#--------------------------------------------------- # Intel (R) MPI Benchmark Suite V3.2, MPI-1 part #--------------------------------------------------- # Date : Thu Sep 1 10:42:40 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 # ( 4 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 51.32 0.00 1 1000 51.80 0.02 2 1000 51.75 0.04 4 1000 51.64 0.07 8 1000 51.87 0.15 16 1000 51.62 0.30 32 1000 52.14 0.59 64 1000 51.88 1.18 128 1000 52.81 2.31 256 1000 54.87 4.45 512 1000 57.65 8.47 1024 1000 74.70 13.07 2048 1000 90.91 21.49 4096 1000 115.36 33.86 8192 1000 147.96 52.80 16384 1000 228.96 68.24 32768 1000 390.84 79.96 65536 640 789.71 79.14 131072 320 1349.10 92.65 262144 160 2479.60 100.82 524288 80 4722.49 105.88 1048576 40 9181.69 108.91 2097152 20 18110.10 110.44 4194304 10 35916.29 111.37 #--------------------------------------------------- # Benchmarking PingPing # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #bytes #repetitions t[usec] Mbytes/sec 0 1000 59.08 0.00 1 1000 58.87 0.02 2 1000 59.84 0.03 4 1000 58.83 0.06 8 1000 59.28 0.13 16 1000 59.40 0.26 32 1000 59.84 0.51 64 1000 60.63 1.01 128 1000 61.31 1.99 256 1000 63.26 3.86 512 1000 70.72 6.90 1024 1000 84.78 11.52 2048 1000 117.30 16.65 4096 1000 143.70 27.18 8192 1000 186.05 41.99 16384 1000 233.02 67.05 32768 1000 395.94 78.93 65536 640 806.53 77.49 131072 320 1401.89 89.17 262144 160 2597.34 96.25 524288 80 4957.96 100.85 1048576 40 9743.42 102.63 2097152 20 19338.00 103.42 4194304 10 38740.09 103.25 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 58.92 58.92 58.92 0.00 1 1000 59.33 59.34 59.34 0.03 2 1000 59.37 59.38 59.38 0.06 4 1000 59.34 59.43 59.39 0.13 8 1000 59.76 59.78 59.77 0.26 16 1000 59.72 59.73 59.72 0.51 32 1000 59.89 59.91 59.90 1.02 64 1000 60.40 60.44 60.42 2.02 128 1000 61.87 61.90 61.89 3.94 256 1000 63.16 63.25 63.21 7.72 512 1000 71.90 71.91 71.91 13.58 1024 1000 89.86 89.86 89.86 21.73 2048 1000 117.62 117.66 117.64 33.20 4096 1000 144.66 144.73 144.70 53.98 8192 1000 186.22 186.28 186.25 83.88 16384 1000 234.77 234.86 234.82 133.06 32768 1000 394.60 394.66 394.63 158.36 65536 640 1438.97 1439.86 1439.42 86.81 131072 320 2552.69 2556.05 2554.37 97.81 262144 160 4782.49 4795.14 4788.81 104.27 524288 80 9262.81 9284.33 9273.57 107.71 1048576 40 18158.72 18202.53 18180.62 109.87 2097152 20 35121.65 35215.95 35168.80 113.58 4194304 10 71480.81 71681.31 71581.06 111.61 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 63.92 64.05 63.98 0.00 1 1000 61.64 61.67 61.65 0.03 2 1000 62.25 62.37 62.29 0.06 4 1000 64.67 64.90 64.79 0.12 8 1000 62.47 62.49 62.48 0.24 16 1000 62.36 62.39 62.38 0.49 32 1000 62.37 62.39 62.38 0.98 64 1000 64.07 64.09 64.09 1.90 128 1000 66.27 66.30 66.28 3.68 256 1000 81.61 81.74 81.68 5.97 512 1000 96.15 96.27 96.18 10.14 1024 1000 115.34 115.57 115.46 16.90 2048 1000 114.87 114.90 114.89 34.00 4096 1000 131.80 132.00 131.87 59.19 8192 1000 197.71 197.95 197.82 78.93 16384 1000 286.15 286.36 286.26 109.13 32768 1000 569.97 570.75 570.41 109.51 65536 640 1362.82 1363.91 1363.36 91.65 131072 320 2807.40 2814.55 2811.46 88.82 262144 160 5359.95 5386.03 5378.53 92.83 524288 80 9967.26 9985.25 9975.29 100.15 1048576 40 19238.65 19276.50 19255.88 103.75 2097152 20 38024.45 38145.35 38107.19 104.86 4194304 10 75315.10 75488.11 75409.50 105.98 #----------------------------------------------------------------------------- # Benchmarking Sendrecv # #processes = 6 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 68.89 69.13 68.99 0.00 1 1000 68.42 68.57 68.50 0.03 2 1000 67.84 67.88 67.87 0.06 4 1000 67.95 68.12 68.04 0.11 8 1000 68.71 68.96 68.84 0.22 16 1000 68.67 68.78 68.71 0.44 32 1000 68.74 68.93 68.85 0.89 64 1000 70.46 70.66 70.55 1.73 128 1000 73.09 73.24 73.17 3.33 256 1000 79.54 79.76 79.67 6.12 512 1000 79.92 80.08 80.01 12.19 1024 1000 94.06 94.24 94.13 20.73 2048 1000 113.99 114.20 114.10 34.21 4096 1000 141.14 141.46 141.32 55.23 8192 1000 215.58 216.04 215.85 72.33 16384 1000 428.15 428.50 428.33 72.93 32768 1000 852.85 853.55 853.22 73.22 65536 640 1889.91 1891.92 1890.88 66.07 131072 320 3726.31 3730.88 3727.82 67.01 262144 160 7132.04 7140.41 7136.32 70.02 524288 80 14739.86 14753.01 14746.25 67.78 1048576 40 28282.17 28303.13 28291.57 70.66 2097152 20 55472.20 55637.05 55583.79 71.89 4194304 10 111106.71 112461.79 111884.37 71.14 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 60.42 60.43 60.42 0.00 1 1000 62.22 62.24 62.23 0.06 2 1000 62.32 62.33 62.32 0.12 4 1000 61.70 61.71 61.71 0.25 8 1000 62.70 62.71 62.70 0.49 16 1000 63.28 63.28 63.28 0.96 32 1000 64.56 64.56 64.56 1.89 64 1000 66.87 66.88 66.87 3.65 128 1000 74.15 74.16 74.15 6.58 256 1000 83.77 83.78 83.78 11.66 512 1000 94.60 94.60 94.60 20.65 1024 1000 115.01 115.04 115.03 33.95 2048 1000 119.79 119.86 119.82 65.18 4096 1000 191.88 191.94 191.91 81.41 8192 1000 227.23 227.27 227.25 137.50 16384 1000 383.27 383.31 383.29 163.05 32768 1000 701.07 701.13 701.10 178.28 65536 640 1589.27 1589.43 1589.35 157.29 131072 320 2817.68 2817.96 2817.82 177.43 262144 160 5731.64 5732.14 5731.89 174.45 524288 80 12593.90 12617.03 12605.46 158.52 1048576 40 27821.95 27868.53 27845.24 143.53 2097152 20 55251.05 55346.31 55298.68 144.54 4194304 10 109927.00 110125.00 110026.00 145.29 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 72.74 72.75 72.74 0.00 1 1000 73.99 74.02 74.00 0.05 2 1000 73.78 73.79 73.78 0.10 4 1000 73.63 73.66 73.65 0.21 8 1000 74.28 74.30 74.29 0.41 16 1000 74.52 74.54 74.53 0.82 32 1000 74.92 74.93 74.92 1.63 64 1000 75.69 75.70 75.69 3.23 128 1000 79.09 79.11 79.10 6.17 256 1000 86.02 86.04 86.03 11.35 512 1000 94.22 94.24 94.23 20.72 1024 1000 116.95 116.96 116.95 33.40 2048 1000 144.19 144.32 144.25 54.13 4096 1000 202.27 202.34 202.31 77.22 8192 1000 317.67 317.81 317.74 98.33 16384 1000 572.85 573.10 572.96 109.06 32768 1000 1145.11 1145.62 1145.33 109.11 65536 640 3030.14 3031.19 3030.65 82.48 131072 320 5898.22 5909.70 5905.05 84.61 262144 160 11082.41 11097.04 11090.31 90.11 524288 80 20299.25 20308.36 20303.67 98.48 1048576 40 39609.05 39699.60 39655.17 100.76 2097152 20 77599.66 77752.25 77669.88 102.89 4194304 10 153690.61 154220.71 154007.65 103.75 #----------------------------------------------------------------------------- # Benchmarking Exchange # #processes = 6 #----------------------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec 0 1000 77.36 77.50 77.43 0.00 1 1000 78.03 78.15 78.09 0.05 2 1000 77.65 77.71 77.69 0.10 4 1000 77.85 77.88 77.86 0.20 8 1000 78.23 78.27 78.24 0.39 16 1000 78.51 78.56 78.54 0.78 32 1000 78.72 78.73 78.73 1.55 64 1000 79.88 79.98 79.93 3.05 128 1000 82.71 82.87 82.78 5.89 256 1000 92.18 92.21 92.20 10.59 512 1000 103.88 103.96 103.92 18.79 1024 1000 130.57 130.74 130.65 29.88 2048 1000 167.94 168.05 168.01 46.49 4096 1000 229.83 229.96 229.91 67.95 8192 1000 429.89 430.14 430.05 72.65 16384 1000 856.50 856.98 856.75 72.93 32768 1000 1707.52 1708.48 1708.07 73.16 65536 640 3991.60 3994.52 3992.94 62.59 131072 320 7754.96 7763.51 7759.48 64.40 262144 160 15631.14 15642.23 15638.05 63.93 524288 80 28613.91 28637.26 28621.25 69.84 1048576 40 56986.85 57039.72 57019.72 70.13 2097152 20 112567.05 112852.75 112757.27 70.89 4194304 10 225418.31 226183.70 225852.90 70.74 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 2 # ( 4 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 4 1000 58.13 58.14 58.13 8 1000 57.77 57.77 57.77 16 1000 58.53 58.54 58.53 32 1000 58.51 58.53 58.52 64 1000 59.07 59.07 59.07 128 1000 60.62 60.64 60.63 256 1000 62.04 62.04 62.04 512 1000 74.90 75.02 74.96 1024 1000 88.98 89.01 89.00 2048 1000 118.77 118.79 118.78 4096 1000 148.32 148.39 148.35 8192 1000 207.24 207.31 207.28 16384 1000 412.18 412.26 412.22 32768 1000 489.03 489.12 489.07 65536 640 830.58 830.80 830.69 131072 320 1727.87 1728.12 1728.00 262144 160 3075.42 3075.67 3075.54 524288 80 5841.02 5841.66 5841.34 1048576 40 11550.90 11553.85 11552.37 2097152 20 22649.10 22658.55 22653.82 4194304 10 44857.40 44888.20 44872.80 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.09 0.09 4 1000 88.60 88.61 88.60 8 1000 88.93 89.03 88.98 16 1000 89.53 89.67 89.60 32 1000 89.87 89.92 89.90 64 1000 90.31 90.32 90.32 128 1000 91.45 91.59 91.52 256 1000 93.85 93.98 93.92 512 1000 98.64 98.75 98.69 1024 1000 114.32 114.36 114.34 2048 1000 146.34 146.45 146.39 4096 1000 203.62 203.68 203.65 8192 1000 274.83 274.86 274.84 16384 1000 791.80 792.05 791.94 32768 1000 1220.61 1220.88 1220.79 65536 640 1720.73 1721.03 1720.90 131072 320 3421.22 3422.66 3421.90 262144 160 9549.01 9553.67 9552.01 524288 80 18395.99 18413.81 18407.68 1048576 40 35390.80 35465.60 35427.53 2097152 20 64337.35 64367.20 64352.31 4194304 10 126474.51 126657.10 126551.30 #---------------------------------------------------------------- # Benchmarking Allreduce # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.10 0.09 4 1000 158.60 158.74 158.67 8 1000 158.18 158.30 158.24 16 1000 158.88 158.99 158.93 32 1000 159.87 159.98 159.93 64 1000 161.00 161.13 161.05 128 1000 172.12 172.27 172.20 256 1000 186.53 186.65 186.59 512 1000 208.61 208.73 208.68 1024 1000 244.50 244.63 244.57 2048 1000 282.98 283.16 283.07 4096 1000 403.92 404.13 404.03 8192 1000 586.04 586.34 586.18 16384 1000 1257.12 1257.49 1257.30 32768 1000 1600.85 1601.10 1600.99 65536 640 2861.34 2862.42 2861.91 131072 320 5703.53 5705.34 5704.65 262144 160 11367.74 11373.46 11370.72 524288 80 28876.84 28902.58 28890.39 1048576 40 53027.03 53136.35 53107.32 2097152 20 107002.75 107053.25 107028.85 4194304 10 203388.29 203538.70 203492.53 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 2 # ( 4 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 4 1000 51.24 51.25 51.25 8 1000 51.19 51.20 51.19 16 1000 51.57 51.57 51.57 32 1000 51.39 51.39 51.39 64 1000 51.84 51.85 51.84 128 1000 52.21 52.22 52.21 256 1000 52.87 52.87 52.87 512 1000 55.85 55.87 55.86 1024 1000 73.73 73.74 73.73 2048 1000 90.49 90.52 90.51 4096 1000 116.86 116.93 116.90 8192 1000 150.97 151.06 151.01 16384 1000 235.14 235.31 235.23 32768 1000 405.16 405.50 405.33 65536 640 679.83 680.76 680.30 131072 320 1567.70 1569.61 1568.65 262144 160 3067.68 3071.52 3069.60 524288 80 6084.49 6092.30 6088.39 1048576 40 12115.52 12131.17 12123.35 2097152 20 24111.95 24143.20 24127.58 4194304 10 48061.19 48123.80 48092.49 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.11 0.10 4 1000 59.37 59.51 59.43 8 1000 59.25 59.37 59.30 16 1000 59.58 59.71 59.64 32 1000 59.85 59.98 59.92 64 1000 59.96 60.09 60.02 128 1000 60.61 60.75 60.68 256 1000 62.40 62.54 62.47 512 1000 86.85 86.92 86.89 1024 1000 98.44 98.51 98.48 2048 1000 127.42 127.50 127.46 4096 1000 161.12 161.23 161.18 8192 1000 247.65 247.84 247.75 16384 1000 416.31 416.68 416.49 32768 1000 654.73 655.90 655.39 65536 640 1027.17 1029.77 1028.59 131072 320 2386.91 2393.82 2390.78 262144 160 4631.63 4658.53 4646.76 524288 80 9096.36 9170.44 9141.98 1048576 40 21073.22 21150.02 21119.61 2097152 20 42635.55 42786.10 42730.42 4194304 10 81815.01 82113.49 82014.40 #---------------------------------------------------------------- # Benchmarking Reduce # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.12 0.11 4 1000 66.23 66.50 66.37 8 1000 66.51 66.78 66.65 16 1000 66.58 66.85 66.72 32 1000 66.55 66.81 66.67 64 1000 66.54 66.81 66.68 128 1000 67.93 68.19 68.06 256 1000 70.03 70.29 70.16 512 1000 93.31 93.38 93.34 1024 1000 107.91 107.99 107.95 2048 1000 131.16 131.28 131.21 4096 1000 197.88 198.04 197.96 8192 1000 275.00 275.28 275.14 16384 1000 441.70 442.25 441.98 32768 1000 613.08 614.79 614.03 65536 640 926.29 930.25 928.42 131072 320 3519.29 3529.75 3525.09 262144 160 6891.86 6933.28 6915.01 524288 80 13580.38 13713.93 13663.36 1048576 40 26931.58 27235.32 27124.49 2097152 20 62906.50 63227.14 63106.85 4194304 10 124174.10 124932.30 124688.20 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.09 4 1000 5.23 5.34 5.29 8 1000 58.49 58.58 58.54 16 1000 58.78 58.89 58.84 32 1000 59.09 59.11 59.10 64 1000 59.09 59.19 59.14 128 1000 59.67 59.78 59.73 256 1000 60.38 60.49 60.43 512 1000 63.56 63.57 63.57 1024 1000 76.83 76.96 76.90 2048 1000 76.34 76.43 76.38 4096 1000 119.79 119.94 119.86 8192 1000 150.72 150.89 150.81 16384 1000 212.95 213.12 213.04 32768 1000 264.57 264.61 264.59 65536 640 448.86 448.94 448.90 131072 320 925.79 926.04 925.92 262144 160 1775.71 1776.47 1776.09 524288 80 3996.21 3997.42 3996.82 1048576 40 8044.30 8048.25 8046.28 2097152 20 15855.81 15864.80 15860.30 4194304 10 31426.41 31429.20 31427.81 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.11 0.10 4 1000 6.40 6.54 6.46 8 1000 108.77 109.67 109.26 16 1000 88.58 88.60 88.59 32 1000 89.35 89.49 89.42 64 1000 89.04 89.09 89.07 128 1000 90.13 90.26 90.20 256 1000 91.28 91.40 91.34 512 1000 92.98 93.01 93.00 1024 1000 96.93 97.06 96.99 2048 1000 102.49 102.55 102.52 4096 1000 117.72 117.74 117.73 8192 1000 155.36 155.39 155.37 16384 1000 210.11 210.21 210.15 32768 1000 341.14 341.24 341.20 65536 640 613.92 614.28 614.10 131072 320 1316.24 1318.14 1317.00 262144 160 2993.06 2999.81 2996.18 524288 80 10236.76 10263.19 10250.47 1048576 40 19968.40 20025.00 19988.14 2097152 20 36968.80 37116.44 37060.85 4194304 10 71565.50 71802.01 71697.75 #---------------------------------------------------------------- # Benchmarking Reduce_scatter # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.11 0.10 4 1000 8.27 8.44 8.30 8 1000 107.30 108.24 107.66 16 1000 118.18 119.36 118.97 32 1000 155.24 155.35 155.30 64 1000 156.35 156.44 156.41 128 1000 159.27 159.37 159.33 256 1000 165.38 165.49 165.45 512 1000 178.04 178.15 178.10 1024 1000 196.89 197.00 196.96 2048 1000 222.30 222.44 222.37 4096 1000 296.44 296.59 296.53 8192 1000 405.64 405.82 405.74 16384 1000 599.62 599.80 599.72 32768 1000 807.91 808.27 808.12 65536 640 1431.45 1432.25 1431.97 131072 320 2846.33 2850.40 2848.69 262144 160 5674.20 5685.83 5680.47 524288 80 15673.87 15694.54 15683.68 1048576 40 28812.93 28860.65 28836.81 2097152 20 56938.61 57238.55 57144.57 4194304 10 111578.30 111863.90 111730.25 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.07 0.07 1 1000 56.08 56.09 56.08 2 1000 56.24 56.25 56.24 4 1000 56.24 56.24 56.24 8 1000 56.20 56.20 56.20 16 1000 56.58 56.58 56.58 32 1000 56.79 56.83 56.81 64 1000 57.66 57.76 57.71 128 1000 59.79 59.81 59.80 256 1000 60.95 60.97 60.96 512 1000 70.37 70.37 70.37 1024 1000 87.49 87.51 87.50 2048 1000 117.40 117.43 117.42 4096 1000 143.95 144.00 143.98 8192 1000 192.81 192.88 192.85 16384 1000 237.72 237.76 237.74 32768 1000 402.67 402.75 402.71 65536 640 1446.47 1447.35 1446.91 131072 320 2605.22 2608.61 2606.91 262144 160 4975.78 4988.57 4982.17 524288 80 9778.49 9800.66 9789.57 1048576 40 19183.30 19222.40 19202.85 2097152 20 21998.40 22007.10 22002.75 4194304 10 45430.11 45524.11 45477.11 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.08 0.07 1 1000 87.82 87.83 87.83 2 1000 88.15 88.29 88.22 4 1000 89.02 89.04 89.04 8 1000 88.94 88.95 88.94 16 1000 88.72 88.85 88.79 32 1000 88.98 89.00 88.99 64 1000 88.82 88.94 88.88 128 1000 91.05 91.16 91.10 256 1000 94.23 94.25 94.24 512 1000 99.64 99.72 99.68 1024 1000 113.70 113.77 113.73 2048 1000 149.01 149.03 149.02 4096 1000 203.75 203.82 203.78 8192 1000 306.04 306.12 306.08 16384 1000 857.30 857.63 857.47 32768 1000 2175.73 2176.29 2176.02 65536 640 4665.72 4667.57 4666.71 131072 320 7636.61 7643.74 7640.27 262144 160 14901.39 14911.22 14906.46 524288 80 32554.01 32591.05 32571.71 1048576 40 63214.48 63309.85 63260.99 2097152 20 124057.50 124142.15 124101.25 4194304 10 254358.71 254727.49 254547.42 #---------------------------------------------------------------- # Benchmarking Allgather # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.09 0.08 1 1000 112.09 112.11 112.10 2 1000 112.79 112.93 112.86 4 1000 112.11 112.13 112.12 8 1000 112.99 113.10 113.05 16 1000 113.91 114.00 113.96 32 1000 113.64 113.74 113.70 64 1000 115.05 115.20 115.13 128 1000 117.59 117.60 117.60 256 1000 124.49 124.51 124.50 512 1000 135.30 135.39 135.35 1024 1000 159.16 159.24 159.20 2048 1000 202.94 202.97 202.95 4096 1000 282.31 282.37 282.34 8192 1000 450.90 450.97 450.94 16384 1000 2133.57 2134.24 2133.88 32768 1000 5364.82 5366.20 5365.52 65536 640 10654.37 10660.00 10657.02 131072 320 18334.33 18348.24 18343.08 262144 160 36934.48 36955.99 36945.74 524288 80 79600.35 79651.80 79629.44 1048576 40 168354.20 168949.45 168729.36 2097152 20 330295.70 333866.70 332570.89 4194304 10 677119.50 678249.89 677844.40 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 2 # ( 4 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 1 1000 56.83 56.83 56.83 2 1000 57.25 57.25 57.25 4 1000 57.12 57.13 57.12 8 1000 57.53 57.54 57.54 16 1000 57.32 57.32 57.32 32 1000 57.77 57.78 57.78 64 1000 58.34 58.34 58.34 128 1000 59.60 59.71 59.65 256 1000 61.29 61.29 61.29 512 1000 72.24 72.28 72.26 1024 1000 74.20 74.22 74.21 2048 1000 117.53 117.56 117.55 4096 1000 145.66 145.74 145.70 8192 1000 190.26 190.32 190.29 16384 1000 237.51 237.57 237.54 32768 1000 404.17 404.24 404.20 65536 640 1453.08 1453.98 1453.53 131072 320 2610.79 2614.13 2612.46 262144 160 4985.82 4998.32 4992.07 524288 80 9781.66 9803.56 9792.61 1048576 40 19161.82 19205.75 19183.79 2097152 20 22808.19 22835.21 22821.70 4194304 10 42139.10 42210.60 42174.85 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 4 # ( 2 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 96.57 96.58 96.57 2 1000 96.52 96.53 96.53 4 1000 97.15 97.17 97.16 8 1000 97.09 97.10 97.09 16 1000 96.82 96.85 96.83 32 1000 97.44 97.45 97.44 64 1000 97.96 97.97 97.96 128 1000 99.97 100.00 99.99 256 1000 103.09 103.11 103.09 512 1000 108.12 108.13 108.13 1024 1000 120.92 121.05 120.99 2048 1000 154.37 154.40 154.39 4096 1000 205.46 205.65 205.55 8192 1000 310.40 310.45 310.43 16384 1000 857.90 858.26 858.08 32768 1000 2160.68 2161.40 2161.01 65536 640 4606.01 4607.84 4606.98 131072 320 7646.55 7653.59 7650.14 262144 160 14910.61 14920.39 14915.69 524288 80 33854.31 33876.09 33863.26 1048576 40 64364.98 64451.33 64412.15 2097152 20 126848.80 128796.95 127805.71 4194304 10 247236.10 254043.19 250641.52 #---------------------------------------------------------------- # Benchmarking Allgatherv # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.11 0.10 1 1000 124.24 124.32 124.28 2 1000 124.31 124.41 124.36 4 1000 124.11 124.23 124.17 8 1000 127.21 127.32 127.26 16 1000 124.75 124.86 124.80 32 1000 124.86 124.98 124.91 64 1000 126.67 126.75 126.71 128 1000 129.29 129.42 129.35 256 1000 133.60 133.71 133.65 512 1000 143.59 143.68 143.63 1024 1000 166.53 166.64 166.58 2048 1000 209.11 209.14 209.12 4096 1000 286.85 286.91 286.89 8192 1000 442.50 442.62 442.57 16384 1000 2133.62 2134.21 2133.92 32768 1000 5258.54 5261.66 5260.11 65536 640 10555.15 10560.76 10557.79 131072 320 18947.57 18957.10 18951.64 262144 160 36968.54 36991.06 36980.07 524288 80 81273.51 81412.75 81360.72 1048576 40 168894.12 169293.75 169142.50 2097152 20 337660.00 339779.55 339020.63 4194304 10 661611.61 662097.80 661869.35 #---------------------------------------------------------------- # Benchmarking Gather # #processes = 2 # ( 4 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 51.39 51.39 51.39 2 1000 51.39 51.39 51.39 4 1000 51.31 51.32 51.31 8 1000 51.41 51.41 51.41 16 1000 51.41 51.42 51.42 32 1000 51.50 51.51 51.50 64 1000 51.53 51.53 51.53 128 1000 51.84 51.84 51.84 256 1000 52.75 52.75 52.75 512 1000 55.34 55.34 55.34 1024 1000 72.65 72.67 72.66 2048 1000 88.73 88.77 88.75 4096 1000 114.58 114.64 114.61 8192 1000 149.85 149.94 149.90 16384 1000 224.78 224.94 224.86 32768 1000 386.84 387.15 387.00 65536 640 698.70 699.62 699.16 131072 320 1404.55 1407.06 1405.81 262144 160 2562.17 2573.31 2567.74 524288 80 4778.22 4796.09 4787.16 1048576 40 9228.30 9264.60 9246.45 2097152 20 18474.40 18549.96 18512.18 4194304 10 38051.00 38206.10 38128.55 #---------------------------------------------------------------- # Benchmarking Gather # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.11 0.10 1 1000 59.11 59.24 59.18 2 1000 59.09 59.21 59.15 4 1000 59.19 59.32 59.26 8 1000 59.14 59.27 59.20 16 1000 59.40 59.52 59.46 32 1000 59.50 59.63 59.56 64 1000 59.83 59.95 59.89 128 1000 60.44 60.56 60.50 256 1000 61.32 61.46 61.39 512 1000 64.03 64.18 64.11 1024 1000 88.82 88.99 88.92 2048 1000 111.73 111.94 111.84 4096 1000 129.19 129.49 129.34 8192 1000 306.28 306.62 306.46 16384 1000 369.78 370.14 369.94 32768 1000 605.89 606.49 606.11 65536 640 1150.82 1152.62 1151.39 131072 320 2344.50 2351.19 2347.31 262144 160 4483.49 4508.70 4491.44 524288 80 8857.67 8957.35 8909.91 1048576 40 17362.47 17755.43 17611.33 2097152 20 34057.11 35650.40 35135.20 4194304 10 67594.10 73823.69 72047.07 #---------------------------------------------------------------- # Benchmarking Gather # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.11 0.10 1 1000 66.43 66.70 66.56 2 1000 66.50 66.76 66.63 4 1000 66.18 66.45 66.32 8 1000 66.53 66.82 66.68 16 1000 66.54 66.79 66.66 32 1000 66.69 66.95 66.82 64 1000 66.64 66.93 66.79 128 1000 67.64 67.89 67.77 256 1000 69.07 69.35 69.22 512 1000 73.51 73.83 73.69 1024 1000 102.22 102.59 102.42 2048 1000 102.14 102.54 102.35 4096 1000 122.94 123.45 123.20 8192 1000 453.40 453.96 453.73 16384 1000 552.33 552.96 552.66 32768 1000 854.60 855.51 855.02 65536 640 1639.44 1642.26 1640.66 131072 320 3321.86 3331.42 3326.09 262144 160 6159.62 6209.01 6184.04 524288 80 12751.70 12900.45 12825.65 1048576 40 25408.35 26063.65 25794.48 2097152 20 50488.60 52873.65 51964.08 4194304 10 97687.70 107899.80 104412.90 #---------------------------------------------------------------- # Benchmarking Gatherv # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.17 0.24 0.20 1 1000 50.90 50.90 50.90 2 1000 50.82 50.82 50.82 4 1000 50.87 50.87 50.87 8 1000 51.11 51.12 51.12 16 1000 50.91 50.92 50.91 32 1000 51.08 51.09 51.08 64 1000 51.08 51.08 51.08 128 1000 51.39 51.40 51.39 256 1000 52.68 52.69 52.68 512 1000 55.21 55.21 55.21 1024 1000 72.23 72.26 72.25 2048 1000 88.40 88.44 88.42 4096 1000 114.40 114.47 114.43 8192 1000 147.62 147.71 147.66 16384 1000 229.83 230.01 229.92 32768 1000 394.75 395.08 394.91 65536 640 793.20 794.14 793.67 131072 320 1373.33 1376.91 1375.12 262144 160 2562.08 2575.97 2569.03 524288 80 4939.00 4966.82 4952.91 1048576 40 9636.33 9701.93 9669.13 2097152 20 18982.35 19166.74 19074.55 4194304 10 37639.89 38160.89 37900.39 #---------------------------------------------------------------- # Benchmarking Gatherv # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.19 0.28 0.23 1 1000 59.07 59.19 59.13 2 1000 59.07 59.19 59.13 4 1000 59.07 59.20 59.14 8 1000 59.14 59.28 59.21 16 1000 59.32 59.47 59.39 32 1000 59.62 59.75 59.69 64 1000 59.69 59.83 59.76 128 1000 60.18 60.30 60.24 256 1000 62.54 62.66 62.60 512 1000 63.92 64.04 63.98 1024 1000 88.92 89.12 89.03 2048 1000 110.98 111.21 111.10 4096 1000 129.26 129.54 129.40 8192 1000 177.79 178.20 178.00 16384 1000 260.06 260.63 260.34 32768 1000 441.57 442.66 442.11 65536 640 1517.71 1520.18 1518.97 131072 320 2613.07 2621.69 2617.46 262144 160 4673.97 4706.78 4690.29 524288 80 9081.26 9177.22 9129.95 1048576 40 18023.93 18381.32 18208.55 2097152 20 35495.50 36754.20 36130.33 4194304 10 69192.00 74149.91 72654.75 #---------------------------------------------------------------- # Benchmarking Gatherv # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.29 0.35 0.31 1 1000 66.43 66.67 66.55 2 1000 66.22 66.51 66.37 4 1000 66.34 66.61 66.48 8 1000 66.46 66.73 66.59 16 1000 66.45 66.73 66.60 32 1000 66.54 66.81 66.67 64 1000 66.71 66.96 66.83 128 1000 67.31 67.56 67.43 256 1000 69.30 69.59 69.45 512 1000 74.71 75.02 74.86 1024 1000 101.43 101.80 101.63 2048 1000 101.58 102.02 101.80 4096 1000 122.80 123.35 123.08 8192 1000 183.27 184.07 183.69 16384 1000 270.66 271.84 271.26 32768 1000 472.30 474.50 473.39 65536 640 2236.42 2241.19 2239.17 131072 320 3869.68 3883.21 3877.82 262144 160 6959.24 7021.19 6994.87 524288 80 13343.08 13511.30 13448.85 1048576 40 25979.25 26626.53 26352.78 2097152 20 50793.95 53127.15 52302.12 4194304 10 99074.10 108540.99 104589.62 #---------------------------------------------------------------- # Benchmarking Scatter # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.10 1 1000 51.28 51.38 51.33 2 1000 51.41 51.51 51.46 4 1000 51.28 51.37 51.32 8 1000 51.32 51.41 51.36 16 1000 51.33 51.43 51.38 32 1000 51.49 51.59 51.54 64 1000 51.58 51.69 51.64 128 1000 51.96 52.05 52.01 256 1000 52.97 53.07 53.02 512 1000 55.36 55.47 55.42 1024 1000 72.63 72.76 72.70 2048 1000 88.85 88.99 88.92 4096 1000 114.54 114.67 114.61 8192 1000 148.14 148.32 148.23 16384 1000 229.94 230.20 230.07 32768 1000 395.95 396.35 396.15 65536 640 796.74 797.77 797.25 131072 320 1372.33 1375.78 1374.06 262144 160 2536.79 2549.09 2542.94 524288 80 4902.10 4919.89 4910.99 1048576 40 9660.32 9685.03 9672.67 2097152 20 19068.05 19073.70 19070.88 4194304 10 37802.19 37964.51 37883.35 #---------------------------------------------------------------- # Benchmarking Scatter # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.10 0.11 0.10 1 1000 59.15 59.25 59.21 2 1000 59.03 59.16 59.10 4 1000 58.98 59.13 59.06 8 1000 59.29 59.40 59.34 16 1000 59.52 59.62 59.57 32 1000 59.68 59.77 59.73 64 1000 60.44 60.54 60.48 128 1000 61.55 61.67 61.60 256 1000 63.00 63.10 63.05 512 1000 76.45 76.57 76.51 1024 1000 90.90 91.04 90.98 2048 1000 115.47 115.62 115.55 4096 1000 141.89 142.05 141.97 8192 1000 215.02 215.26 215.13 16384 1000 331.40 331.75 331.55 32768 1000 570.10 570.72 570.35 65536 640 1438.98 1440.92 1439.90 131072 320 2520.10 2527.04 2523.43 262144 160 4489.33 4513.45 4500.41 524288 80 8796.98 8866.25 8830.10 1048576 40 17076.02 17311.20 17189.12 2097152 20 34601.50 35616.60 35135.71 4194304 10 68154.90 72586.10 71308.10 #---------------------------------------------------------------- # Benchmarking Scatter # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.09 0.10 0.10 1 1000 68.90 69.00 68.95 2 1000 68.73 68.84 68.79 4 1000 68.53 68.63 68.58 8 1000 68.68 68.80 68.74 16 1000 69.01 69.11 69.06 32 1000 69.15 69.23 69.19 64 1000 69.98 70.08 70.03 128 1000 72.16 72.28 72.22 256 1000 77.18 77.28 77.23 512 1000 93.59 93.72 93.66 1024 1000 106.65 106.79 106.72 2048 1000 121.44 121.59 121.53 4096 1000 168.90 169.09 168.99 8192 1000 242.93 243.26 243.08 16384 1000 405.30 405.79 405.51 32768 1000 719.63 720.49 719.96 65536 640 2006.63 2009.71 2008.34 131072 320 3518.24 3526.73 3522.53 262144 160 6480.69 6518.69 6501.17 524288 80 12253.60 12370.57 12325.41 1048576 40 23958.93 24423.23 24229.18 2097152 20 48906.65 50866.90 50190.55 4194304 10 97132.60 106029.30 102348.00 #---------------------------------------------------------------- # Benchmarking Scatterv # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.20 0.29 0.25 1 1000 50.67 50.77 50.72 2 1000 50.66 50.77 50.71 4 1000 50.66 50.76 50.71 8 1000 50.63 50.73 50.68 16 1000 50.70 50.80 50.75 32 1000 50.77 50.88 50.83 64 1000 50.82 50.92 50.87 128 1000 51.02 51.11 51.07 256 1000 52.59 52.70 52.64 512 1000 54.74 54.84 54.79 1024 1000 72.38 72.50 72.44 2048 1000 88.56 88.70 88.63 4096 1000 113.95 114.10 114.03 8192 1000 147.49 147.67 147.58 16384 1000 228.99 229.23 229.11 32768 1000 394.04 394.44 394.24 65536 640 795.18 796.19 795.68 131072 320 1370.79 1374.24 1372.51 262144 160 2533.74 2545.83 2539.79 524288 80 4892.14 4909.89 4901.01 1048576 40 9647.30 9671.65 9659.48 2097152 20 19065.40 19071.75 19068.57 4194304 10 37817.70 37991.21 37904.45 #---------------------------------------------------------------- # Benchmarking Scatterv # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.18 0.30 0.24 1 1000 58.87 59.01 58.95 2 1000 58.76 58.87 58.81 4 1000 59.01 59.13 59.08 8 1000 59.12 59.21 59.17 16 1000 59.31 59.42 59.36 32 1000 59.49 59.61 59.54 64 1000 59.93 60.05 59.99 128 1000 60.99 61.08 61.04 256 1000 62.82 62.94 62.86 512 1000 75.45 75.58 75.51 1024 1000 90.84 90.96 90.90 2048 1000 114.84 114.97 114.91 4096 1000 141.63 141.82 141.72 8192 1000 214.73 214.97 214.84 16384 1000 331.67 332.02 331.82 32768 1000 569.55 570.19 569.81 65536 640 1440.84 1442.76 1441.73 131072 320 2493.45 2500.49 2496.84 262144 160 4468.91 4493.01 4480.08 524288 80 8749.84 8820.40 8783.93 1048576 40 17369.92 17605.18 17482.66 2097152 20 34087.25 35047.30 34580.78 4194304 10 67819.69 71969.30 70830.50 #---------------------------------------------------------------- # Benchmarking Scatterv # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.22 0.30 0.26 1 1000 68.89 69.00 68.93 2 1000 69.03 69.12 69.07 4 1000 68.80 68.90 68.85 8 1000 68.93 69.06 69.00 16 1000 69.11 69.23 69.18 32 1000 69.31 69.42 69.37 64 1000 70.36 70.51 70.42 128 1000 72.50 72.61 72.55 256 1000 77.07 77.17 77.12 512 1000 93.53 93.62 93.57 1024 1000 106.69 106.83 106.76 2048 1000 121.62 121.78 121.70 4096 1000 168.83 169.03 168.92 8192 1000 243.39 243.69 243.52 16384 1000 403.47 403.94 403.65 32768 1000 719.37 720.18 719.67 65536 640 1995.16 1998.14 1996.82 131072 320 3518.75 3527.07 3522.89 262144 160 6404.10 6442.39 6424.76 524288 80 12260.99 12377.75 12333.69 1048576 40 23940.70 24413.50 24215.43 2097152 20 48474.05 50554.25 49820.27 4194304 10 96856.90 105808.69 102109.13 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.07 0.07 1 1000 57.04 57.05 57.04 2 1000 57.28 57.28 57.28 4 1000 56.96 57.07 57.01 8 1000 57.28 57.29 57.28 16 1000 57.38 57.40 57.39 32 1000 57.73 57.73 57.73 64 1000 58.59 58.60 58.60 128 1000 59.53 59.64 59.58 256 1000 61.02 61.02 61.02 512 1000 71.12 71.12 71.12 1024 1000 85.02 85.03 85.03 2048 1000 116.69 116.71 116.70 4096 1000 143.16 143.21 143.19 8192 1000 193.30 193.37 193.34 16384 1000 239.48 239.53 239.51 32768 1000 401.82 401.87 401.85 65536 640 1461.20 1462.08 1461.64 131072 320 2623.29 2626.65 2624.97 262144 160 5016.91 5029.31 5023.11 524288 80 9785.61 9806.36 9795.99 1048576 40 19167.68 19207.65 19187.66 2097152 20 22888.15 22891.75 22889.95 4194304 10 42193.20 42255.30 42224.25 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.07 0.07 1 1000 90.17 90.19 90.18 2 1000 90.96 90.98 90.97 4 1000 89.44 89.57 89.50 8 1000 91.55 91.57 91.56 16 1000 91.66 91.67 91.67 32 1000 92.00 92.03 92.02 64 1000 94.18 94.20 94.19 128 1000 96.38 96.39 96.38 256 1000 102.49 102.51 102.50 512 1000 104.74 104.77 104.75 1024 1000 118.39 118.41 118.40 2048 1000 146.64 146.79 146.71 4096 1000 312.00 312.12 312.07 8192 1000 451.75 451.80 451.78 16384 1000 714.69 714.82 714.76 32768 1000 1345.37 1345.71 1345.55 65536 640 3818.38 3820.41 3819.42 131072 320 6921.78 6927.78 6924.31 262144 160 12214.65 12223.44 12218.59 524288 80 23369.66 23379.84 23374.18 1048576 40 45019.30 45070.70 45047.59 2097152 20 88316.00 88496.95 88444.01 4194304 10 175043.11 175613.30 175337.05 #---------------------------------------------------------------- # Benchmarking Alltoall # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.07 0.07 1 1000 119.77 119.85 119.81 2 1000 119.41 119.45 119.42 4 1000 117.80 117.85 117.84 8 1000 117.97 118.09 118.03 16 1000 119.12 119.24 119.16 32 1000 118.87 118.95 118.91 64 1000 119.77 119.89 119.83 128 1000 123.35 123.44 123.42 256 1000 139.23 139.30 139.28 512 1000 142.96 142.99 142.97 1024 1000 176.76 176.81 176.78 2048 1000 244.77 244.88 244.83 4096 1000 541.57 541.63 541.59 8192 1000 808.14 808.28 808.21 16384 1000 1379.83 1380.16 1379.97 32768 1000 2643.54 2644.26 2643.90 65536 640 7565.47 7568.20 7566.81 131072 320 14641.30 14652.53 14647.36 262144 160 27768.28 27789.86 27777.06 524288 80 55881.58 55886.25 55883.87 1048576 40 109620.65 109781.40 109735.88 2097152 20 226124.60 226271.10 226227.77 4194304 10 422511.30 423497.11 423021.30 #---------------------------------------------------------------- # Benchmarking Alltoallv # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.14 0.14 0.14 1 1000 57.18 57.18 57.18 2 1000 57.15 57.15 57.15 4 1000 57.24 57.26 57.25 8 1000 57.37 57.37 57.37 16 1000 57.67 57.70 57.69 32 1000 57.82 57.84 57.83 64 1000 58.47 58.48 58.47 128 1000 60.03 60.04 60.03 256 1000 61.08 61.09 61.09 512 1000 72.28 72.30 72.29 1024 1000 87.12 87.13 87.13 2048 1000 117.67 117.70 117.68 4096 1000 144.18 144.24 144.21 8192 1000 192.79 192.85 192.82 16384 1000 239.19 239.21 239.20 32768 1000 406.28 406.36 406.32 65536 640 1453.75 1454.63 1454.19 131072 320 1485.30 1485.45 1485.37 262144 160 2821.49 2822.21 2821.85 524288 80 5454.79 5455.86 5455.33 1048576 40 10688.10 10697.32 10692.71 2097152 20 21159.40 21166.25 21162.83 4194304 10 42310.01 42383.71 42346.86 #---------------------------------------------------------------- # Benchmarking Alltoallv # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.15 0.16 0.15 1 1000 85.82 85.87 85.85 2 1000 86.80 86.89 86.85 4 1000 86.50 86.61 86.55 8 1000 86.92 87.03 86.98 16 1000 87.27 87.35 87.31 32 1000 87.71 87.79 87.75 64 1000 88.30 88.40 88.35 128 1000 91.09 91.13 91.11 256 1000 94.46 94.55 94.51 512 1000 100.83 100.92 100.87 1024 1000 117.67 117.76 117.71 2048 1000 148.66 148.75 148.70 4096 1000 199.70 199.83 199.77 8192 1000 318.39 318.52 318.47 16384 1000 572.54 572.90 572.75 32768 1000 1138.89 1139.25 1139.08 65536 640 3032.84 3034.21 3033.49 131072 320 5881.38 5892.30 5887.70 262144 160 16696.20 16746.91 16721.81 524288 80 32174.21 32284.28 32240.24 1048576 40 68246.48 68485.40 68387.65 2097152 20 95430.05 95787.05 95628.55 4194304 10 159342.49 159923.59 159633.42 #---------------------------------------------------------------- # Benchmarking Alltoallv # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.17 0.18 0.17 1 1000 122.79 122.82 122.81 2 1000 122.63 122.67 122.65 4 1000 121.91 122.10 122.01 8 1000 123.48 123.53 123.51 16 1000 124.83 124.87 124.86 32 1000 123.94 124.08 124.01 64 1000 125.92 125.99 125.96 128 1000 129.53 129.63 129.58 256 1000 141.54 141.59 141.56 512 1000 148.23 148.30 148.26 1024 1000 167.44 167.49 167.45 2048 1000 243.29 243.32 243.30 4096 1000 340.28 340.50 340.41 8192 1000 643.97 644.21 644.09 16384 1000 1287.60 1288.11 1287.83 32768 1000 2585.31 2586.42 2585.82 65536 640 5949.87 5954.05 5952.34 131072 320 11770.69 11790.63 11781.70 262144 160 36469.79 36590.22 36534.72 524288 80 75128.57 75365.21 75266.78 1048576 40 152921.60 153425.32 153221.98 2097152 20 217665.50 217883.40 217776.84 4194304 10 376332.91 396450.71 392562.15 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.09 0.08 1 1000 51.60 51.70 51.65 2 1000 51.60 51.71 51.66 4 1000 51.63 51.73 51.68 8 1000 51.62 51.72 51.67 16 1000 51.56 51.66 51.61 32 1000 51.62 51.72 51.67 64 1000 51.69 51.79 51.74 128 1000 52.02 52.13 52.08 256 1000 52.60 52.70 52.65 512 1000 55.28 55.37 55.32 1024 1000 72.48 72.61 72.55 2048 1000 87.06 87.19 87.12 4096 1000 117.03 117.17 117.10 8192 1000 144.74 144.90 144.82 16384 1000 227.05 227.23 227.14 32768 1000 372.77 373.11 372.94 65536 640 660.64 661.44 661.04 131072 320 1411.97 1414.08 1413.02 262144 160 2576.20 2583.42 2579.81 524288 80 5265.41 5279.90 5272.66 1048576 40 10492.00 10521.35 10506.68 2097152 20 20904.55 20961.70 20933.13 4194304 10 41707.11 41822.11 41764.61 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.08 0.09 0.08 1 1000 57.77 57.87 57.82 2 1000 57.93 58.05 58.00 4 1000 57.90 58.02 57.96 8 1000 57.96 58.11 58.04 16 1000 57.91 57.95 57.93 32 1000 58.07 58.21 58.13 64 1000 58.45 58.56 58.50 128 1000 59.62 59.77 59.70 256 1000 65.27 65.39 65.33 512 1000 72.08 72.26 72.18 1024 1000 82.99 83.14 83.06 2048 1000 129.79 129.96 129.91 4096 1000 148.97 149.17 149.10 8192 1000 206.37 206.61 206.52 16384 1000 340.51 340.80 340.71 32768 1000 598.34 598.76 598.60 65536 640 1124.13 1125.21 1124.77 131072 320 2874.58 2880.39 2877.57 262144 160 5371.42 5393.14 5383.24 524288 80 9229.81 9313.55 9277.36 1048576 40 17966.33 18182.45 18086.43 2097152 20 37258.75 37548.05 37429.03 4194304 10 73024.49 73599.79 73362.07 #---------------------------------------------------------------- # Benchmarking Bcast # #processes = 6 #---------------------------------------------------------------- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] 0 1000 0.07 0.10 0.08 1 1000 63.51 63.63 63.57 2 1000 62.75 62.87 62.81 4 1000 62.57 62.72 62.64 8 1000 62.66 62.79 62.72 16 1000 63.04 63.19 63.11 32 1000 63.19 63.34 63.26 64 1000 64.20 64.34 64.27 128 1000 67.15 67.30 67.23 256 1000 73.85 73.99 73.92 512 1000 79.65 79.81 79.73 1024 1000 90.73 90.88 90.81 2048 1000 140.90 141.06 141.02 4096 1000 179.48 179.72 179.65 8192 1000 266.56 266.86 266.78 16384 1000 444.57 445.01 444.89 32768 1000 779.12 779.90 779.63 65536 640 1458.74 1460.79 1460.09 131072 320 3731.42 3741.65 3737.59 262144 160 7662.66 7691.72 7679.68 524288 80 13532.62 13665.15 13615.63 1048576 40 26478.07 26852.15 26717.24 2097152 20 52535.80 53741.15 53317.91 4194304 10 111857.09 113262.41 112738.45 #--------------------------------------------------- # Benchmarking Barrier # #processes = 2 # ( 4 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 56.41 56.41 56.41 #--------------------------------------------------- # Benchmarking Barrier # #processes = 4 # ( 2 additional processes waiting in MPI_Barrier) #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 88.00 88.00 88.00 #--------------------------------------------------- # Benchmarking Barrier # #processes = 6 #--------------------------------------------------- #repetitions t_min[usec] t_max[usec] t_avg[usec] 1000 117.00 117.02 117.01 # All processes entering MPI_Finalize