SPEC® CFP2006 Result

IBM Corporation

IBM BladeCenter LS41 (AMD Opteron 8220)

SPECfp®_rate2006 = 89.2

SPECfp_rate_base2006 = 84.0

CPU2006 license:	11	Test date:	Feb-2007
Test sponsor:	IBM Corporation	Hardware Availability:	Apr-2007
Tested by:	IBM Corporation	Software Availability:	Aug-2006

Hardware
CPU Name:	AMD Opteron 8220
CPU Characteristics:
CPU MHz:	2800
FPU:	Integrated
CPU(s) enabled:	8 cores, 4 chips, 2 cores/chip
CPU(s) orderable:	1, 2, 4 chips
Primary Cache:	64 KB I + 64 KB D on chip per core
Secondary Cache:	1 MB I+D on chip per core
L3 Cache:	None
Other Cache:	None
Memory:	32 GB (16 x 2GB DDR2-5300 ECC)
Disk Subsystem:	1 x 73 GB SATA, 10000 RPM
Other Hardware:	None

Software
Operating System:	SLES9 SP3 for AMD64/EM64T
Compiler:	QLogic PathScale Compiler Suite 2.5
Auto Parallel:	No
File System:	ext3
System State:	Multi-user, run level 3
Base Pointers:	64-bit
Peak Pointers:	32/64-bit
Other Software:	None

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.
410.bwaves	8	1142	95.2	1141	95.3	1142	95.2	8	1120	97.1	1118	97.3	1119	97.2
416.gamess	8	1409	111	1408	111	1408	111	8	1230	127	1228	128	1229	127
433.milc	8	1215	60.5	1211	60.6	1213	60.6	8	1205	61.0	1203	61.1	1202	61.1
434.zeusmp	8	887	82.1	888	82.0	889	81.9	8	871	83.6	872	83.5	871	83.5
435.gromacs	8	587	97.4	586	97.5	586	97.5	8	516	111	516	111	516	111
436.cactusADM	8	1061	90.1	1057	90.5	1056	90.5	8	1058	90.3	1054	90.7	1043	91.7
437.leslie3d	8	1118	67.3	1116	67.4	1124	66.9	8	1118	67.3	1116	67.4	1124	66.9
444.namd	8	657	97.7	657	97.7	657	97.7	8	643	99.8	643	99.8	643	99.8
447.dealII	8	743	123	741	123	741	124	8	574	159	573	160	574	159
450.soplex	8	1177	56.7	1178	56.6	1180	56.5	8	1026	65.0	1027	65.0	1026	65.0
453.povray	8	343	124	343	124	343	124	8	295	144	295	144	295	144
454.calculix	8	1125	58.7	1126	58.6	1126	58.6	8	1077	61.3	1078	61.2	1077	61.3
459.GemsFDTD	8	1394	60.9	1411	60.2	1409	60.2	8	1333	63.7	1343	63.2	1339	63.4
465.tonto	8	776	101	775	102	775	102	8	758	104	758	104	759	104
470.lbm	8	1738	63.2	1710	64.3	1699	64.7	8	1687	65.2	1707	64.4	1698	64.7
481.wrf	8	917	97.5	918	97.3	918	97.3	8	917	97.5	918	97.3	918	97.3
482.sphinx3	8	1779	87.7	1773	87.9	1777	87.8	8	1760	88.6	1755	88.9	1753	88.9

Operating System Notes

 taskset utility used to bind CPU(s) to processes

Base Compiler Invocation

C benchmarks:

pathcc

C++ benchmarks:

pathCC

Fortran benchmarks:

pathf95

Benchmarks using both Fortran and C:

pathcc pathf95

Base Portability Flags

410.bwaves:	-DSPEC_CPU_LP64
416.gamess:	-DSPEC_CPU_LP64
433.milc:	-DSPEC_CPU_LP64
434.zeusmp:	-DSPEC_CPU_LP64
435.gromacs:	-DSPEC_CPU_LP64
436.cactusADM:	-DSPEC_CPU_LP64 -fno-second-underscore
437.leslie3d:	-DSPEC_CPU_LP64
444.namd:	-DSPEC_CPU_LP64
447.dealII:	-DSPEC_CPU_LP64 -DSPEC_CPU_TABLE_WORKAROUND
450.soplex:	-DSPEC_CPU_LP64
453.povray:	-DSPEC_CPU_LP64
454.calculix:	-DSPEC_CPU_LP64
459.GemsFDTD:	-DSPEC_CPU_LP64
465.tonto:	-DSPEC_CPU_LP64
470.lbm:	-DSPEC_CPU_LP64
481.wrf:	-DSPEC_CPU_LP64 -DSPEC_CPU_LINUX -fno-second-underscore
482.sphinx3:	-DSPEC_CPU_LP64

Base Optimization Flags

C benchmarks:

-march=auto -Ofast

C++ benchmarks:

-march=auto -Ofast

Fortran benchmarks:

-march=auto -Ofast

Benchmarks using both Fortran and C:

-march=auto -Ofast

Base Other Flags

Peak Compiler Invocation

C benchmarks:

pathcc

C++ benchmarks:

pathCC

Fortran benchmarks:

pathf95

Benchmarks using both Fortran and C:

pathcc pathf95

Peak Portability Flags

410.bwaves:	-DSPEC_CPU_LP64
416.gamess:	-DSPEC_CPU_LP64
433.milc:	-DSPEC_CPU_LP64
434.zeusmp:	-DSPEC_CPU_LP64
435.gromacs:	-DSPEC_CPU_LP64
436.cactusADM:	-DSPEC_CPU_LP64 -fno-second-underscore
437.leslie3d:	-DSPEC_CPU_LP64
444.namd:	-DSPEC_CPU_LP64
447.dealII:	-DSPEC_CPU_TABLE_WORKAROUND
453.povray:	-DSPEC_CPU_LP64
454.calculix:	-DSPEC_CPU_LP64
459.GemsFDTD:	-DSPEC_CPU_LP64
465.tonto:	-DSPEC_CPU_LP64
470.lbm:	-DSPEC_CPU_LP64
481.wrf:	-DSPEC_CPU_LP64 -DSPEC_CPU_LINUX -fno-second-underscore
482.sphinx3:	-DSPEC_CPU_LP64

Peak Optimization Flags

C benchmarks:

-march=auto -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast

C++ benchmarks:

444.namd:	-march=auto -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast
447.dealII:	-march=auto -Ofast -m32 -fno-exceptions
450.soplex:	-march=auto -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -m32 -O3 -OPT:IEEE_arith=3 -CG:load_exe=0 -CG:movnti=1 -LNO:minvariant=off -fno-exceptions
453.povray:	-march=auto -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -fno-fast-math

Fortran benchmarks:

410.bwaves:	-march=auto -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -OPT:Ofast -OPT:IEEE_arith=3 -LNO:blocking=off -LNO:ignore_feedback=off
416.gamess:	-march=auto -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O2 -OPT:Ofast -OPT:ro=3 -OPT:unroll_size=256
434.zeusmp:	-march=auto -Ofast -CG:local_fwd_sched=on -LNO:blocking=off -LNO:interchange=off -LNO:fu=10 -LNO:full_unroll_outer=on
437.leslie3d:	basepeak = yes
459.GemsFDTD:	-march=auto -Ofast -LNO:fission=2 -LNO:prefetch=0
465.tonto:	-march=auto -Ofast -CG:local_fwd_sched=on -IPA:plimit=525

Benchmarks using both Fortran and C:

435.gromacs:	-march=auto -O3 -OPT:rsqrt=2 -OPT:ro=3
436.cactusADM:	-march=auto -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -LNO:prefetch_ahead=5 -LNO:ou_prod_max=10 -LNO:full_unroll=5 -ipa
454.calculix:	-march=auto -Ofast -CG:prefetch=off -LNO:simd=0 -OPT:unroll_times_max=8 -WOPT:mem_opnds=on
481.wrf:	basepeak = yes

Peak Other Flags

C benchmarks:

-IPA:max_jobs=2

C++ benchmarks:

-IPA:max_jobs=2

Fortran benchmarks:

-IPA:max_jobs=2

Benchmarks using both Fortran and C:

-IPA:max_jobs=2

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/CPU2006_flags.20090714.17.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/CPU2006_flags.20090714.17.xml.