#--------------------------------------------------- # Intel (R) MPI Benchmark Suite V3.2, MPI-1 part #--------------------------------------------------- # Date : Tue Aug 30 09:29:13 2011 # Machine : i686 # System : Linux # Release : 2.6.32-24-generic-pae # Version : #39-Ubuntu SMP Wed Jul 28 07:39:26 UTC 2010 # MPI Version : 2.1 # MPI Thread Environment: MPI_THREAD_SINGLE # New default behavior from Version 3.2 on: # the number of iterations per message size is cut down # dynamically when a certain run time (per message size sample) # is expected to be exceeded. Time limit is defined by variable # "SECS_PER_SAMPLE" (=> IMB_settings.h) # or through the flag => -time # Calling sequence was: # ./IMB-MPI1 # 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 # Gather # Gatherv # Scatter # Scatterv # Alltoall # Alltoallv # Bcast # Barrier #--------------------------------------------------- # Benchmarking PingPong # #processes = 2 #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 83.32 0.00 1 1000 83.39 0.01 2 1000 83.66 0.02 4 1000 84.56 0.05 8 1000 107.01 0.07 16 1000 124.88 0.12 32 1000 124.90 0.24 64 1000 124.88 0.49 128 1000 125.01 0.98 256 1000 124.90 1.95 512 1000 125.04 3.91 1024 1000 166.61 5.86 2048 1000 230.08 8.49 4096 1000 291.42 13.40 8192 1000 458.24 17.05 16384 1000 721.79 21.65 32768 1000 1295.71 24.12 65536 640 2659.35 23.50 131072 320 4374.14 28.58 262144 160 8165.03 30.62 524288 80 15841.19 31.56 1048576 40 30995.40 32.26 2097152 20 60772.67 32.91 4194304 10 120246.25 33.27 #--------------------------------------------------- # Benchmarking PingPing # #processes = 2 #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 166.67 0.00 1 1000 168.03 0.01 2 1000 166.63 0.01 4 1000 166.41 0.02 8 1000 166.78 0.05 16 1000 166.64 0.09 32 1000 166.65 0.18 64 1000 166.76 0.37 128 1000 166.66 0.73 256 1000 166.65 1.46 512 1000 166.76 2.93 1024 1000 249.89 3.91 2048 1000 333.08 5.86 4096 1000 416.89 9.37 8192 1000 666.69 11.72 16384 1000 1138.73 13.72 32768 1000 2083.22 15.00 65536 640 2750.90 22.72 131072 320 4465.91 27.99 262144 160 8335.28 29.99 524288 80 16463.15 30.37 1048576 40 32339.15 30.92 2097152 20 64327.26 31.09 4194304 10 127857.31 31.28 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 2 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 124.88 124.90 124.89 0.00 1 1000 124.84 124.94 124.89 0.02 2 1000 124.95 125.07 125.01 0.03 4 1000 124.43 124.54 124.49 0.06 8 1000 124.83 124.94 124.88 0.12 16 1000 122.69 122.83 122.76 0.25 32 1000 123.44 123.54 123.49 0.49 64 1000 124.32 124.43 124.37 0.98 128 1000 124.94 125.08 125.01 1.95 256 1000 124.90 124.93 124.91 3.91 512 1000 124.82 124.93 124.88 7.82 1024 1000 166.80 166.90 166.85 11.70 2048 1000 209.44 209.47 209.46 18.65 4096 1000 291.36 291.41 291.38 26.81 8192 1000 428.15 428.24 428.20 36.49 16384 1000 748.99 749.04 749.02 41.72 32768 1000 1331.67 1331.70 1331.68 46.93 65536 640 2689.80 2689.85 2689.82 46.47 131072 320 5864.73 5877.27 5871.00 42.54 262144 160 11176.86 11177.08 11176.97 44.73 524288 80 21622.60 21623.01 21622.81 46.25 1048576 40 39329.30 39335.13 39332.21 50.85 2097152 20 81255.00 81302.30 81278.65 49.20 4194304 10 172975.50 173124.40 173049.95 46.21 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 2 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 166.67 166.82 166.75 0.00 1 1000 166.69 166.92 166.80 0.02 2 1000 166.54 166.81 166.67 0.05 4 1000 166.68 166.82 166.75 0.09 8 1000 166.68 166.91 166.80 0.18 16 1000 166.55 166.80 166.67 0.37 32 1000 166.42 166.56 166.49 0.73 64 1000 166.66 166.67 166.66 1.46 128 1000 166.55 166.81 166.68 2.93 256 1000 166.56 166.78 166.67 5.86 512 1000 249.60 249.85 249.73 7.82 1024 1000 292.52 292.74 292.63 13.34 2048 1000 415.98 416.38 416.18 18.76 4096 1000 582.72 583.17 582.95 26.79 8192 1000 915.31 916.40 915.85 34.10 16384 1000 1665.85 1666.14 1665.99 37.51 32768 1000 3079.51 3082.04 3080.78 40.56 65536 640 6585.04 6585.05 6585.04 37.96 131072 320 12063.76 12076.49 12070.12 41.40 262144 160 20404.34 20452.68 20428.51 48.89 524288 80 38160.13 38160.62 38160.38 52.41 1048576 40 71830.70 71835.57 71833.14 55.68 2097152 20 174175.14 175093.40 174634.27 45.69 4194304 10 308588.00 310403.10 309495.55 51.55 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.09 0.08 4 1000 83.21 83.32 83.26 8 1000 83.20 83.33 83.27 16 1000 83.31 83.32 83.31 32 1000 83.21 83.32 83.26 64 1000 85.45 85.58 85.52 128 1000 166.25 166.29 166.27 256 1000 166.41 166.51 166.46 512 1000 166.41 166.78 166.59 1024 1000 249.75 250.02 249.89 2048 1000 332.84 333.19 333.02 4096 1000 422.80 423.48 423.14 8192 1000 665.95 666.57 666.26 16384 1000 1332.40 1332.43 1332.42 32768 1000 2331.52 2333.22 2332.37 65536 640 4329.15 4329.43 4329.29 131072 320 5849.08 5849.32 5849.20 262144 160 10444.55 10446.08 10445.32 524288 80 17419.00 17421.56 17420.28 1048576 40 36347.63 36351.87 36349.75 2097152 20 68447.90 68452.80 68450.35 4194304 10 135604.71 135647.20 135625.95 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.10 0.10 4 1000 82.97 83.09 83.03 8 1000 83.46 83.69 83.57 16 1000 83.21 83.21 83.21 32 1000 106.94 107.07 107.00 64 1000 83.46 83.69 83.57 128 1000 83.45 83.46 83.46 256 1000 125.18 125.30 125.24 512 1000 124.69 124.91 124.80 1024 1000 166.16 166.66 166.41 2048 1000 208.40 208.54 208.47 4096 1000 291.11 291.36 291.23 8192 1000 457.78 458.76 458.27 16384 1000 707.40 707.64 707.52 32768 1000 1330.83 1331.29 1331.06 65536 640 2327.08 2331.81 2329.44 131072 320 4723.25 4741.15 4732.20 262144 160 9164.09 9200.09 9182.09 524288 80 18106.61 18176.20 18141.41 1048576 40 35587.47 35602.70 35595.09 2097152 20 69831.45 70127.86 69979.65 4194304 10 140214.30 140795.70 140505.00 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.09 0.09 4 1000 5.72 6.01 5.87 8 1000 83.31 83.45 83.38 16 1000 83.31 83.44 83.38 32 1000 83.35 83.42 83.39 64 1000 83.31 83.45 83.38 128 1000 83.31 83.45 83.38 256 1000 101.09 101.17 101.13 512 1000 166.52 166.90 166.71 1024 1000 166.44 166.65 166.54 2048 1000 250.01 250.12 250.06 4096 1000 332.77 333.32 333.04 8192 1000 438.53 439.27 438.90 16384 1000 665.24 666.14 665.69 32768 1000 1165.42 1166.88 1166.15 65536 640 2167.66 2168.02 2167.84 131072 320 2821.46 2822.57 2822.01 262144 160 5247.50 5248.27 5247.88 524288 80 9904.91 9906.34 9905.62 1048576 40 20018.88 20021.45 20020.16 2097152 20 39385.95 39391.65 39388.80 4194304 10 78549.61 78720.80 78635.20 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.07 0.07 1 1000 83.20 83.35 83.28 2 1000 83.22 83.58 83.40 4 1000 83.30 83.32 83.31 8 1000 83.21 83.33 83.27 16 1000 83.22 83.58 83.40 32 1000 83.30 83.32 83.31 64 1000 83.71 83.84 83.77 128 1000 127.18 127.55 127.37 256 1000 166.51 166.53 166.52 512 1000 166.41 166.54 166.48 1024 1000 249.62 250.09 249.85 2048 1000 332.99 333.21 333.10 4096 1000 416.04 416.44 416.24 8192 1000 665.67 666.75 666.21 16384 1000 1165.35 1166.56 1165.95 32768 1000 2163.37 2163.94 2163.66 65536 640 2920.51 2929.48 2925.00 131072 320 5514.53 5515.59 5515.06 262144 160 9366.71 9367.60 9367.16 524288 80 17007.32 17009.41 17008.37 1048576 40 33668.32 33674.07 33671.20 2097152 20 65819.55 65923.15 65871.35 4194304 10 132655.40 132887.00 132771.20 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.08 0.08 1 1000 83.35 83.35 83.35 2 1000 83.23 83.30 83.26 4 1000 83.22 83.33 83.27 8 1000 83.34 83.36 83.35 16 1000 83.22 83.30 83.26 32 1000 83.21 83.31 83.26 64 1000 83.32 83.35 83.34 128 1000 85.99 86.06 86.02 256 1000 124.93 124.94 124.93 512 1000 125.03 125.07 125.05 1024 1000 166.45 166.57 166.51 2048 1000 208.18 208.33 208.25 4096 1000 291.73 291.93 291.83 8192 1000 457.68 457.86 457.77 16384 1000 742.08 742.21 742.14 32768 1000 1368.43 1368.82 1368.63 65536 640 2943.65 2943.90 2943.77 131072 320 4968.62 4981.13 4974.87 262144 160 8509.21 8510.49 8509.85 524288 80 17457.37 17459.48 17458.43 1048576 40 33637.10 33637.32 33637.21 2097152 20 71884.05 72004.35 71944.20 4194304 10 131966.49 132105.41 132035.95 #---------------------------------------------------------------- # Benchmarking Gather # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.10 0.10 1 1000 83.45 83.55 83.50 2 1000 83.56 83.56 83.56 4 1000 124.68 124.75 124.72 8 1000 83.45 83.54 83.50 16 1000 83.56 83.56 83.56 32 1000 124.68 124.76 124.72 64 1000 83.44 83.56 83.50 128 1000 83.56 83.57 83.57 256 1000 124.94 125.02 124.98 512 1000 147.92 147.95 147.93 1024 1000 166.82 166.85 166.84 2048 1000 208.19 208.30 208.24 4096 1000 290.95 291.34 291.15 8192 1000 612.93 613.01 612.97 16384 1000 1581.66 1581.91 1581.78 32768 1000 1746.24 1749.22 1747.73 65536 640 3255.00 3255.99 3255.50 131072 320 6603.48 6622.19 6612.84 262144 160 8267.40 8308.92 8288.16 524288 80 15175.85 15351.15 15263.50 1048576 40 31347.85 31733.27 31540.56 2097152 20 61956.50 62838.60 62397.55 4194304 10 119212.61 120932.20 120072.40 #---------------------------------------------------------------- # Benchmarking Gatherv # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.38 0.46 0.42 1 1000 83.46 83.68 83.57 2 1000 124.68 125.01 124.85 4 1000 89.71 89.94 89.82 8 1000 83.46 83.67 83.57 16 1000 124.69 125.01 124.85 32 1000 124.69 124.93 124.81 64 1000 83.45 83.67 83.56 128 1000 124.68 125.00 124.84 256 1000 124.69 124.93 124.81 512 1000 166.41 166.62 166.51 1024 1000 166.41 166.73 166.57 2048 1000 207.90 208.39 208.15 4096 1000 317.58 317.82 317.70 8192 1000 417.04 417.39 417.22 16384 1000 747.38 749.11 748.25 32768 1000 1301.08 1301.53 1301.30 65536 640 2620.09 2620.80 2620.44 131072 320 4401.79 4414.69 4408.24 262144 160 8242.65 8290.97 8266.81 524288 80 15933.68 16125.92 16029.80 1048576 40 31258.40 31705.15 31481.77 2097152 20 61118.10 62151.14 61634.62 4194304 10 120888.01 123196.51 122042.26 #---------------------------------------------------------------- # Benchmarking Scatter # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.09 1 1000 83.45 83.53 83.49 2 1000 83.21 83.31 83.26 4 1000 83.09 83.20 83.15 8 1000 83.45 83.53 83.49 16 1000 84.21 84.32 84.26 32 1000 83.07 83.20 83.14 64 1000 83.44 83.53 83.48 128 1000 124.69 124.79 124.74 256 1000 124.80 124.93 124.87 512 1000 124.69 124.79 124.74 1024 1000 166.44 166.56 166.50 2048 1000 248.38 248.86 248.62 4096 1000 291.76 291.92 291.84 8192 1000 457.61 457.80 457.71 16384 1000 707.57 707.83 707.70 32768 1000 1287.14 1290.05 1288.59 65536 640 2699.22 2700.09 2699.65 131072 320 4400.43 4411.66 4406.05 262144 160 8259.55 8305.96 8282.75 524288 80 15927.52 16103.76 16015.64 1048576 40 31187.25 31576.73 31381.99 2097152 20 61222.19 62028.40 61625.30 4194304 10 121413.80 122757.09 122085.44 #---------------------------------------------------------------- # Benchmarking Scatterv # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.16 0.39 0.27 1 1000 83.55 83.56 83.56 2 1000 83.45 83.56 83.50 4 1000 124.78 124.93 124.85 8 1000 83.55 83.57 83.56 16 1000 83.45 83.57 83.51 32 1000 124.78 124.93 124.86 64 1000 83.55 83.56 83.55 128 1000 83.46 83.55 83.51 256 1000 124.79 124.94 124.86 512 1000 124.81 124.82 124.81 1024 1000 166.43 166.55 166.49 2048 1000 207.82 208.14 207.98 4096 1000 291.84 291.90 291.87 8192 1000 457.63 457.80 457.72 16384 1000 747.60 749.09 748.34 32768 1000 1334.13 1334.43 1334.28 65536 640 2662.07 2671.19 2666.63 131072 320 4402.00 4414.41 4408.21 262144 160 8217.71 8264.72 8241.22 524288 80 15925.36 16103.64 16014.50 1048576 40 31205.37 31595.17 31400.27 2097152 20 61205.45 62003.20 61604.33 4194304 10 121338.49 122651.01 121994.75 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.07 0.07 1 1000 83.25 83.28 83.26 2 1000 83.26 83.27 83.26 4 1000 83.34 83.39 83.36 8 1000 83.26 83.27 83.26 16 1000 83.26 83.27 83.26 32 1000 83.34 83.38 83.36 64 1000 83.26 83.27 83.26 128 1000 83.25 83.28 83.26 256 1000 83.34 83.37 83.36 512 1000 163.68 163.72 163.70 1024 1000 166.47 166.52 166.49 2048 1000 249.76 250.00 249.88 4096 1000 292.24 292.32 292.28 8192 1000 448.03 448.12 448.07 16384 1000 748.86 749.00 748.93 32768 1000 1363.13 1363.43 1363.28 65536 640 3615.99 3623.98 3619.99 131072 320 5047.32 5047.71 5047.52 262144 160 8606.22 8606.56 8606.39 524288 80 17075.45 17076.21 17075.83 1048576 40 33530.60 33531.80 33531.20 2097152 20 69143.55 69159.20 69151.37 4194304 10 131056.59 131091.81 131074.20 #---------------------------------------------------------------- # Benchmarking Alltoallv # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.14 0.14 0.14 1 1000 83.20 83.32 83.26 2 1000 83.44 83.59 83.51 4 1000 83.22 83.32 83.27 8 1000 83.21 83.33 83.27 16 1000 83.21 83.35 83.28 32 1000 83.23 83.33 83.28 64 1000 83.96 84.09 84.02 128 1000 83.22 83.35 83.28 256 1000 164.44 164.51 164.48 512 1000 167.92 168.06 167.99 1024 1000 249.62 250.01 249.81 2048 1000 253.24 253.45 253.34 4096 1000 416.03 416.27 416.15 8192 1000 675.16 676.03 675.60 16384 1000 1164.91 1165.27 1165.09 32768 1000 2163.41 2166.73 2165.07 65536 640 2662.34 2662.35 2662.34 131072 320 4641.82 4642.85 4642.33 262144 160 8625.29 8628.29 8626.79 524288 80 17067.64 17068.79 17068.21 1048576 40 33315.80 33319.93 33317.86 2097152 20 65997.45 66014.19 66005.82 4194304 10 143176.19 143287.50 143231.85 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 2 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.07 0.07 1 1000 83.45 83.69 83.57 2 1000 82.96 83.20 83.08 4 1000 83.21 83.44 83.32 8 1000 83.71 83.95 83.83 16 1000 98.95 98.95 98.95 32 1000 83.46 83.69 83.57 64 1000 83.46 83.72 83.59 128 1000 124.69 124.93 124.81 256 1000 125.19 125.42 125.30 512 1000 124.69 124.96 124.82 1024 1000 166.42 166.66 166.54 2048 1000 251.74 252.35 252.05 4096 1000 378.96 379.05 379.00 8192 1000 540.24 540.88 540.56 16384 1000 511.99 512.48 512.23 32768 1000 1213.45 1214.10 1213.78 65536 640 1248.10 1249.55 1248.83 131072 320 4693.22 4695.31 4694.26 262144 160 8344.76 8370.39 8357.58 524288 80 16044.16 16134.94 16089.55 1048576 40 31676.47 31857.75 31767.11 2097152 20 62990.75 63178.30 63084.52 4194304 10 125093.00 125792.49 125442.74 #--------------------------------------------------- # Benchmarking Barrier # #processes = 2 #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 83.22 83.30 83.26 # All processes entering MPI_Finalize