Skip to content

Instantly share code, notes, and snippets.

@wdv4758h
Created May 31, 2015 07:56
Show Gist options
  • Select an option

  • Save wdv4758h/9ba4bb2b7df273be64bf to your computer and use it in GitHub Desktop.

Select an option

Save wdv4758h/9ba4bb2b7df273be64bf to your computer and use it in GitHub Desktop.
Intel MPI Benchmark result
#------------------------------------------------------------
# Intel (R) MPI Benchmarks 4.0 Update 1, MPI-1 part
#------------------------------------------------------------
# Date : Sun May 31 15:54:04 2015
# Machine : x86_64
# System : Linux
# Release : 3.10.0-229.4.2.el7.x86_64
# Version : #1 SMP Tue May 12 12:10:40 CDT 2015
# 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:
# /home/tscc/imb/src/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 0.39 0.00
1 1000 0.40 2.39
2 1000 0.37 5.14
4 1000 0.37 10.31
8 1000 0.37 20.43
16 1000 0.37 41.08
32 1000 0.42 72.56
64 1000 0.48 126.76
128 1000 0.48 254.60
256 1000 0.51 480.08
512 1000 0.62 782.43
1024 1000 0.71 1368.76
2048 1000 0.91 2148.72
4096 1000 1.43 2729.76
8192 1000 2.35 3325.86
16384 1000 3.95 3958.20
32768 1000 5.99 5219.18
65536 640 8.46 7388.89
131072 320 16.88 7405.36
262144 160 23.76 10520.61
524288 80 41.33 12099.10
1048576 40 75.20 13297.84
2097152 20 159.65 12527.79
4194304 10 637.60 6273.50
#---------------------------------------------------
# Benchmarking PingPing
# #processes = 2
#---------------------------------------------------
#bytes #repetitions t[usec] Mbytes/sec
0 1000 0.31 0.00
1 1000 0.31 3.06
2 1000 0.31 6.09
4 1000 0.31 12.27
8 1000 0.31 24.62
16 1000 0.31 49.23
32 1000 0.32 94.46
64 1000 0.32 188.37
128 1000 0.32 379.26
256 1000 0.34 722.65
512 1000 0.40 1226.35
1024 1000 0.47 2096.21
2048 1000 0.58 3361.51
4096 1000 0.94 4177.46
8192 1000 1.41 5537.01
16384 1000 2.27 6871.04
32768 1000 4.46 7000.59
65536 640 11.47 5448.92
131072 320 19.95 6266.70
262144 160 37.23 6714.92
524288 80 68.31 7319.26
1048576 40 130.90 7639.20
2097152 20 300.35 6658.95
4194304 10 1272.99 3142.21
#-----------------------------------------------------------------------------
# Benchmarking Sendrecv
# #processes = 2
#-----------------------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 0.25 0.25 0.25 0.00
1 1000 0.28 0.28 0.28 6.81
2 1000 0.27 0.27 0.27 13.88
4 1000 0.27 0.27 0.27 27.83
8 1000 0.27 0.27 0.27 55.90
16 1000 0.27 0.27 0.27 111.40
32 1000 0.28 0.28 0.28 221.84
64 1000 0.28 0.28 0.28 432.80
128 1000 0.29 0.29 0.29 844.88
256 1000 0.30 0.30 0.30 1601.25
512 1000 0.36 0.36 0.36 2682.38
1024 1000 0.42 0.42 0.42 4705.34
2048 1000 0.54 0.54 0.54 7262.41
4096 1000 0.80 0.80 0.80 9729.22
8192 1000 1.25 1.25 1.25 12521.21
16384 1000 2.21 2.21 2.21 14127.18
32768 1000 3.84 3.84 3.84 16289.32
65536 640 11.12 11.12 11.12 11242.15
131072 320 19.39 19.40 19.40 12888.70
262144 160 36.07 36.08 36.07 13858.02
524288 80 66.36 66.39 66.38 15063.04
1048576 40 127.58 127.63 127.60 15670.85
2097152 20 294.40 294.55 294.48 13579.84
4194304 10 1278.21 1278.61 1278.41 6256.77
#-----------------------------------------------------------------------------
# Benchmarking Exchange
# #processes = 2
#-----------------------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 0.58 0.58 0.58 0.00
1 1000 0.59 0.59 0.59 6.44
2 1000 0.59 0.59 0.59 12.93
4 1000 0.59 0.59 0.59 25.78
8 1000 0.59 0.59 0.59 51.55
16 1000 0.60 0.60 0.60 102.56
32 1000 0.63 0.63 0.63 194.09
64 1000 0.65 0.65 0.65 373.31
128 1000 0.69 0.69 0.69 711.85
256 1000 0.70 0.70 0.70 1395.10
512 1000 0.76 0.76 0.76 2563.20
1024 1000 0.88 0.88 0.88 4424.52
2048 1000 1.07 1.07 1.07 7294.75
4096 1000 1.56 1.56 1.56 10022.33
8192 1000 2.34 2.34 2.34 13337.95
16384 1000 3.91 3.92 3.92 15960.06
32768 1000 8.29 8.29 8.29 15081.78
65536 640 23.12 23.13 23.12 10810.76
131072 320 39.99 40.00 40.00 12500.95
262144 160 72.37 72.38 72.37 13815.80
524288 80 132.69 132.72 132.71 15068.79
1048576 40 272.60 272.67 272.64 14669.57
2097152 20 919.80 919.90 919.85 8696.58
4194304 10 3203.20 3203.61 3203.40 4994.37
#----------------------------------------------------------------
# Benchmarking Allreduce
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.03 0.03 0.03
4 1000 0.40 0.40 0.40
8 1000 0.40 0.40 0.40
16 1000 0.39 0.39 0.39
32 1000 0.41 0.41 0.41
64 1000 0.42 0.42 0.42
128 1000 0.46 0.46 0.46
256 1000 0.49 0.49 0.49
512 1000 0.54 0.54 0.54
1024 1000 0.60 0.60 0.60
2048 1000 0.76 0.76 0.76
4096 1000 1.09 1.09 1.09
8192 1000 1.83 1.83 1.83
16384 1000 3.05 3.05 3.05
32768 1000 5.81 5.81 5.81
65536 640 10.88 10.88 10.88
131072 320 29.08 29.08 29.08
262144 160 59.16 59.18 59.17
524288 80 114.36 114.39 114.37
1048576 40 230.82 230.87 230.85
2097152 20 1058.80 1059.29 1059.05
4194304 10 4410.31 4410.72 4410.52
#----------------------------------------------------------------
# Benchmarking Reduce
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.03 0.03 0.03
4 1000 0.29 0.29 0.29
8 1000 0.29 0.29 0.29
16 1000 0.28 0.28 0.28
32 1000 0.30 0.30 0.30
64 1000 0.31 0.31 0.31
128 1000 0.33 0.33 0.33
256 1000 0.35 0.35 0.35
512 1000 0.42 0.42 0.42
1024 1000 0.47 0.47 0.47
2048 1000 0.63 0.63 0.63
4096 1000 0.93 0.93 0.93
8192 1000 1.53 1.53 1.53
16384 1000 2.78 2.78 2.78
32768 1000 4.36 4.37 4.37
65536 640 7.35 7.35 7.35
131072 320 14.38 14.40 14.39
262144 160 27.77 27.84 27.80
524288 80 54.77 55.05 54.91
1048576 40 128.20 129.52 128.86
2097152 20 662.45 678.25 670.35
4194304 10 1885.99 1940.39 1913.19
#----------------------------------------------------------------
# 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 0.36 0.41 0.39
8 1000 0.45 0.45 0.45
16 1000 0.44 0.44 0.44
32 1000 0.44 0.44 0.44
64 1000 0.46 0.46 0.46
128 1000 0.47 0.47 0.47
256 1000 0.52 0.52 0.52
512 1000 0.55 0.55 0.55
1024 1000 0.62 0.62 0.62
2048 1000 0.70 0.70 0.70
4096 1000 0.87 0.87 0.87
8192 1000 1.23 1.23 1.23
16384 1000 1.99 1.99 1.99
32768 1000 3.29 3.29 3.29
65536 640 6.17 6.17 6.17
131072 320 16.57 16.57 16.57
262144 160 31.88 31.89 31.88
524288 80 61.21 61.24 61.23
1048576 40 117.85 117.90 117.88
2097152 20 320.74 321.20 320.97
4194304 10 1998.50 1999.50 1999.00
#----------------------------------------------------------------
# Benchmarking Allgather
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.03 0.03 0.03
1 1000 0.32 0.32 0.32
2 1000 0.32 0.32 0.32
4 1000 0.32 0.32 0.32
8 1000 0.32 0.32 0.32
16 1000 0.32 0.32 0.32
32 1000 0.36 0.36 0.36
64 1000 0.36 0.36 0.36
128 1000 0.37 0.37 0.37
256 1000 0.39 0.39 0.39
512 1000 0.45 0.45 0.45
1024 1000 0.51 0.51 0.51
2048 1000 0.65 0.65 0.65
4096 1000 0.93 0.93 0.93
8192 1000 1.57 1.57 1.57
16384 1000 2.71 2.71 2.71
32768 1000 4.94 4.94 4.94
65536 640 13.42 13.42 13.42
131072 320 25.56 25.57 25.56
262144 160 49.82 49.84 49.83
524288 80 94.49 94.51 94.50
1048576 40 188.20 188.27 188.24
2097152 20 853.86 854.46 854.16
4194304 10 3588.20 3588.70 3588.45
#----------------------------------------------------------------
# Benchmarking Allgatherv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.03 0.04 0.03
1 1000 0.33 0.33 0.33
2 1000 0.33 0.33 0.33
4 1000 0.32 0.32 0.32
8 1000 0.33 0.33 0.33
16 1000 0.33 0.33 0.33
32 1000 0.34 0.34 0.34
64 1000 0.37 0.37 0.37
128 1000 0.38 0.38 0.38
256 1000 0.40 0.40 0.40
512 1000 0.46 0.46 0.46
1024 1000 0.51 0.51 0.51
2048 1000 0.66 0.66 0.66
4096 1000 0.93 0.93 0.93
8192 1000 1.58 1.58 1.58
16384 1000 2.69 2.69 2.69
32768 1000 4.92 4.92 4.92
65536 640 13.35 13.36 13.36
131072 320 25.56 25.56 25.56
262144 160 50.01 50.03 50.02
524288 80 93.89 93.91 93.90
1048576 40 182.72 182.80 182.76
2097152 20 816.35 817.10 816.72
4194304 10 3585.10 3585.41 3585.26
#----------------------------------------------------------------
# Benchmarking Gather
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.04 0.04 0.04
1 1000 0.23 0.23 0.23
2 1000 0.24 0.24 0.24
4 1000 0.22 0.22 0.22
8 1000 0.22 0.22 0.22
16 1000 0.22 0.22 0.22
32 1000 0.24 0.24 0.24
64 1000 0.25 0.25 0.25
128 1000 0.25 0.25 0.25
256 1000 0.27 0.27 0.27
512 1000 0.34 0.34 0.34
1024 1000 0.38 0.38 0.38
2048 1000 0.51 0.51 0.51
4096 1000 0.76 0.76 0.76
8192 1000 1.18 1.18 1.18
16384 1000 2.05 2.05 2.05
32768 1000 3.59 3.59 3.59
65536 640 6.49 6.49 6.49
131072 320 13.52 13.53 13.52
262144 160 26.97 26.98 26.97
524288 80 55.14 55.16 55.15
1048576 40 112.53 112.58 112.55
2097152 20 490.36 491.36 490.86
4194304 10 1949.41 1949.79 1949.60
#----------------------------------------------------------------
# Benchmarking Gatherv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.06 0.06 0.06
1 1000 0.23 0.23 0.23
2 1000 0.23 0.24 0.24
4 1000 0.24 0.24 0.24
8 1000 0.24 0.24 0.24
16 1000 0.24 0.24 0.24
32 1000 0.25 0.25 0.25
64 1000 0.26 0.26 0.26
128 1000 0.27 0.27 0.27
256 1000 0.29 0.29 0.29
512 1000 0.35 0.35 0.35
1024 1000 0.39 0.39 0.39
2048 1000 0.52 0.52 0.52
4096 1000 0.76 0.76 0.76
8192 1000 1.17 1.17 1.17
16384 1000 2.05 2.05 2.05
32768 1000 3.60 3.60 3.60
65536 640 6.56 6.56 6.56
131072 320 13.54 13.54 13.54
262144 160 27.02 27.03 27.03
524288 80 55.14 55.16 55.15
1048576 40 112.61 112.68 112.64
2097152 20 489.54 490.64 490.09
4194304 10 1955.89 1956.58 1956.24
#----------------------------------------------------------------
# Benchmarking Scatter
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.03 0.03 0.03
1 1000 0.26 0.26 0.26
2 1000 0.25 0.25 0.25
4 1000 0.24 0.24 0.24
8 1000 0.24 0.24 0.24
16 1000 0.24 0.24 0.24
32 1000 0.27 0.27 0.27
64 1000 0.28 0.28 0.28
128 1000 0.29 0.29 0.29
256 1000 0.31 0.31 0.31
512 1000 0.36 0.36 0.36
1024 1000 0.41 0.41 0.41
2048 1000 0.57 0.57 0.57
4096 1000 0.85 0.85 0.85
8192 1000 1.51 1.51 1.51
16384 1000 2.73 2.73 2.73
32768 1000 4.84 4.84 4.84
65536 640 8.31 8.32 8.31
131072 320 15.74 15.75 15.75
262144 160 30.71 30.72 30.71
524288 80 58.76 58.79 58.77
1048576 40 117.37 117.42 117.40
2097152 20 515.06 515.20 515.13
4194304 10 1970.60 1970.79 1970.70
#----------------------------------------------------------------
# Benchmarking Scatterv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.07 0.07 0.07
1 1000 0.27 0.27 0.27
2 1000 0.25 0.25 0.25
4 1000 0.26 0.26 0.26
8 1000 0.26 0.26 0.26
16 1000 0.26 0.26 0.26
32 1000 0.28 0.28 0.28
64 1000 0.29 0.29 0.29
128 1000 0.30 0.30 0.30
256 1000 0.32 0.32 0.32
512 1000 0.38 0.38 0.38
1024 1000 0.42 0.42 0.42
2048 1000 0.56 0.56 0.56
4096 1000 0.83 0.83 0.83
8192 1000 1.36 1.36 1.36
16384 1000 2.40 2.40 2.40
32768 1000 4.22 4.22 4.22
65536 640 8.20 8.20 8.20
131072 320 15.62 15.63 15.62
262144 160 30.68 30.69 30.68
524288 80 58.77 58.80 58.79
1048576 40 116.68 116.73 116.70
2097152 20 513.70 513.90 513.80
4194304 10 1859.50 1860.00 1859.75
#----------------------------------------------------------------
# Benchmarking Alltoall
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.03 0.03 0.03
1 1000 0.33 0.33 0.33
2 1000 0.32 0.32 0.32
4 1000 0.32 0.32 0.32
8 1000 0.32 0.32 0.32
16 1000 0.32 0.32 0.32
32 1000 0.33 0.33 0.33
64 1000 0.34 0.34 0.34
128 1000 0.35 0.35 0.35
256 1000 0.37 0.37 0.37
512 1000 0.42 0.42 0.42
1024 1000 0.48 0.48 0.48
2048 1000 0.62 0.62 0.62
4096 1000 0.93 0.93 0.93
8192 1000 1.60 1.61 1.60
16384 1000 2.79 2.79 2.79
32768 1000 4.95 4.95 4.95
65536 640 14.16 14.16 14.16
131072 320 26.18 26.19 26.19
262144 160 48.73 48.74 48.73
524288 80 92.52 92.56 92.54
1048576 40 216.98 217.05 217.01
2097152 20 1653.65 1653.90 1653.77
4194304 10 4274.49 4274.99 4274.74
#----------------------------------------------------------------
# Benchmarking Alltoallv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.14 0.16 0.15
1 1000 0.53 0.53 0.53
2 1000 0.53 0.53 0.53
4 1000 0.54 0.54 0.54
8 1000 0.53 0.53 0.53
16 1000 0.53 0.53 0.53
32 1000 0.55 0.55 0.55
64 1000 0.57 0.57 0.57
128 1000 0.58 0.58 0.58
256 1000 0.61 0.61 0.61
512 1000 0.65 0.65 0.65
1024 1000 0.70 0.70 0.70
2048 1000 0.85 0.85 0.85
4096 1000 1.19 1.19 1.19
8192 1000 1.81 1.81 1.81
16384 1000 2.96 2.96 2.96
32768 1000 5.11 5.11 5.11
65536 640 14.53 14.54 14.53
131072 320 26.13 26.13 26.13
262144 160 48.94 48.95 48.94
524288 80 91.91 91.94 91.93
1048576 40 216.83 216.90 216.87
2097152 20 1654.76 1655.05 1654.91
4194304 10 4271.10 4271.60 4271.35
#----------------------------------------------------------------
# Benchmarking Bcast
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.02 0.02 0.02
1 1000 0.24 0.24 0.24
2 1000 0.25 0.25 0.25
4 1000 0.24 0.24 0.24
8 1000 0.24 0.24 0.24
16 1000 0.24 0.24 0.24
32 1000 0.27 0.27 0.27
64 1000 0.28 0.28 0.28
128 1000 0.28 0.28 0.28
256 1000 0.30 0.30 0.30
512 1000 0.36 0.36 0.36
1024 1000 0.40 0.40 0.40
2048 1000 0.54 0.54 0.54
4096 1000 0.80 0.80 0.80
8192 1000 1.33 1.33 1.33
16384 1000 2.33 2.33 2.33
32768 1000 3.87 3.87 3.87
65536 640 5.82 5.82 5.82
131072 320 9.87 9.87 9.87
262144 160 18.33 18.34 18.34
524288 80 33.45 33.47 33.46
1048576 40 63.63 63.68 63.65
2097152 20 139.51 139.65 139.58
4194304 10 645.18 645.59 645.39
#---------------------------------------------------
# Benchmarking Barrier
# #processes = 2
#---------------------------------------------------
#repetitions t_min[usec] t_max[usec] t_avg[usec]
1000 0.25 0.25 0.25
# All processes entering MPI_Finalize
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment