Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #---------------------------------------------------
- # Intel (R) MPI Benchmark Suite V4.0.0, MPI-1 part
- #---------------------------------------------------
- # Date : Wed Jan 29 00:18:01 2014
- # Machine : x86_64
- # System : Linux
- # Release : 2.6.32-431.3.1.el6.x86_64
- # Version : #1 SMP Fri Jan 3 21:39:27 UTC 2014
- # MPI Version : 3.0
- # MPI Thread Environment:
- # 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
- # ( 6 additional processes waiting in MPI_Barrier)
- #---------------------------------------------------
- #bytes #repetitions t[usec] Mbytes/sec
- 0 1000 0.46 0.00
- 1 1000 0.45 2.10
- 2 1000 0.45 4.20
- 4 1000 0.46 8.34
- 8 1000 0.47 16.39
- 16 1000 0.46 32.99
- 32 1000 0.73 42.03
- 64 1000 0.73 83.55
- 128 1000 0.77 158.44
- 256 1000 0.79 309.41
- 512 1000 0.84 578.20
- 1024 1000 1.04 936.23
- 2048 1000 1.45 1351.15
- 4096 1000 1.86 2098.90
- 8192 1000 2.84 2749.45
- 16384 1000 5.46 2862.77
- 32768 1000 10.89 2870.55
- 65536 640 20.11 3107.52
- 131072 320 36.41 3433.45
- 262144 160 80.66 3099.46
- 524288 80 133.92 3733.62
- 1048576 40 250.66 3989.45
- 2097152 20 481.85 4150.67
- 4194304 10 1243.20 3217.51
- #---------------------------------------------------
- # Benchmarking PingPing
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #---------------------------------------------------
- #bytes #repetitions t[usec] Mbytes/sec
- 0 1000 0.97 0.00
- 1 1000 1.06 0.90
- 2 1000 1.03 1.85
- 4 1000 1.07 3.58
- 8 1000 1.10 6.96
- 16 1000 1.08 14.08
- 32 1000 1.05 29.06
- 64 1000 1.08 56.78
- 128 1000 1.13 108.20
- 256 1000 1.16 210.83
- 512 1000 1.25 391.51
- 1024 1000 1.44 678.60
- 2048 1000 1.84 1064.31
- 4096 1000 2.45 1593.77
- 8192 1000 3.53 2210.62
- 16384 1000 6.58 2374.23
- 32768 1000 12.97 2408.66
- 65536 640 39.96 1564.08
- 131072 320 72.23 1730.56
- 262144 160 160.73 1555.39
- 524288 80 267.06 1872.23
- 1048576 40 494.60 2021.84
- 2097152 20 938.70 2130.60
- 4194304 10 2498.10 1601.22
- #-----------------------------------------------------------------------------
- # Benchmarking Sendrecv
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #-----------------------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
- 0 1000 0.84 0.84 0.84 0.00
- 1 1000 0.94 0.94 0.94 2.03
- 2 1000 0.94 0.94 0.94 4.06
- 4 1000 0.97 0.97 0.97 7.89
- 8 1000 0.94 0.94 0.94 16.23
- 16 1000 0.97 0.97 0.97 31.47
- 32 1000 0.94 0.94 0.94 64.94
- 64 1000 0.97 0.97 0.97 125.83
- 128 1000 1.06 1.06 1.06 229.85
- 256 1000 1.01 1.01 1.01 485.77
- 512 1000 1.14 1.14 1.14 858.16
- 1024 1000 1.33 1.33 1.33 1467.31
- 2048 1000 1.80 1.80 1.80 2166.62
- 4096 1000 2.39 2.39 2.39 3266.35
- 8192 1000 3.51 3.51 3.51 4446.43
- 16384 1000 6.45 6.45 6.45 4842.68
- 32768 1000 12.36 12.36 12.36 5054.94
- 65536 640 39.24 39.24 39.24 3185.62
- 131072 320 71.65 71.66 71.66 3488.71
- 262144 160 156.84 156.87 156.86 3187.40
- 524288 80 260.42 260.49 260.46 3838.96
- 1048576 40 484.72 484.90 484.81 4124.55
- 2097152 20 936.54 936.85 936.70 4269.61
- 4194304 10 2453.11 2454.71 2453.91 3259.04
- #-----------------------------------------------------------------------------
- # Benchmarking Sendrecv
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #-----------------------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
- 0 1000 1.04 1.05 1.05 0.00
- 1 1000 1.13 1.13 1.13 1.68
- 2 1000 1.26 1.26 1.26 3.03
- 4 1000 1.13 1.13 1.13 6.76
- 8 1000 1.13 1.13 1.13 13.53
- 16 1000 1.12 1.12 1.12 27.20
- 32 1000 1.21 1.21 1.21 50.40
- 64 1000 1.12 1.12 1.12 108.89
- 128 1000 1.14 1.14 1.14 213.60
- 256 1000 1.19 1.19 1.19 411.41
- 512 1000 1.44 1.44 1.44 679.16
- 1024 1000 1.70 1.70 1.70 1146.22
- 2048 1000 2.38 2.38 2.38 1639.22
- 4096 1000 3.34 3.34 3.34 2338.40
- 8192 1000 5.01 5.01 5.01 3118.09
- 16384 1000 9.20 9.21 9.20 3394.86
- 32768 1000 19.12 19.13 19.13 3266.96
- 65536 640 39.06 39.07 39.07 3199.13
- 131072 320 72.50 72.56 72.53 3445.44
- 262144 160 177.38 177.52 177.45 2816.60
- 524288 80 373.65 374.39 374.02 2671.04
- 1048576 40 749.90 750.13 750.00 2666.20
- 2097152 20 1892.29 1897.80 1895.07 2107.70
- 4194304 10 4288.48 4289.70 4289.10 1864.93
- #-----------------------------------------------------------------------------
- # Benchmarking Sendrecv
- # #processes = 8
- #-----------------------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
- 0 1000 1.12 1.12 1.12 0.00
- 1 1000 1.20 1.20 1.20 1.59
- 2 1000 1.20 1.21 1.20 3.16
- 4 1000 1.20 1.20 1.20 6.34
- 8 1000 1.20 1.20 1.20 12.67
- 16 1000 1.19 1.19 1.19 25.58
- 32 1000 1.28 1.28 1.28 47.68
- 64 1000 1.20 1.21 1.21 101.13
- 128 1000 1.25 1.25 1.25 195.79
- 256 1000 1.30 1.30 1.30 376.19
- 512 1000 1.60 1.60 1.60 611.53
- 1024 1000 1.86 1.86 1.86 1048.37
- 2048 1000 2.77 2.77 2.77 1411.20
- 4096 1000 4.11 4.11 4.11 1899.04
- 8192 1000 7.31 7.31 7.31 2136.88
- 16384 1000 14.82 14.82 14.82 2108.49
- 32768 1000 31.58 31.60 31.59 1977.97
- 65536 640 55.07 55.10 55.09 2268.40
- 131072 320 106.59 106.69 106.63 2343.30
- 262144 160 259.56 260.19 259.92 1921.65
- 524288 80 518.66 520.28 519.49 1922.05
- 1048576 40 1437.77 1445.12 1442.72 1383.97
- 2097152 20 3733.15 3779.95 3764.56 1058.22
- 4194304 10 8054.49 8161.02 8119.88 980.27
- #-----------------------------------------------------------------------------
- # Benchmarking Exchange
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #-----------------------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
- 0 1000 1.99 1.99 1.99 0.00
- 1 1000 2.08 2.08 2.08 1.83
- 2 1000 2.13 2.13 2.13 3.59
- 4 1000 2.14 2.14 2.14 7.12
- 8 1000 2.12 2.12 2.12 14.40
- 16 1000 2.13 2.13 2.13 28.59
- 32 1000 2.10 2.10 2.10 58.10
- 64 1000 2.14 2.14 2.14 113.98
- 128 1000 2.22 2.22 2.22 219.65
- 256 1000 2.34 2.34 2.34 416.98
- 512 1000 2.62 2.62 2.62 746.63
- 1024 1000 3.06 3.06 3.06 1276.11
- 2048 1000 3.49 3.49 3.49 2239.17
- 4096 1000 4.65 4.65 4.65 3360.82
- 8192 1000 7.06 7.06 7.06 4428.86
- 16384 1000 13.98 13.98 13.98 4469.71
- 32768 1000 27.34 27.34 27.34 4571.71
- 65536 640 80.08 80.08 80.08 3121.76
- 131072 320 144.74 144.75 144.74 3454.31
- 262144 160 321.46 321.49 321.47 3110.55
- 524288 80 540.01 540.07 540.04 3703.19
- 1048576 40 998.22 998.35 998.29 4006.60
- 2097152 20 2001.86 2002.20 2002.03 3995.60
- 4194304 10 4831.91 4832.70 4832.30 3310.78
- #-----------------------------------------------------------------------------
- # Benchmarking Exchange
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #-----------------------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
- 0 1000 2.15 2.15 2.15 0.00
- 1 1000 2.28 2.28 2.28 1.67
- 2 1000 2.28 2.28 2.28 3.35
- 4 1000 2.36 2.36 2.36 6.47
- 8 1000 2.29 2.29 2.29 13.30
- 16 1000 2.34 2.35 2.35 26.02
- 32 1000 2.29 2.30 2.29 53.17
- 64 1000 2.39 2.39 2.39 101.98
- 128 1000 2.43 2.43 2.43 200.69
- 256 1000 2.61 2.61 2.61 374.17
- 512 1000 2.81 2.81 2.81 694.06
- 1024 1000 3.33 3.33 3.33 1173.05
- 2048 1000 4.25 4.25 4.25 1839.45
- 4096 1000 6.00 6.00 6.00 2604.15
- 8192 1000 9.61 9.61 9.61 3250.87
- 16384 1000 18.12 18.13 18.13 3447.36
- 32768 1000 37.60 37.61 37.60 3323.50
- 65536 640 102.80 102.83 102.82 2431.20
- 131072 320 195.68 195.74 195.71 2554.40
- 262144 160 432.88 433.20 433.08 2308.40
- 524288 80 831.40 831.54 831.47 2405.19
- 1048576 40 1575.80 1576.30 1576.04 2537.58
- 2097152 20 4041.35 4041.80 4041.54 1979.31
- 4194304 10 8601.90 8604.38 8603.14 1859.52
- #-----------------------------------------------------------------------------
- # Benchmarking Exchange
- # #processes = 8
- #-----------------------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
- 0 1000 2.25 2.26 2.26 0.00
- 1 1000 2.31 2.31 2.31 1.65
- 2 1000 2.32 2.33 2.32 3.28
- 4 1000 2.38 2.39 2.39 6.39
- 8 1000 2.31 2.31 2.31 13.20
- 16 1000 2.39 2.39 2.39 25.52
- 32 1000 2.31 2.32 2.31 52.69
- 64 1000 2.42 2.42 2.42 100.85
- 128 1000 2.42 2.43 2.43 201.10
- 256 1000 2.61 2.62 2.61 373.31
- 512 1000 2.95 2.95 2.95 661.18
- 1024 1000 3.63 3.64 3.63 1074.29
- 2048 1000 5.15 5.15 5.15 1516.41
- 4096 1000 7.81 7.82 7.81 1999.15
- 8192 1000 14.03 14.04 14.04 2225.63
- 16384 1000 27.18 27.19 27.18 2298.88
- 32768 1000 55.46 55.49 55.48 2252.58
- 65536 640 165.41 165.46 165.44 1510.96
- 131072 320 324.96 325.25 325.13 1537.28
- 262144 160 705.85 707.58 707.13 1413.26
- 524288 80 1224.10 1230.12 1228.19 1625.85
- 1048576 40 3552.77 3555.55 3554.16 1125.00
- 2097152 20 8016.46 8028.21 8023.92 996.49
- 4194304 10 16013.79 16396.00 16229.31 975.85
- #----------------------------------------------------------------
- # Benchmarking Allreduce
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 4 1000 1.56 1.56 1.56
- 8 1000 1.60 1.60 1.60
- 16 1000 1.59 1.59 1.59
- 32 1000 1.64 1.64 1.64
- 64 1000 1.68 1.68 1.68
- 128 1000 1.92 1.92 1.92
- 256 1000 1.98 1.99 1.99
- 512 1000 2.29 2.29 2.29
- 1024 1000 2.79 2.79 2.79
- 2048 1000 3.48 3.48 3.48
- 4096 1000 6.63 6.64 6.64
- 8192 1000 9.45 9.45 9.45
- 16384 1000 16.13 16.13 16.13
- 32768 1000 30.03 30.04 30.03
- 65536 640 68.60 68.61 68.61
- 131072 320 126.49 126.50 126.49
- 262144 160 245.30 245.32 245.31
- 524288 80 513.14 513.19 513.16
- 1048576 40 992.87 993.03 992.95
- 2097152 20 2121.85 2122.15 2122.00
- 4194304 10 6768.51 6774.81 6771.66
- #----------------------------------------------------------------
- # Benchmarking Allreduce
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 4 1000 2.52 2.52 2.52
- 8 1000 2.52 2.52 2.52
- 16 1000 2.59 2.59 2.59
- 32 1000 2.70 2.71 2.70
- 64 1000 2.67 2.67 2.67
- 128 1000 3.05 3.05 3.05
- 256 1000 3.09 3.09 3.09
- 512 1000 3.85 3.85 3.85
- 1024 1000 4.35 4.36 4.36
- 2048 1000 5.67 5.67 5.67
- 4096 1000 10.85 10.85 10.85
- 8192 1000 15.49 15.49 15.49
- 16384 1000 26.79 26.80 26.80
- 32768 1000 49.49 49.50 49.50
- 65536 640 105.52 105.53 105.53
- 131072 320 204.24 204.25 204.25
- 262144 160 467.91 467.98 467.94
- 524288 80 998.75 998.86 998.81
- 1048576 40 2179.32 2179.60 2179.47
- 2097152 20 5642.70 5643.65 5643.17
- 4194304 10 14539.60 14540.91 14540.23
- #----------------------------------------------------------------
- # Benchmarking Allreduce
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 4 1000 4.04 4.04 4.04
- 8 1000 3.98 3.98 3.98
- 16 1000 4.09 4.09 4.09
- 32 1000 4.11 4.11 4.11
- 64 1000 4.27 4.27 4.27
- 128 1000 4.62 4.63 4.62
- 256 1000 4.91 4.91 4.91
- 512 1000 5.98 5.99 5.98
- 1024 1000 7.48 7.48 7.48
- 2048 1000 9.65 9.65 9.65
- 4096 1000 16.77 16.77 16.77
- 8192 1000 24.55 24.55 24.55
- 16384 1000 44.51 44.52 44.51
- 32768 1000 78.76 78.76 78.76
- 65536 640 153.80 153.82 153.81
- 131072 320 355.72 355.78 355.75
- 262144 160 850.33 850.49 850.43
- 524288 80 1972.30 1972.65 1972.48
- 1048576 40 5503.93 5507.25 5505.62
- 2097152 20 11941.65 11946.61 11944.48
- 4194304 10 28002.21 28030.40 28014.63
- #----------------------------------------------------------------
- # Benchmarking Reduce
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 4 1000 0.92 0.92 0.92
- 8 1000 0.93 0.93 0.93
- 16 1000 0.95 0.95 0.95
- 32 1000 1.00 1.01 1.00
- 64 1000 1.03 1.03 1.03
- 128 1000 1.09 1.09 1.09
- 256 1000 1.15 1.15 1.15
- 512 1000 1.48 1.48 1.48
- 1024 1000 1.77 1.77 1.77
- 2048 1000 2.26 2.26 2.26
- 4096 1000 4.80 4.80 4.80
- 8192 1000 6.97 6.97 6.97
- 16384 1000 11.01 11.01 11.01
- 32768 1000 20.00 20.01 20.01
- 65536 640 52.01 52.01 52.01
- 131072 320 100.92 100.93 100.93
- 262144 160 188.37 188.38 188.38
- 524288 80 414.40 414.45 414.42
- 1048576 40 896.05 896.13 896.09
- 2097152 20 2044.94 2045.19 2045.07
- 4194304 10 6881.09 6901.10 6891.10
- #----------------------------------------------------------------
- # Benchmarking Reduce
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 4 1000 1.39 1.39 1.39
- 8 1000 1.40 1.40 1.40
- 16 1000 1.44 1.45 1.44
- 32 1000 1.46 1.46 1.46
- 64 1000 1.51 1.52 1.52
- 128 1000 1.75 1.75 1.75
- 256 1000 1.82 1.82 1.82
- 512 1000 2.18 2.18 2.18
- 1024 1000 2.80 2.80 2.80
- 2048 1000 3.64 3.64 3.64
- 4096 1000 7.63 7.63 7.63
- 8192 1000 10.63 10.63 10.63
- 16384 1000 16.56 16.57 16.56
- 32768 1000 29.66 29.66 29.66
- 65536 640 62.49 62.51 62.50
- 131072 320 140.49 140.57 140.53
- 262144 160 294.73 294.98 294.85
- 524288 80 701.49 702.90 702.28
- 1048576 40 1642.48 1648.00 1645.70
- 2097152 20 4023.40 4050.74 4040.68
- 4194304 10 11699.49 11800.48 11766.01
- #----------------------------------------------------------------
- # Benchmarking Reduce
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 4 1000 2.06 2.06 2.06
- 8 1000 2.20 2.20 2.20
- 16 1000 2.12 2.13 2.12
- 32 1000 2.16 2.17 2.16
- 64 1000 2.26 2.26 2.26
- 128 1000 2.46 2.46 2.46
- 256 1000 2.70 2.70 2.70
- 512 1000 3.20 3.20 3.20
- 1024 1000 4.00 4.01 4.00
- 2048 1000 5.53 5.54 5.54
- 4096 1000 10.90 10.91 10.91
- 8192 1000 15.05 15.05 15.05
- 16384 1000 23.66 23.67 23.66
- 32768 1000 41.62 41.64 41.63
- 65536 640 80.62 80.65 80.63
- 131072 320 188.97 189.12 189.04
- 262144 160 410.24 410.85 410.54
- 524288 80 1022.11 1023.65 1022.69
- 1048576 40 3534.05 3541.32 3537.00
- 2097152 20 7947.90 7988.14 7970.06
- 4194304 10 20539.59 20719.72 20644.02
- #----------------------------------------------------------------
- # Benchmarking Reduce_scatter
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.12 0.12 0.12
- 4 1000 1.18 1.26 1.22
- 8 1000 1.41 1.41 1.41
- 16 1000 1.41 1.41 1.41
- 32 1000 1.41 1.41 1.41
- 64 1000 1.41 1.41 1.41
- 128 1000 1.72 1.72 1.72
- 256 1000 1.70 1.70 1.70
- 512 1000 1.79 1.79 1.79
- 1024 1000 2.09 2.09 2.09
- 2048 1000 2.53 2.53 2.53
- 4096 1000 3.29 3.29 3.29
- 8192 1000 4.85 4.85 4.85
- 16384 1000 7.89 7.89 7.89
- 32768 1000 14.22 14.22 14.22
- 65536 640 47.40 47.40 47.40
- 131072 320 80.98 80.98 80.98
- 262144 160 152.62 152.63 152.62
- 524288 80 227.06 227.14 227.10
- 1048576 40 416.37 416.50 416.44
- 2097152 20 838.45 838.45 838.45
- 4194304 10 2020.50 2020.60 2020.55
- #----------------------------------------------------------------
- # Benchmarking Reduce_scatter
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.12 0.12 0.12
- 4 1000 1.21 2.54 2.10
- 8 1000 2.15 2.29 2.22
- 16 1000 2.55 2.55 2.55
- 32 1000 2.63 2.63 2.63
- 64 1000 2.58 2.58 2.58
- 128 1000 2.82 2.82 2.82
- 256 1000 2.82 2.82 2.82
- 512 1000 3.04 3.04 3.04
- 1024 1000 3.48 3.48 3.48
- 2048 1000 4.09 4.09 4.09
- 4096 1000 5.48 5.49 5.49
- 8192 1000 7.84 7.84 7.84
- 16384 1000 12.46 12.46 12.46
- 32768 1000 21.21 21.21 21.21
- 65536 640 43.04 43.05 43.05
- 131072 320 102.09 102.12 102.10
- 262144 160 215.66 215.69 215.67
- 524288 80 368.15 368.25 368.21
- 1048576 40 856.85 858.80 857.87
- 2097152 20 1823.79 1829.49 1826.85
- 4194304 10 4336.19 4355.98 4346.69
- #----------------------------------------------------------------
- # Benchmarking Reduce_scatter
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.13 0.13 0.13
- 4 1000 0.96 5.60 3.44
- 8 1000 0.96 4.13 3.20
- 16 1000 3.34 4.00 3.71
- 32 1000 3.96 3.96 3.96
- 64 1000 3.98 3.98 3.98
- 128 1000 4.10 4.10 4.10
- 256 1000 4.27 4.27 4.27
- 512 1000 4.47 4.48 4.47
- 1024 1000 5.22 5.22 5.22
- 2048 1000 6.21 6.22 6.22
- 4096 1000 8.25 8.25 8.25
- 8192 1000 12.05 12.05 12.05
- 16384 1000 19.89 19.89 19.89
- 32768 1000 35.01 35.01 35.01
- 65536 640 68.90 68.91 68.90
- 131072 320 165.99 166.02 166.01
- 262144 160 374.51 374.59 374.55
- 524288 80 604.86 605.04 604.96
- 1048576 40 1299.40 1300.72 1300.08
- 2097152 20 3310.66 3321.25 3316.55
- 4194304 10 8290.41 8309.01 8303.02
- #----------------------------------------------------------------
- # Benchmarking Allgather
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 1.10 1.10 1.10
- 2 1000 1.10 1.10 1.10
- 4 1000 1.21 1.21 1.21
- 8 1000 1.11 1.11 1.11
- 16 1000 1.10 1.10 1.10
- 32 1000 1.10 1.10 1.10
- 64 1000 1.19 1.19 1.19
- 128 1000 1.15 1.15 1.15
- 256 1000 1.17 1.17 1.17
- 512 1000 1.33 1.33 1.33
- 1024 1000 1.61 1.61 1.61
- 2048 1000 1.96 1.96 1.96
- 4096 1000 2.81 2.81 2.81
- 8192 1000 4.09 4.09 4.09
- 16384 1000 7.91 7.91 7.91
- 32768 1000 15.49 15.49 15.49
- 65536 640 46.31 46.31 46.31
- 131072 320 84.32 84.33 84.33
- 262144 160 182.63 182.65 182.64
- 524288 80 315.86 315.93 315.89
- 1048576 40 656.21 656.38 656.29
- 2097152 20 1391.55 1391.85 1391.70
- 4194304 10 3450.61 3453.40 3452.00
- #----------------------------------------------------------------
- # Benchmarking Allgather
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 2.25 2.25 2.25
- 2 1000 2.24 2.24 2.24
- 4 1000 2.24 2.24 2.24
- 8 1000 2.31 2.32 2.31
- 16 1000 2.24 2.24 2.24
- 32 1000 2.37 2.37 2.37
- 64 1000 2.27 2.27 2.27
- 128 1000 2.39 2.39 2.39
- 256 1000 2.44 2.44 2.44
- 512 1000 2.87 2.88 2.87
- 1024 1000 3.42 3.42 3.42
- 2048 1000 4.80 4.81 4.81
- 4096 1000 7.25 7.25 7.25
- 8192 1000 11.89 11.89 11.89
- 16384 1000 22.67 22.68 22.68
- 32768 1000 57.86 57.88 57.87
- 65536 640 129.08 129.14 129.11
- 131072 320 241.88 241.96 241.92
- 262144 160 699.59 699.63 699.61
- 524288 80 1373.05 1373.21 1373.13
- 1048576 40 3774.70 3775.23 3774.95
- 2097152 20 7720.65 7722.50 7721.57
- 4194304 10 15470.00 15481.28 15475.82
- #----------------------------------------------------------------
- # Benchmarking Allgather
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 3.75 3.75 3.75
- 2 1000 3.65 3.66 3.66
- 4 1000 3.63 3.63 3.63
- 8 1000 3.65 3.65 3.65
- 16 1000 3.66 3.66 3.66
- 32 1000 3.70 3.71 3.71
- 64 1000 3.77 3.77 3.77
- 128 1000 4.09 4.09 4.09
- 256 1000 4.70 4.70 4.70
- 512 1000 6.13 6.14 6.13
- 1024 1000 8.90 8.90 8.90
- 2048 1000 14.33 14.33 14.33
- 4096 1000 26.08 26.08 26.08
- 8192 1000 51.01 51.01 51.01
- 16384 1000 118.31 118.33 118.32
- 32768 1000 249.35 249.38 249.36
- 65536 640 392.33 392.36 392.35
- 131072 320 788.99 789.26 789.16
- 262144 160 3394.36 3395.83 3395.28
- 524288 80 6876.10 6879.94 6878.27
- 1048576 40 14927.67 14930.95 14929.20
- 2097152 20 30903.20 30941.10 30928.29
- 4194304 10 60859.32 61331.49 61183.52
- #----------------------------------------------------------------
- # Benchmarking Allgatherv
- # #processes = 2
- # ( 6 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 1.31 1.31 1.31
- 2 1000 1.31 1.31 1.31
- 4 1000 1.30 1.30 1.30
- 8 1000 1.30 1.31 1.30
- 16 1000 1.33 1.33 1.33
- 32 1000 1.36 1.37 1.36
- 64 1000 1.42 1.42 1.42
- 128 1000 1.45 1.45 1.45
- 256 1000 1.52 1.52 1.52
- 512 1000 1.81 1.81 1.81
- 1024 1000 2.10 2.10 2.10
- 2048 1000 2.49 2.49 2.49
- 4096 1000 3.39 3.39 3.39
- 8192 1000 5.36 5.36 5.36
- 16384 1000 10.78 10.78 10.78
- 32768 1000 21.62 21.62 21.62
- 65536 640 59.87 59.87 59.87
- 131072 320 112.05 112.06 112.05
- 262144 160 183.67 183.69 183.68
- 524288 80 318.09 318.16 318.12
- 1048576 40 659.63 659.82 659.73
- 2097152 20 1377.19 1377.45 1377.32
- 4194304 10 3435.02 3437.11 3436.06
- #----------------------------------------------------------------
- # Benchmarking Allgatherv
- # #processes = 4
- # ( 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 2.53 2.53 2.53
- 2 1000 2.57 2.57 2.57
- 4 1000 2.54 2.54 2.54
- 8 1000 2.66 2.66 2.66
- 16 1000 2.54 2.55 2.54
- 32 1000 2.70 2.70 2.70
- 64 1000 2.64 2.64 2.64
- 128 1000 2.83 2.83 2.83
- 256 1000 2.94 2.94 2.94
- 512 1000 3.37 3.37 3.37
- 1024 1000 4.26 4.26 4.26
- 2048 1000 6.06 6.06 6.06
- 4096 1000 9.39 9.39 9.39
- 8192 1000 16.04 16.04 16.04
- 16384 1000 30.31 30.31 30.31
- 32768 1000 70.36 70.38 70.37
- 65536 640 158.52 158.55 158.54
- 131072 320 238.62 238.72 238.69
- 262144 160 700.48 700.55 700.51
- 524288 80 1366.21 1366.26 1366.24
- 1048576 40 3778.15 3778.65 3778.38
- 2097152 20 7712.79 7713.65 7713.19
- 4194304 10 15616.99 15630.10 15623.87
- #----------------------------------------------------------------
- # Benchmarking Allgatherv
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.09 0.10 0.09
- 1 1000 4.26 4.26 4.26
- 2 1000 4.15 4.16 4.16
- 4 1000 4.16 4.17 4.17
- 8 1000 4.18 4.18 4.18
- 16 1000 4.27 4.27 4.27
- 32 1000 4.28 4.29 4.28
- 64 1000 4.43 4.43 4.43
- 128 1000 4.90 4.90 4.90
- 256 1000 5.60 5.60 5.60
- 512 1000 7.16 7.16 7.16
- 1024 1000 10.21 10.21 10.21
- 2048 1000 16.72 16.72 16.72
- 4096 1000 30.04 30.05 30.04
- 8192 1000 58.65 58.65 58.65
- 16384 1000 134.09 134.11 134.10
- 32768 1000 295.89 295.90 295.89
- 65536 640 392.54 392.57 392.55
- 131072 320 789.71 790.04 789.87
- 262144 160 3391.75 3392.43 3392.17
- 524288 80 6859.45 6864.29 6862.02
- 1048576 40 14924.20 14930.00 14928.14
- 2097152 20 30915.45 30939.05 30928.81
- 4194304 10 61120.70 61218.91 61181.18
- #----------------------------------------------------------------
- # Benchmarking Gather
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 0.71 0.71 0.71
- 2 1000 0.72 0.72 0.72
- 4 1000 0.73 0.73 0.73
- 8 1000 0.73 0.73 0.73
- 16 1000 0.74 0.74 0.74
- 32 1000 0.81 0.81 0.81
- 64 1000 0.84 0.84 0.84
- 128 1000 0.88 0.88 0.88
- 256 1000 0.90 0.90 0.90
- 512 1000 1.09 1.09 1.09
- 1024 1000 1.08 1.08 1.08
- 2048 1000 1.37 1.37 1.37
- 4096 1000 1.83 1.83 1.83
- 8192 1000 2.85 2.85 2.85
- 16384 1000 5.58 5.59 5.58
- 32768 1000 10.94 10.94 10.94
- 65536 640 24.26 24.26 24.26
- 131072 320 47.31 47.32 47.32
- 262144 160 101.83 101.86 101.84
- 524288 80 180.91 180.95 180.93
- 1048576 40 353.10 353.22 353.16
- 2097152 20 774.50 774.80 774.65
- 4194304 10 1839.61 1844.31 1841.96
- #----------------------------------------------------------------
- # Benchmarking Gather
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 1.25 1.25 1.25
- 2 1000 1.26 1.26 1.26
- 4 1000 1.37 1.38 1.38
- 8 1000 1.30 1.30 1.30
- 16 1000 1.31 1.32 1.31
- 32 1000 1.38 1.38 1.38
- 64 1000 1.40 1.41 1.40
- 128 1000 1.49 1.49 1.49
- 256 1000 1.64 1.65 1.64
- 512 1000 2.05 2.05 2.05
- 1024 1000 3.61 3.61 3.61
- 2048 1000 4.23 4.24 4.23
- 4096 1000 5.89 5.89 5.89
- 8192 1000 8.82 8.83 8.83
- 16384 1000 16.51 16.53 16.52
- 32768 1000 31.59 31.62 31.61
- 65536 640 51.05 51.12 51.09
- 131072 320 111.65 111.93 111.79
- 262144 160 244.10 245.03 244.57
- 524288 80 497.10 500.36 498.72
- 1048576 40 1151.17 1166.75 1158.88
- 2097152 20 2299.70 2360.09 2329.34
- 4194304 10 4630.61 4886.10 4757.38
- #----------------------------------------------------------------
- # Benchmarking Gather
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 1.96 1.96 1.96
- 2 1000 2.09 2.09 2.09
- 4 1000 2.01 2.01 2.01
- 8 1000 2.12 2.13 2.12
- 16 1000 2.10 2.10 2.10
- 32 1000 2.20 2.21 2.21
- 64 1000 2.41 2.42 2.42
- 128 1000 2.47 2.47 2.47
- 256 1000 2.91 2.91 2.91
- 512 1000 3.46 3.46 3.46
- 1024 1000 7.24 7.25 7.25
- 2048 1000 9.08 9.09 9.09
- 4096 1000 13.23 13.25 13.24
- 8192 1000 21.90 21.94 21.92
- 16384 1000 40.83 40.89 40.86
- 32768 1000 73.23 73.33 73.28
- 65536 640 155.23 155.56 155.40
- 131072 320 369.95 371.39 370.70
- 262144 160 775.80 781.72 778.94
- 524288 80 1537.24 1560.20 1549.16
- 1048576 40 3110.72 3205.42 3160.99
- 2097152 20 6201.99 6593.00 6411.09
- 4194304 10 11670.59 13161.80 12425.23
- #----------------------------------------------------------------
- # Benchmarking Gatherv
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.11 0.12 0.11
- 1 1000 0.70 0.70 0.70
- 2 1000 0.70 0.70 0.70
- 4 1000 0.70 0.70 0.70
- 8 1000 0.71 0.71 0.71
- 16 1000 0.71 0.71 0.71
- 32 1000 0.77 0.77 0.77
- 64 1000 0.82 0.82 0.82
- 128 1000 0.84 0.84 0.84
- 256 1000 0.82 0.82 0.82
- 512 1000 0.96 0.97 0.96
- 1024 1000 1.14 1.14 1.14
- 2048 1000 1.41 1.41 1.41
- 4096 1000 1.89 1.90 1.90
- 8192 1000 2.93 2.94 2.93
- 16384 1000 5.71 5.71 5.71
- 32768 1000 11.06 11.06 11.06
- 65536 640 24.33 24.33 24.33
- 131072 320 47.31 47.32 47.31
- 262144 160 101.76 101.78 101.77
- 524288 80 180.86 180.90 180.88
- 1048576 40 353.40 353.52 353.46
- 2097152 20 774.05 774.30 774.17
- 4194304 10 1824.09 1829.20 1826.64
- #----------------------------------------------------------------
- # Benchmarking Gatherv
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.09 0.12 0.10
- 1 1000 0.80 0.80 0.80
- 2 1000 0.81 0.81 0.81
- 4 1000 0.80 0.81 0.80
- 8 1000 0.92 0.92 0.92
- 16 1000 0.83 0.83 0.83
- 32 1000 0.83 0.83 0.83
- 64 1000 0.84 0.84 0.84
- 128 1000 0.87 0.88 0.88
- 256 1000 0.91 0.91 0.91
- 512 1000 1.06 1.06 1.06
- 1024 1000 1.21 1.22 1.22
- 2048 1000 1.53 1.54 1.54
- 4096 1000 2.27 2.27 2.27
- 8192 1000 3.55 3.56 3.55
- 16384 1000 6.75 6.76 6.75
- 32768 1000 13.18 13.20 13.19
- 65536 640 40.04 40.10 40.08
- 131072 320 78.20 78.43 78.35
- 262144 160 178.00 179.04 178.64
- 524288 80 308.64 312.06 310.74
- 1048576 40 831.82 847.35 840.99
- 2097152 20 1625.25 1687.85 1662.77
- 4194304 10 3433.99 3680.30 3584.97
- #----------------------------------------------------------------
- # Benchmarking Gatherv
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.07 0.09 0.09
- 1 1000 0.93 0.93 0.93
- 2 1000 0.93 0.93 0.93
- 4 1000 0.94 0.94 0.94
- 8 1000 0.94 0.95 0.95
- 16 1000 0.95 0.96 0.95
- 32 1000 0.96 0.97 0.96
- 64 1000 0.99 0.99 0.99
- 128 1000 1.03 1.03 1.03
- 256 1000 1.09 1.09 1.09
- 512 1000 1.25 1.25 1.25
- 1024 1000 1.50 1.50 1.50
- 2048 1000 2.14 2.15 2.15
- 4096 1000 3.14 3.15 3.15
- 8192 1000 5.41 5.43 5.42
- 16384 1000 10.48 10.50 10.49
- 32768 1000 21.99 22.04 22.02
- 65536 640 69.66 69.90 69.80
- 131072 320 157.68 158.74 158.32
- 262144 160 465.79 472.29 469.73
- 524288 80 864.37 884.21 876.38
- 1048576 40 1688.65 1755.88 1728.63
- 2097152 20 3179.30 3517.81 3397.21
- 4194304 10 6382.01 7625.82 7182.30
- #----------------------------------------------------------------
- # Benchmarking Scatter
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 0.72 0.72 0.72
- 2 1000 0.72 0.72 0.72
- 4 1000 0.72 0.72 0.72
- 8 1000 0.72 0.72 0.72
- 16 1000 0.74 0.74 0.74
- 32 1000 0.79 0.79 0.79
- 64 1000 0.82 0.83 0.83
- 128 1000 0.86 0.86 0.86
- 256 1000 0.89 0.89 0.89
- 512 1000 1.12 1.12 1.12
- 1024 1000 1.23 1.23 1.23
- 2048 1000 1.53 1.53 1.53
- 4096 1000 2.18 2.18 2.18
- 8192 1000 3.45 3.45 3.45
- 16384 1000 6.93 6.93 6.93
- 32768 1000 13.94 13.94 13.94
- 65536 640 28.97 28.97 28.97
- 131072 320 55.11 55.14 55.12
- 262144 160 117.25 117.37 117.31
- 524288 80 241.49 242.37 241.93
- 1048576 40 506.40 510.48 508.44
- 2097152 20 1082.75 1099.35 1091.05
- 4194304 10 2394.10 2463.51 2428.81
- #----------------------------------------------------------------
- # Benchmarking Scatter
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.06 0.05
- 1 1000 1.29 1.29 1.29
- 2 1000 1.28 1.28 1.28
- 4 1000 1.29 1.30 1.30
- 8 1000 1.29 1.30 1.30
- 16 1000 1.33 1.34 1.34
- 32 1000 1.36 1.36 1.36
- 64 1000 1.40 1.40 1.40
- 128 1000 1.44 1.44 1.44
- 256 1000 1.53 1.53 1.53
- 512 1000 1.79 1.79 1.79
- 1024 1000 2.01 2.02 2.02
- 2048 1000 2.85 2.85 2.85
- 4096 1000 4.03 4.03 4.03
- 8192 1000 7.68 7.68 7.68
- 16384 1000 15.60 15.61 15.61
- 32768 1000 37.31 37.32 37.32
- 65536 640 67.60 67.60 67.60
- 131072 320 153.65 153.68 153.67
- 262144 160 344.84 345.05 344.92
- 524288 80 805.07 806.24 805.53
- 1048576 40 2279.42 2283.90 2281.43
- 2097152 20 5501.95 5529.34 5516.18
- 4194304 10 7102.30 7210.21 7156.35
- #----------------------------------------------------------------
- # Benchmarking Scatter
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 1.45 1.45 1.45
- 2 1000 1.46 1.46 1.46
- 4 1000 1.47 1.48 1.47
- 8 1000 1.50 1.50 1.50
- 16 1000 1.53 1.53 1.53
- 32 1000 1.65 1.66 1.65
- 64 1000 1.61 1.62 1.61
- 128 1000 1.68 1.69 1.69
- 256 1000 1.93 1.93 1.93
- 512 1000 2.24 2.24 2.24
- 1024 1000 3.32 3.33 3.32
- 2048 1000 5.13 5.13 5.13
- 4096 1000 9.61 9.61 9.61
- 8192 1000 19.13 19.14 19.13
- 16384 1000 43.45 43.45 43.45
- 32768 1000 99.50 99.50 99.50
- 65536 640 228.74 228.75 228.74
- 131072 320 524.25 524.32 524.28
- 262144 160 1117.36 1118.07 1117.68
- 524288 80 2411.41 2414.85 2413.20
- 1048576 40 5029.48 5049.07 5038.80
- 2097152 20 9665.39 9751.45 9708.51
- 4194304 10 25193.00 25567.22 25429.36
- #----------------------------------------------------------------
- # Benchmarking Scatterv
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.11 0.11 0.11
- 1 1000 0.82 0.82 0.82
- 2 1000 0.83 0.83 0.83
- 4 1000 0.83 0.83 0.83
- 8 1000 0.93 0.93 0.93
- 16 1000 0.83 0.84 0.84
- 32 1000 0.82 0.82 0.82
- 64 1000 0.84 0.84 0.84
- 128 1000 0.88 0.88 0.88
- 256 1000 0.86 0.87 0.87
- 512 1000 0.99 0.99 0.99
- 1024 1000 1.22 1.22 1.22
- 2048 1000 1.50 1.50 1.50
- 4096 1000 2.17 2.17 2.17
- 8192 1000 3.49 3.49 3.49
- 16384 1000 6.31 6.31 6.31
- 32768 1000 12.53 12.53 12.53
- 65536 640 26.50 26.51 26.51
- 131072 320 49.28 49.30 49.29
- 262144 160 106.04 106.08 106.06
- 524288 80 186.09 186.16 186.12
- 1048576 40 361.96 362.10 362.03
- 2097152 20 803.70 804.40 804.05
- 4194304 10 1758.60 1760.01 1759.30
- #----------------------------------------------------------------
- # Benchmarking Scatterv
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.09 0.13 0.11
- 1 1000 1.04 1.04 1.04
- 2 1000 1.05 1.05 1.05
- 4 1000 1.15 1.15 1.15
- 8 1000 1.05 1.05 1.05
- 16 1000 1.05 1.06 1.05
- 32 1000 1.04 1.04 1.04
- 64 1000 1.08 1.08 1.08
- 128 1000 1.12 1.12 1.12
- 256 1000 1.16 1.17 1.16
- 512 1000 1.34 1.34 1.34
- 1024 1000 1.57 1.58 1.58
- 2048 1000 2.00 2.00 2.00
- 4096 1000 2.90 2.90 2.90
- 8192 1000 4.72 4.72 4.72
- 16384 1000 9.18 9.18 9.18
- 32768 1000 18.44 18.46 18.45
- 65536 640 48.83 48.88 48.86
- 131072 320 93.73 93.94 93.86
- 262144 160 204.01 204.97 204.60
- 524288 80 349.38 352.80 351.48
- 1048576 40 781.27 795.53 790.11
- 2097152 20 1533.15 1587.09 1566.47
- 4194304 10 3301.98 3550.70 3462.02
- #----------------------------------------------------------------
- # Benchmarking Scatterv
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.08 0.10 0.09
- 1 1000 1.53 1.53 1.53
- 2 1000 1.53 1.53 1.53
- 4 1000 1.53 1.53 1.53
- 8 1000 1.53 1.53 1.53
- 16 1000 1.54 1.54 1.54
- 32 1000 1.63 1.63 1.63
- 64 1000 1.61 1.61 1.61
- 128 1000 1.70 1.70 1.70
- 256 1000 1.86 1.87 1.87
- 512 1000 2.06 2.06 2.06
- 1024 1000 2.66 2.66 2.66
- 2048 1000 3.29 3.29 3.29
- 4096 1000 4.77 4.78 4.78
- 8192 1000 8.06 8.07 8.06
- 16384 1000 16.56 16.58 16.57
- 32768 1000 35.01 35.05 35.03
- 65536 640 83.40 83.60 83.52
- 131072 320 177.98 178.64 178.34
- 262144 160 413.71 418.24 416.53
- 524288 80 742.24 757.03 751.35
- 1048576 40 1484.10 1546.28 1522.64
- 2097152 20 3445.85 3627.75 3548.79
- 4194304 10 6555.10 7413.20 7066.23
- #----------------------------------------------------------------
- # Benchmarking Alltoall
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 1.94 1.94 1.94
- 2 1000 2.05 2.05 2.05
- 4 1000 1.94 1.94 1.94
- 8 1000 1.94 1.94 1.94
- 16 1000 1.94 1.94 1.94
- 32 1000 1.95 1.96 1.95
- 64 1000 1.96 1.96 1.96
- 128 1000 1.98 1.98 1.98
- 256 1000 2.04 2.04 2.04
- 512 1000 2.18 2.19 2.18
- 1024 1000 2.42 2.42 2.42
- 2048 1000 2.76 2.76 2.76
- 4096 1000 3.49 3.49 3.49
- 8192 1000 5.02 5.02 5.02
- 16384 1000 8.82 8.82 8.82
- 32768 1000 16.39 16.39 16.39
- 65536 640 46.40 46.40 46.40
- 131072 320 85.25 85.26 85.26
- 262144 160 184.81 184.84 184.82
- 524288 80 360.11 360.20 360.16
- 1048576 40 693.50 693.60 693.55
- 2097152 20 1769.15 1769.70 1769.42
- 4194304 10 3479.00 3483.01 3481.01
- #----------------------------------------------------------------
- # Benchmarking Alltoall
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 4.01 4.01 4.01
- 2 1000 3.93 3.93 3.93
- 4 1000 3.93 3.93 3.93
- 8 1000 3.90 3.90 3.90
- 16 1000 3.89 3.90 3.90
- 32 1000 3.89 3.89 3.89
- 64 1000 3.91 3.91 3.91
- 128 1000 4.04 4.04 4.04
- 256 1000 4.17 4.17 4.17
- 512 1000 4.68 4.68 4.68
- 1024 1000 5.30 5.30 5.30
- 2048 1000 6.92 6.93 6.92
- 4096 1000 9.65 9.65 9.65
- 8192 1000 15.09 15.10 15.09
- 16384 1000 27.17 27.18 27.17
- 32768 1000 52.87 52.89 52.88
- 65536 640 148.18 148.19 148.19
- 131072 320 342.89 342.92 342.90
- 262144 160 730.39 730.47 730.44
- 524288 80 1957.90 1958.49 1958.21
- 1048576 40 3891.97 3894.10 3893.07
- 2097152 20 7493.79 7499.04 7496.47
- 4194304 10 14320.02 14326.79 14321.95
- #----------------------------------------------------------------
- # Benchmarking Alltoall
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.05 0.05 0.05
- 1 1000 8.07 8.07 8.07
- 2 1000 8.17 8.17 8.17
- 4 1000 8.19 8.19 8.19
- 8 1000 8.25 8.26 8.25
- 16 1000 8.63 8.63 8.63
- 32 1000 8.77 8.77 8.77
- 64 1000 9.22 9.23 9.23
- 128 1000 10.02 10.02 10.02
- 256 1000 11.34 11.35 11.35
- 512 1000 10.52 10.52 10.52
- 1024 1000 12.58 12.58 12.58
- 2048 1000 17.46 17.47 17.47
- 4096 1000 26.20 26.20 26.20
- 8192 1000 44.23 44.24 44.24
- 16384 1000 84.27 84.29 84.28
- 32768 1000 196.26 196.31 196.28
- 65536 640 594.41 594.48 594.45
- 131072 320 2143.71 2143.90 2143.84
- 262144 160 4732.23 4733.35 4732.92
- 524288 80 8312.08 8314.91 8314.06
- 1048576 40 15473.82 15487.27 15483.10
- 2097152 20 29428.49 29472.99 29460.38
- 4194304 10 56933.21 57101.18 57042.83
- #----------------------------------------------------------------
- # Benchmarking Alltoallv
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.22 0.27 0.24
- 1 1000 1.92 1.92 1.92
- 2 1000 2.05 2.05 2.05
- 4 1000 1.89 1.90 1.90
- 8 1000 1.90 1.90 1.90
- 16 1000 1.87 1.87 1.87
- 32 1000 1.92 1.92 1.92
- 64 1000 1.94 1.94 1.94
- 128 1000 1.94 1.95 1.94
- 256 1000 1.94 1.94 1.94
- 512 1000 2.13 2.13 2.13
- 1024 1000 2.40 2.40 2.40
- 2048 1000 2.72 2.72 2.72
- 4096 1000 3.44 3.44 3.44
- 8192 1000 4.99 4.99 4.99
- 16384 1000 8.78 8.78 8.78
- 32768 1000 16.34 16.34 16.34
- 65536 640 47.28 47.28 47.28
- 131072 320 85.99 86.00 86.00
- 262144 160 186.88 186.91 186.90
- 524288 80 364.30 364.36 364.33
- 1048576 40 694.63 694.73 694.68
- 2097152 20 1786.26 1786.85 1786.55
- 4194304 10 3456.21 3459.81 3458.01
- #----------------------------------------------------------------
- # Benchmarking Alltoallv
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.25 0.29 0.27
- 1 1000 4.10 4.10 4.10
- 2 1000 4.00 4.00 4.00
- 4 1000 3.98 3.98 3.98
- 8 1000 3.97 3.97 3.97
- 16 1000 3.99 3.99 3.99
- 32 1000 3.99 4.00 3.99
- 64 1000 4.02 4.02 4.02
- 128 1000 4.13 4.14 4.13
- 256 1000 4.25 4.25 4.25
- 512 1000 4.79 4.79 4.79
- 1024 1000 5.49 5.49 5.49
- 2048 1000 7.04 7.04 7.04
- 4096 1000 9.75 9.76 9.76
- 8192 1000 15.06 15.06 15.06
- 16384 1000 27.24 27.25 27.25
- 32768 1000 53.14 53.16 53.15
- 65536 640 133.65 133.68 133.67
- 131072 320 304.23 304.42 304.34
- 262144 160 695.03 695.14 695.08
- 524288 80 1784.84 1787.91 1786.51
- 1048576 40 3852.40 3853.03 3852.69
- 2097152 20 7396.46 7399.94 7398.20
- 4194304 10 14339.30 14347.29 14343.30
- #----------------------------------------------------------------
- # Benchmarking Alltoallv
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.34 0.51 0.39
- 1 1000 8.63 8.63 8.63
- 2 1000 8.69 8.69 8.69
- 4 1000 8.70 8.70 8.70
- 8 1000 8.67 8.67 8.67
- 16 1000 8.70 8.71 8.70
- 32 1000 8.65 8.65 8.65
- 64 1000 8.83 8.83 8.83
- 128 1000 9.20 9.20 9.20
- 256 1000 9.48 9.48 9.48
- 512 1000 10.71 10.71 10.71
- 1024 1000 12.86 12.87 12.87
- 2048 1000 17.72 17.73 17.72
- 4096 1000 26.56 26.57 26.57
- 8192 1000 44.70 44.71 44.70
- 16384 1000 84.67 84.70 84.68
- 32768 1000 196.35 196.41 196.39
- 65536 640 557.22 557.29 557.27
- 131072 320 1992.38 1992.75 1992.58
- 262144 160 4704.55 4706.84 4706.09
- 524288 80 8687.38 8690.79 8689.34
- 1048576 40 16293.65 16303.07 16299.10
- 2097152 20 31088.21 31134.05 31119.97
- 4194304 10 59587.88 59909.01 59815.58
- #----------------------------------------------------------------
- # Benchmarking Bcast
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.03 0.03 0.03
- 1 1000 1.10 1.10 1.10
- 2 1000 1.08 1.08 1.08
- 4 1000 1.15 1.15 1.15
- 8 1000 1.08 1.08 1.08
- 16 1000 1.13 1.13 1.13
- 32 1000 1.12 1.12 1.12
- 64 1000 1.19 1.19 1.19
- 128 1000 1.16 1.16 1.16
- 256 1000 1.21 1.21 1.21
- 512 1000 1.35 1.35 1.35
- 1024 1000 1.65 1.65 1.65
- 2048 1000 1.88 1.89 1.89
- 4096 1000 2.52 2.52 2.52
- 8192 1000 4.00 4.00 4.00
- 16384 1000 7.29 7.29 7.29
- 32768 1000 15.36 15.36 15.36
- 65536 640 28.28 28.29 28.29
- 131072 320 50.62 50.63 50.63
- 262144 160 110.22 110.24 110.23
- 524288 80 190.03 190.08 190.05
- 1048576 40 356.30 356.40 356.35
- 2097152 20 693.15 693.36 693.26
- 4194304 10 1742.91 1743.39 1743.15
- #----------------------------------------------------------------
- # Benchmarking Bcast
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.03 0.03 0.03
- 1 1000 1.25 1.26 1.25
- 2 1000 1.24 1.25 1.24
- 4 1000 1.34 1.34 1.34
- 8 1000 1.26 1.26 1.26
- 16 1000 1.31 1.31 1.31
- 32 1000 1.35 1.35 1.35
- 64 1000 1.37 1.37 1.37
- 128 1000 1.42 1.42 1.42
- 256 1000 1.50 1.50 1.50
- 512 1000 1.74 1.74 1.74
- 1024 1000 2.05 2.05 2.05
- 2048 1000 2.63 2.63 2.63
- 4096 1000 3.58 3.58 3.58
- 8192 1000 5.76 5.76 5.76
- 16384 1000 11.96 11.96 11.96
- 32768 1000 24.59 24.60 24.59
- 65536 640 45.81 45.82 45.82
- 131072 320 85.04 85.06 85.05
- 262144 160 189.96 190.02 189.99
- 524288 80 394.31 394.42 394.37
- 1048576 40 845.10 845.35 845.22
- 2097152 20 1790.45 1791.45 1790.95
- 4194304 10 3985.60 3987.50 3986.55
- #----------------------------------------------------------------
- # Benchmarking Bcast
- # #processes = 8
- #----------------------------------------------------------------
- #bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 0 1000 0.03 0.03 0.03
- 1 1000 1.74 1.74 1.74
- 2 1000 1.82 1.82 1.82
- 4 1000 1.75 1.75 1.75
- 8 1000 1.77 1.77 1.77
- 16 1000 1.82 1.82 1.82
- 32 1000 1.85 1.85 1.85
- 64 1000 1.94 1.94 1.94
- 128 1000 1.98 1.98 1.98
- 256 1000 2.08 2.08 2.08
- 512 1000 2.45 2.45 2.45
- 1024 1000 2.96 2.96 2.96
- 2048 1000 3.86 3.86 3.86
- 4096 1000 5.63 5.64 5.63
- 8192 1000 9.18 9.19 9.19
- 16384 1000 14.26 14.27 14.26
- 32768 1000 29.79 29.81 29.80
- 65536 640 63.94 63.96 63.95
- 131072 320 126.47 126.49 126.48
- 262144 160 340.98 341.19 341.11
- 524288 80 542.50 543.02 542.80
- 1048576 40 1208.90 1209.75 1209.35
- 2097152 20 3724.44 3732.96 3728.42
- 4194304 10 7420.99 7430.60 7425.71
- #---------------------------------------------------
- # Benchmarking Barrier
- # #processes = 2
- # ( 6 additional processes waiting in MPI_Barrier)
- #---------------------------------------------------
- #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 1000 1.69 1.70 1.69
- #---------------------------------------------------
- # Benchmarking Barrier
- # #processes = 4
- # ( 4 additional processes waiting in MPI_Barrier)
- #---------------------------------------------------
- #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 1000 2.98 2.98 2.98
- #---------------------------------------------------
- # Benchmarking Barrier
- # #processes = 8
- #---------------------------------------------------
- #repetitions t_min[usec] t_max[usec] t_avg[usec]
- 1000 4.95 4.95 4.95
- # All processes entering MPI_Finalize
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement