SPEC® CINT2006 Result

SGI

SGI Rackable C1001-G5 (AMD Opteron 6174, 2.20 GHz)

SPECint®_rate2006 = 395

SPECint_rate_base2006 = 343

CPU2006 license:	4	Test date:	Dec-2010
Test sponsor:	SGI	Hardware Availability:	Sep-2010
Tested by:	SGI	Software Availability:	Nov-2010

Hardware
CPU Name:	AMD Opteron 6174
CPU Characteristics:
CPU MHz:	2200
FPU:	Integrated
CPU(s) enabled:	24 cores, 2 chips, 12 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:	12 MB I+D on chip per chip, 6 MB shared / 6 cores
Other Cache:	None
Memory:	64 GB (16 x 4 GB 2Rx4 PC3-10600R-9, ECC)
Disk Subsystem:	5.8 TB RAID 5 20 x 146 GB + 40 x 73 GB FC (Seagate Cheetah 15K.4)
Other Hardware:	None

Software
Operating System:	SUSE Linux Enterprise Server 11 (x86_64) sp1, Kernel 2.6.32.13-0.4-default
Compiler:	x86 Open64 4.2.4 Compiler Suite (from AMD)
Auto Parallel:	No
File System:	NFSv3 IPoIB
System State:	Run level 3 (multi-user)
Base Pointers:	32/64-bit
Peak Pointers:	32/64-bit
Other Software:	binutils 2.18 SmartHeap 8.1 32-bit Library for Linux

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	24	737	318	700	335	700	335	24	560	418	557	421	559	420
401.bzip2	24	992	233	993	233	989	234	24	934	248	933	248	932	248
403.gcc	24	762	254	757	255	750	258	24	664	291	639	302	639	302
429.mcf	24	764	287	759	288	765	286	24	455	482	463	472	472	463
445.gobmk	24	805	313	785	321	800	315	24	698	361	705	357	730	345
456.hmmer	24	454	494	452	495	452	495	24	385	581	380	589	382	586
458.sjeng	24	922	315	935	311	957	303	24	906	320	908	320	908	320
462.libquantum	24	407	1220	408	1220	409	1220	24	409	1220	408	1220	408	1220
464.h264ref	24	1187	447	1183	449	1184	449	24	1057	502	1058	502	1057	502
471.omnetpp	24	683	220	682	220	684	219	24	683	220	682	220	684	219
473.astar	24	795	212	792	213	798	211	24	635	265	637	264	637	264
483.xalancbmk	24	433	382	433	383	433	383	24	410	404	410	404	410	404

Submit Notes

The config file option 'submit' was used.
'numactl' was used to bind copies to the cores.
See the configuration file for details.

Operating System Notes

'ulimit -s unlimited' was used to set environment stack size
'ulimit -l 2097152'  was used to set environment locked pages in memory limit

Set vm/nr_hugepages=10800 in /etc/sysctl.conf
mount -t hugetlbfs nodev /mnt/hugepages

General Notes

Environment variables set by runspec before the start of the run:
HUGETLB_LIMIT = "450"
LD_LIBRARY_PATH = "/nas/store/cma/cpu2006-1.1/amd1002mc-rate-libs-revC/64:/nas/store/cma/cpu2006-1.1/amd1002mc-rate-libs-revC/32"

The x86 Open64 Compiler Suite is only available from (and supported by) AMD at
http://developer.amd.com/cpu/open64

Base Compiler Invocation

C benchmarks:

opencc

C++ benchmarks:

openCC

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:

-march=barcelona -mso -Ofast -CG:local_sched_alg=1 -INLINE:aggressive=on -IPA:plimit=8000 -IPA:small_pu=100 -HP:bdt=2m:heap=2m

C++ benchmarks:

-march=barcelona -mso -Ofast -m32 -INLINE:aggressive=on -CG:cmp_peep=on -L/root/work/libraries/SmartHeap-8.1/lib -lsmartheap

Peak Compiler Invocation

C benchmarks:

opencc

C++ benchmarks:

openCC

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 -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -IPA:plimit=20000 -LNO:opt=0 -OPT:unroll_times_max=8 -OPT:unroll_size=256 -OPT:unroll_level=2 -OPT:keep_ext=on -WOPT:if_conv=0 -CG:local_sched_alg=1 -CG:unroll_fb_req=on -HP:bdt=2m:heap=2m
401.bzip2:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -OPT:alias=disjoint -OPT:goto=off -CG:local_sched_alg=1 -HP:bdt=2m:heap=2m
403.gcc:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -LNO:trip_count=256 -LNO:prefetch_ahead=10 -CG:cmp_peep=on -m32 -HP:bdt=2m:heap=2m -GRA:unspill=on -IPA:small_pu=200
429.mcf:	-march=barcelona -mso -O3 -ipa -INLINE:aggressive=on -CG:gcm=off -GRA:prioritize_by_density=on -m32 -HP:bdt=2m:heap=2m
445.gobmk:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -OPT:alias=restrict -OPT:unroll_times_max=8 -OPT:unroll_size=256 -OPT:unroll_level=2 -OPT:keep_ext=on -ipa -IPA:plimit=750 -IPA:min_hotness=300 -IPA:pu_reorder=1 -LNO:prefetch=1 -LNO:ignore_feedback=off -CG:p2align=on -CG:unroll_fb_req=on -HP:bdt=2m:heap=2m
456.hmmer:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -LNO:prefetch=0 -OPT:alias=disjoint -OPT:unroll_times_max=8 -OPT:unroll_size=256 -OPT:unroll_level=2 -OPT:keep_ext=on -CG:local_sched_alg=1 -CG:cflow=0 -CG:push_pop_int_saved_regs=off -CG:cmp_peep=on -HP:bdt=2m:heap=2m
458.sjeng:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -ipa -LNO:ignore_feedback=off -LNO:full_unroll=10 -LNO:fusion=0 -LNO:fission=2 -IPA:pu_reorder=2 -CG:ptr_load_use=0 -OPT:unroll_times_max=8 -INLINE:aggressive=on
462.libquantum:	-march=barcelona -mso -Ofast -LNO:pf2=0 -CG:gcm=off -CG:use_prefetchnta=on -CG:cmp_peep=on -WOPT:aggstr=0 -HP:bdt=2m:heap=2m -OPT:alias=disjoint -INLINE:aggressive=on -IPA:space=1000 -IPA:plimit=20000
464.h264ref:	-march=barcelona -mso -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:

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/x86-open64-424-flags-rate-revC.20100901.html,
http://www.spec.org/cpu2006/flags/amd-platform-rate-revC.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/x86-open64-424-flags-rate-revC.20100901.xml,
http://www.spec.org/cpu2006/flags/amd-platform-rate-revC.xml.

471.omnetpp:	basepeak = yes
473.astar:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -TENV:frame_pointer=off -WOPT:if_conv=0 -GRA:optimize_boundary=on -OPT:alias=disjoint -INLINE:aggressive=on -IPA:small_pu=3000 -IPA:plimit=3000 -m32 -HP:bdt=2m:heap=2m
483.xalancbmk:	-march=barcelona -mso -Ofast -INLINE:aggressive=on -m32 -CG:cmp_peep=on -GRA:unspill=on -TENV:frame_pointer=off -fno-emit-exceptions -L/root/work/libraries/SmartHeap-8.1/lib -lsmartheap