Application Kernel Remote Runner (AKRR) Module 2.1.1
Example of appstdout from IMB
===ExeBinSignature=== MD5: bf9d0e2c36a9b3d3a2f56ba4f0935577 /projects/ccrstaff/general/nikolays/huey/appker/execs/mpi-benchmarks-IMB-v2019.2/IMB-MPI1
===ExeBinSignature=== MD5: ebc6518301d43233b1de262f6cfdbfcc /util/academic/intel/18.3/compilers_and_libraries_2018.3.222/linux/mpi/intel64/lib/libmpicxx.so.12
===ExeBinSignature=== MD5: 0f65391c22de4d15744ea80ec857419a /util/academic/intel/18.3/compilers_and_libraries_2018.3.222/linux/mpi/intel64/lib/libmpifort.so.12
===ExeBinSignature=== MD5: d9196e5f82db2befd02eb55c78747724 /util/academic/intel/18.3/compilers_and_libraries_2018.3.222/linux/mpi/intel64/lib/release_mt/libmpi.so.12
===ExeBinSignature=== MD5: bbb4814755042554781fce1b1da6fdb1 /lib64/libdl.so.2
===ExeBinSignature=== MD5: 5928d7f9554dde0b45bc87ac09598ad0 /lib64/librt.so.1
===ExeBinSignature=== MD5: 23902bbccc0e350c1fdf09d070f3cd48 /lib64/libpthread.so.0
===ExeBinSignature=== MD5: b06038960f153e36545ed9ea947f80f6 /lib64/libstdc++.so.6
===ExeBinSignature=== MD5: 2705d15430ebce01274ef94967122bcb /lib64/libm.so.6
===ExeBinSignature=== MD5: c8f2c137eee1a4581bc0be7b63d2c603 /lib64/libgcc_s.so.1
===ExeBinSignature=== MD5: a2737e5fc2c2059bd357ef6015c99262 /lib64/libc.so.6
===ExeBinSignature=== MD5: 2a9b682ef82e8972466e91c305ffaaff /projects/ccrstaff/general/nikolays/huey/appker/execs/mpi-benchmarks-IMB-v2019.2/IMB-EXT
===ExeBinSignature=== MD5: ebc6518301d43233b1de262f6cfdbfcc /util/academic/intel/18.3/compilers_and_libraries_2018.3.222/linux/mpi/intel64/lib/libmpicxx.so.12
===ExeBinSignature=== MD5: 0f65391c22de4d15744ea80ec857419a /util/academic/intel/18.3/compilers_and_libraries_2018.3.222/linux/mpi/intel64/lib/libmpifort.so.12
===ExeBinSignature=== MD5: d9196e5f82db2befd02eb55c78747724 /util/academic/intel/18.3/compilers_and_libraries_2018.3.222/linux/mpi/intel64/lib/release_mt/libmpi.so.12
===ExeBinSignature=== MD5: bbb4814755042554781fce1b1da6fdb1 /lib64/libdl.so.2
===ExeBinSignature=== MD5: 5928d7f9554dde0b45bc87ac09598ad0 /lib64/librt.so.1
===ExeBinSignature=== MD5: 23902bbccc0e350c1fdf09d070f3cd48 /lib64/libpthread.so.0
===ExeBinSignature=== MD5: b06038960f153e36545ed9ea947f80f6 /lib64/libstdc++.so.6
===ExeBinSignature=== MD5: 2705d15430ebce01274ef94967122bcb /lib64/libm.so.6
===ExeBinSignature=== MD5: c8f2c137eee1a4581bc0be7b63d2c603 /lib64/libgcc_s.so.1
===ExeBinSignature=== MD5: a2737e5fc2c2059bd357ef6015c99262 /lib64/libc.so.6
#------------------------------------------------------------
# Intel(R) MPI Benchmarks 2019 Update 2, MPI-1 part
#------------------------------------------------------------
# Date : Fri Mar 22 15:08:42 2019
# Machine : x86_64
# System : Linux
# Release : 3.10.0-957.1.3.el7.x86_64
# Version : #1 SMP Thu Nov 29 14:49:43 UTC 2018
# MPI Version : 3.1
# MPI Thread Environment:
# Calling sequence was:
# /projects/ccrstaff/general/nikolays/huey/appker/execs/imb/IMB-MPI1 -multi 0 -npmin 2 -iter 1000
# 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_local
# Reduce_scatter
# Reduce_scatter_block
# Allgather
# Allgatherv
# Gather
# Gatherv
# Scatter
# Scatterv
# Alltoall
# Alltoallv
# Bcast
# Barrier
#-----------------------------------------------------------------------------
# Benchmarking PingPong
# #processes = 2
#-----------------------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 2.08 2.08 2.08 0.00
1 1000 2.06 2.06 2.06 0.49
2 1000 1.91 1.91 1.91 1.05
4 1000 1.94 1.94 1.94 2.06
8 1000 1.89 1.90 1.89 4.22
16 1000 1.92 1.92 1.92 8.32
32 1000 3.61 3.62 3.61 8.85
64 1000 3.38 3.38 3.38 18.96
128 1000 3.31 3.31 3.31 38.70
256 1000 3.48 3.48 3.48 73.64
512 1000 3.64 3.64 3.64 140.70
1024 1000 4.05 4.05 4.05 253.03
2048 1000 5.22 5.22 5.22 392.53
4096 1000 6.23 6.23 6.23 657.67
8192 1000 8.46 8.46 8.46 968.26
16384 1000 11.70 11.70 11.70 1399.80
32768 1000 16.75 16.75 16.75 1955.84
65536 640 27.61 27.62 27.62 2372.48
131072 320 49.03 49.06 49.05 2671.62
262144 160 236.37 236.56 236.46 1108.14
524288 80 341.77 341.77 341.77 1534.04
1048576 40 544.47 544.51 544.49 1925.72
2097152 20 998.53 999.48 999.00 2098.24
4194304 10 1825.09 1825.95 1825.52 2297.05
#-----------------------------------------------------------------------------
# Benchmarking PingPing
# #processes = 2
#-----------------------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 1.97 1.97 1.97 0.00
1 1000 1.98 1.99 1.98 0.50
2 1000 2.02 2.02 2.02 0.99
4 1000 2.01 2.01 2.01 1.99
8 1000 2.14 2.14 2.14 3.74
16 1000 2.25 2.25 2.25 7.10
32 1000 3.59 3.59 3.59 8.91
64 1000 3.42 3.43 3.42 18.68
128 1000 3.76 3.82 3.79 33.49
256 1000 3.78 3.78 3.78 67.67
512 1000 4.03 4.04 4.04 126.86
1024 1000 4.50 4.50 4.50 227.61
2048 1000 6.91 6.91 6.91 296.20
4096 1000 6.78 6.78 6.78 604.12
8192 1000 9.16 9.17 9.17 893.44
16384 1000 12.63 12.63 12.63 1296.72
32768 1000 18.34 18.35 18.34 1786.20
65536 640 30.21 30.22 30.21 2168.82
131072 320 65.08 65.11 65.10 2013.11
262144 160 289.57 289.58 289.57 905.26
524288 80 416.79 416.81 416.80 1257.85
1048576 40 649.25 650.57 649.91 1611.77
2097152 20 1116.41 1116.55 1116.48 1878.24
4194304 10 2098.61 2099.49 2099.05 1997.77
#-----------------------------------------------------------------------------
# Benchmarking Sendrecv
# #processes = 2
#-----------------------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 2.07 2.07 2.07 0.00
1 1000 2.06 2.06 2.06 0.97
2 1000 2.05 2.05 2.05 1.95
4 1000 2.10 2.10 2.10 3.81
8 1000 2.43 2.43 2.43 6.58
16 1000 2.16 2.16 2.16 14.82
32 1000 3.40 3.40 3.40 18.81
64 1000 3.40 3.41 3.40 37.59
128 1000 3.84 3.84 3.84 66.72
256 1000 3.91 3.91 3.91 130.85
512 1000 4.06 4.06 4.06 252.21
1024 1000 4.54 4.54 4.54 450.61
2048 1000 5.68 5.68 5.68 720.72
4096 1000 6.78 6.79 6.79 1206.66
8192 1000 9.50 9.51 9.51 1722.81
16384 1000 12.50 12.50 12.50 2620.58
32768 1000 18.17 18.17 18.17 3606.42
65536 640 29.87 29.88 29.88 4386.86
131072 320 60.78 60.80 60.79 4311.60
262144 160 289.90 289.90 289.90 1808.51
524288 80 409.70 409.76 409.73 2558.99
1048576 40 643.35 643.38 643.36 3259.59
2097152 20 1118.55 1118.60 1118.58 3749.60
4194304 10 2083.80 2084.09 2083.95 4025.07
#-----------------------------------------------------------------------------
# Benchmarking Exchange
# #processes = 2
#-----------------------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 2.48 2.48 2.48 0.00
1 1000 2.48 2.48 2.48 1.62
2 1000 2.53 2.53 2.53 3.16
4 1000 2.71 2.71 2.71 5.90
8 1000 3.08 3.08 3.08 10.39
16 1000 2.93 2.93 2.93 21.83
32 1000 4.20 4.20 4.20 30.48
64 1000 4.07 4.07 4.07 62.93
128 1000 4.35 4.35 4.35 117.73
256 1000 4.59 4.59 4.59 223.18
512 1000 4.84 4.84 4.84 423.32
1024 1000 5.69 5.69 5.69 719.33
2048 1000 7.17 7.17 7.17 1142.05
4096 1000 8.92 8.92 8.92 1836.78
8192 1000 12.54 12.54 12.54 2612.46
16384 1000 18.46 18.47 18.47 3548.78
32768 1000 29.72 29.72 29.72 4410.54
65536 640 54.06 54.07 54.07 4848.24
131072 320 198.48 198.74 198.61 2638.01
262144 160 577.41 577.42 577.42 1815.97
524288 80 818.43 818.44 818.43 2562.39
1048576 40 1307.30 1307.43 1307.36 3208.06
2097152 20 2245.56 2245.75 2245.65 3735.33
4194304 10 4350.61 4355.91 4353.26 3851.60
#----------------------------------------------------------------
# Benchmarking Allreduce
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.13 0.17 0.15
4 1000 2.08 3.63 2.86
8 1000 2.07 3.33 2.70
16 1000 2.44 4.33 3.38
32 1000 3.61 4.33 3.97
64 1000 3.58 4.34 3.96
128 1000 3.47 5.39 4.43
256 1000 4.39 4.50 4.45
512 1000 4.34 4.86 4.60
1024 1000 3.73 5.97 4.85
2048 1000 5.20 7.31 6.26
4096 1000 6.59 8.22 7.41
8192 1000 9.58 10.59 10.08
16384 1000 15.03 15.86 15.44
32768 1000 45.87 45.91 45.89
65536 640 78.74 78.78 78.76
131072 320 143.44 143.67 143.55
262144 160 288.82 290.18 289.50
524288 80 950.15 954.51 952.33
1048576 40 1545.40 1552.96 1549.18
2097152 20 2719.68 2727.22 2723.45
4194304 10 5277.42 5283.38 5280.40
#----------------------------------------------------------------
# Benchmarking Reduce
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.10 0.10 0.10
4 1000 0.78 3.32 2.05
8 1000 0.77 3.32 2.05
16 1000 0.85 3.44 2.15
32 1000 1.05 4.84 2.95
64 1000 1.16 5.00 3.08
128 1000 1.15 5.13 3.14
256 1000 1.49 5.73 3.61
512 1000 1.31 5.61 3.46
1024 1000 1.26 6.06 3.66
2048 1000 1.31 8.38 4.85
4096 1000 1.30 8.29 4.79
8192 1000 1.63 10.45 6.04
16384 1000 4.48 14.73 9.60
32768 1000 6.89 19.61 13.25
65536 640 13.98 30.11 22.05
131072 320 29.87 53.14 41.50
262144 160 67.92 94.35 81.13
524288 80 149.92 176.56 163.24
1048576 40 309.88 337.53 323.71
2097152 20 634.80 662.65 648.73
4194304 10 1471.52 1503.73 1487.62
#----------------------------------------------------------------
# Benchmarking Reduce_local
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.06 0.07 0.07
4 1000 0.07 0.09 0.08
8 1000 0.07 0.08 0.07
16 1000 0.09 0.10 0.09
32 1000 0.09 0.09 0.09
64 1000 0.10 0.12 0.11
128 1000 0.09 0.12 0.11
256 1000 0.13 0.13 0.13
512 1000 0.14 0.15 0.14
1024 1000 0.18 0.20 0.19
2048 1000 0.29 0.31 0.30
4096 1000 0.53 0.53 0.53
8192 1000 0.98 0.99 0.98
16384 1000 2.25 2.25 2.25
32768 1000 4.58 4.98 4.78
65536 640 8.52 9.21 8.86
131072 320 18.12 19.14 18.63
262144 160 37.55 43.29 40.42
524288 80 80.97 92.64 86.80
1048576 40 154.06 201.57 177.82
2097152 20 312.92 334.24 323.58
4194304 10 774.77 789.52 782.14
#----------------------------------------------------------------
# Benchmarking Reduce_scatter
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.24 0.33 0.29
4 1000 2.24 3.07 2.65
8 1000 2.30 3.33 2.82
16 1000 1.97 3.57 2.77
32 1000 3.84 4.31 4.08
64 1000 3.69 4.44 4.07
128 1000 3.78 4.90 4.34
256 1000 3.96 5.39 4.68
512 1000 4.36 5.63 4.99
1024 1000 4.84 5.79 5.31
2048 1000 6.41 6.54 6.48
4096 1000 7.57 7.73 7.65
8192 1000 11.09 11.39 11.24
16384 1000 15.81 15.98 15.89
32768 1000 40.06 40.58 40.32
65536 640 75.43 75.56 75.49
131072 320 154.52 154.68 154.60
262144 160 484.78 486.98 485.88
524288 80 789.73 790.04 789.88
1048576 40 1405.60 1407.07 1406.34
2097152 20 2714.10 2788.35 2751.23
4194304 10 5483.29 5520.96 5502.13
#----------------------------------------------------------------
# Benchmarking Reduce_scatter_block
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.10 0.13 0.11
4 1000 1.61 3.72 2.67
8 1000 1.65 3.67 2.66
16 1000 1.69 3.64 2.66
32 1000 3.04 4.84 3.94
64 1000 3.15 4.85 4.00
128 1000 3.58 5.29 4.44
256 1000 3.90 5.41 4.65
512 1000 4.58 5.55 5.07
1024 1000 4.89 5.98 5.43
2048 1000 6.29 7.94 7.12
4096 1000 8.02 9.75 8.89
8192 1000 10.75 13.08 11.92
16384 1000 34.22 34.96 34.59
32768 1000 77.07 78.59 77.83
65536 640 151.69 151.88 151.79
131072 320 300.69 303.27 301.98
262144 160 478.21 489.40 483.81
524288 80 805.86 807.85 806.85
1048576 40 1439.90 1446.66 1443.28
2097152 20 2720.18 2730.98 2725.58
4194304 10 5606.96 5648.30 5627.63
#----------------------------------------------------------------
# Benchmarking Allgather
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.16 0.17 0.16
1 1000 1.59 3.03 2.31
2 1000 1.20 3.71 2.46
4 1000 1.59 3.06 2.32
8 1000 1.43 3.30 2.37
16 1000 1.62 3.02 2.32
32 1000 2.84 4.24 3.54
64 1000 2.55 4.54 3.55
128 1000 2.83 5.05 3.94
256 1000 3.83 5.01 4.42
512 1000 3.96 5.13 4.55
1024 1000 3.96 5.60 4.78
2048 1000 5.54 6.63 6.09
4096 1000 6.68 7.08 6.88
8192 1000 8.96 10.44 9.70
16384 1000 13.15 14.60 13.88
32768 1000 35.36 38.19 36.77
65536 640 66.18 67.42 66.80
131072 320 136.32 138.27 137.29
262144 160 445.15 447.27 446.21
524288 80 725.12 727.23 726.18
1048576 40 1257.57 1263.52 1260.55
2097152 20 2356.79 2357.85 2357.32
4194304 10 4676.82 4678.56 4677.69
#----------------------------------------------------------------
# Benchmarking Allgatherv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.11 0.12 0.12
1 1000 1.54 3.73 2.63
2 1000 1.49 3.69 2.59
4 1000 1.52 3.61 2.56
8 1000 1.55 3.56 2.55
16 1000 1.61 3.83 2.72
32 1000 3.48 5.34 4.41
64 1000 3.94 4.92 4.43
128 1000 3.55 5.18 4.37
256 1000 4.52 4.56 4.54
512 1000 4.80 4.81 4.81
1024 1000 4.88 5.56 5.22
2048 1000 5.82 7.64 6.73
4096 1000 7.13 9.11 8.12
8192 1000 11.05 11.23 11.14
16384 1000 15.45 17.09 16.27
32768 1000 70.64 71.68 71.16
65536 640 136.89 140.66 138.78
131072 320 274.98 276.14 275.56
262144 160 438.23 439.55 438.89
524288 80 703.95 705.19 704.57
1048576 40 1239.51 1239.66 1239.58
2097152 20 2283.84 2287.11 2285.47
4194304 10 4576.92 4584.67 4580.80
#----------------------------------------------------------------
# Benchmarking Gather
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.15 0.16 0.16
1 1000 0.73 3.31 2.02
2 1000 0.83 3.49 2.16
4 1000 0.80 3.36 2.08
8 1000 0.84 3.43 2.14
16 1000 0.70 3.44 2.07
32 1000 0.90 4.69 2.80
64 1000 0.96 4.75 2.86
128 1000 1.00 4.95 2.98
256 1000 1.04 5.94 3.49
512 1000 0.96 5.20 3.08
1024 1000 0.81 5.56 3.19
2048 1000 0.91 6.84 3.88
4096 1000 1.05 7.77 4.41
8192 1000 1.35 9.81 5.58
16384 1000 2.75 12.99 7.87
32768 1000 6.49 24.32 15.41
65536 640 13.88 49.08 31.48
131072 320 85.49 99.64 92.57
262144 160 383.61 386.12 384.86
524288 80 633.05 633.77 633.41
1048576 40 1141.27 1142.47 1141.87
2097152 20 2158.75 2159.69 2159.22
4194304 10 4254.94 4309.25 4282.09
#----------------------------------------------------------------
# Benchmarking Gatherv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.17 0.41 0.29
1 1000 1.52 4.08 2.80
2 1000 1.57 3.90 2.74
4 1000 2.82 5.08 3.95
8 1000 2.62 4.92 3.77
16 1000 2.72 4.99 3.86
32 1000 2.63 4.90 3.77
64 1000 2.91 5.12 4.02
128 1000 3.09 5.34 4.21
256 1000 3.19 5.48 4.34
512 1000 3.38 5.63 4.50
1024 1000 3.93 6.18 5.06
2048 1000 5.01 7.29 6.15
4096 1000 5.94 8.27 7.11
8192 1000 8.04 10.22 9.13
16384 1000 9.16 12.76 10.96
32768 1000 20.09 24.49 22.29
65536 640 39.67 49.77 44.72
131072 320 79.67 99.62 89.65
262144 160 383.17 384.28 383.73
524288 80 632.09 633.28 632.69
1048576 40 1138.78 1139.68 1139.23
2097152 20 2152.79 2156.63 2154.71
4194304 10 4257.51 4296.78 4277.15
#----------------------------------------------------------------
# Benchmarking Scatter
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.12 0.13 0.12
1 1000 0.72 3.57 2.15
2 1000 0.80 3.43 2.12
4 1000 0.86 3.51 2.19
8 1000 0.80 3.43 2.11
16 1000 0.80 3.45 2.13
32 1000 0.83 4.66 2.75
64 1000 0.84 4.65 2.75
128 1000 0.89 4.83 2.86
256 1000 1.00 5.04 3.02
512 1000 1.01 5.29 3.15
1024 1000 1.15 5.78 3.47
2048 1000 1.24 6.97 4.11
4096 1000 1.43 7.77 4.60
8192 1000 2.18 9.91 6.05
16384 1000 4.09 12.84 8.46
32768 1000 24.99 37.45 31.22
65536 640 50.35 66.01 58.18
131072 320 105.48 127.29 116.38
262144 160 378.69 386.93 382.81
524288 80 631.70 638.97 635.33
1048576 40 1135.82 1146.68 1141.25
2097152 20 2142.07 2148.08 2145.08
4194304 10 4330.49 4344.08 4337.29
#----------------------------------------------------------------
# Benchmarking Scatterv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.14 0.31 0.22
1 1000 0.92 3.33 2.13
2 1000 0.91 3.31 2.11
4 1000 0.91 3.33 2.12
8 1000 0.95 3.38 2.17
16 1000 0.92 3.34 2.13
32 1000 1.03 4.64 2.83
64 1000 0.97 4.56 2.76
128 1000 1.04 5.03 3.03
256 1000 1.15 5.89 3.52
512 1000 1.13 5.42 3.28
1024 1000 1.20 5.64 3.42
2048 1000 1.30 6.83 4.06
4096 1000 1.59 7.90 4.75
8192 1000 2.32 10.31 6.31
16384 1000 5.15 14.22 9.68
32768 1000 25.00 37.28 31.14
65536 640 50.46 65.51 57.99
131072 320 105.67 127.46 116.57
262144 160 387.27 392.78 390.03
524288 80 634.41 639.78 637.09
1048576 40 1140.12 1144.12 1142.12
2097152 20 2149.89 2159.02 2154.46
4194304 10 4309.20 4314.92 4312.06
#----------------------------------------------------------------
# Benchmarking Alltoall
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.14 0.23 0.18
1 1000 1.35 3.00 2.17
2 1000 1.57 2.80 2.19
4 1000 1.10 3.25 2.17
8 1000 1.45 3.23 2.34
16 1000 1.64 3.07 2.36
32 1000 2.30 4.74 3.52
64 1000 2.32 4.76 3.54
128 1000 2.60 4.98 3.79
256 1000 2.84 5.15 3.99
512 1000 3.01 5.32 4.17
1024 1000 3.32 5.56 4.44
2048 1000 5.63 5.72 5.67
4096 1000 6.61 7.01 6.81
8192 1000 8.56 10.04 9.30
16384 1000 12.73 13.77 13.25
32768 1000 35.23 36.90 36.06
65536 640 68.85 68.87 68.86
131072 320 134.76 136.89 135.82
262144 160 446.66 446.92 446.79
524288 80 719.03 719.87 719.45
1048576 40 1264.51 1264.99 1264.75
2097152 20 2326.85 2355.93 2341.39
4194304 10 4658.29 4684.73 4671.51
#----------------------------------------------------------------
# Benchmarking Alltoallv
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.42 0.51 0.47
1 1000 2.06 3.70 2.88
2 1000 2.17 3.39 2.78
4 1000 2.20 3.38 2.79
8 1000 2.66 2.98 2.82
16 1000 2.94 2.97 2.96
32 1000 3.98 4.31 4.14
64 1000 3.09 5.10 4.10
128 1000 3.37 5.21 4.29
256 1000 4.17 4.99 4.58
512 1000 4.29 5.09 4.69
1024 1000 5.05 6.13 5.59
2048 1000 6.36 7.28 6.82
4096 1000 6.91 8.45 7.68
8192 1000 8.92 11.35 10.14
16384 1000 13.40 14.26 13.83
32768 1000 36.20 37.44 36.82
65536 640 68.86 68.93 68.89
131072 320 137.36 137.61 137.49
262144 160 456.63 458.88 457.76
524288 80 718.28 719.76 719.02
1048576 40 1262.10 1264.83 1263.47
2097152 20 2347.00 2372.91 2359.96
4194304 10 4706.31 4722.69 4714.50
#----------------------------------------------------------------
# Benchmarking Bcast
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.11 0.14 0.12
1 1000 0.67 3.32 1.99
2 1000 0.67 3.30 1.98
4 1000 0.67 3.32 1.99
8 1000 0.71 3.37 2.04
16 1000 0.71 3.36 2.04
32 1000 0.76 4.53 2.64
64 1000 0.81 4.60 2.71
128 1000 0.86 4.91 2.88
256 1000 0.89 5.01 2.95
512 1000 0.95 5.37 3.16
1024 1000 1.04 5.72 3.38
2048 1000 1.17 6.98 4.08
4096 1000 1.21 7.82 4.51
8192 1000 1.49 9.81 5.65
16384 1000 3.42 12.65 8.04
32768 1000 5.97 18.30 12.13
65536 640 13.98 28.87 21.43
131072 320 28.14 50.43 39.29
262144 160 222.74 229.54 226.14
524288 80 326.25 331.94 329.10
1048576 40 531.01 536.75 533.88
2097152 20 936.21 948.70 942.46
4194304 10 1833.32 1888.54 1860.93
#---------------------------------------------------
# Benchmarking Barrier
# #processes = 2
#---------------------------------------------------
#repetitions t_min[usec] t_max[usec] t_avg[usec]
1000 2.06 2.06 2.06
# All processes entering MPI_Finalize
#------------------------------------------------------------
# Intel(R) MPI Benchmarks 2019 Update 2, MPI-2 part
#------------------------------------------------------------
# Date : Fri Mar 22 15:09:43 2019
# Machine : x86_64
# System : Linux
# Release : 3.10.0-957.1.3.el7.x86_64
# Version : #1 SMP Thu Nov 29 14:49:43 UTC 2018
# MPI Version : 3.1
# MPI Thread Environment:
# Calling sequence was:
# /projects/ccrstaff/general/nikolays/huey/appker/execs/imb/IMB-EXT -multi 0 -npmin 2 -iter 1000
# 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:
# Window
# Unidir_Get
# Unidir_Put
# Bidir_Get
# Bidir_Put
# Accumulate
#----------------------------------------------------------------
# Benchmarking Window
# #processes = 2
#----------------------------------------------------------------
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 100 41.00 41.01 41.01
4 100 41.64 41.64 41.64
8 100 42.23 42.24 42.23
16 100 39.91 39.92 39.91
32 100 41.97 41.97 41.97
64 100 38.64 38.65 38.64
128 100 41.93 41.94 41.94
256 100 38.35 38.36 38.35
512 100 39.94 39.95 39.94
1024 100 38.72 38.72 38.72
2048 100 39.66 39.66 39.66
4096 100 39.70 39.71 39.71
8192 100 38.27 38.27 38.27
16384 100 40.79 40.79 40.79
32768 100 44.25 44.25 44.25
65536 100 39.85 39.86 39.85
131072 100 37.83 37.84 37.83
262144 100 37.18 37.18 37.18
524288 80 34.43 34.44 34.43
1048576 40 36.03 36.03 36.03
2097152 20 36.50 36.55 36.53
4194304 10 41.70 41.70 41.70
#-----------------------------------------------------------------------------
# Benchmarking Unidir_Get
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 0.07 0.08 0.07 0.00
4 1000 0.86 0.86 0.86 4.65
8 1000 0.86 0.86 0.86 9.30
16 1000 0.97 0.97 0.97 16.46
32 1000 0.91 0.92 0.91 34.93
64 1000 0.90 0.90 0.90 71.13
128 1000 0.81 0.81 0.81 157.21
256 1000 0.81 0.81 0.81 314.51
512 1000 0.87 0.87 0.87 589.97
1024 1000 0.95 0.96 0.95 1071.06
2048 1000 1.15 1.15 1.15 1779.56
4096 1000 1.61 1.62 1.62 2531.66
8192 1000 2.65 2.65 2.65 3086.85
16384 1000 5.11 5.11 5.11 3203.71
32768 1000 10.10 10.10 10.10 3244.32
65536 640 20.40 20.40 20.40 3212.54
131072 320 40.09 40.09 40.09 3269.13
262144 160 230.22 230.28 230.25 1138.37
524288 80 333.15 333.25 333.20 1573.25
1048576 40 537.03 537.20 537.11 1951.93
2097152 20 977.65 978.10 977.87 2144.11
4194304 10 1760.48 1761.39 1760.94 2381.25
#-----------------------------------------------------------------------------
# Benchmarking Unidir_Get
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: NON-AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 100 4.33 4.33 4.33 0.00
4 100 14.86 14.87 14.87 0.27
8 100 14.85 14.85 14.85 0.54
16 100 16.28 16.29 16.29 0.98
32 100 16.24 16.25 16.25 1.97
64 100 17.10 17.10 17.10 3.74
128 100 15.56 15.57 15.57 8.22
256 100 15.67 15.69 15.68 16.32
512 100 17.09 17.10 17.09 29.94
1024 100 17.38 17.38 17.38 58.92
2048 100 19.01 19.02 19.02 107.68
4096 100 19.83 19.83 19.83 206.56
8192 100 22.65 22.65 22.65 361.68
16384 100 26.47 26.49 26.48 618.48
32768 100 32.08 32.09 32.09 1021.09
65536 100 43.64 43.66 43.65 1501.08
131072 100 65.49 65.50 65.49 2001.08
262144 100 252.92 252.98 252.95 1036.22
524288 80 350.11 350.19 350.15 1497.17
1048576 40 547.55 547.70 547.63 1914.50
2097152 20 994.21 994.66 994.43 2108.41
4194304 10 1917.31 1918.51 1917.91 2186.23
#-----------------------------------------------------------------------------
# Benchmarking Unidir_Put
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 0.05 0.06 0.05 0.00
4 1000 0.51 0.51 0.51 7.77
8 1000 0.55 0.55 0.55 14.49
16 1000 0.73 0.73 0.73 22.01
32 1000 0.76 0.76 0.76 42.00
64 1000 0.76 0.76 0.76 83.89
128 1000 0.81 0.81 0.81 157.81
256 1000 0.84 0.85 0.85 299.76
512 1000 0.78 0.79 0.79 647.22
1024 1000 0.90 0.90 0.90 1135.03
2048 1000 0.98 1.01 1.00 2017.84
4096 1000 1.48 1.50 1.49 2723.50
8192 1000 2.60 2.63 2.61 3117.10
16384 1000 5.14 5.16 5.15 3175.28
32768 1000 10.11 10.12 10.11 3236.98
65536 640 20.02 20.05 20.04 3267.86
131072 320 40.10 40.18 40.14 3261.80
262144 160 229.94 229.99 229.97 1139.82
524288 80 333.05 333.14 333.09 1573.79
1048576 40 533.25 533.43 533.34 1965.74
2097152 20 974.75 975.20 974.98 2150.48
4194304 10 1752.40 1755.81 1754.11 2388.81
#-----------------------------------------------------------------------------
# Benchmarking Unidir_Put
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: NON-AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 100 4.10 4.10 4.10 0.00
4 100 9.25 9.26 9.26 0.43
8 100 9.90 9.92 9.91 0.81
16 100 11.33 11.36 11.35 1.41
32 100 12.91 12.92 12.92 2.48
64 100 12.97 12.98 12.98 4.93
128 100 12.88 12.88 12.88 9.94
256 100 13.70 13.72 13.71 18.66
512 100 13.05 13.06 13.05 39.20
1024 100 13.64 13.65 13.64 75.02
2048 100 13.39 13.41 13.40 152.74
4096 100 12.63 12.68 12.66 322.99
8192 100 13.53 13.59 13.56 602.80
16384 100 17.06 17.13 17.09 956.56
32768 100 23.16 23.22 23.19 1411.22
65536 100 33.81 33.91 33.86 1932.63
131072 100 54.72 54.86 54.79 2389.20
262144 100 263.66 263.72 263.69 994.03
524288 80 351.44 351.51 351.48 1491.52
1048576 40 548.27 548.45 548.36 1911.88
2097152 20 999.86 1000.15 1000.01 2096.83
4194304 10 1799.80 1809.29 1804.54 2318.21
#-----------------------------------------------------------------------------
# Benchmarking Bidir_Get
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 0.06 0.06 0.06 0.00
4 1000 1.18 1.18 1.18 3.38
8 1000 1.15 1.16 1.16 6.93
16 1000 1.19 1.19 1.19 13.44
32 1000 1.29 1.29 1.29 24.79
64 1000 1.34 1.34 1.34 47.90
128 1000 1.15 1.15 1.15 111.02
256 1000 1.18 1.18 1.18 216.39
512 1000 1.26 1.26 1.26 406.03
1024 1000 1.51 1.51 1.51 678.08
2048 1000 2.09 2.09 2.09 979.91
4096 1000 2.94 2.94 2.94 1393.23
8192 1000 4.51 4.51 4.51 1815.57
16384 1000 8.49 8.49 8.49 1929.56
32768 1000 14.97 14.97 14.97 2188.62
65536 640 31.40 31.41 31.41 2086.73
131072 320 59.14 59.17 59.15 2215.22
262144 160 293.09 293.11 293.10 894.36
524288 80 376.91 376.92 376.92 1390.96
1048576 40 598.72 598.90 598.81 1750.83
2097152 20 1082.25 1082.60 1082.43 1937.15
4194304 10 2058.79 2059.51 2059.15 2036.56
#-----------------------------------------------------------------------------
# Benchmarking Bidir_Get
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: NON-AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 100 4.21 4.22 4.22 0.00
4 100 13.16 13.16 13.16 0.30
8 100 14.68 14.68 14.68 0.54
16 100 14.70 14.70 14.70 1.09
32 100 16.19 16.22 16.21 1.97
64 100 16.18 16.18 16.18 3.96
128 100 17.12 17.12 17.12 7.48
256 100 17.87 17.88 17.88 14.32
512 100 17.68 17.76 17.72 28.83
1024 100 19.00 19.00 19.00 53.89
2048 100 19.93 19.93 19.93 102.75
4096 100 21.40 21.40 21.40 191.40
8192 100 24.23 24.23 24.23 338.09
16384 100 27.07 27.07 27.07 605.24
32768 100 40.49 40.51 40.50 808.89
65536 100 50.59 50.59 50.59 1295.43
131072 100 87.26 87.27 87.26 1501.94
262144 100 310.53 310.58 310.55 844.04
524288 80 421.66 421.72 421.69 1243.20
1048576 40 650.00 650.15 650.08 1612.82
2097152 20 1119.90 1120.05 1119.98 1872.37
4194304 10 2086.02 2086.69 2086.35 2010.03
#-----------------------------------------------------------------------------
# Benchmarking Bidir_Put
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 1000 0.05 0.05 0.05 0.00
4 1000 0.56 0.57 0.57 7.07
8 1000 0.71 0.71 0.71 11.22
16 1000 0.68 0.69 0.69 23.32
32 1000 0.67 0.67 0.67 47.54
64 1000 0.87 0.87 0.87 73.56
128 1000 0.83 0.83 0.83 153.48
256 1000 1.15 1.15 1.15 222.03
512 1000 0.99 1.00 1.00 514.49
1024 1000 1.29 1.29 1.29 791.41
2048 1000 1.84 1.84 1.84 1115.43
4096 1000 2.61 2.61 2.61 1569.94
8192 1000 4.42 4.42 4.42 1853.78
16384 1000 7.87 7.87 7.87 2080.77
32768 1000 13.87 13.87 13.87 2362.51
65536 640 27.13 27.13 27.13 2415.51
131072 320 56.70 56.71 56.70 2311.42
262144 160 294.23 294.27 294.25 890.83
524288 80 369.14 369.22 369.18 1419.97
1048576 40 604.35 604.47 604.41 1734.69
2097152 20 1084.30 1084.65 1084.48 1933.48
4194304 10 2042.89 2044.20 2043.55 2051.81
#-----------------------------------------------------------------------------
# Benchmarking Bidir_Put
# #processes = 2
#-----------------------------------------------------------------------------
#
# MODE: NON-AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec] Mbytes/sec
0 100 4.95 4.95 4.95 0.00
4 100 11.47 11.47 11.47 0.35
8 100 13.17 13.18 13.18 0.61
16 100 14.24 14.25 14.24 1.12
32 100 14.08 14.09 14.09 2.27
64 100 17.97 18.03 18.00 3.55
128 100 13.74 13.76 13.75 9.30
256 100 14.36 14.36 14.36 17.83
512 100 14.79 14.80 14.80 34.60
1024 100 14.69 14.69 14.69 69.70
2048 100 15.52 15.54 15.53 131.79
4096 100 16.91 16.94 16.93 241.77
8192 100 18.25 18.29 18.27 447.92
16384 100 23.29 23.31 23.30 702.87
32768 100 31.45 31.46 31.46 1041.52
65536 100 48.41 48.46 48.43 1352.41
131072 100 85.54 85.59 85.56 1531.40
262144 100 313.76 313.83 313.79 835.30
524288 80 430.62 430.70 430.66 1217.29
1048576 40 661.38 661.55 661.46 1585.04
2097152 20 1126.80 1127.15 1126.97 1860.58
4194304 10 2091.60 2094.89 2093.24 2002.16
#----------------------------------------------------------------
# Benchmarking Accumulate
# #processes = 2
#----------------------------------------------------------------
#
# MODE: AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 1000 0.05 0.05 0.05
4 1000 0.47 0.48 0.47
8 1000 0.53 0.54 0.54
16 1000 0.66 0.68 0.67
32 1000 0.68 0.70 0.69
64 1000 0.70 0.72 0.71
128 1000 0.71 0.73 0.72
256 1000 0.73 0.75 0.74
512 1000 0.80 0.83 0.82
1024 1000 0.99 1.01 1.00
2048 1000 1.32 1.35 1.34
4096 1000 2.06 2.09 2.07
8192 1000 3.44 3.47 3.45
16384 1000 7.30 7.33 7.31
32768 1000 14.32 14.35 14.33
65536 640 27.31 27.35 27.33
131072 320 55.66 55.74 55.70
262144 160 275.13 275.39 275.26
524288 80 552.26 552.74 552.50
1048576 40 1128.35 1129.40 1128.88
2097152 20 2220.05 2222.16 2221.10
4194304 10 4627.80 4632.09 4629.95
#----------------------------------------------------------------
# Benchmarking Accumulate
# #processes = 2
#----------------------------------------------------------------
#
# MODE: NON-AGGREGATE
#
#bytes #repetitions t_min[usec] t_max[usec] t_avg[usec]
0 100 4.48 4.49 4.48
4 100 9.45 9.45 9.45
8 100 10.17 10.17 10.17
16 100 12.13 12.13 12.13
32 100 12.35 12.36 12.35
64 100 13.24 13.25 13.25
128 100 13.40 13.40 13.40
256 100 13.45 13.45 13.45
512 100 13.26 13.35 13.30
1024 100 13.67 13.68 13.67
2048 100 12.76 12.77 12.76
4096 100 14.01 14.04 14.02
8192 100 15.14 15.25 15.19
16384 100 19.69 19.92 19.80
32768 100 29.17 29.39 29.28
65536 100 44.91 45.01 44.96
131072 100 92.49 92.49 92.49
262144 100 303.10 303.10 303.10
524288 80 550.92 550.93 550.92
1048576 40 1111.50 1111.70 1111.60
2097152 20 2223.05 2223.10 2223.07
4194304 10 4664.59 4664.90 4664.74
# All processes entering MPI_Finalize
