SPEC® CFP2006 Result

Dell Inc.

PowerEdge R815 (AMD Opteron 6172, 2.10 GHz)

SPECfp®_rate2006 = 614

SPECfp_rate_base2006 = 562

CPU2006 license:	55	Test date:	Apr-2010
Test sponsor:	Dell Inc.	Hardware Availability:	Mar-2010
Tested by:	Dell Inc.	Software Availability:	Feb-2010

Hardware
CPU Name:	AMD Opteron 6172
CPU Characteristics:
CPU MHz:	2100
FPU:	Integrated
CPU(s) enabled:	48 cores, 4 chips, 12 cores/chip
CPU(s) orderable:	2,4 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:	128 GB (32 x 4 GB DDR3-1333 DR RDIMM, CL9, ECC)
Disk Subsystem:	1 x 148 GB 10000 RPM SAS
Other Hardware:	None

Software
Operating System:	SUSE Linux Enterprise Server 11 (x86_64), Kernel 2.6.27.19-5-smp
Compiler:	x86 Open64 4.2.3 Compiler Suite (from AMD)
Auto Parallel:	Yes
File System:	ext3
System State:	Run level 3 (Full multiuser with network)
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	48	1241	526	1245	524	1246	523	48	1227	532	1230	530	1230	530
416.gamess	48	1441	652	1433	656	1438	654	48	1330	706	1393	675	1332	706
433.milc	48	1148	384	1149	383	1149	383	48	1045	421	1046	421	1045	422
434.zeusmp	48	799	546	799	547	799	547	48	756	578	758	576	759	576
435.gromacs	48	652	526	650	528	650	527	48	509	673	521	658	529	648
436.cactusADM	48	947	606	949	605	949	605	8	109	877	109	878	116	823
437.leslie3d	48	1201	376	1198	377	1198	377	48	1199	376	1197	377	1197	377
444.namd	48	749	514	741	519	742	519	48	708	544	684	563	677	569
447.dealII	48	639	860	646	850	631	871	48	534	1030	531	1030	528	1040
450.soplex	48	1452	276	1099	364	1101	364	48	1382	290	982	408	962	416
453.povray	48	348	733	343	744	344	743	48	338	756	335	763	334	766
454.calculix	48	523	757	529	749	524	756	48	494	802	492	805	492	805
459.GemsFDTD	48	1480	344	1476	345	1481	344	48	1409	361	1408	362	1409	361
465.tonto	48	723	653	718	658	718	658	48	649	727	648	729	649	728
470.lbm	48	3299	200	893	739	891	740	48	3299	200	893	739	891	740
481.wrf	48	894	600	892	601	896	598	48	861	623	862	622	857	626
482.sphinx3	48	1350	693	1328	705	1327	705	48	1314	712	1306	716	1312	713

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=21600 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 = "/root/cpu2006-1.1/amd1002mc-rate-revA-libs/64:/root/cpu2006-1.1/amd1002mc-rate-revA-libs/32"
OMP_NUM_THREADS = "6"

The x86 Open64 Compiler Suite is only available from (and supported by) AMD at
http://developer.amd.com/cpu/open64
Binaries were compiled on SLES10 SP2 with binutils 2.18

Base Compiler Invocation

C benchmarks:

opencc

C++ benchmarks:

openCC

Fortran benchmarks:

openf95

Benchmarks using both Fortran and C:

opencc openf95

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
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 -DSPEC_CPU_CASE_FLAG -fno-second-underscore
482.sphinx3:	-DSPEC_CPU_LP64

Peak Compiler Invocation

C benchmarks:

opencc

C++ benchmarks:

openCC

Fortran benchmarks:

openf95

Benchmarks using both Fortran and C:

opencc openf95

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
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 -DSPEC_CPU_CASE_FLAG -fno-second-underscore
482.sphinx3:	-DSPEC_CPU_LP64

Peak Optimization Flags

C benchmarks:

433.milc:	-march=barcelona -mso -Ofast -CG:movnti=1 -CG:local_sched_alg=1 -CG:locs_shallow_depth=1 -HP:bdt=2m:heap=2m -LNO:prefetch=3
470.lbm:	basepeak = yes
482.sphinx3:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -OPT:malloc_alg=2 -CG:sse_cse_regs=0 -CG:locs_shallow_depth=1 -CG:cmp_peep=on -CG:local_sched_alg=1 -INLINE:aggressive=on

C++ benchmarks:

444.namd:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -LNO:ignore_feedback=off -CG:local_sched_alg=2 -CG:load_exe=0 -CG:compute_to=on -OPT:unroll_size=256 -fno-exceptions -HP:bdt=2m:heap=2m
447.dealII:	-march=barcelona -mso -Ofast -static -INLINE:aggressive=on -LNO:opt=0 -fno-emit-exceptions -m32 -OPT:unroll_times_max=8 -OPT:unroll_size=256 -OPT:unroll_level=2 -HP:bdt=2m:heap=2m -GRA:unspill=on -CG:cmp_peep=on -TENV:frame_pointer=off
450.soplex:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -INLINE:aggressive=on -OPT:IEEE_arith=3 -OPT:IEEE_NaN_Inf=off -OPT:fold_unsigned_relops=on -OPT:malloc_alg=1 -CG:load_exe=0 -fno-exceptions -m32 -HP:bdt=2m
453.povray:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -INLINE:aggressive=on

Fortran benchmarks:

410.bwaves:	-march=barcelona -mso -O3 -OPT:Ofast -OPT:treeheight=on -LNO:blocking=off -LNO:prefetch_ahead=5 -LNO:ignore_feedback=off -WOPT:aggstr=0 -HP:bdt=2m:heap=2m -CG:cmp_peep=on
416.gamess:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -LNO:fu=6 -LNO:blocking=0 -LNO:prefetch=0 -OPT:Ofast -OPT:ro=3 -OPT:unroll_size=256 -HP:bdt=2m:heap=2m
434.zeusmp:	-march=barcelona -mso -Ofast -LNO:blocking=off -LNO:interchange=off -OPT:treeheight=on -OPT:unroll_size=256 -CG:cmp_peep=on -GRA:prioritize_by_density=on -HP
437.leslie3d:	-march=barcelona -mso -Ofast -HP:bdt=2m:heap=2m
459.GemsFDTD:	-march=barcelona -mso -Ofast -LNO:fission=2 -LNO:prefetch_ahead=1 -CG:load_exe=0 -CG:local_sched_alg=1 -HP
465.tonto:	-march=barcelona -mso -Ofast -OPT:alias=no_f90_pointer_alias -LNO:blocking=off -CG:load_exe=1 -IPA:plimit=525 -HP

Benchmarks using both Fortran and C:

435.gromacs:	-march=barcelona -mso -Ofast -OPT:rsqrt=2 -HP:bdt=2m:heap=2m
436.cactusADM:	-march=barcelona -mso -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -apo -LNO:prefetch_ahead=1 -HP:bdt=2m:heap=2m -LANG:heap_allocation_threshold=100
454.calculix:	-march=barcelona -mso -Ofast -CG:load_exe=0 -CG:ptr_load_use=0 -CG:local_sched_alg=2 -CG:compute_to=on -LNO:prefetch_ahead=30 -WOPT:unroll=2 -GRA:optimize_boundary=on -HP:bdt=2m:heap=2m
481.wrf:	-march=barcelona -mso -Ofast -LNO:blocking=off -LNO:prefetch_ahead=10 -LANG:copyinout=off -IPA:callee_limit=5000 -GRA:prioritize_by_density=on -m3dnow -HP

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/x86-open64-4.2.3-flags-revA.html,
http://www.spec.org/cpu2006/flags/amd-platform-revA.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/x86-open64-4.2.3-flags-revA.xml,
http://www.spec.org/cpu2006/flags/amd-platform-revA.xml.