Table of Contents
Advertisement
Chapter 7
MVAPICH MPI
When the test completes successfully, you see output similar to the following:
#---------------------------------------------------
#
#---------------------------------------------------
# Date
# Machine
# Release
# Version
#
# Minimum message length in bytes:
# Maximum message length in bytes:
#
# MPI_Datatype
# MPI_Datatype for reductions
# MPI_Op
#
# List of Benchmarks to run:
# PingPong
# PingPing
# Sendrecv
# Exchange
# Allreduce
# Reduce
# Reduce_scatter
# Allgather
# Allgatherv
# Alltoall
# Bcast
# Barrier
#---------------------------------------------------
# Benchmarking PingPong
# #processes = 2
#---------------------------------------------------
<output truncated>
OL-12309-01
Intel (R) MPI Benchmark Suite V2.3, MPI-1 part
: Thu Oct 12 17:48:21 2006
: x86_64# System
: 2.6.9-42.ELsmp
: #1 SMP Wed Jul 12 23:32:02 EDT 2006
#bytes #repetitions
0
1000
1
1000
2
1000
4
1000
8
1000
16
1000
32
1000
64
1000
128
1000
256
1000
512
1000
1024
1000
2048
1000
4096
1000
8192
1000
16384
1000
32768
1000
65536
640
131072
320
262144
160
524288
80
1048576
40
2097152
20
4194304
10
: Linux
0
4194304
:
MPI_BYTE
:
MPI_FLOAT
:
MPI_SUM
t[usec]
Mbytes/sec
2.86
0.00
2.86
0.33
2.86
0.67
2.98
1.28
2.96
2.58
2.97
5.14
3.08
9.91
3.17
19.27
3.95
30.87
4.28
57.03
5.03
97.08
6.15
158.89
7.51
259.97
10.26
380.71
22.93
340.73
29.34
532.59
41.80
747.56
66.16
944.69
114.53
1091.41
214.48
1165.64
405.76
1232.25
792.88
1261.23
1570.12
1273.78
3113.90
1284.56
Cisco SFS InfiniBand Host Drivers User Guide for Linux
Intel MPI Benchmarks (IMB) Test Performance
7-11
Advertisement
Table of Contents
