5002.95 5001.04 399.76 2097152 20 9829.85 9845.65 9839.78 406.27 4194304 10 19393.10 19553.60 19492.84 409.13 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # ( #processes = 16 ) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 10.77 10.78 10.77 0.00 1 1000 10.86 10.87 10.87 0.18 2 1000 10.86 10.87 10.87 0.35 4 1000 10.94 10.95 10.95 0.70 8 1000 11.25 11.26 11.25 1.36 16 1000 11.21 11.22 11.22 2.72 32 1000 11.81 11.83 11.82 5.16 64 1000 11.45 11.47 11.46 10.65 128 1000 12.30 12.32 12.31 19.82 256 1000 14.61 14.63 14.62 33.37 512 1000 15.96 15.98 15.97 61.11 1024 1000 19.14 19.16 19.15 101.93 2048 1000 28.37 28.46 28.42 137.26 4096 1000 43.30 43.43 43.37 179.90 8192 1000 63.45 63.59 63.50 245.72 16384 1000 170.36 170.54 170.45 183.24 32768 1000 262.85 263.07 262.98 237.57 65536 640 425.92 426.12 426.03 293.34 131072 320 732.37 733.54 732.90 340.81 262144 160 1398.54 1405.06 1401.71 355.86 524288 80 2724.45 2757.81 2743.11 362.61 1048576 40 5340.85 5473.42 5409.80 365.40 2097152 20 10152.15 10678.91 10440.26 374.57 4194304 10 19143.51 21377.60 20310.78 374.22 #----------------------------------------------------------------------------- # 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 19.07 19.08 19.07 0.00 1 1000 19.09 19.09 19.09 0.20 2 1000 19.10 19.10 19.10 0.40 4 1000 19.10 19.11 19.11 0.80 8 1000 19.03 19.03 19.03 1.60 16 1000 19.31 19.31 19.31 3.16 32 1000 19.34 19.34 19.34 6.31 64 1000 19.50 19.50 19.50 12.52 128 1000 20.98 20.99 20.99 23.26 256 1000 22.48 22.49 22.48 43.42 512 1000 23.52 23.53 23.53 83.02 1024 1000 26.45 26.45 26.45 147.69 2048 1000 36.30 36.30 36.30 215.22 4096 1000 58.83 58.84 58.83 265.56 8192 1000 95.80 95.83 95.82 326.09 16384 1000 228.09 228.10 228.09 274.01 32768 1000 361.56 361.57 361.57 345.72 65536 640 637.27 637.27 637.27 392.30 131072 320 1188.55 1188.56 1188.55 420.68 262144 160 2291.14 2291.18 2291.16 436.46 524288 80 4522.64 4522.73 4522.68 442.21 1048576 40 9001.85 9002.02 9001.94 444.34 2097152 20 17579.81 17580.15 17579.98 455.06 4194304 10 34870.70 34871.30 34871.00 458.83 #----------------------------------------------------------------------------- # 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 20.62 20.62 20.62 0.00 1 1000 20.59 20.60 20.59 0.19 2 1000 20.72 20.72 20.72 0.37 4 1000 20.55 20.56 20.55 0.74 8 1000 20.58 20.58 20.58 1.48 16 1000 20.67 20.68 20.68 2.95 32 1000 20.80 20.81 20.80 5.87 64 1000 20.93 20.94 20.93 11.66 128 1000 22.40 22.41 22.41 21.79 256 1000 22.74 22.75 22.74 42.94 512 1000 24.11 24.11 24.11 81.02 1024 1000 27.33 27.34 27.33 142.90 2048 1000 36.75 36.75 36.75 212.58 4096 1000 67.14 67.17 67.16 232.62 8192 1000 114.05 114.07 114.06 273.95 16384 1000 306.28 306.32 306.30 204.04 32768 1000 443.95 443.97 443.96 281.55 65536 640 685.69 685.72 685.71 364.58 131072 320 1252.48 1252.86 1252.71 399.09 262144 160 2363.21 2363.35 2363.27 423.13 524288 80 4607.37 4607.82 4607.61 434.04 1048576 40 9125.15 9128.90 9127.67 438.17 2097152 20 17776.65 17780.70 17777.97 449.93 4194304 10 35078.80 35085.20 35082.78 456.03 #----------------------------------------------------------------------------- # 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 20.53 20.54 20.53 0.00 1 1000 20.61 20.61 20.61 0.19 2 1000 20.61 20.61 20.61 0.37 4 1000 20.62 20.62 20.62 0.74 8 1000 20.61 20.62 20.61 1.48 16 1000 20.75 20.76 20.75 2.94 32 1000 20.84 20.85 20.85 5.85 64 1000 20.99 21.00 21.00 11.62 128 1000 22.39 22.40 22.40 21.80 256 1000 23.18 23.19 23.18 42.11 512 1000 24.84 24.85 24.84 78.61 1024 1000 28.40 28.41 28.41 137.49 2048 1000 39.77 39.80 39.78 196.31 4096 1000 66.46 66.49 66.48 234.98 8192 1000 113.80 113.82 113.81 274.55 16384 1000 291.17 291.25 291.22 214.59 32768 1000 472.13 472.30 472.22 264.67 65536 640 794.31 794.38 794.33 314.71 131072 320 1417.86 1418.51 1418.27 352.48 262144 160 2627.65 2627.97 2627.85 380.52 524288 80 5068.02 5070.09 5069.28 394.47 1048576 40 9971.82 9973.75 9972.64 401.05 2097152 20 19787.60 19808.35 19799.98 403.87 4194304 10 38977.41 39313.90 39142.46 406.98 #----------------------------------------------------------------------------- # Benchmarking Exchange # ( #processes = 16 ) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 20.50 20.51 20.50 0.00 1 1000 20.64 20.65 20.64 0.18 2 1000 20.60 20.64 20.62 0.37 4 1000 20.59 20.61 20.60 0.74 8 1000 20.61 20.62 20.61 1.48 16 1000 20.76 20.77 20.77 2.94 32 1000 21.00 21.02 21.01 5.81 64 1000 20.99 21.00 20.99 11.63 128 1000 22.42 22.44 22.43 21.76 256 1000 23.34 23.35 23.35 41.82 512 1000 24.90 24.91 24.91 78.40 1024 1000 28.81 28.83 28.82 135.51 2048 1000 41.27 41.32 41.29 189.09 4096 1000 66.39 66.43 66.41 235.22 8192 1000 113.11 113.20 113.16 276.07 16384 1000 287.44 287.58 287.49 217.33 32768 1000 467.37 467.60 467.49 267.32 65536 640 791.43 791.76 791.61 315.75 131072 320 1415.58 1417.05 1416.25 352.84 262144 160 2780.54 2785.47 2783.17 359.01 524288 80 5528.49 5556.85 5543.96 359.92 1048576 40 10949.00 11068.28 11017.34 361.39 2097152 20 21424.10 21864.25 21650.79 365.89 4194304 10 41611.30 43449.29 42545.09 368.25 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 4 1000 10.15 10.15 10.15 8 1000 10.32 10.32 10.32 16 1000 10.65 10.65 10.65 32 1000 10.87 10.87 10.87 64 1000 10.72 10.72 10.72 128 1000 12.55 12.55 12.55 256 1000 13.85 13.86 13.86 512 1000 16.23 16.23 16.23 1024 1000 21.52 21.53 21.53 2048 1000 31.65 31.66 31.65 4096 1000 45.52 45.54 45.53 8192 1000 81.23 81.23 81.23 16384 1000 165.52 165.53 165.53 32768 1000 284.90 284.91 284.90 65536 640 529.98 529.99 529.99 131072 320 1590.24 1590.26 1590.25 262144 160 3196.89 3197.23 3197.06 524288 80 6203.06 6203.63 6203.34 1048576 40 12409.53 12411.73 12410.63 2097152 20 25154.95 25169.70 25162.33 4194304 10 47755.00 47840.39 47797.70 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 4 1000 22.83 22.84 22.84 8 1000 22.58 22.59 22.58 16 1000 22.66 22.67 22.67 32 1000 22.89 22.89 22.89 64 1000 23.19 23.20 23.19 128 1000 26.14 26.14 26.14 256 1000 27.72 27.72 27.72 512 1000 33.22 33.22 33.22 1024 1000 40.59 40.59 40.59 2048 1000 58.03 58.05 58.04 4096 1000 87.16 87.18 87.17 8192 1000 144.33 144.35 144.34 16384 1000 290.48 290.48 290.48 32768 1000 489.72 489.73 489.72 65536 640 893.40 893.41 893.41 131072 320 2299.44 2299.71 2299.58 262144 160 4610.26 4611.11 4610.67 524288 80 9079.35 9081.91 9080.57 1048576 40 18191.47 18198.42 18195.20 2097152 20 36588.45 36608.51 36601.49 4194304 10 70599.70 70690.41 70661.97 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.04 0.04 4 1000 34.73 34.74 34.73 8 1000 34.80 34.80 34.80 16 1000 35.15 35.16 35.15 32 1000 35.56 35.57 35.56 64 1000 36.28 36.29 36.28 128 1000 39.02 39.02 39.02 256 1000 42.62 42.63 42.62 512 1000 49.88 49.89 49.89 1024 1000 60.43 60.44 60.43 2048 1000 85.09 85.10 85.09 4096 1000 126.67 126.69 126.68 8192 1000 206.54 206.59 206.57 16384 1000 415.82 415.84 415.83 32768 1000 697.09 697.10 697.09 65536 640 1270.31 1270.37 1270.34 131072 320 2992.19 2992.44 2992.29 262144 160 6001.09 6001.81 6001.48 524288 80 11941.56 11943.85 11942.88 1048576 40 24019.75 24027.05 24023.77 2097152 20 48207.10 48234.70 48226.81 4194304 10 93737.10 93835.20 93811.13 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.04 0.05 0.04 4 1000 46.79 46.80 46.79 8 1000 46.63 46.63 46.63 16 1000 47.16 47.17 47.16 32 1000 47.50 47.51 47.50 64 1000 48.23 48.24 48.23 128 1000 51.90 51.91 51.91 256 1000 59.28 59.30 59.29 512 1000 67.56 67.57 67.56 1024 1000 82.31 82.32 82.31 2048 1000 116.61 116.65 116.63 4096 1000 194.82 194.89 194.85 8192 1000 346.03 346.19 346.10 16384 1000 966.64 966.81 966.72 32768 1000 1682.98 1683.30 1683.12 65536 640 3137.98 3138.97 3138.42 131072 320 6607.47 6611.46 6609.25 262144 160 13164.77 13180.66 13171.91 524288 80 26228.07 26290.84 26255.59 1048576 40 52310.93 52565.55 52425.19 2097152 20 92325.50 93356.60 92796.23 4194304 10 178910.20 183032.80 180783.56 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.08 0.08 4 1000 7.02 7.04 7.03 8 1000 7.10 7.11 7.11 16 1000 7.23 7.24 7.24 32 1000 7.30 7.31 7.30 64 1000 7.54 7.55 7.54 128 1000 8.83 8.85 8.84 256 1000 11.16 11.17 11.17 512 1000 13.31 13.33 13.32 1024 1000 16.99 17.01 17.00 2048 1000 24.36 24.39 24.37 4096 1000 35.60 35.64 35.62 8192 1000 58.15 58.21 58.18 16384 1000 115.84 115.86 115.85 32768 1000 198.00 198.03 198.02 65536 640 738.54 738.83 738.69 131072 320 1445.27 1445.48 1445.37 262144 160 3093.23 3094.87 3094.05 524288 80 6059.35 6067.13 6063.24 1048576 40 11795.18 11828.10 11811.64 2097152 20 19983.80 20113.60 20048.70 4194304 10 35999.89 36520.50 36260.20 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.08 0.08 4 1000 13.65 13.68 13.67 8 1000 13.78 13.80 13.79 16 1000 14.00 14.02 14.01 32 1000 14.22 14.24 14.23 64 1000 14.64 14.66 14.65 128 1000 17.07 17.10 17.09 256 1000 22.31 22.33 22.32 512 1000 26.55 26.59 26.57 1024 1000 33.07 33.12 33.10 2048 1000 47.53 47.60 47.57 4096 1000 69.32 69.42 69.37 8192 1000 115.48 115.65 115.56 16384 1000 226.57 226.70 226.63 32768 1000 388.40 388.63 388.52 65536 640 1184.40 1185.40 1184.88 131072 320 2320.14 2323.27 2321.67 262144 160 4742.82 4756.10 4749.48 524288 80 9382.25 9436.19 9408.93 1048576 40 18415.02 18628.78 18521.08 2097152 20 32095.85 32904.60 32496.41 4194304 10 64965.70 67932.11 66437.38 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.08 0.08 4 1000 20.34 20.38 20.35 8 1000 20.47 20.51 20.49 16 1000 20.83 20.86 20.85 32 1000 21.14 21.18 21.16 64 1000 21.73 21.77 21.75 128 1000 25.43 25.48 25.45 256 1000 33.49 33.56 33.52 512 1000 39.71 39.79 39.75 1024 1000 49.36 49.45 49.40 2048 1000 70.70 70.83 70.76 4096 1000 103.07 103.26 103.16 8192 1000 175.38 175.68 175.52 16384 1000 337.93 338.31 338.12 32768 1000 578.40 579.04 578.72 65536 640 1600.48 1602.87 1601.69 131072 320 3135.10 3143.37 3139.22 262144 160 6401.51 6436.07 6418.87 524288 80 12643.71 12787.96 12715.88 1048576 40 24804.88 25382.47 25093.85 2097152 20 43519.25 45692.30 44606.79 4194304 10 75722.50 83648.90 79695.95 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.08 0.08 4 1000 27.51 27.57 27.53 8 1000 27.81 27.88 27.84 16 1000 28.00 28.06 28.03 32 1000 28.35 28.41 28.38 64 1000 29.21 29.27 29.24 128 1000 34.00 34.08 34.03 256 1000 45.42 45.52 45.47 512 1000 53.16 53.29 53.23 1024 1000 66.15 66.30 66.22 2048 1000 94.33 94.54 94.43 4096 1000 139.08 139.40 139.24 8192 1000 237.34 237.84 237.58 16384 1000 452.30 453.00 452.65 32768 1000 776.03 777.24 776.63 65536 640 2023.21 2027.37 2025.30 131072 320 3970.42 3986.74 3978.70 262144 160 8088.84 8156.74 8122.77 524288 80 15963.54 16241.87 16102.54 1048576 40 31251.70 32359.73 31805.32 2097152 20 54720.75 58895.05 56812.81 4194304 10 93030.20 108197.90 100613.34 #---------------------------------------------------------------- # 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 10.52 10.52 10.52 4 1000 11.60 11.60 11.60 8 1000 12.89 12.89 12.89 16 1000 12.92 12.93 12.93 32 1000 12.99 13.00 12.99 64 1000 13.16 13.16 13.16 128 1000 13.80 13.80 13.80 256 1000 15.75 15.75 15.75 512 1000 20.93 20.93 20.93 1024 1000 17.74 17.75 17.75 2048 1000 20.69 20.70 20.70 4096 1000 32.14 32.15 32.15 8192 1000 60.04 60.06 60.05 16384 1000 81.24 81.28 81.26 32768 1000 163.08 163.09 163.08 65536 640 278.11 278.11 278.11 131072 320 515.18 515.21 515.20 262144 160 1507.93 1508.50 1508.22 524288 80 3108.35 3108.56 3108.46 1048576 40 6042.70 6043.45 6043.08 2097152 20 11869.50 11878.55 11874.02 4194304 10 23465.80 23491.80 23478.80 #---------------------------------------------------------------- # 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 22.40 22.41 22.41 4 1000 24.11 24.12 24.11 8 1000 23.92 23.92 23.92 16 1000 24.63 24.63 24.63 32 1000 24.74 24.74 24.74 64 1000 26.22 26.23 26.22 128 1000 27.24 27.24 27.24 256 1000 30.12 30.12 30.12 512 1000 39.35 39.37 39.36 1024 1000 43.94 43.95 43.95 2048 1000 51.83 51.84 51.84 4096 1000 62.35 62.37 62.36 8192 1000 93.09 93.12 93.10 16384 1000 141.22 141.25 141.23 32768 1000 210.69 210.72 210.70 65536 640 475.77 475.78 475.78 131072 320 866.69 866.81 866.75 262144 160 1558.91 1558.94 1558.93 524288 80 2927.57 2928.39 2928.12 1048576 40 5962.58 5964.75 5963.74 2097152 20 11892.80 11896.65 11894.82 4194304 10 23432.21 23443.81 23438.36 #---------------------------------------------------------------- # 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 35.21 35.22 35.22 4 1000 37.72 37.73 37.72 8 1000 37.76 37.77 37.77 16 1000 38.40 38.41 38.40 32 1000 39.29 39.30 39.30 64 1000 40.25 40.26 40.25 128 1000 42.72 42.72 42.72 256 1000 46.48 46.49 46.48 512 1000 58.32 58.33 58.33 1024 1000 91.20 91.21 91.20 2048 1000 104.95 104.96 104.95 4096 1000 117.74 117.75 117.75 8192 1000 143.68 143.70 143.69 16384 1000 207.84 207.87 207.86 32768 1000 335.95 336.00 335.97 65536 640 524.85 524.93 524.88 131072 320 1312.44 1312.48 1312.45 262144 160 2154.23 2154.81 2154.44 524288 80 3569.82 3571.47 3570.84 1048576 40 6579.50 6582.62 6580.71 2097152 20 12339.60 12350.75 12345.72 4194304 10 24884.40 24894.30 24889.60 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 47.56 47.57 47.57 4 1000 51.66 51.68 51.67 8 1000 51.77 51.78 51.77 16 1000 52.40 52.41 52.41 32 1000 52.95 52.96 52.95 64 1000 54.84 54.85 54.85 128 1000 58.38 58.39 58.38 256 1000 64.48 64.49 64.48 512 1000 78.35 78.37 78.36 1024 1000 181.84 181.86 181.85 2048 1000 196.22 196.23 196.23 4096 1000 227.34 227.36 227.35 8192 1000 254.11 254.13 254.12 16384 1000 309.06 309.08 309.07 32768 1000 449.14 449.18 449.16 65536 640 770.07 770.15 770.12 131072 320 1429.08 1429.35 1429.19 262144 160 3409.02 3409.67 3409.34 524288 80 5888.49 5890.89 5889.54 1048576 40 10552.25 10559.27 10555.83 2097152 20 20256.45 20285.75 20273.88 4194304 10 40232.60 40321.99 40293.39 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.09 0.09 1 1000 10.05 10.06 10.05 2 1000 9.94 9.95 9.95 4 1000 10.18 10.19 10.19 8 1000 10.38 10.38 10.38 16 1000 10.89 10.90 10.89 32 1000 10.72 10.72 10.72 64 1000 10.66 10.66 10.66 128 1000 12.29 12.29 12.29 256 1000 13.62 13.63 13.63 512 1000 15.60 15.61 15.60 1024 1000 21.26 21.28 21.27 2048 1000 30.50 30.50 30.50 4096 1000 45.09 45.12 45.11 8192 1000 78.16 78.20 78.18 16384 1000 152.50 152.50 152.50 32768 1000 261.02 261.02 261.02 65536 640 478.20 478.22 478.21 131072 320 908.32 908.33 908.32 262144 160 1807.91 1808.01 1807.96 524288 80 3583.79 3584.00 3583.89 1048576 40 7132.47 7132.90 7132.69 2097152 20 14066.90 14067.15 14067.02 4194304 10 27740.10 27741.00 27740.55 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.09 1 1000 22.35 22.35 22.35 2 1000 22.84 22.84 22.84 4 1000 22.69 22.69 22.69 8 1000 22.97 22.97 22.97 16 1000 23.00 23.00 23.00 32 1000 23.45 23.46 23.46 64 1000 25.12 25.13 25.12 128 1000 26.28 26.29 26.28 256 1000 28.72 28.73 28.72 512 1000 35.47 35.47 35.47 1024 1000 46.23 46.24 46.23 2048 1000 67.98 67.99 67.98 4096 1000 108.23 108.25 108.24 8192 1000 191.77 191.77 191.77 16384 1000 340.48 340.48 340.48 32768 1000 599.69 599.69 599.69 65536 640 1152.02 1152.04 1152.03 131072 320 3132.82 3132.87 3132.84 262144 160 6243.22 6243.34 6243.27 524288 80 8097.64 8098.30 8097.90 1048576 40 17798.53 17799.25 17798.79 2097152 20 37407.70 37408.45 37408.14 4194304 10 70713.51 70737.60 70725.68 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.09 1 1000 34.50 34.51 34.51 2 1000 34.59 34.60 34.60 4 1000 34.90 34.92 34.91 8 1000 35.21 35.22 35.22 16 1000 35.49 35.50 35.50 32 1000 36.90 36.91 36.91 64 1000 38.41 38.42 38.42 128 1000 41.81 41.82 41.82 256 1000 49.40 49.41 49.41 512 1000 61.82 61.83 61.82 1024 1000 84.24 84.25 84.25 2048 1000 129.07 129.10 129.09 4096 1000 222.71 222.73 222.72 8192 1000 380.73 380.75 380.74 16384 1000 711.67 711.68 711.68 32768 1000 1362.52 1362.54 1362.53 65536 640 3770.60 3770.64 3770.62 131072 320 7082.34 7082.46 7082.42 262144 160 13408.03 13408.61 13408.28 524288 80 23828.58 23829.35 23828.97 1048576 40 41942.40 41947.77 41944.33 2097152 20 96956.95 96960.30 96958.19 4194304 10 235582.90 235608.10 235591.89 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.09 1 1000 46.49 46.50 46.49 2 1000 46.52 46.53 46.52 4 1000 47.06 47.07 47.06 8 1000 47.24 47.25 47.25 16 1000 48.76 48.78 48.77 32 1000 50.91 50.92 50.92 64 1000 55.97 55.98 55.97 128 1000 65.18 65.20 65.19 256 1000 84.89 84.92 84.90 512 1000 123.00 123.05 123.02 1024 1000 201.86 201.95 201.90 2048 1000 439.30 439.47 439.37 4096 1000 877.15 877.50 877.35 8192 1000 1698.63 1699.33 1698.96 16384 1000 3312.96 3314.21 3313.51 32768 1000 6920.17 6923.56 6921.24 65536 640 14429.63 14437.63 14432.96 131072 320 28748.21 28780.88 28764.40 262144 160 55582.61 55742.80 55649.67 524288 80 114344.50 115004.61 114560.65 1048576 40 230422.40 232965.17 231703.12 2097152 20 454263.55 464420.50 458517.20 4194304 10 886298.61 926991.59 906815.86 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.09 1 1000 10.91 10.91 10.91 2 1000 10.71 10.72 10.72 4 1000 11.09 11.09 11.09 8 1000 10.91 10.92 10.92 16 1000 10.52 10.53 10.52 32 1000 10.56 10.56 10.56 64 1000 11.13 11.13 11.13 128 1000 12.73 12.73 12.73 256 1000 15.66 15.66 15.66 512 1000 21.31 21.31 21.31 1024 1000 27.06 27.08 27.07 2048 1000 40.32 40.33 40.32 4096 1000 60.94 60.95 60.95 8192 1000 106.64 106.69 106.66 16384 1000 225.27 225.27 225.27 32768 1000 397.28 397.30 397.29 65536 640 1206.64 1206.71 1206.68 131072 320 2396.70 2396.80 2396.75 262144 160 1831.61 1831.71 1831.66 524288 80 3617.90 3617.91 3617.91 1048576 40 7158.60 7158.63 7158.61 2097152 20 14214.40 14215.65 14215.03 4194304 10 27996.90 27999.31 27998.10 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.09 0.09 1 1000 22.17 22.18 22.17 2 1000 22.14 22.15 22.14 4 1000 22.07 22.08 22.08 8 1000 22.10 22.10 22.10 16 1000 22.57 22.57 22.57 32 1000 23.06 23.06 23.06 64 1000 24.60 24.61 24.61 128 1000 27.49 27.49 27.49 256 1000 36.20 36.21 36.20 512 1000 43.50 43.51 43.51 1024 1000 58.49 58.51 58.50 2048 1000 89.90 89.94 89.92 4096 1000 159.35 159.41 159.38 8192 1000 265.32 265.33 265.33 16384 1000 487.82 487.83 487.82 32768 1000 1594.60 1594.91 1594.76 65536 640 2964.42 2964.60 2964.53 131072 320 2331.33 2331.45 2331.41 262144 160 4367.72 4367.89 4367.81 524288 80 8370.60 8371.18 8370.88 1048576 40 16383.05 16384.03 16383.39 2097152 20 32216.50 32236.90 32227.55 4194304 10 63526.09 63529.61 63528.30 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.10 0.10 1 1000 35.51 35.52 35.51 2 1000 35.84 35.85 35.85 4 1000 36.01 36.01 36.01 8 1000 36.24 36.25 36.24 16 1000 37.08 37.08 37.08 32 1000 38.87 38.88 38.88 64 1000 42.42 42.43 42.42 128 1000 50.41 50.43 50.42 256 1000 59.27 59.30 59.29 512 1000 76.53 76.55 76.54 1024 1000 113.46 113.51 113.48 2048 1000 186.93 186.99 186.95 4096 1000 297.64 297.67 297.65 8192 1000 541.47 541.64 541.52 16384 1000 1837.29 1837.38 1837.34 32768 1000 3416.44 3416.56 3416.52 65536 640 3166.78 3167.14 3166.99 131072 320 5468.73 5469.10 5468.88 262144 160 10091.90 10093.70 10092.96 524288 80 19413.82 19416.87 19415.23 1048576 40 37981.20 37991.05 37986.28 2097152 20 74524.60 74557.45 74540.37 4194304 10 160238.00 160580.80 160441.40 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.11 0.12 0.11 1 1000 53.31 53.32 53.31 2 1000 53.60 53.62 53.61 4 1000 53.78 53.79 53.78 8 1000 54.38 54.38 54.38 16 1000 57.14 57.15 57.14 32 1000 61.19 61.20 61.20 64 1000 68.55 68.57 68.56 128 1000 80.36 80.39 80.37 256 1000 103.56 103.60 103.58 512 1000 147.51 147.57 147.53 1024 1000 236.74 236.84 236.78 2048 1000 496.05 496.21 496.13 4096 1000 1008.54 1008.94 1008.77 8192 1000 2763.03 2763.91 2763.41 16384 1000 5268.97 5270.58 5269.63 32768 1000 4012.75 4013.10 4012.94 65536 640 6517.63 6518.13 6517.89 131072 320 11319.67 11321.01 11320.30 262144 160 21976.44 21983.15 21979.72 524288 80 42778.62 42808.63 42794.60 1048576 40 84496.23 84624.30 84563.12 2097152 20 173111.90 173410.25 173251.27 4194304 10 351132.80 352906.30 352301.34 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 10.00 10.00 10.00 1 1000 10.36 10.37 10.36 2 1000 10.42 10.42 10.42 4 1000 10.32 10.32 10.32 8 1000 10.64 10.64 10.64 16 1000 10.81 10.81 10.81 32 1000 11.17 11.17 11.17 64 1000 12.69 12.69 12.69 128 1000 12.21 12.21 12.21 256 1000 14.16 14.17 14.17 512 1000 15.66 15.67 15.66 1024 1000 21.47 21.47 21.47 2048 1000 30.74 30.75 30.74 4096 1000 45.18 45.20 45.19 8192 1000 77.15 77.17 77.16 16384 1000 149.41 149.41 149.41 32768 1000 248.77 248.78 248.78 65536 640 453.68 453.69 453.68 131072 320 850.14 850.15 850.14 262144 160 1709.48 1709.48 1709.48 524288 80 3388.61 3388.61 3388.61 1048576 40 6748.88 6749.02 6748.95 2097152 20 13312.55 13312.85 13312.70 4194304 10 26357.01 26357.31 26357.16 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 21.88 21.88 21.88 1 1000 22.19 22.19 22.19 2 1000 22.08 22.08 22.08 4 1000 22.48 22.48 22.48 8 1000 22.99 22.99 22.99 16 1000 24.88 24.89 24.88 32 1000 26.99 27.00 26.99 64 1000 32.63 32.64 32.64 128 1000 34.96 34.97 34.97 256 1000 36.87 36.88 36.87 512 1000 39.65 39.66 39.65 1024 1000 44.38 44.38 44.38 2048 1000 54.16 54.16 54.16 4096 1000 101.23 101.24 101.24 8192 1000 186.09 186.13 186.11 16384 1000 506.26 506.36 506.33 32768 1000 924.76 924.76 924.76 65536 640 1310.22 1310.27 1310.25 131072 320 2404.59 2404.63 2404.60 262144 160 4306.22 4306.36 4306.28 524288 80 8148.05 8148.35 8148.22 1048576 40 16225.05 16225.95 16225.42 2097152 20 34895.25 34896.95 34896.39 4194304 10 78478.90 78498.10 78488.90 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 35.10 35.11 35.11 1 1000 36.40 36.40 36.40 2 1000 36.94 36.95 36.94 4 1000 38.80 38.81 38.80 8 1000 41.63 41.64 41.63 16 1000 48.79 48.80 48.79 32 1000 71.99 72.01 72.00 64 1000 72.69 72.69 72.69 128 1000 77.49 77.50 77.50 256 1000 79.72 79.74 79.73 512 1000 84.72 84.73 84.73 1024 1000 94.31 94.33 94.32 2048 1000 124.15 124.17 124.16 4096 1000 235.49 235.53 235.51 8192 1000 477.01 477.15 477.08 16384 1000 1326.14 1326.43 1326.32 32768 1000 2046.01 2046.11 2046.06 65536 640 3372.51 3372.77 3372.65 131072 320 5846.64 5847.37 5847.07 262144 160 10998.71 10999.06 10998.82 524288 80 20906.68 20907.29 20906.93 1048576 40 40230.58 40231.75 40231.26 2097152 20 79676.45 79684.15 79679.46 4194304 10 172850.41 173066.01 172986.85 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 51.92 51.93 51.93 1 1000 56.50 56.51 56.51 2 1000 61.21 61.22 61.22 4 1000 66.76 66.78 66.77 8 1000 76.47 76.49 76.48 16 1000 155.92 155.96 155.94 32 1000 155.77 155.83 155.80 64 1000 157.81 157.86 157.84 128 1000 172.95 173.05 173.00 256 1000 177.98 178.10 178.04 512 1000 184.02 184.10 184.06 1024 1000 200.83 200.87 200.85 2048 1000 314.78 314.86 314.82 4096 1000 611.32 611.47 611.41 8192 1000 1223.51 1223.75 1223.67 16384 1000 3331.14 3331.43 3331.36 32768 1000 5722.17 5722.75 5722.62 65536 640 10212.40 10213.23 10212.99 131072 320 19113.42 19115.21 19114.54 262144 160 36643.85 36646.63 36645.37 524288 80 71606.41 71639.67 71628.11 1048576 40 137896.37 137921.25 137912.91 2097152 20 283752.75 283874.05 283799.71 4194304 10 566431.20 567306.20 566849.02 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.05 0.05 0.05 1 1000 6.62 6.63 6.63 2 1000 6.63 6.63 6.63 4 1000 6.66 6.66 6.66 8 1000 6.70 6.70 6.70 16 1000 6.79 6.79 6.79 32 1000 6.88 6.88 6.88 64 1000 7.09 7.09 7.09 128 1000 8.22 8.22 8.22 256 1000 10.33 10.34 10.34 512 1000 12.42 12.43 12.43 1024 1000 15.69 15.70 15.70 2048 1000 22.63 22.65 22.64 4096 1000 32.61 32.64 32.63 8192 1000 53.45 53.51 53.48 16384 1000 94.60 94.63 94.62 32768 1000 216.30 216.31 216.31 65536 640 350.01 350.03 350.02 131072 320 623.48 623.49 623.49 262144 160 1178.63 1178.69 1178.66 524288 80 2285.09 2285.15 2285.12 1048576 40 4500.75 4500.90 4500.83 2097152 20 8991.35 8992.75 8992.05 4194304 10 17488.80 17489.30 17489.05 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.06 0.06 0.06 1 1000 13.62 13.63 13.63 2 1000 13.44 13.46 13.45 4 1000 13.49 13.50 13.50 8 1000 13.51 13.52 13.52 16 1000 13.64 13.66 13.65 32 1000 12.98 12.99 12.99 64 1000 11.78 11.79 11.79 128 1000 12.77 12.78 12.78 256 1000 14.49 14.51 14.51 512 1000 16.81 16.83 16.82 1024 1000 20.77 20.80 20.79 2048 1000 31.33 31.37 31.35 4096 1000 49.57 49.63 49.61 8192 1000 95.19 95.31 95.26 16384 1000 192.93 192.99 192.96 32768 1000 322.67 322.68 322.68 65536 640 568.82 568.83 568.82 131072 320 977.43 977.45 977.44 262144 160 1809.21 1809.28 1809.25 524288 80 3488.71 3488.84 3488.78 1048576 40 6811.92 6812.47 6812.14 2097152 20 13564.45 13566.40 13565.64 4194304 10 27395.31 27402.20 27398.52 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.05 0.06 0.05 1 1000 17.36 17.38 17.37 2 1000 17.35 17.37 17.36 4 1000 17.38 17.40 17.39 8 1000 17.49 17.50 17.50 16 1000 17.65 17.68 17.67 32 1000 17.78 17.80 17.79 64 1000 17.71 17.73 17.72 128 1000 20.25 20.27 20.26 256 1000 21.95 21.98 21.97 512 1000 23.57 23.61 23.59 1024 1000 25.60 25.65 25.63 2048 1000 40.27 40.33 40.31 4096 1000 67.03 67.12 67.09 8192 1000 128.70 128.88 128.82 16384 1000 252.39 252.46 252.43 32768 1000 412.90 412.95 412.92 65536 640 676.01 676.03 676.02 131072 320 1201.84 1201.88 1201.87 262144 160 2164.89 2164.94 2164.92 524288 80 4120.01 4120.21 4120.16 1048576 40 8059.70 8060.52 8060.06 2097152 20 16067.85 16070.85 16069.52 4194304 10 31119.89 31129.50 31123.96 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.05 0.05 0.05 1 1000 45.18 45.20 45.19 2 1000 48.27 48.28 48.28 4 1000 54.88 54.90 54.89 8 1000 63.77 63.79 63.78 16 1000 71.30 71.32 71.31 32 1000 71.53 71.54 71.53 64 1000 73.08 73.09 73.09 128 1000 73.17 73.18 73.17 256 1000 75.67 75.69 75.68 512 1000 82.96 82.97 82.97 1024 1000 94.14 94.16 94.15 2048 1000 108.46 108.48 108.47 4096 1000 138.39 138.44 138.42 8192 1000 191.87 191.93 191.89 16384 1000 317.15 317.28 317.20 32768 1000 590.38 590.51 590.43 65536 640 1061.12 1061.60 1061.39 131072 320 2000.77 2003.26 2002.05 262144 160 3847.17 3857.05 3851.48 524288 80 7408.26 7448.01 7431.19 1048576 40 14837.43 14966.52 14900.83 2097152 20 29786.60 30303.70 30041.56 4194304 10 59254.30 61267.10 60155.73 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 9.78 9.78 9.78 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 21.30 21.31 21.31 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 32.95 32.96 32.96 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 16 ) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 44.19 44.20 44.20 #===================================================== # # Thanks for using PMB2.2 # # The Pallas team kindly requests that you # give us as much feedback for PMB as possible. # # It would be very helpful when you sent the # output tables of your run(s) of PMB to # # ####################### # # # # # pmb@pallas.com # # # # # ####################### # # You might also add # # - personal information (institution, motivation # for using PMB) # - basic information about the machine you used # (number of CPUs, processor type e.t.c.) # #=====================================================