| CPU2006 license: | 11 | Test date: | Jan-2010 |
|---|---|---|---|
| Test sponsor: | IBM Corporation | Hardware Availability: | Feb-2010 |
| Tested by: | IBM Corporation | Software Availability: | Dec-2009 |
| Hardware | |
|---|---|
| CPU Name: | POWER7 |
| CPU Characteristics: | Intelligent Energy Optimization enabled, up to 3.64 GHz |
| CPU MHz: | 3300 |
| FPU: | Integrated |
| CPU(s) enabled: | 32 cores, 4 chips, 8 cores/chip, 4 threads/core |
| CPU(s) orderable: | 32 cores |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 256 KB I+D on chip per core |
| L3 Cache: | 4 MB I+D on chip per core |
| Other Cache: | None |
| Memory: | 256 GB (32x8 GB) DDR3 1066 MHz |
| Disk Subsystem: | 8x146.8 GB SAS SFF 15K RPM |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | SUSE Linux Enterprise Server 11 (ppc64), Kernel 2.6.27.19-5-ppc64 |
| Compiler: | IBM XL C/C++ for Linux, V10.1 Updated with the Oct2009 PTF |
| Auto Parallel: | No |
| File System: | ext3 |
| System State: | Run level 3 (multi-user) |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32/64-bit |
| Other Software: | -Post-Link Optimization for Linux on POWER, Version 5.5.0-1 -MicroQuill SmartHeap 9 |
Results Table
| Benchmark | Base | Peak | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Copies | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | Copies | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | |
| Results appear in the order in which they were run. Bold underlined text indicates a median measurement. | ||||||||||||||
| 400.perlbench | 128 | 1486 | 841 | 1483 | 843 | 1467 | 853 | 128 | 1258 | 994 | 1210 | 1030 | 1233 | 1010 |
| 401.bzip2 | 128 | 1497 | 825 | 1521 | 812 | 1511 | 817 | 128 | 1428 | 865 | 1428 | 865 | 1420 | 870 |
| 403.gcc | 128 | 1148 | 898 | 1143 | 902 | 1145 | 900 | 128 | 1054 | 978 | 1040 | 991 | 1053 | 979 |
| 429.mcf | 128 | 939 | 1240 | 936 | 1250 | 941 | 1240 | 64 | 430 | 1360 | 423 | 1380 | 423 | 1380 |
| 445.gobmk | 128 | 1278 | 1050 | 1277 | 1050 | 1277 | 1050 | 128 | 1010 | 1330 | 1021 | 1310 | 1016 | 1320 |
| 456.hmmer | 128 | 1300 | 919 | 1299 | 920 | 1300 | 919 | 128 | 973 | 1230 | 984 | 1210 | 987 | 1210 |
| 458.sjeng | 128 | 1436 | 1080 | 1429 | 1080 | 1434 | 1080 | 128 | 1322 | 1170 | 1323 | 1170 | 1316 | 1180 |
| 462.libquantum | 128 | 2250 | 1180 | 2250 | 1180 | 2266 | 1170 | 32 | 522 | 1270 | 523 | 1270 | 522 | 1270 |
| 464.h264ref | 128 | 2135 | 1330 | 2077 | 1360 | 2070 | 1370 | 128 | 1897 | 1490 | 1934 | 1460 | 1992 | 1420 |
| 471.omnetpp | 128 | 1865 | 429 | 1865 | 429 | 1863 | 429 | 128 | 1849 | 433 | 1845 | 434 | 1847 | 433 |
| 473.astar | 128 | 1333 | 674 | 1334 | 674 | 1333 | 674 | 128 | 1201 | 748 | 1206 | 745 | 1206 | 745 |
| 483.xalancbmk | 128 | 857 | 1030 | 851 | 1040 | 858 | 1030 | 128 | 821 | 1080 | 817 | 1080 | 816 | 1080 |
Submit Notes
The config file option 'submit' was used.
Operating System Notes
ulimit -s (stack) set to 1048576.
Large pages reserved as follows by root user:
echo 7040 > /proc/sys/vm/nr_hugepages
System configured with libhugetlbfs library for application access to large pages
Environment variables set before executing benchmarks.
export HUGETLB_VERBOSE=0
export HUGETLB_MORECORE=yes
export XLFRTEOPTS=intrinthds=1
General Notes
The "IBM Power 750 Express (3.3 GHz)" and "IBM Power 755 (3.3 GHz)"
are electronically equivalent. The results have been measured on the
"IBM Power 755 (3.3 GHz)"
IBM Post-Link Optimization tool with
options "-O4 -omullX -see 0 -m power6" used for
400.perlbench 401.bzip2 403.gcc 456.hmmer 458.sjeng
483.xalancbmk
options "-bf -dp -hr -las -pca -RC -RD -rmte -si -tlo -A 64 -isf 104 -lu 8 -rt 0.16
-hrf 0.18 -ihf 40 -sdp 6 -sdpms 128 -shci 65 -si -sidf 45 -omullX" used for
429.mcf
options "-q -O3 -A 32 -omullX" used for
445.gobmk
options "-bf -dp -lro -nop -RC -RD -tb -tlo -vro -A 4
-isf 88 -lu 8 -hrf 0.10 -sdp 4 -lun 27 -omullX" used for
462.libquantum
options "-O4 -omullX -see 1" used for
473.astar
options "-O4" used for
464.h264ref
Whenever option "-omullX" was used during the optimization phase,
option "-imullX" was also used during the instrumentation phase.
Benchmarks bound to a processor using numactl on the submit command.
See flags file for details on settings.
Base Portability Flags
| 400.perlbench: | -DSPEC_CPU_LINUX_PPC |
| 462.libquantum: | -DSPEC_CPU_LINUX |
| 464.h264ref: | -qchars=signed |
| 483.xalancbmk: | -DSPEC_CPU_LINUX |
Base Optimization Flags
C benchmarks:
| -O5 -qalias=noansi -qalloca -lhugetlbfs |
C++ benchmarks:
| -O5 -qrtti -lsmartheap |
Base Other Flags
C benchmarks:
| -qipa=noobject -qipa=threads |
C++ benchmarks:
| -qipa=noobject -qipa=threads |
Peak Portability Flags
| 400.perlbench: | -DSPEC_CPU_LINUX_PPC |
| 462.libquantum: | -DSPEC_CPU_LINUX |
| 464.h264ref: | -qchars=signed |
| 483.xalancbmk: | -DSPEC_CPU_LINUX |
Peak Optimization Flags
C benchmarks:
| 400.perlbench: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qalias=noansi -lsmartheap |
| 401.bzip2: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O3 -qarch=auto -qtune=auto -lhugetlbfs |
| 403.gcc: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qalloca -lhugetlbfs |
| 429.mcf: | -Wl,-q -O5 -qnoenablevmx -lhugetlbfs |
| 445.gobmk: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qnoenablevmx -lhugetlbfs |
| 456.hmmer: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O5 -lhugetlbfs |
| 458.sjeng: | -Wl,-q -O5 -lhugetlbfs |
| 462.libquantum: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qnoenablevmx -q64 -lhugetlbfs |
| 464.h264ref: | Same as 456.hmmer |
C++ benchmarks:
| 471.omnetpp: | -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qrtti -lsmartheap |
| 473.astar: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qnoenablevmx -lsmartheap |
| 483.xalancbmk: | -Wl,-q -O5 -lsmartheap |