Visible to Intel only — GUID: GUID-727924F2-5096-4D6F-826C-58977830C395
Measuring Communication and Computation Overlap
Measuring Pure Communication Time
Iallgather
Iallgather_pure
Iallgatherv
Iallgatherv_pure
Iallreduce
Iallreduce_pure
Ialltoall
Ialltoall_pure
Ialltoallv
Ialltoallv_pure
Ibarrier
Ibarrier_pure
Ibcast
Ibcast_pure
Igather
Igather_pure
Igatherv
Igatherv_pure
Ireduce
Ireduce_pure
Ireduce_scatter
Ireduce_scatter_pure
Iscatter
Iscatter_pure
Iscatterv
Iscatterv_pure
Visible to Intel only — GUID: GUID-727924F2-5096-4D6F-826C-58977830C395
Sample 3 - IMB-IO p_write_indv
The following example shows the results of the p_write_indv benchmark:
<..> IMB-IO -np 2 p_write_indv -npmin 2
#---------------------------------------------------
# Date : Thu Sep 4 13:43:34 2008
# Machine : x86_64
# System : Linux
# Release : 2.6.9-42.ELsmp
# Version : #1 SMP Wed Jul 12 23:32:02 EDT 2006
# 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:
# ./IMB-IO p_write_indv -npmin 2
# Minimum io portion in bytes: 0
# Maximum io portion in bytes: 16777216
#
#
#
# List of Benchmarks to run:
# P_Write_Indv
#--------------------------------------------------------------
# Benchmarking P_Write_Indv
# #processes = 2
#--------------------------------------------------------------
#
# MODE: AGGREGATE
#
#bytes #rep.s t_min[μsec] t_max t_avg Mb/sec
0 50 .. .. .. ..
1 50
2 50
4 50
8 50
16 50
32 50
64 50
128 50
256 50
512 50
1024 50
2048 50
4096 50
8192 50
16384 50
32768 50
65536 50
131072 50
262144 50
524288 32
1048576 16
2097152 8
4194304 4
8388608 2
16777216 1
#--------------------------------------------------------------
# Benchmarking P_Write_Indv
# #processes = 2
#--------------------------------------------------------------
#
# MODE: NON-AGGREGATE
#
#bytes #rep.s t_min[μsec] t_max t_avg Mb/sec
0 10 .. .. .. ..
1 10
2 10
4 10
8 10
16 10
32 10
64 10
128 10
256 10
512 10
1024 10
2048 10
4096 10
8192 10
16384 10
32768 10
65536 10
131072 10
262144 10
524288 10
1048576 10
2097152 8
4194304 4
8388608 2
16777216 1
# All processes entering MPI_Finalize