Sample 4 - IMB-EXT.exe

The example below shows the results for the Window benchmark received after running IMB-EXT.exe on a Microsoft Windows* cluster using two processes. The performance diagnostics for Unidir_Get, Unidir_Put, Bidir_Get, Bidir_Put, and Accumulate are omitted.

 <..> -n 2 IMB-EXT.exe
 
#---------------------------------------------------
#    Intel ® MPI Benchmark Suite V3.2.2, MPI-2 part 
#---------------------------------------------------
# Date                  : Fri Sep 05 12:26:52 2008
# Machine             : Intel64 Family 6 Model 15 Stepping 6, GenuineIntel
# System               : Windows Server 2008
# Release              : .0.6001
# Version               : Service Pack 1
# MPI Version        : 2.0
# MPI Thread Environment: MPI_THREAD_SINGLE
 
# New default behavior from Version 3.2 on:
# the number of iterations per message size is cut down
# dynamically when a certain run time (per message size sample)
# is expected to be exceeded. Time limit is defined by variable
# SECS_PER_SAMPLE (=> IMB_settings.h)
# or through the flag => -time 
 
# Calling sequence was:
# \\master-node\MPI_Share_Area\IMB_3.1\src\IMB-EXT.exe
# 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[μsec]  t_max[μsec] t_avg[μsec]
            0          100       ..           ..           ..
            4          100
            8          100
           16          100
           32          100
           64          100
          128          100
          256          100
          512          100
         1024          100
         2048          100
         4096          100
         8192          100
        16384          100
        32768          100
        65536          100
       131072          100
       262144          100
       524288           80
      1048576           40
      2097152           20
      4194304           10
...
# All processes entering MPI_Finalize

The above example listing shows the results of running IMB-EXT.exe on a Microsoft Windows* cluster using two processes.

The listing only shows the result for the Window benchmark. The performance diagnostics for Unidir_Get, Unidir_Put, Bidir_Get, Bidir_Put, and Accumulate are omitted.