SPEC® CFP2006 Result

Dell Inc.

PowerEdge M905 (AMD Opteron 8356, 2.3 GHz)

SPECfp®_rate2006 = 158

SPECfp_rate_base2006 = 145

CPU2006 license:	55	Test date:	Jul-2008
Test sponsor:	Dell Inc.	Hardware Availability:	Aug-2008
Tested by:	Dell Inc.	Software Availability:	May-2008

Hardware
CPU Name:	AMD Opteron 8356
CPU Characteristics:
CPU MHz:	2300
FPU:	Integrated
CPU(s) enabled:	16 cores, 4 chips, 4 cores/chip
CPU(s) orderable:	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:	2 MB I+D on chip per chip
Other Cache:	None
Memory:	32 GB (16 x 2GB, DDR2-667, CL5)
Disk Subsystem:	1 x 36 GB SAS 15 K RPM (OS), 1 x 73 GB SAS 10K RPM (CPU2006)
Other Hardware:	None

Software
Operating System:	SUSE Linux Enterprise Server 10 (x86_64) SP2, Kernel 2.6.16-60.0.21-smp
Compiler:	PGI Server Complete Version 7.2 PathScale Compiler Suite Version 3.1
Auto Parallel:	No
File System:	ReiserFS
System State:	Run level 3 (multi-user)
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	16	1927	113	1924	113	1931	113	16	1844	118	1828	119	1836	118
416.gamess	16	1382	227	1383	227	1385	226	16	1288	243	1277	245	1274	246
433.milc	16	1442	102	1441	102	1455	101	16	1409	104	1408	104	1408	104
434.zeusmp	16	887	164	886	164	884	165	16	893	163	897	162	891	163
435.gromacs	16	667	171	667	171	667	171	16	541	211	541	211	540	212
436.cactusADM	16	1164	164	1171	163	1204	159	16	1113	172	1109	172	1093	175
437.leslie3d	16	1776	84.7	1775	84.7	1777	84.6	16	1618	93.0	1617	93.0	1615	93.2
444.namd	16	757	170	757	170	757	169	16	667	192	665	193	665	193
447.dealII	16	901	203	898	204	897	204	16	599	306	603	304	602	304
450.soplex	16	1388	96.1	1379	96.8	1379	96.7	16	1393	95.8	1360	98.1	1359	98.2
453.povray	16	372	229	372	229	371	229	16	310	274	309	275	309	275
454.calculix	16	592	223	592	223	593	223	16	594	222	594	222	593	223
459.GemsFDTD	16	1957	86.8	1954	86.9	1956	86.8	16	1831	92.7	1835	92.5	1832	92.7
465.tonto	16	849	185	846	186	849	185	16	742	212	744	212	742	212
470.lbm	16	2375	92.6	2386	92.1	2386	92.1	16	2281	96.4	2282	96.3	2283	96.3
481.wrf	16	1112	161	1112	161	1114	160	16	1126	159	1121	159	1124	159
482.sphinx3	16	2436	128	2440	128	2440	128	16	2216	141	2223	140	2223	140

Operating System Notes

 'numactl' was used to bind copies to the cores
 Environment variable PGI_HUGE_PAGES set to 150
 'ulimit -s unlimited' was used to set environment stack size
 mount -t hugetlbfs nodev /mnt/hugepages
 'ulimit -l 4915200'  was used to set environment locked pages in memory limit
 Set vm/nr_hugepages=2400 in /etc/sysctl.conf

Base Compiler Invocation

C benchmarks:

pgcc

C++ benchmarks:

pgcpp

Fortran benchmarks:

pgf95

Benchmarks using both Fortran and C:

pgcc pgf95

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 -Mnomain
436.cactusADM:	-DSPEC_CPU_LP64 -Mnomain
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 -Mnomain
459.GemsFDTD:	-DSPEC_CPU_LP64
465.tonto:	-DSPEC_CPU_LP64
470.lbm:	-DSPEC_CPU_LP64
481.wrf:	-DSPEC_CPU_LP64 -DSPEC_CPU_CASE_FLAG -DSPEC_CPU_LINUX
482.sphinx3:	-DSPEC_CPU_LP64

Base Optimization Flags

Base Other Flags

C benchmarks:

-w -Mipa=jobs:4

C++ benchmarks:

-w -Mipa=jobs:4

Fortran benchmarks:

-w -Mipa=jobs:4

Benchmarks using both Fortran and C:

-w -Mipa=jobs:4

Peak Compiler Invocation

C benchmarks (except as noted below):

	pathcc
433.milc:	pgcc

C++ benchmarks (except as noted below):

	pathCC
444.namd:	pgcpp

Fortran benchmarks (except as noted below):

	pathf95
410.bwaves:	pgf95
434.zeusmp:	pgf95

Benchmarks using both Fortran and C (except as noted below):

	pgcc pgf95
436.cactusADM:	pathcc pathf95
481.wrf:	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 -Mnomain
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 -Mnomain
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:

433.milc:	-fastsse -Msmartalloc=huge:150 -Msafeptr -Mfprelaxed -Mipa=inline -Mipa=arg -Mipa=const -Mipa=ptr -Mipa=shape -tp barcelona-64 -Bstatic_pgi
470.lbm:	-march=barcelona -Ofast -m3dnow
482.sphinx3:	-march=barcelona -Ofast

C++ benchmarks:

444.namd:	-Mpfi(pass 1) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mpfo(pass 2) -fast -Mfprelaxed -Msmartalloc=huge:150 --zc_eh -Mnodepchk -Munroll=n:4 -Munroll=m:8 -tp barcelona-64 -Bstatic_pgi
447.dealII:	-march=barcelona -Ofast -static -INLINE:aggressive=on -OPT:malloc_alg=1 -m32 -fno-exceptions
450.soplex:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -m32 -O3 -TENV:frame_pointer=off -LNO:prefetch=1
453.povray:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -CG:load_exe=0

Fortran benchmarks:

410.bwaves:	-Mpfi(pass 1) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mpfo(pass 2) -fastsse -Mfprelaxed -Msmartalloc -Mprefetch=distance:12 -Mprefetch=nta -tp barcelona-64 -Bstatic_pgi
416.gamess:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O2 -OPT:Ofast -OPT:ro=3 -OPT:unroll_size=256
434.zeusmp:	-fastsse -Mfprelaxed -Msmartalloc=huge:150 -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi
437.leslie3d:	-march=barcelona -Ofast -m3dnow -OPT:unroll_size=256 -CG:load_exe=0 -OPT:malloc_alg=1
459.GemsFDTD:	-march=barcelona -Ofast -LNO:fission=2 -LNO:simd=2 -OPT:malloc_alg=1
465.tonto:	-march=barcelona -Ofast -OPT:malloc_alg=1 -OPT:alias=no_f90_pointer_alias -LNO:blocking=off -CG:load_exe=1 -IPA:plimit=525

Benchmarks using both Fortran and C:

435.gromacs:	-fast -Mfpapprox=rsqrt -Mipa=fast -Mipa=inline -Mfprelaxed -Msmartalloc=huge:150 -tp barcelona-64 -Bstatic_pgi
436.cactusADM:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -WOPT:aggstr=0
454.calculix:	-fastsse -Mfprelaxed -Msmartalloc=huge:150 -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi
481.wrf:	-march=barcelona -Ofast -LNO:blocking=off -LNO:prefetch_ahead=10 -OPT:malloc_alg=1 -m3dnow -LANG:copyinout=off -IPA:callee_limit=5000

Peak Other Flags

C benchmarks:

433.milc:

-w -Mipa=jobs:4

C++ benchmarks:

444.namd:

-w -Mipa=jobs:4(pass 2)

Fortran benchmarks:

410.bwaves:	-w -Mipa=jobs:4(pass 2)
434.zeusmp:	-w -Mipa=jobs:4

Benchmarks using both Fortran and C:

435.gromacs:	-w -Mipa=jobs:4
454.calculix:	-w -Mipa=jobs:4

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/amd123GH-flags.20090713.01.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/amd123GH-flags.20090713.01.xml.