#--------------------------------------------------- # PALLAS MPI Benchmark Suite V2.2, MPI-1 part #--------------------------------------------------- # Date : Tue Oct 15 16:24:50 2002 # Machine : i686# System : Linux # Release : 2.4.19 # Version : #1 SMP Tue Oct 8 19:37:08 EDT 2002 # # 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 1.16 0.00 1 1000 1.56 0.61 2 1000 1.56 1.22 4 1000 1.56 2.45 8 1000 1.61 4.74 16 1000 1.61 9.48 32 1000 1.66 18.39 64 1000 1.81 33.72 128 1000 2.21 55.16 256 1000 2.87 85.17 512 1000 3.92 124.49 1024 1000 6.14 159.17 2048 1000 10.51 185.82 4096 1000 19.46 200.71 8192 1000 37.16 210.22 16384 1000 63.31 246.79 32768 1000 114.00 274.11 65536 640 273.60 228.43 131072 320 823.48 151.79 262144 160 1813.86 137.83 524288 80 3720.74 134.38 1048576 40 7772.13 128.66 2097152 20 16069.80 124.46 4194304 10 32924.05 121.49 #--------------------------------------------------- # Benchmarking PingPing # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 3.02 0.00 1 1000 3.32 0.29 2 1000 3.32 0.57 4 1000 3.42 1.12 8 1000 3.52 2.17 16 1000 3.72 4.10 32 1000 3.82 7.98 64 1000 4.12 14.80 128 1000 4.93 24.77 256 1000 6.24 39.15 512 1000 8.35 58.49 1024 1000 12.47 78.30 2048 1000 21.32 91.60 4096 1000 37.11 105.25 8192 1000 70.00 111.60 16384 1000 176.41 88.57 32768 1000 338.04 92.44 65536 640 636.94 98.13 131072 320 1760.42 71.01 262144 160 4075.28 61.35 524288 80 8503.84 58.80 1048576 40 17299.33 57.81 2097152 20 34744.52 57.56 4194304 10 69237.65 57.77 #----------------------------------------------------------------------------- # 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 2.72 2.72 2.72 0.00 1 1000 3.12 3.12 3.12 0.61 2 1000 3.02 3.02 3.02 1.26 4 1000 3.12 3.12 3.12 2.45 8 1000 3.22 3.22 3.22 4.74 16 1000 3.22 3.22 3.22 9.48 32 1000 3.32 3.32 3.32 18.39 64 1000 3.62 3.62 3.62 33.71 128 1000 4.43 4.43 4.43 55.17 256 1000 5.73 5.73 5.73 85.18 512 1000 8.25 8.25 8.25 118.41 1024 1000 13.28 13.28 13.28 147.11 2048 1000 21.93 21.93 21.93 178.16 4096 1000 38.32 38.42 38.37 203.34 8192 1000 90.92 90.92 90.92 171.85 16384 1000 171.28 171.28 171.28 182.45 32768 1000 336.43 336.43 336.43 185.77 65536 640 633.01 633.01 633.01 197.47 131072 320 1822.97 1822.97 1822.97 137.14 262144 160 4096.64 4096.64 4096.64 122.05 524288 80 8556.65 8556.65 8556.65 116.87 1048576 40 17334.55 17334.55 17334.55 115.38 2097152 20 34674.08 34674.08 34674.08 115.36 4194304 10 69207.45 69207.45 69207.45 115.59 #----------------------------------------------------------------------------- # 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 11.69 11.80 11.74 0.00 1 1000 11.89 11.94 11.91 0.16 2 1000 11.85 11.90 11.87 0.32 4 1000 11.90 11.98 11.94 0.64 8 1000 11.89 11.92 11.91 1.28 16 1000 11.97 12.10 12.01 2.52 32 1000 11.94 12.04 11.98 5.07 64 1000 12.09 12.14 12.11 10.06 128 1000 14.36 14.44 14.40 16.91 256 1000 14.89 14.90 14.89 32.78 512 1000 17.21 17.26 17.23 56.58 1024 1000 22.07 22.12 22.09 88.31 2048 1000 33.63 33.74 33.71 115.77 4096 1000 56.89 56.95 56.92 137.18 8192 1000 104.55 104.58 104.57 149.40 16384 1000 199.39 199.54 199.47 156.61 32768 1000 311.09 311.29 311.19 200.78 65536 640 553.17 553.85 553.55 225.69 131072 320 1328.15 1330.24 1329.18 187.94 262144 160 2945.74 2954.29 2950.55 169.25 524288 80 6058.96 6089.24 6076.88 164.22 1048576 40 12288.05 12409.85 12360.31 161.16 2097152 20 25179.63 25659.98 25461.33 155.88 4194304 10 51048.40 52850.70 52039.05 151.37 #----------------------------------------------------------------------------- # 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 12.08 12.13 12.10 0.00 1 1000 12.30 12.41 12.35 0.15 2 1000 12.32 12.43 12.39 0.31 4 1000 12.33 12.42 12.36 0.61 8 1000 12.32 12.48 12.42 1.22 16 1000 12.26 12.39 12.33 2.46 32 1000 12.32 12.48 12.38 4.89 64 1000 12.48 12.61 12.56 9.68 128 1000 14.54 14.67 14.60 16.64 256 1000 15.23 15.36 15.30 31.79 512 1000 17.41 17.55 17.49 55.65 1024 1000 22.93 23.03 22.98 84.82 2048 1000 35.44 35.60 35.50 109.73 4096 1000 58.37 58.49 58.41 133.57 8192 1000 107.99 108.09 108.05 144.56 16384 1000 192.91 193.10 193.00 161.84 32768 1000 322.14 322.62 322.37 193.72 65536 640 591.92 593.28 592.59 210.69 131072 320 1374.53 1381.14 1377.90 181.01 262144 160 3091.28 3118.14 3105.59 160.35 524288 80 6171.59 6276.51 6229.89 159.32 1048576 40 12841.91 13182.00 13046.53 151.72 2097152 20 25437.48 27216.85 26408.58 146.97 4194304 10 51329.70 53518.20 52455.84 149.48 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # ( #processes = 16 ) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 13.06 13.16 13.11 0.00 1 1000 12.88 13.02 12.92 0.15 2 1000 12.87 13.01 12.96 0.29 4 1000 12.82 12.95 12.88 0.59 8 1000 13.13 13.25 13.18 1.15 16 1000 13.05 13.29 13.17 2.30 32 1000 13.16 13.44 13.31 4.54 64 1000 13.24 13.44 13.35 9.08 128 1000 15.15 15.33 15.23 15.93 256 1000 15.55 15.71 15.64 31.09 512 1000 17.79 17.96 17.88 54.37 1024 1000 24.92 25.11 25.01 77.79 2048 1000 44.61 44.88 44.73 87.03 4096 1000 93.97 94.57 94.25 82.61 8192 1000 121.51 122.66 122.10 127.39 16384 1000 193.11 193.65 193.36 161.38 32768 1000 315.89 316.54 316.22 197.44 65536 640 570.05 572.73 571.33 218.25 131072 320 1382.78 1394.70 1389.35 179.25 262144 160 3060.93 3111.70 3086.88 160.68 524288 80 6214.62 6408.68 6306.83 156.04 1048576 40 12681.20 13122.83 12944.97 152.41 2097152 20 25837.63 27636.13 26866.15 144.74 4194304 10 51864.60 54833.35 53451.67 145.90 #----------------------------------------------------------------------------- # 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 4.93 4.93 4.93 0.00 1 1000 6.03 6.03 6.03 0.63 2 1000 6.03 6.03 6.03 1.26 4 1000 6.13 6.13 6.13 2.49 8 1000 6.44 6.44 6.44 4.74 16 1000 6.44 6.44 6.44 9.48 32 1000 6.64 6.64 6.64 18.39 64 1000 6.84 6.84 6.84 35.70 128 1000 8.35 8.35 8.35 58.49 256 1000 10.46 10.46 10.46 93.36 512 1000 14.18 14.18 14.18 137.72 1024 1000 23.43 23.43 23.43 166.68 2048 1000 39.83 39.83 39.83 196.15 4096 1000 73.12 73.12 73.12 213.69 8192 1000 145.13 145.13 145.13 215.32 16384 1000 279.91 279.91 279.91 223.29 32768 1000 620.26 620.26 620.26 201.53 65536 640 1297.61 1297.61 1297.61 192.66 131072 320 3617.65 3617.65 3617.65 138.21 262144 160 8135.47 8135.47 8135.47 122.92 524288 80 17010.19 17010.19 17010.19 117.58 1048576 40 32949.21 32984.41 32966.81 121.27 2097152 20 69338.23 69343.25 69340.74 115.37 4194304 10 138173.65 138173.65 138173.65 115.80 #----------------------------------------------------------------------------- # 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 23.22 23.29 23.25 0.00 1 1000 23.42 23.52 23.46 0.16 2 1000 23.38 23.43 23.40 0.33 4 1000 23.40 23.42 23.41 0.65 8 1000 23.49 23.50 23.50 1.30 16 1000 23.37 23.38 23.38 2.61 32 1000 23.55 23.55 23.55 5.18 64 1000 23.66 23.76 23.73 10.28 128 1000 27.59 27.69 27.66 17.64 256 1000 28.43 28.43 28.43 34.35 512 1000 31.67 31.72 31.70 61.57 1024 1000 40.27 40.37 40.32 96.76 2048 1000 60.93 61.03 60.98 128.01 4096 1000 104.39 104.51 104.42 149.51 8192 1000 191.71 191.93 191.79 162.82 16384 1000 402.29 402.33 402.31 155.34 32768 1000 840.06 840.27 840.16 148.76 65536 640 1494.67 1495.15 1494.96 167.21 131072 320 3415.65 3419.20 3417.74 146.23 262144 160 6816.01 6831.51 6824.55 146.38 524288 80 14311.40 14374.28 14344.44 139.14 1048576 40 28952.22 29215.11 29091.92 136.92 2097152 20 58407.95 59512.85 59006.11 134.42 4194304 10 115028.90 119625.10 117578.02 133.75 #----------------------------------------------------------------------------- # 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 23.47 23.60 23.54 0.00 1 1000 23.63 23.75 23.69 0.16 2 1000 23.61 23.71 23.66 0.32 4 1000 23.75 23.86 23.77 0.64 8 1000 23.88 23.98 23.93 1.27 16 1000 23.91 24.01 23.92 2.54 32 1000 23.96 24.06 24.02 5.07 64 1000 24.15 24.35 24.24 10.03 128 1000 27.83 27.97 27.91 17.46 256 1000 28.86 28.96 28.90 33.72 512 1000 32.08 32.22 32.12 60.62 1024 1000 40.81 40.91 40.87 95.49 2048 1000 62.33 62.43 62.40 125.14 4096 1000 105.76 105.88 105.82 147.58 8192 1000 193.06 193.16 193.12 161.78 16384 1000 484.88 485.44 485.22 128.75 32768 1000 896.20 897.17 896.76 139.33 65536 640 1629.80 1632.21 1631.24 153.17 131072 320 3420.67 3429.64 3425.55 145.79 262144 160 6753.17 6785.77 6771.55 147.37 524288 80 13678.53 13808.04 13737.64 144.84 1048576 40 28800.71 29224.70 28978.57 136.87 2097152 20 55196.93 57505.45 56504.53 139.12 4194304 10 122322.40 135445.15 129452.01 118.13 #----------------------------------------------------------------------------- # Benchmarking Exchange # ( #processes = 16 ) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 23.91 24.11 24.01 0.00 1 1000 24.21 24.36 24.27 0.16 2 1000 24.10 24.29 24.21 0.31 4 1000 24.12 24.28 24.19 0.63 8 1000 24.03 24.14 24.09 1.26 16 1000 24.21 24.39 24.31 2.50 32 1000 24.29 24.42 24.33 5.00 64 1000 24.70 24.83 24.77 9.83 128 1000 28.12 28.23 28.18 17.29 256 1000 29.28 29.46 29.36 33.15 512 1000 32.39 32.50 32.45 60.09 1024 1000 41.13 41.31 41.22 94.55 2048 1000 62.77 62.98 62.88 124.04 4096 1000 106.56 106.79 106.68 146.31 8192 1000 194.20 194.49 194.33 160.67 16384 1000 474.72 475.21 475.01 131.52 32768 1000 812.67 813.64 813.20 153.63 65536 640 1584.91 1588.45 1586.61 157.39 131072 320 3266.78 3273.49 3270.12 152.74 262144 160 6580.81 6626.39 6605.45 150.91 524288 80 13579.61 13695.32 13637.90 146.04 1048576 40 28186.54 28743.24 28436.64 139.16 2097152 20 57237.85 59604.65 58517.04 134.22 4194304 10 104586.80 119753.35 112269.33 133.61 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.40 0.40 0.40 4 1000 4.22 4.22 4.22 8 1000 4.32 4.32 4.32 16 1000 4.33 4.33 4.33 32 1000 4.63 4.63 4.63 64 1000 4.83 4.83 4.83 128 1000 5.83 5.83 5.83 256 1000 7.34 7.34 7.34 512 1000 9.86 9.86 9.86 1024 1000 14.89 14.89 14.89 2048 1000 24.94 24.94 24.94 4096 1000 45.46 45.46 45.46 8192 1000 87.60 87.60 87.60 16384 1000 151.97 151.97 151.97 32768 1000 280.71 280.81 280.76 65536 640 848.31 848.62 848.47 131072 320 3011.67 3012.30 3011.99 262144 160 7185.03 7187.54 7186.28 524288 80 15231.25 15241.31 15236.28 1048576 40 31018.17 31053.37 31035.77 2097152 20 64958.15 65078.82 65018.49 4194304 10 141291.70 141633.70 141462.70 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.40 0.40 0.40 4 1000 21.86 21.93 21.90 8 1000 22.17 22.27 22.22 16 1000 22.90 23.00 22.95 32 1000 23.33 23.33 23.33 64 1000 24.12 24.13 24.12 128 1000 31.80 31.82 31.81 256 1000 38.58 38.61 38.59 512 1000 47.37 47.42 47.40 1024 1000 66.04 66.08 66.06 2048 1000 102.62 102.72 102.67 4096 1000 164.91 164.92 164.91 8192 1000 290.26 290.39 290.33 16384 1000 493.18 493.30 493.24 32768 1000 878.13 878.33 878.23 65536 640 2073.92 2074.59 2074.30 131072 320 5384.46 5385.52 5384.91 262144 160 11854.00 11856.52 11855.30 524288 80 24514.93 24525.05 24519.99 1048576 40 49118.76 49159.01 49138.98 2097152 20 103842.28 103968.00 103909.18 4194304 10 220228.05 220606.60 220419.87 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.40 0.40 0.40 4 1000 39.37 39.45 39.40 8 1000 39.86 39.97 39.91 16 1000 41.31 41.43 41.37 32 1000 42.15 42.24 42.19 64 1000 43.43 43.54 43.48 128 1000 56.52 56.58 56.56 256 1000 69.50 69.60 69.57 512 1000 84.82 84.96 84.89 1024 1000 116.24 116.31 116.29 2048 1000 178.97 179.05 179.00 4096 1000 281.62 281.83 281.72 8192 1000 488.83 489.04 488.96 16384 1000 800.56 800.70 800.65 32768 1000 1416.52 1416.65 1416.61 65536 640 3118.44 3118.83 3118.73 131072 320 7426.56 7427.59 7427.09 262144 160 16065.31 16068.46 16066.89 524288 80 33594.15 33605.80 33599.71 1048576 40 67602.06 67641.15 67621.69 2097152 20 142493.02 142628.12 142562.16 4194304 10 292072.50 292460.75 292263.61 #---------------------------------------------------------------- # Benchmarking Allreduce # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.40 0.40 0.40 4 1000 58.01 58.15 58.09 8 1000 58.68 58.84 58.77 16 1000 60.73 60.94 60.85 32 1000 61.99 62.10 62.05 64 1000 63.56 63.65 63.60 128 1000 81.95 82.08 82.01 256 1000 101.36 101.56 101.46 512 1000 122.83 123.00 122.91 1024 1000 166.85 167.00 166.91 2048 1000 253.83 254.04 253.96 4096 1000 396.78 397.03 396.91 8192 1000 683.76 684.13 684.00 16384 1000 1110.10 1110.24 1110.16 32768 1000 1938.92 1939.08 1939.01 65536 640 4087.15 4087.76 4087.50 131072 320 9900.41 9901.60 9901.20 262144 160 21442.77 21446.24 21444.69 524288 80 44391.94 44404.42 44398.22 1048576 40 88910.66 88952.87 88931.91 2097152 20 184608.65 184755.45 184688.59 4194304 10 364220.90 364609.35 364414.32 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.20 0.20 4 1000 2.21 2.21 2.21 8 1000 2.41 2.41 2.41 16 1000 2.31 2.31 2.31 32 1000 2.61 2.61 2.61 64 1000 2.72 2.72 2.72 128 1000 3.32 3.32 3.32 256 1000 4.32 4.32 4.32 512 1000 5.83 5.83 5.83 1024 1000 8.85 8.85 8.85 2048 1000 14.48 14.48 14.48 4096 1000 26.55 26.55 26.55 8192 1000 50.59 50.59 50.59 16384 1000 90.52 90.62 90.57 32768 1000 189.39 189.59 189.49 65536 640 762.51 763.13 762.82 131072 320 2427.39 2430.85 2429.12 262144 160 5474.58 5488.41 5481.50 524288 80 11343.94 11399.26 11371.60 1048576 40 23341.64 23557.88 23449.76 2097152 20 50207.87 51027.60 50617.74 4194304 10 101935.85 105918.80 103927.32 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.20 0.20 4 1000 15.80 15.81 15.80 8 1000 15.95 16.05 16.00 16 1000 16.35 16.45 16.40 32 1000 16.67 16.68 16.67 64 1000 17.02 17.08 17.05 128 1000 23.60 23.70 23.67 256 1000 26.96 27.11 27.03 512 1000 32.35 32.36 32.36 1024 1000 42.70 42.85 42.78 2048 1000 65.29 65.50 65.45 4096 1000 104.97 105.16 105.06 8192 1000 177.89 178.17 178.01 16384 1000 355.82 356.29 356.03 32768 1000 637.21 637.84 637.53 65536 640 1459.69 1461.87 1460.90 131072 320 3900.87 3911.72 3906.62 262144 160 8727.34 8785.40 8757.96 524288 80 18322.31 18562.08 18450.72 1048576 40 36789.64 37732.64 37293.97 2097152 20 79689.60 82764.45 81321.49 4194304 10 154705.55 167481.00 161385.94 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.20 0.20 4 1000 24.44 24.54 24.52 8 1000 24.54 24.72 24.67 16 1000 25.31 25.45 25.38 32 1000 25.50 25.58 25.55 64 1000 26.49 26.56 26.53 128 1000 36.83 36.96 36.92 256 1000 42.52 42.70 42.59 512 1000 51.24 51.34 51.30 1024 1000 68.16 68.36 68.25 2048 1000 103.58 103.83 103.74 4096 1000 165.42 165.75 165.55 8192 1000 279.62 280.22 279.90 16384 1000 548.79 549.63 549.21 32768 1000 992.55 994.03 993.28 65536 640 2058.71 2063.73 2061.47 131072 320 5388.30 5413.36 5402.08 262144 160 12133.78 12246.48 12193.11 524288 80 24781.27 25227.01 25012.44 1048576 40 48980.27 50697.71 49849.28 2097152 20 103608.18 110329.17 107141.70 4194304 10 193943.80 221472.65 208556.01 #---------------------------------------------------------------- # Benchmarking Reduce # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.27 0.21 4 1000 33.60 33.82 33.72 8 1000 33.93 34.07 34.00 16 1000 35.25 35.46 35.33 32 1000 35.58 35.74 35.69 64 1000 37.11 37.24 37.17 128 1000 51.17 51.50 51.36 256 1000 58.85 59.05 58.97 512 1000 70.31 70.60 70.42 1024 1000 93.62 93.89 93.76 2048 1000 142.09 142.45 142.28 4096 1000 226.44 227.01 226.72 8192 1000 384.96 385.83 385.41 16384 1000 775.32 776.77 776.01 32768 1000 1398.46 1401.19 1399.85 65536 640 2836.74 2845.40 2841.32 131072 320 7047.01 7090.41 7069.26 262144 160 15967.00 16163.58 16069.59 524288 80 32948.64 33738.36 33357.55 1048576 40 64673.08 68000.11 66382.51 2097152 20 127568.48 139576.10 133734.41 4194304 10 233224.30 284675.20 260747.10 #---------------------------------------------------------------- # 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 0.30 0.30 0.30 4 1000 5.63 5.63 5.63 8 1000 6.24 6.24 6.24 16 1000 6.34 6.34 6.34 32 1000 6.54 6.54 6.54 64 1000 6.74 6.74 6.74 128 1000 7.74 7.74 7.74 256 1000 9.25 9.25 9.25 512 1000 11.77 11.77 11.77 1024 1000 16.49 16.49 16.49 2048 1000 25.95 25.95 25.95 4096 1000 45.06 45.06 45.06 8192 1000 84.49 84.59 84.54 16384 1000 154.19 154.19 154.19 32768 1000 310.08 310.08 310.08 65536 640 860.41 860.57 860.49 131072 320 3017.66 3018.29 3017.97 262144 160 7774.06 7774.68 7774.37 524288 80 16567.73 16572.76 16570.25 1048576 40 33517.67 33535.27 33526.47 2097152 20 71380.32 71385.37 71382.85 4194304 10 145174.55 145315.30 145244.92 #---------------------------------------------------------------- # 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 0.30 0.30 0.30 4 1000 31.49 31.56 31.52 8 1000 31.81 31.91 31.84 16 1000 32.32 32.46 32.39 32 1000 32.80 32.80 32.80 64 1000 33.67 33.70 33.69 128 1000 38.16 38.22 38.19 256 1000 42.07 42.08 42.07 512 1000 50.12 50.27 50.20 1024 1000 59.27 59.33 59.30 2048 1000 82.68 82.70 82.69 4096 1000 123.90 124.07 123.98 8192 1000 205.99 206.22 206.06 16384 1000 406.03 406.13 406.10 32768 1000 731.14 731.34 731.24 65536 640 1539.56 1539.91 1539.77 131072 320 4294.77 4296.08 4295.58 262144 160 10817.53 10821.96 10820.22 524288 80 22827.66 22844.23 22837.83 1048576 40 45383.53 45441.52 45418.83 2097152 20 95321.45 95804.10 95535.77 4194304 10 194926.20 196244.35 195624.56 #---------------------------------------------------------------- # 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 0.30 0.30 0.30 4 1000 71.52 71.62 71.59 8 1000 71.93 72.10 72.01 16 1000 72.36 72.51 72.40 32 1000 72.87 72.95 72.92 64 1000 74.78 74.90 74.84 128 1000 82.50 82.66 82.54 256 1000 89.73 89.87 89.82 512 1000 98.04 98.15 98.07 1024 1000 111.60 111.76 111.65 2048 1000 141.87 141.97 141.92 4096 1000 195.86 195.96 195.92 8192 1000 314.47 314.57 314.50 16384 1000 588.15 588.32 588.26 32768 1000 1066.14 1066.30 1066.24 65536 640 2353.25 2353.70 2353.47 131072 320 5943.61 5946.31 5945.09 262144 160 14188.62 14196.21 14192.93 524288 80 29452.06 29478.14 29466.66 1048576 40 59300.37 59396.45 59355.22 2097152 20 124200.02 124850.37 124469.42 4194304 10 248677.25 250707.75 249635.72 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.40 0.40 0.40 4 1000 140.60 140.72 140.66 8 1000 141.25 141.41 141.30 16 1000 141.57 141.77 141.63 32 1000 142.36 142.54 142.41 64 1000 144.59 144.78 144.70 128 1000 156.96 157.17 157.05 256 1000 167.10 167.29 167.19 512 1000 178.47 178.61 178.54 1024 1000 197.47 197.66 197.55 2048 1000 240.79 240.98 240.90 4096 1000 314.84 315.03 314.94 8192 1000 442.30 442.46 442.41 16384 1000 828.01 828.27 828.16 32768 1000 1410.21 1410.44 1410.36 65536 640 3023.54 3024.18 3023.89 131072 320 7548.56 7550.92 7549.99 262144 160 17586.46 17598.18 17592.73 524288 80 36166.82 36203.43 36185.76 1048576 40 72751.24 72872.63 72815.68 2097152 20 152573.90 153327.55 152872.73 4194304 10 303673.85 306190.45 304775.46 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 4.53 4.53 4.53 1 1000 4.73 4.73 4.73 2 1000 4.83 4.83 4.83 4 1000 4.73 4.73 4.73 8 1000 4.93 4.93 4.93 16 1000 5.03 5.03 5.03 32 1000 5.13 5.13 5.13 64 1000 5.53 5.53 5.53 128 1000 6.64 6.64 6.64 256 1000 8.15 8.15 8.15 512 1000 11.26 11.26 11.26 1024 1000 17.70 17.70 17.70 2048 1000 28.87 28.87 28.87 4096 1000 55.32 55.32 55.32 8192 1000 94.74 94.74 94.74 16384 1000 175.01 175.01 175.01 32768 1000 364.60 364.60 364.60 65536 640 1239.94 1240.10 1240.02 131072 320 3372.20 3372.20 3372.20 262144 160 7341.58 7341.58 7341.58 524288 80 15367.11 15367.11 15367.11 1048576 40 30779.46 30779.46 30779.46 2097152 20 61724.85 61724.85 61724.85 4194304 10 124757.20 124767.30 124762.25 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 35.80 35.87 35.84 1 1000 36.13 36.23 36.16 2 1000 36.58 36.61 36.60 4 1000 36.20 36.30 36.25 8 1000 36.11 36.12 36.11 16 1000 36.37 36.47 36.44 32 1000 36.50 36.61 36.56 64 1000 37.27 37.33 37.30 128 1000 42.72 42.73 42.72 256 1000 45.75 45.75 45.75 512 1000 52.12 52.25 52.19 1024 1000 66.34 66.45 66.38 2048 1000 103.41 103.44 103.42 4096 1000 174.08 174.08 174.08 8192 1000 344.39 344.51 344.48 16384 1000 682.40 682.61 682.51 32768 1000 1293.54 1293.75 1293.65 65536 640 2760.11 2760.89 2760.50 131072 320 5805.50 5807.85 5806.68 262144 160 11892.28 11900.57 11896.58 524288 80 24337.11 24369.93 24355.52 1048576 40 50036.99 50163.38 50108.69 2097152 20 100019.52 100495.12 100288.77 4194304 10 203047.30 204806.05 204002.05 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 85.95 86.05 86.02 1 1000 86.88 87.08 87.00 2 1000 86.75 86.90 86.82 4 1000 86.63 86.78 86.73 8 1000 87.03 87.14 87.09 16 1000 87.00 87.07 87.04 32 1000 87.08 87.25 87.19 64 1000 88.07 88.18 88.11 128 1000 99.49 99.62 99.54 256 1000 106.07 106.13 106.10 512 1000 119.30 119.45 119.40 1024 1000 154.42 154.48 154.45 2048 1000 243.40 243.46 243.42 4096 1000 431.99 432.07 432.03 8192 1000 864.00 864.07 864.04 16384 1000 1623.15 1623.52 1623.31 32768 1000 3053.82 3054.31 3054.10 65536 640 5989.18 5991.21 5990.31 131072 320 11866.05 11872.40 11869.24 262144 160 24301.35 24329.62 24316.68 524288 80 49554.13 49657.09 49610.88 1048576 40 101439.55 101856.71 101669.74 2097152 20 204907.55 206593.50 205827.22 4194304 10 481456.05 489003.45 485615.56 #---------------------------------------------------------------- # Benchmarking Allgather # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 188.37 188.57 188.46 1 1000 192.36 192.51 192.44 2 1000 189.59 189.71 189.67 4 1000 191.04 191.15 191.07 8 1000 192.47 192.63 192.60 16 1000 192.86 192.97 192.91 32 1000 194.02 194.16 194.08 64 1000 192.18 192.30 192.24 128 1000 218.51 218.64 218.58 256 1000 231.71 231.81 231.78 512 1000 257.03 257.20 257.09 1024 1000 335.89 336.14 336.01 2048 1000 545.07 545.30 545.16 4096 1000 1212.93 1213.08 1213.01 8192 1000 3013.32 3014.26 3013.77 16384 1000 3421.95 3422.65 3422.26 32768 1000 6124.81 6125.89 6125.36 65536 640 12145.33 12148.29 12146.85 131072 320 24345.81 24364.45 24355.16 262144 160 49609.74 49673.98 49642.95 524288 80 101894.60 102117.39 102004.62 1048576 40 208438.18 209307.19 208823.42 2097152 20 504027.83 507297.82 505761.95 4194304 10 1032605.45 1051170.10 1042022.46 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 4.43 4.43 4.43 1 1000 4.83 4.83 4.83 2 1000 4.83 4.83 4.83 4 1000 4.83 4.83 4.83 8 1000 4.93 4.93 4.93 16 1000 5.03 5.03 5.03 32 1000 5.23 5.23 5.23 64 1000 5.63 5.63 5.63 128 1000 6.54 6.54 6.54 256 1000 8.25 8.25 8.25 512 1000 11.26 11.26 11.26 1024 1000 16.80 16.80 16.80 2048 1000 30.17 30.17 30.17 4096 1000 54.71 54.71 54.71 8192 1000 95.15 95.15 95.15 16384 1000 186.37 186.37 186.37 32768 1000 377.87 377.87 377.87 65536 640 1117.04 1117.04 1117.04 131072 320 3304.94 3304.94 3304.94 262144 160 7293.82 7293.82 7293.82 524288 80 15413.64 15416.15 15414.89 1048576 40 31199.41 31199.41 31199.41 2097152 20 62398.90 62403.95 62401.43 4194304 10 125531.95 125542.05 125537.00 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 35.83 35.93 35.88 1 1000 36.35 36.45 36.40 2 1000 37.02 37.03 37.03 4 1000 35.95 36.06 36.03 8 1000 36.48 36.59 36.55 16 1000 36.52 36.62 36.59 32 1000 36.45 36.49 36.47 64 1000 37.32 37.33 37.33 128 1000 43.04 43.09 43.07 256 1000 45.85 45.86 45.85 512 1000 52.32 52.36 52.34 1024 1000 66.39 66.49 66.43 2048 1000 103.27 103.28 103.28 4096 1000 174.65 174.65 174.65 8192 1000 322.10 322.10 322.10 16384 1000 679.36 679.46 679.41 32768 1000 1279.05 1279.35 1279.19 65536 640 2724.42 2725.05 2724.70 131072 320 5914.39 5916.78 5915.59 262144 160 11888.48 11897.32 11893.27 524288 80 24395.38 24428.22 24414.23 1048576 40 49936.40 50065.44 50011.80 2097152 20 101269.70 101745.35 101540.56 4194304 10 206342.80 208155.25 207336.20 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 84.36 84.50 84.41 1 1000 86.75 86.87 86.82 2 1000 86.84 86.95 86.91 4 1000 86.69 86.85 86.77 8 1000 87.05 87.24 87.15 16 1000 86.75 86.85 86.79 32 1000 87.23 87.28 87.26 64 1000 87.76 87.87 87.80 128 1000 100.90 101.05 100.95 256 1000 106.14 106.26 106.21 512 1000 118.99 119.12 119.05 1024 1000 154.31 154.44 154.39 2048 1000 241.92 242.03 241.96 4096 1000 434.20 434.27 434.22 8192 1000 858.12 858.24 858.16 16384 1000 1611.40 1611.57 1611.52 32768 1000 3039.75 3040.07 3039.93 65536 640 5883.78 5885.40 5884.69 131072 320 11960.41 11967.14 11963.91 262144 160 24348.65 24376.01 24362.97 524288 80 49648.84 49754.76 49706.93 1048576 40 102211.56 102653.03 102461.52 2097152 20 207611.95 209269.38 208492.91 4194304 10 492940.75 501232.50 497759.87 #---------------------------------------------------------------- # Benchmarking Allgatherv # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 194.27 194.42 194.33 1 1000 195.97 196.13 196.06 2 1000 195.83 195.99 195.92 4 1000 194.75 194.82 194.79 8 1000 192.76 192.88 192.83 16 1000 196.38 196.55 196.45 32 1000 197.99 198.12 198.06 64 1000 199.20 199.40 199.28 128 1000 223.85 224.04 223.96 256 1000 231.42 231.58 231.50 512 1000 257.90 258.05 257.98 1024 1000 338.27 338.47 338.36 2048 1000 546.48 546.64 546.56 4096 1000 1356.60 1357.15 1356.89 8192 1000 2930.22 2931.81 2931.02 16384 1000 3424.48 3424.91 3424.67 32768 1000 6136.10 6136.51 6136.30 65536 640 11916.69 11919.69 11917.95 131072 320 24275.25 24291.90 24284.05 262144 160 49502.25 49564.95 49535.08 524288 80 101503.81 101742.29 101621.58 1048576 40 208150.72 209084.47 208626.52 2097152 20 504179.77 509180.80 506917.78 4194304 10 1041189.15 1051762.65 1046877.33 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 4.12 4.12 4.12 1 1000 4.63 4.63 4.63 2 1000 4.53 4.53 4.53 4 1000 4.63 4.63 4.63 8 1000 4.73 4.73 4.73 16 1000 4.83 4.83 4.83 32 1000 4.83 4.83 4.83 64 1000 5.03 5.03 5.03 128 1000 6.14 6.14 6.14 256 1000 7.04 7.14 7.09 512 1000 9.05 9.05 9.05 1024 1000 14.08 14.08 14.08 2048 1000 24.04 24.04 24.04 4096 1000 48.28 48.28 48.28 8192 1000 79.26 79.26 79.26 16384 1000 214.94 214.94 214.94 32768 1000 540.81 540.91 540.86 65536 640 1515.91 1516.07 1515.99 131072 320 3335.75 3335.75 3335.75 262144 160 7215.25 7215.88 7215.57 524288 80 15147.13 15148.39 15147.76 1048576 40 30724.20 30726.73 30725.46 2097152 20 62001.65 62011.70 62006.67 4194304 10 124445.85 124445.85 124445.85 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 44.90 45.00 44.92 1 1000 45.01 45.11 45.05 2 1000 45.18 45.24 45.21 4 1000 45.13 45.20 45.16 8 1000 45.04 45.20 45.15 16 1000 45.11 45.14 45.13 32 1000 45.12 45.18 45.15 64 1000 45.36 45.46 45.41 128 1000 53.39 53.51 53.43 256 1000 52.70 52.76 52.73 512 1000 55.73 55.85 55.76 1024 1000 66.01 66.05 66.03 2048 1000 97.10 97.20 97.12 4096 1000 179.08 179.18 179.14 8192 1000 335.85 335.99 335.94 16384 1000 619.07 619.27 619.17 32768 1000 1211.24 1211.64 1211.45 65536 640 2542.83 2544.04 2543.59 131072 320 5808.19 5810.55 5809.53 262144 160 11133.84 11150.63 11143.49 524288 80 23278.74 23336.92 23308.13 1048576 40 45985.97 46213.25 46100.28 2097152 20 88796.13 90016.22 89490.62 4194304 10 179734.55 184722.45 182596.82 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 131.74 131.87 131.82 1 1000 132.01 132.21 132.13 2 1000 133.86 133.98 133.92 4 1000 132.85 133.08 132.97 8 1000 131.73 131.83 131.78 16 1000 130.52 130.72 130.62 32 1000 131.14 131.33 131.23 64 1000 132.03 132.13 132.10 128 1000 151.47 151.59 151.54 256 1000 153.52 153.62 153.57 512 1000 160.55 160.64 160.58 1024 1000 183.41 183.57 183.51 2048 1000 265.98 266.12 266.03 4096 1000 531.89 532.16 532.06 8192 1000 1159.70 1160.24 1160.05 16384 1000 2046.37 2046.67 2046.53 32768 1000 3668.74 3669.42 3669.15 65536 640 6982.52 6986.21 6985.02 131072 320 13670.01 13676.13 13673.83 262144 160 27088.14 27118.08 27106.87 524288 80 53846.04 54024.18 53950.06 1048576 40 109816.80 110513.75 110309.11 2097152 20 256270.45 258101.62 257573.68 4194304 10 517087.55 526141.00 522546.07 #---------------------------------------------------------------- # Benchmarking Alltoall # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 301.95 302.21 302.05 1 1000 301.97 302.13 302.04 2 1000 302.16 302.36 302.24 4 1000 302.67 302.90 302.79 8 1000 302.25 302.52 302.39 16 1000 299.22 299.39 299.30 32 1000 300.16 300.41 300.31 64 1000 301.06 301.43 301.25 128 1000 345.03 345.27 345.18 256 1000 358.36 358.57 358.48 512 1000 389.78 390.03 389.93 1024 1000 470.90 471.19 471.05 2048 1000 845.73 846.00 845.88 4096 1000 1629.90 1630.52 1630.23 8192 1000 3237.30 3239.58 3238.64 16384 1000 5652.32 5653.20 5652.80 32768 1000 9888.34 9890.06 9889.47 65536 640 18188.94 18194.56 18192.61 131072 320 34887.84 34902.37 34896.68 262144 160 67889.16 67951.56 67929.29 524288 80 132878.64 133268.27 133166.80 1048576 40 322129.50 323950.36 323461.58 2097152 20 641554.45 645451.80 644060.45 4194304 10 1323551.50 1348095.00 1338625.88 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.20 0.20 1 1000 1.81 1.81 1.81 2 1000 1.81 1.81 1.81 4 1000 1.81 1.81 1.81 8 1000 1.81 1.81 1.81 16 1000 1.81 1.81 1.81 32 1000 1.91 1.91 1.91 64 1000 2.11 2.11 2.11 128 1000 2.51 2.51 2.51 256 1000 3.22 3.22 3.22 512 1000 4.53 4.53 4.53 1024 1000 6.84 6.84 6.84 2048 1000 11.27 11.27 11.27 4096 1000 20.12 20.12 20.12 8192 1000 37.92 37.92 37.92 16384 1000 66.08 66.18 66.13 32768 1000 114.86 114.96 114.91 65536 640 280.36 280.52 280.44 131072 320 725.11 725.11 725.11 262144 160 1617.42 1619.30 1618.36 524288 80 3292.68 3297.71 3295.20 1048576 40 6806.65 6841.86 6824.26 2097152 20 14277.10 14402.85 14339.97 4194304 10 29640.45 29982.45 29811.45 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.20 0.20 1 1000 14.39 14.49 14.43 2 1000 14.51 14.62 14.59 4 1000 14.47 14.49 14.48 8 1000 14.46 14.56 14.50 16 1000 14.89 15.00 14.94 32 1000 14.94 15.04 14.99 64 1000 14.64 14.64 14.64 128 1000 17.89 17.90 17.89 256 1000 18.03 18.04 18.04 512 1000 20.15 20.19 20.17 1024 1000 26.67 26.68 26.68 2048 1000 41.26 41.37 41.32 4096 1000 68.91 69.01 68.97 8192 1000 122.01 122.21 122.14 16384 1000 228.91 229.04 229.00 32768 1000 372.51 372.54 372.52 65536 640 674.68 674.81 674.74 131072 320 1347.17 1347.26 1347.21 262144 160 2738.26 2738.89 2738.54 524288 80 5576.97 5578.22 5577.72 1048576 40 11299.65 11304.69 11301.37 2097152 20 22295.30 22305.35 22298.73 4194304 10 44542.25 44552.30 44548.41 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.20 0.20 1 1000 22.21 22.34 22.25 2 1000 22.08 22.19 22.13 4 1000 22.17 22.38 22.29 8 1000 22.16 22.28 22.21 16 1000 22.40 22.54 22.49 32 1000 22.37 22.57 22.45 64 1000 22.64 22.74 22.68 128 1000 24.97 25.08 25.02 256 1000 26.22 26.42 26.32 512 1000 29.18 29.35 29.24 1024 1000 35.18 35.33 35.22 2048 1000 49.87 50.12 49.97 4096 1000 84.52 84.72 84.66 8192 1000 151.04 151.34 151.17 16384 1000 356.22 356.37 356.30 32768 1000 580.77 580.89 580.84 65536 640 1035.35 1035.51 1035.43 131072 320 1976.42 1976.73 1976.63 262144 160 3892.78 3893.41 3893.20 524288 80 7793.11 7794.75 7793.95 1048576 40 15691.36 15694.30 15692.73 2097152 20 31062.42 31070.33 31064.94 4194304 10 62324.75 62334.85 62329.26 #---------------------------------------------------------------- # Benchmarking Bcast # ( #processes = 16 ) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.20 0.20 1 1000 29.56 29.76 29.68 2 1000 28.89 29.02 28.96 4 1000 29.07 29.30 29.21 8 1000 28.82 29.00 28.92 16 1000 29.19 29.42 29.31 32 1000 29.50 29.64 29.56 64 1000 29.60 29.73 29.66 128 1000 33.16 33.36 33.28 256 1000 33.14 33.26 33.18 512 1000 36.87 37.00 36.94 1024 1000 47.02 47.32 47.19 2048 1000 59.09 59.29 59.19 4096 1000 103.31 103.57 103.45 8192 1000 189.08 189.58 189.40 16384 1000 464.49 464.70 464.59 32768 1000 765.69 765.90 765.76 65536 640 1368.71 1369.17 1368.95 131072 320 2626.12 2626.48 2626.28 262144 160 5172.85 5174.68 5173.50 524288 80 10284.15 10288.74 10286.02 1048576 40 20704.35 20712.35 20706.60 2097152 20 40734.40 40750.70 40740.90 4194304 10 81021.70 81060.20 81035.10 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 2 ) # ( 14 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 2.92 2.92 2.92 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 4 ) # ( 12 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 28.71 28.74 28.72 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 8 ) # ( 8 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 52.06 52.19 52.12 #--------------------------------------------------- # Benchmarking Barrier # ( #processes = 16 ) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 80.62 80.73 80.66 #===================================================== # # 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.) # #=====================================================