SPEC® CINT2006 Result

Copyright 2006-2012 Standard Performance Evaluation Corporation

IBM Corporation

IBM Power 780 Server (4.14 GHz, 16 core)

SPECint®2006 = 44.0

CPU2006 license: 11 Test date: Apr-2010
Test sponsor: IBM Corporation Hardware Availability: Mar-2010
Tested by: IBM Corporation Software Availability: Apr-2010
Benchmark results graph
Hardware
CPU Name: POWER7
CPU Characteristics: TurboCore mode
CPU MHz: 4140
FPU: Integrated
CPU(s) enabled: 16 cores, 4 chips, 4 cores/chip
CPU(s) orderable: 8,16,24,32 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: 16 MB I+D on chip per chip
Memory: 256 GB (32x8 GB) DDR3 1066 MHz
Disk Subsystem: 2x146.8 GB SAS SFF 15K RPM
Other Hardware: --
Software
Operating System: IBM AIX V6.1
with the 6100-05 Technology Level SP1
Compiler: XL C/C++ Enterprise Edition V11.1.0.1 for AIX
Auto Parallel: Yes
File System: AIX/JFS2
System State: Multi-user
Base Pointers: 32-bit
Peak Pointers: 32/64-bit
Other Software: None

Results Table

Benchmark Base Peak
Seconds Ratio Seconds Ratio Seconds Ratio 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 449 21.8 447 21.9 448 21.8 348   28.1 348   28.1 348   28.1
401.bzip2 433 22.3 433 22.3 433 22.3 373   25.8 374   25.8 373   25.9
403.gcc 326 24.7 326 24.7 326 24.7 282   28.6 282   28.6 281   28.6
429.mcf 144 63.2 144 63.1 144 63.2 121   75.3 121   75.5 121   75.5
445.gobmk 456 23.0 457 22.9 457 22.9 371   28.3 370   28.3 370   28.4
456.hmmer 386 24.2 389 24.0 386 24.2 238   39.3 238   39.3 238   39.3
458.sjeng 526 23.0 526 23.0 526 23.0 447   27.1 437   27.7 438   27.6
462.libquantum 265 78.0 266 78.0 267 77.5 22.6 917   22.9 904   22.8 909  
464.h264ref 519 42.6 519 42.6 520 42.6 454   48.8 458   48.3 452   48.9
471.omnetpp 290 21.5 290 21.5 292 21.4 262   23.8 263   23.8 262   23.8
473.astar 321 21.9 320 21.9 320 21.9 267   26.3 267   26.3 267   26.3
483.xalancbmk 258 26.8 258 26.8 256 26.9 175   39.4 175   39.4 176   39.3

Peak Tuning Notes

fdpr binary optimization tool used for:
  400.perlbench 401.bzip2
     with options -O4 -vrox
  403.gcc
     with options -O4 -nodp -rtb
  429.mcf 445.gobmk 458.sjeng 473.astar
     with options -O3
  456.hmmer
     with options -O4 -nodp -m power7
  462.libquantum
     with options -O4 -vrox -nodp
  464.h264ref
     with options -O4 -vrox -nodp -rtb
  471.omnetpp
     with options -O3 -lu -1 -nodp -sdp 9
  483.xalancbmk
     with options -O3 -m power7

Operating System Notes

 all ulimits set to unlimited.
 2000 16M large pages defined with vmo command
System set to single thread mode with the OS command:
 smtctl -m off -w boot

General Notes

Environment variables set by runspec before the start of the run:
MALLOCMULTIHEAP = "1"
MALLOCOPTIONS = "pool"
MEMORY_AFFINITY = "MCM"
XLFRTEOPTS = "intrinthds=1"
XLSMPOPTS = "spins=0:yields=0"

 See the flags file for details on settings.

Base Compiler Invocation

C benchmarks:

 /usr/vac/bin/xlc   -qlanglvl=extc99 

C++ benchmarks:

 /usr/vacpp/bin/xlC_r 

Base Portability Flags

400.perlbench:  -DSPEC_CPU_AIX 
462.libquantum:  -DSPEC_CPU_AIX 
464.h264ref:  -DSPEC_CPU_AIX   -qchars=signed 
483.xalancbmk:  -DSPEC_CPU_AIX 

Base Optimization Flags

C benchmarks:

 -qipa=threads   -bmaxdata:0x50000000   -O5   -qlargepage   -D_ILS_MACROS   -qalias=noansi   -qalloca   -blpdata 

C++ benchmarks:

 -qipa=threads   -bmaxdata:0x20000000   -O5   -qlargepage   -D_ILS_MACROS   -qsmp=auto   -qrtti=all   -D__IBM_FAST_SET_MAP_ITERATOR   -blpdata 

Base Other Flags

C benchmarks:

 -qipa=noobject   -qsuppress=1500-036 

C++ benchmarks:

 -qipa=noobject   -qsuppress=1500-036 

Peak Compiler Invocation

C benchmarks (except as noted below):

 /usr/vac/bin/xlc   -qlanglvl=extc99 
458.sjeng:  /usr/vac/bin/xlc_r   -qlanglvl=extc99 
462.libquantum:  /usr/vac/bin/xlc_r   -qlanglvl=extc99 

C++ benchmarks:

 /usr/vacpp/bin/xlC 

Peak Portability Flags

400.perlbench:  -DSPEC_CPU_AIX 
462.libquantum:  -DSPEC_CPU_AIX 
464.h264ref:  -DSPEC_CPU_AIX   -qchars=signed 
483.xalancbmk:  -DSPEC_CPU_AIX 

Peak Optimization Flags

C benchmarks:

400.perlbench:  -qipa=threads   -bmaxdata:0x50000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O2   -qarch=auto   -qtune=auto   -qipa=level=2   -qipa=inline=threshold=2048   -qipa=inline=limit=10240   -D_ILS_MACROS   -qalias=noansi   -blpdata   -btextpsize:64K 
401.bzip2:  -qipa=threads   -bmaxdata:0x4ffffffc   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qlargepage   -qipa=inline=threshold=2888   -qipa=inline=limit=11880   -qipa=partition=large   -D_ILS_MACROS   -blpdata 
403.gcc:  -qipa=threads   -bmaxdata:0x50000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qsimd   -qvecnvol   -qlargepage   -qipa=inline=threshold=630   -qipa=inline=limit=4920   -qipa=partition=large   -D_ILS_MACROS   -qalloca   -blpdata 
429.mcf:  -qipa=threads   -bmaxdata:0x50000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qsimd   -qvecnvol   -qlargepage   -D_ILS_MACROS   -blpdata 
445.gobmk:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O4   -qsimd   -qvecnvol   -qlargepage   -D_ILS_MACROS   -blpdata 
456.hmmer:  -qipa=threads   -O5   -qsimd   -qvecnvol   -qassert=refalign   -qipa=inline=threshold=2888   -qipa=inline=limit=11880   -D_ILS_MACROS   -blpdata   -btextpsize:64K 
458.sjeng:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qsmp=auto   -D_ILS_MACROS   -blpdata 
462.libquantum:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qsmp=auto   -q64   -qlargepage   -D_ILS_MACROS   -blpdata 
464.h264ref:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qsmp=auto   -qsimd   -qvecnvol   -qipa=inline=threshold=1864   -qipa=inline=limit=9830   -D_ILS_MACROS   -blpdata   -btextpsize:64K 

C++ benchmarks:

471.omnetpp:  -qipa=threads   -bmaxdata:0x20000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O4   -D_ILS_MACROS   -qalign=natural   -qrtti=all   -qinlglue   -D__IBM_FAST_SET_MAP_ITERATOR   -blpdata   -btextpsize:64K 
473.astar:  -qipa=threads   -bmaxdata:0x20000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qlargepage   -qipa=inline=threshold=2468   -qipa=inline=limit=11060   -qipa=partition=large   -D_ILS_MACROS   -qinlglue   -qalign=natural   -blpdata 
483.xalancbmk:  -qipa=threads   -bmaxdata:0x20000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O4   -qarch=pwr5   -qtune=pwr5   -qlargepage   -qipa=inline=threshold=2468   -qipa=inline=limit=11060   -D_ILS_MACROS   -qinlglue   -D__IBM_FAST_VECTOR   -blpdata   -btextpsize:64K 

Peak Other Flags

C benchmarks:

 -qipa=noobject   -qsuppress=1500-036 

C++ benchmarks (except as noted below):

 -qipa=noobject   -qsuppress=1500-036 
471.omnetpp:  -qsuppress=1500-036 

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/IBM-AIX.20100511.html,
http://www.spec.org/cpu2006/flags/IBM-XL.20100511.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/IBM-AIX.20100511.xml,
http://www.spec.org/cpu2006/flags/IBM-XL.20100511.xml.