Source

pupyMPI-benchmarkdata / LAM-benchmark_output / LAM_at_klynge_8_procs.txt

Full commit
#---------------------------------------------------
#    Intel (R) MPI Benchmark Suite V3.2, MPI-1 part    
#---------------------------------------------------
# Date                  : Thu May 12 18:30:45 2011
# Machine               : x86_64
# System                : Linux
# Release               : 2.6.28-19-server
# Version               : #66-Ubuntu SMP Sat Oct 16 18:11:06 UTC 2010
# MPI Version           : 1.2
# MPI Thread Environment: MPI_THREAD_SERIALIZED


# 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/src/IMB-MPI1 -npmin 8 -input LAM-mpi/benchmarks_to_run.txt

# 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
# Allgather
# Gather
# Scatter
# Alltoall
# Bcast
# Barrier

#---------------------------------------------------
# Benchmarking PingPong 
# #processes = 2 
# ( 6 additional processes waiting in MPI_Barrier)
#---------------------------------------------------
       #bytes #repetitions      t[usec]   Mbytes/sec
            0         1000        58.63         0.00
            1         1000        60.59         0.02
            2         1000        59.90         0.03
            4         1000        59.72         0.06
            8         1000        59.84         0.13
           16         1000        59.94         0.25
           32         1000        59.97         0.51
           64         1000        61.52         0.99
          128         1000        64.31         1.90
          256         1000        70.84         3.45
          512         1000        83.66         5.84
         1024         1000        91.80        10.64
         2048         1000       112.95        17.29
         4096         1000       112.62        34.69
         8192         1000       165.20        47.29
        16384         1000       290.35        53.81
        32768         1000       430.94        72.52
        65536          640       730.46        85.56
       131072          320      1378.53        90.68
       262144          160      2526.70        98.94
       524288           80      4746.78       105.33
      1048576           40      9209.17       108.59
      2097152           20     18305.27       109.26
      4194304           10     36230.71       110.40

#---------------------------------------------------
# Benchmarking PingPing 
# #processes = 2 
# ( 6 additional processes waiting in MPI_Barrier)
#---------------------------------------------------
       #bytes #repetitions      t[usec]   Mbytes/sec
            0         1000        62.06         0.00
            1         1000        63.01         0.02
            2         1000        63.99         0.03
            4         1000        62.88         0.06
            8         1000        62.63         0.12
           16         1000        63.27         0.24
           32         1000        63.96         0.48
           64         1000        65.72         0.93
          128         1000        70.18         1.74
          256         1000        81.25         3.00
          512         1000        69.94         6.98
         1024         1000        94.78        10.30
         2048         1000       107.69        18.14
         4096         1000       111.55        35.02
         8192         1000       246.81        31.65
        16384         1000       265.67        58.81
        32768         1000       443.54        70.46
        65536          640       753.70        82.92
       131072          320      1712.50        72.99
       262144          160      3130.91        79.85
       524288           80      5927.89        84.35
      1048576           40     11526.10        86.76
      2097152           20     22635.15        88.36
      4194304           10     45060.61        88.77

#-----------------------------------------------------------------------------
# Benchmarking Sendrecv 
# #processes = 8 
#-----------------------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]   Mbytes/sec
            0         1000        74.37        74.66        74.51         0.00
            1         1000        73.34        73.62        73.48         0.03
            2         1000        73.07        73.34        73.20         0.05
            4         1000        74.33        74.62        74.47         0.10
            8         1000        73.01        73.30        73.15         0.21
           16         1000        73.60        73.88        73.74         0.41
           32         1000        73.35        73.65        73.50         0.83
           64         1000        80.62        80.95        80.77         1.51
          128         1000        82.80        83.12        82.95         2.94
          256         1000        85.04        85.38        85.21         5.72
          512         1000        90.70        90.96        90.82        10.74
         1024         1000        97.21        97.36        97.30        20.06
         2048         1000       107.95       108.14       108.06        36.12
         4096         1000       124.27       124.53       124.40        62.74
         8192         1000       190.21       190.73       190.39        81.92
        16384         1000       325.94       326.54       326.17        95.70
        32768         1000       481.17       481.68       481.31       129.75
        65536          640       822.59       824.90       823.70       151.53
       131072          320      2164.87      2169.87      2166.82       115.21
       262144          160      3612.74      3621.77      3618.11       138.05
       524288           80      6491.10      6518.64      6503.95       153.41
      1048576           40     12142.22     12195.43     12166.50       164.00
      2097152           20     23255.94     23363.29     23326.39       171.21
      4194304           10     44863.20     44993.90     44915.74       177.80

#-----------------------------------------------------------------------------
# Benchmarking Exchange 
# #processes = 8 
#-----------------------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]   Mbytes/sec
            0         1000        67.73        67.92        67.83         0.00
            1         1000        68.81        68.97        68.90         0.06
            2         1000        68.50        68.67        68.60         0.11
            4         1000        68.90        69.10        69.00         0.22
            8         1000        68.91        69.05        68.98         0.44
           16         1000        70.53        70.69        70.62         0.86
           32         1000        69.48        69.67        69.58         1.75
           64         1000        76.15        76.41        76.27         3.19
          128         1000        75.47        75.67        75.58         6.45
          256         1000        82.48        82.67        82.58        11.81
          512         1000        89.26        89.41        89.35        21.85
         1024         1000       108.44       108.66       108.54        35.95
         2048         1000       128.02       128.18       128.10        60.95
         4096         1000       221.68       221.97       221.84        70.39
         8192         1000       354.00       354.32       354.15        88.20
        16384         1000       511.54       511.83       511.67       122.11
        32768         1000       814.64       814.87       814.80       153.40
        65536          640      1595.77      1597.76      1596.88       156.47
       131072          320      4183.79      4188.83      4186.60       119.37
       262144          160      7100.11      7116.13      7106.56       140.53
       524288           80     12588.69     12593.55     12590.88       158.81
      1048576           40     24146.15     24184.93     24165.11       165.39
      2097152           20     45685.10     45798.16     45734.72       174.68
      4194304           10     91291.02     91489.01     91370.28       174.88

#----------------------------------------------------------------
# Benchmarking Allreduce 
# #processes = 8 
#----------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
            0         1000       345.08       345.11       345.10
            4         1000       355.18       355.22       355.21
            8         1000       350.98       351.02       351.01
           16         1000       355.93       355.96       355.96
           32         1000       357.38       357.42       357.41
           64         1000       364.50       364.53       364.52
          128         1000       407.95       407.97       407.96
          256         1000       423.78       423.81       423.79
          512         1000       494.41       494.46       494.44
         1024         1000       543.42       543.49       543.45
         2048         1000       630.64       630.73       630.69
         4096         1000       661.87       661.97       661.94
         8192         1000      1019.76      1020.04      1019.94
        16384         1000      1599.87      1600.46      1600.27
        32768         1000      2671.84      2673.05      2672.59
        65536          640      4393.48      4396.60      4395.58
       131072          320      8418.05      8420.24      8419.13
       262144          160     15795.26     15800.90     15797.82
       524288           80     29468.47     29476.80     29472.47
      1048576           40     57699.85     57717.57     57708.61
      2097152           20    115332.10    115394.51    115363.48
      4194304           10    228799.58    228924.39    228850.52

#----------------------------------------------------------------
# Benchmarking Reduce 
# #processes = 8 
#----------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
            0         1000         0.20         0.22         0.20
            4         1000       200.86       201.07       200.97
            8         1000       198.26       198.48       198.38
           16         1000       200.46       200.70       200.58
           32         1000       202.74       202.98       202.88
           64         1000       203.87       204.09       203.98
          128         1000       209.96       210.18       210.08
          256         1000       232.32       232.55       232.44
          512         1000       250.79       251.07       250.94
         1024         1000       277.54       277.87       277.71
         2048         1000       311.33       311.70       311.51
         4096         1000       340.00       340.41       340.21
         8192         1000       629.74       630.63       630.19
        16384         1000       959.61       961.36       960.48
        32768         1000      1465.24      1467.89      1466.58
        65536          640      2386.02      2392.44      2389.09
       131072          320      4345.03      4361.45      4352.54
       262144          160      7979.50      8037.37      8007.58
       524288           80     15106.29     15322.15     15212.86
      1048576           40     29156.27     29996.78     29573.28
      2097152           20     56737.10     60097.80     58410.08
      4194304           10    106878.02    120494.10    113706.11

#----------------------------------------------------------------
# Benchmarking Allgather 
# #processes = 8 
#----------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
            0         1000       238.44       238.47       238.46
            1         1000       243.40       243.42       243.41
            2         1000       241.24       241.29       241.27
            4         1000       244.39       244.41       244.40
            8         1000       260.41       260.45       260.44
           16         1000       268.41       268.44       268.43
           32         1000       285.13       285.16       285.15
           64         1000       299.85       299.91       299.87
          128         1000       323.97       324.04       324.01
          256         1000       363.39       363.48       363.44
          512         1000       389.99       390.09       390.06
         1024         1000       698.15       698.58       698.40
         2048         1000       883.24       883.78       883.62
         4096         1000      1378.76      1379.79      1379.40
         8192         1000      2423.36      2425.19      2424.64
        16384         1000      5505.90      5506.84      5506.31
        32768          987     10140.56     10141.54     10141.07
        65536          140     22499.18     22506.51     22502.78
       131072          140     37751.46     37756.46     37753.93
       262144          139     71933.63     71940.73     71937.23
       524288           71    141349.44    141361.34    141355.33
      1048576           36    280544.80    280586.22    280567.05
      2097152           18    558476.34    558543.38    558511.15
      4194304            9   1116283.31   1116428.67   1116351.66

#----------------------------------------------------------------
# Benchmarking Gather 
# #processes = 8 
#----------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
            0         1000        67.05        67.37        67.22
            1         1000        70.45        70.76        70.60
            2         1000        67.66        67.98        67.81
            4         1000        68.90        69.22        69.05
            8         1000        68.36        68.69        68.52
           16         1000        73.33        73.67        73.50
           32         1000        72.82        73.14        72.99
           64         1000        73.39        73.75        73.57
          128         1000        74.80        75.15        74.98
          256         1000        80.74        81.13        80.93
          512         1000        88.34        88.75        88.55
         1024         1000        98.21        98.68        98.45
         2048         1000       116.24       116.82       116.54
         4096         1000       160.28       161.31       160.82
         8192         1000       236.38       237.69       237.05
        16384         1000       349.09       351.02       350.12
        32768         1000       980.75       984.45       982.73
        65536          640      1627.59      1640.77      1634.90
       131072          320      7575.98      7604.49      7591.41
       262144          160     13282.53     13381.15     13336.09
       524288           80     24860.90     25227.71     25062.38
      1048576           40     48689.38     50129.87     49489.56
      2097152           20     92828.25    100214.24     97301.21
      4194304           10    183505.30    205622.60    195953.17

#----------------------------------------------------------------
# Benchmarking Scatter 
# #processes = 8 
#----------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
            0         1000        70.93        71.12        71.04
            1         1000        72.75        72.95        72.87
            2         1000        72.58        72.77        72.69
            4         1000        74.56        74.76        74.68
            8         1000        73.26        73.46        73.38
           16         1000        74.30        74.51        74.42
           32         1000        73.89        74.10        74.01
           64         1000        73.22        73.40        73.33
          128         1000        76.48        76.69        76.61
          256         1000        79.14        79.35        79.27
          512         1000        94.47        94.72        94.62
         1024         1000       114.03       114.25       114.17
         2048         1000       151.43       151.70       151.63
         4096         1000       205.22       205.61       205.48
         8192         1000       362.52       363.21       362.93
        16384         1000       670.75       671.86       671.44
        32768         1000      1213.99      1216.02      1215.12
        65536          640      2276.05      2282.07      2279.16
       131072          320      7210.46      7236.20      7224.72
       262144          160     12905.14     12996.36     12955.76
       524288           80     24609.39     24961.04     24805.72
      1048576           40     48371.88     49755.05     49144.43
      2097152           20     92362.95     99639.80     96799.14
      4194304           10    183010.70    205065.89    195426.25

#----------------------------------------------------------------
# Benchmarking Alltoall 
# #processes = 8 
#----------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
            0         1000        98.43        98.56        98.50
            1         1000       102.59       102.71       102.63
            2         1000       102.56       102.72       102.63
            4         1000       101.99       102.13       102.04
            8         1000       101.63       101.76       101.70
           16         1000       101.25       101.41       101.34
           32         1000       103.54       103.70       103.62
           64         1000       105.33       105.47       105.39
          128         1000       106.66       106.83       106.73
          256         1000       107.92       108.08       107.99
          512         1000       118.18       118.32       118.26
         1024         1000       157.57       157.69       157.62
         2048         1000       245.55       245.70       245.63
         4096         1000       484.67       484.98       484.78
         8192         1000       732.15       732.43       732.27
        16384          145      1390.82      1395.29      1393.53
        32768          145     18117.91     18126.74     18119.88
        65536          145     16862.80     16878.93     16870.62
       131072          145     40235.82     42373.83     40510.32
       262144          145     58669.16     58711.97     58685.78
       524288           80    112931.35    115132.12    113258.06
      1048576           40    129263.80    133942.47    130506.42
      2097152           20    230136.80    232285.34    231432.01
      4194304           10    341253.69    353328.90    347085.93

#----------------------------------------------------------------
# Benchmarking Bcast 
# #processes = 8 
#----------------------------------------------------------------
       #bytes #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
            0         1000         0.19         0.20         0.20
            1         1000        64.31        64.73        64.58
            2         1000        64.07        64.32        64.24
            4         1000        64.91        65.24        65.13
            8         1000        64.86        65.12        65.03
           16         1000        64.80        65.21        65.05
           32         1000        65.56        65.83        65.74
           64         1000        66.61        67.00        66.85
          128         1000        68.76        69.15        69.00
          256         1000        71.39        71.71        71.61
          512         1000        86.60        87.04        86.88
         1024         1000       109.39       109.74       109.62
         2048         1000       135.28       135.70       135.55
         4096         1000       187.09       187.52       187.39
         8192         1000       343.16       343.91       343.65
        16384         1000       582.19       583.20       582.85
        32768         1000      1028.89      1030.39      1029.84
        65536          640      1912.82      1916.65      1915.31
       131072          320      4057.66      4060.33      4059.06
       262144          160      7540.55      7546.99      7543.76
       524288           80     14112.93     14124.40     14119.25
      1048576           40     27506.08     27530.68     27520.26
      2097152           20     54625.70     54691.30     54661.96
      4194304           10    108641.10    108795.91    108721.41

#---------------------------------------------------
# Benchmarking Barrier 
# #processes = 8 
#---------------------------------------------------
 #repetitions  t_min[usec]  t_max[usec]  t_avg[usec]
         1000       410.83       410.85       410.84


# All processes entering MPI_Finalize