SPEC® CINT2006 Result

Fujitsu Limited

PRIMEQUEST 580A

SPECint®_rate2006 = 808

SPECint_rate_base2006 = 727

CPU2006 license:	19	Test date:	Mar-2008
Test sponsor:	Fujitsu Limited	Hardware Availability:	May-2008
Tested by:	Fujitsu Limited	Software Availability:	Feb-2008

Hardware
CPU Name:	Dual-Core Intel Itanium 9150M
CPU Characteristics:	1.66GHz/24MB, 667MHz FSB
CPU MHz:	1667
FPU:	Integrated
CPU(s) enabled:	64 cores, 32 chips, 2 cores/chip
CPU(s) orderable:	2-32 chips
Primary Cache:	16 KB I + 16 KB D on chip per core
Secondary Cache:	1 MB I + 256 KB D on chip per core
L3 Cache:	12 MB I+D on chip per core
Other Cache:	None
Memory:	512 GB (256 x 2GB DDR2-667 DIMMs)
Disk Subsystem:	2 x 147GB (SCSI Ultra 320, 10000rpm) No RAID configuration
Other Hardware:	None

Software
Operating System:	Red Hat Enterprise Linux 5.1, Kernel 2.6.18-53.el5 on an ia64
Compiler:	Intel C++ Compiler for Linux 10.1 (Build 20080112)
Auto Parallel:	No
File System:	ext2
System State:	Runlevel 1 (single user mode)
Base Pointers:	64-bit
Peak Pointers:	32/64-bit
Other Software:	MicroQuill Smartheap 8.0

Results Table

Benchmark	Base							Peak
Benchmark	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	64	1058	591	1058	591	1059	591	64	851	735	852	734	849	737
401.bzip2	64	1082	571	1082	571	1082	571	64	1021	605	1022	604	1023	603
403.gcc	64	959	537	960	537	960	537	64	845	610	844	610	845	610
429.mcf	64	1042	560	1045	559	1047	557	64	731	799	728	802	730	800
445.gobmk	64	976	688	977	687	977	687	64	818	821	819	820	818	821
456.hmmer	64	344	1730	345	1730	344	1730	64	345	1730	344	1730	345	1730
458.sjeng	64	1277	606	1276	607	1277	606	64	1128	686	1129	686	1129	686
462.libquantum	64	873	1520	870	1520	856	1550	64	844	1570	834	1590	804	1650
464.h264ref	64	1118	1270	1118	1270	1118	1270	64	1060	1340	1060	1340	1060	1340
471.omnetpp	64	1157	346	1156	346	1155	346	64	1099	364	1098	364	1101	363
473.astar	64	631	712	631	712	630	713	64	595	756	595	756	598	751
483.xalancbmk	64	700	631	700	631	700	631	64	702	630	703	628	701	630

General Notes


 Processes are bound to CPUs using taskset.

 limit stacksize unlimited

 Memory system is in "Non Mirror Mode".

 The following 2 environment variables were set
     MALLOC_MMAP_MAX_=0
     MALLOC_TRIM_THRESHOLD_=-1
 This will cause use of sbrk() calls instead of
 mmap() calls to get memory from the system.

Base Compiler Invocation

C benchmarks:

icc

C++ benchmarks:

icpc

Base Portability Flags

400.perlbench:	-DSPEC_CPU_LP64 -DSPEC_CPU_LINUX_IA64
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
471.omnetpp:	-DSPEC_CPU_LP64
473.astar:	-DSPEC_CPU_LP64
483.xalancbmk:	-DSPEC_CPU_LP64 -DSPEC_CPU_LINUX

Peak Compiler Invocation

C benchmarks:

icc

C++ benchmarks:

icpc

Peak Portability Flags

Same as Base Portability Flags

Peak Optimization Flags

C benchmarks:

400.perlbench:	-prof-gen(pass 1) -prof-use(pass 2) -fast -ansi_alias -IPF_fp_relaxed -opt-mod-versioning -unroll-aggressive -inline-factor=150
401.bzip2:	-prof-gen(pass 1) -prof-use(pass 2) -fast -IPF-fp-relaxed -ansi-alias -fno-alias -auto-ilp32 -opt-prefetch-next-iteration
403.gcc:	-prof-gen(pass 1) -prof-use(pass 2) -fast -ansi_alias -auto-ilp32 -IPF_fp_relaxed -no-opt-prefetch-initial-values -opt-prefetch-next-iteration -unroll-aggressive
429.mcf:	-fast -IPF-fp-relaxed -auto-ilp32 -ansi-alias -opt-prefetch-next-iteration
445.gobmk:	-prof-gen(pass 1) -prof-use(pass 2) -fast -IPF_fp_relaxed -auto-ilp32 -no-opt-prefetch-initial-values -opt-prefetch-next-iteration -ansi-alias
456.hmmer:	-fast -IPF_fp_relaxed -auto-ilp32 -no-opt-prefetch-initial-values
458.sjeng:	-prof-gen(pass 1) -prof-use(pass 2) -fast -IPF_fp_relaxed -unroll-aggressive -no-prefetch -opt-prefetch-next-iteration
462.libquantum:	-fast -IPF-fp-relaxed -auto-ilp32 -ansi-alias -opt-mod-versioning -no-opt-prefetch-initial-values -opt-prefetch-issue-excl-hint
464.h264ref:	-fast -IPF-fp-relaxed -ansi-alias -fno-alias -auto-ilp32 -no-prefetch -inline-factor=150 -opt-mod-versioning -unroll-aggressive -opt-prefetch-next-iteration

C++ benchmarks:

471.omnetpp:	-prof-gen(pass 1) -prof-use(pass 2) -fast -IPF-fp-relaxed -ansi-alias -fno-alias -inline-max-per-routine=50 -inline-factor=150 -Wl,-z,muldefs /opt/SmartHeap_8/lib/libsmartheapC64.a /opt/SmartHeap_8/lib/libsmartheap64.a
473.astar:	-fast -IPF-fp-relaxed -no-prefetch -ansi-alias -fno-alias -inline-max-size=5000 -Wl,-z,muldefs /opt/SmartHeap_8/lib/libsmartheapC64.a /opt/SmartHeap_8/lib/libsmartheap64.a
483.xalancbmk:	-fast -IPF-fp-relaxed -unroll-aggressive -ansi-alias -no-opt-prefetch-initial-values -Wl,-z,muldefs /opt/SmartHeap_8/lib/libsmartheapC64.a /opt/SmartHeap_8/lib/libsmartheap64.a

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/Fujitsu.PQ580A.ipf.linux.flags.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/Fujitsu.PQ580A.ipf.linux.flags.xml.