SPEC® CINT2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

Fujitsu Siemens Computers

CELSIUS V840, AMD Opteron 2350 (2.0 GHz)

CPU2006 license: 22 Test date: Jun-2008
Test sponsor: Fujitsu Siemens Computers Hardware Availability: May-2008
Tested by: Fujitsu Siemens Computers Software Availability: May-2008
Benchmark results graph
Hardware
CPU Name: AMD Opteron 2350
CPU Characteristics:
CPU MHz: 2000
FPU: Integrated
CPU(s) enabled: 8 cores, 2 chips, 4 cores/chip
CPU(s) orderable: 1,2 chips
Primary Cache: 64 KB I + 64 KB D on chip per core
Secondary Cache: 512 KB I+D on chip per core
L3 Cache: 2 MB I+D on chip per chip
Other Cache: None
Memory: 16 GB (8x2GB PC2-5300P, CL5, dual rank ECC)
Disk Subsystem: 1 x 400 GB SATA II
Other Hardware: None
Software
Operating System: SUSE Linux Enterprise Server 10 (x86_64) SP1,
Kernel 2.6.16.46-0.12-smp
Compiler: PGI Workstation Complete Version 7.2-1
PathScale Compiler Suite, Release 3.2 Beta
Auto Parallel: No
File System: ext3
System State: Multi-User SuSE Run Level 3
Base Pointers: 32/64-bit
Peak Pointers: 32/64-bit
Other Software: binutils 2.18.50
Microquill SmartHeap 8.1 32-bit Library for Linux

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 8 937 83.4 940 83.1 939 83.2 8 721 108   708 110   708 110  
401.bzip2 8 1270 60.8 1279 60.4 1281 60.3 8 1229 62.8 1217 63.4 1220 63.3
403.gcc 8 1156 55.7 1169 55.1 1165 55.3 8 994 64.8 979 65.8 982 65.6
429.mcf 8 1209 60.3 1184 61.6 1184 61.6 8 912 80.0 914 79.8 913 79.9
445.gobmk 8 1038 80.9 1037 80.9 1037 80.9 8 817 103   817 103   817 103  
456.hmmer 8 702 106   697 107   703 106   8 464 161   465 160   464 161  
458.sjeng 8 1124 86.2 1124 86.1 1124 86.1 8 1033 93.7 1033 93.7 1033 93.7
462.libquantum 8 1147 145   1147 145   1148 144   8 1135 146   1138 146   1138 146  
464.h264ref 8 1327 133   1335 133   1331 133   8 1290 137   1292 137   1291 137  
471.omnetpp 8 862 58.0 863 58.0 861 58.0 8 862 58.0 863 58.0 861 58.0
473.astar 8 962 58.4 962 58.4 962 58.4 8 868 64.7 865 64.9 866 64.9
483.xalancbmk 8 731 75.5 731 75.5 731 75.5 8 606 91.1 605 91.3 606 91.0

Operating System Notes

 powersave -f is applied to set CPU to maximum frequency prior to run
 stacksize is set to unlimited prior to run
 ulimit -l 2457600
 PGI_HUGE_PAGES set to 150
 (Total number of huge pages available is 1200)

General Notes



The command numactl has been used to bind processes to CPUs

For information about Fujitsu Siemens Computers please see:
http://www.fujitsu-siemens.com

Base Compiler Invocation

C benchmarks:

 pgcc 

C++ benchmarks:

 pgcpp 

Base Portability Flags

400.perlbench:  -DSPEC_CPU_LP64   -DSPEC_CPU_LINUX_X64 
401.bzip2:  -DSPEC_CPU_LP64 
403.gcc:  -DSPEC_CPU_LP64 
429.mcf:  -DSPEC_CPU_LP64 
445.gobmk:  -DSPEC_CPU_LP64 
456.hmmer:  -DSPEC_CPU_LP64 
458.sjeng:  -DSPEC_CPU_LP64 
462.libquantum:  -DSPEC_CPU_LP64   -DSPEC_CPU_LINUX 
464.h264ref:  -DSPEC_CPU_LP64 
483.xalancbmk:  -DSPEC_CPU_LINUX 

Base Optimization Flags

C benchmarks:

 -fastsse   -Msmartalloc=huge:150   -Mfprelaxed   -Mipa=jobs:4   -Mipa=fast   -Mipa=inline   -tp barcelona-64   -Bstatic_pgi 

C++ benchmarks:

 -fastsse   -Msmartalloc=huge:150   -Mfprelaxed   --zc_eh   -Mipa=jobs:4   -Mipa=fast   -Mipa=inline   -tp barcelona   -Bstatic_pgi 

Peak Compiler Invocation

C benchmarks (except as noted below):

 pgcc 
400.perlbench:  pathcc 
403.gcc:  pathcc 
445.gobmk:  pathcc 
464.h264ref:  pathcc 

C++ benchmarks (except as noted below):

 pgcpp 
483.xalancbmk:  pathCC 

Peak Portability Flags

400.perlbench:  -DSPEC_CPU_LP64   -DSPEC_CPU_LINUX_X64 
401.bzip2:  -DSPEC_CPU_LP64 
445.gobmk:  -DSPEC_CPU_LP64 
456.hmmer:  -DSPEC_CPU_LP64 
458.sjeng:  -DSPEC_CPU_LP64 
462.libquantum:  -DSPEC_CPU_LP64   -DSPEC_CPU_LINUX 
464.h264ref:  -DSPEC_CPU_LP64 
483.xalancbmk:  -DSPEC_CPU_LINUX 

Peak Optimization Flags

C benchmarks:

400.perlbench:  -march=barcelona   -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -IPA:plimit=20000   -LNO:opt=0   -WOPT:if_conv=0   -CG:local_sched_alg=1 
401.bzip2:  -Mpfi=indirect(pass 1)   -Mpfo=indirect(pass 2)   -fastsse   -O4   -Msmartalloc=huge:150   -Mprefetch=t0   -Mnounroll   -tp barcelona-64   -Bstatic_pgi 
403.gcc:  -march=barcelona   -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -OPT:Ofast   -m32 
429.mcf:  -fastsse   -Msmartalloc=huge:150   -Mipa=jobs:4   -Mipa=fast   -Mipa=inline:1   -tp barcelona   -Bstatic_pgi 
445.gobmk:  -march=barcelona   -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -OPT:alias=restrict   -LNO:prefetch=1   -LNO:ignore_feedback=off   -CG:p2align=on 
456.hmmer:  -fastsse   -Mvect=partial   -Munroll=n:8   -Msmartalloc=huge:150   -Msafeptr   -Mprefetch=t0   -Mfprelaxed   -Mipa=jobs:4   -Mipa=const   -Mipa=ptr   -Mipa=arg   -Mipa=inline   -tp barcelona-64   -Bstatic_pgi 
458.sjeng:  -Mpfi(pass 1)   -Mpfo(pass 2)   -Mipa=jobs:4(pass 2)   -Mipa=fast(pass 2)   -Mipa=inline:1(pass 2)   -Mipa=noarg(pass 2)   -fastsse   -Msmartalloc=huge:150   -Mfprelaxed   -tp barcelona-64   -Bstatic_pgi 
462.libquantum:  -fastsse   -Munroll=m:8   -Msmartalloc=huge:150   -Mprefetch=distance:4   -Mfprelaxed   -Mipa=jobs:4   -Mipa=fast   -Mipa=inline   -Mipa=noarg   -tp barcelona-64   -Bstatic_pgi 
464.h264ref:  -march=barcelona   -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -IPA:plimit=20000   -OPT:alias=disjoint   -LNO:prefetch=0   -CG:ptr_load_use=0   -CG:push_pop_int_saved_regs=off 

C++ benchmarks:

471.omnetpp:  basepeak = yes 
473.astar:  -Mpfi(pass 1)   -Mpfo(pass 2)   -Mipa=jobs:4(pass 2)   -Mipa=fast(pass 2)   -Mipa=inline:6(pass 2)   -fastsse   -O4   -Msmartalloc=huge:150   -Msafeptr=global   -Mfprelaxed   --zc_eh   -tp barcelona   -Bstatic_pgi 
483.xalancbmk:  -march=barcelona   -Ofast   -OPT:unroll_times_max=8   -CG:push_pop_int_saved_regs=off   -CG:ptr_load_use=0   -m32   -lsmartheap 

Peak Other Flags

C++ benchmarks:

483.xalancbmk:  -L/opt/SmartHeap_8.1/lib 

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/fsc-mix-pgi-path.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/fsc-mix-pgi-path.xml.