SPEC® CFP2006 Result

IBM Corporation

IBM System x3755 (AMD Opteron 8384)

SPECfp®_rate2006 = 204

SPECfp_rate_base2006 = 183

CPU2006 license:	11	Test date:	Nov-2008
Test sponsor:	IBM Corporation	Hardware Availability:	Mar-2009
Tested by:	Advanced Micro Devices	Software Availability:	Jun-2008

Hardware
CPU Name:	AMD Opteron 8384
CPU Characteristics:
CPU MHz:	2700
FPU:	Integrated
CPU(s) enabled:	16 cores, 4 chips, 4 cores/chip
CPU(s) orderable:	1,2,3,4 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:	6 MB I+D on chip per chip
Other Cache:	None
Memory:	64 GB (16 x 4 GB, DDR2-667 CL5 Reg Dual Rank)
Disk Subsystem:	1 x 73.4 GB SAS, 15000 RPM
Other Hardware:	None

Software
Operating System:	SuSE Linux Enterprise Server 10 (x86_64) SP1, Kernel 2.6.16.46-0.12-smp
Compiler:	PGI Server Complete Version 7.2 PathScale Compiler Suite Version 3.2
Auto Parallel:	Yes
File System:	ReiserFS
System State:	Run level 3 (Full multiuser with network)
Base Pointers:	64-bit
Peak Pointers:	32/64-bit
Other Software:	binutils 2.18 32-bit and 64-bit libhugetlbfs libraries

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	1442	151	1452	150	1447	150	16	1457	149	1459	149	1447	150
416.gamess	16	1171	268	1170	268	1173	267	16	1050	298	1050	298	1050	299
433.milc	16	1182	124	1184	124	1174	125	16	1182	124	1184	124	1174	125
434.zeusmp	16	753	193	753	193	754	193	16	706	206	701	208	706	206
435.gromacs	16	477	239	481	238	477	239	16	391	292	391	292	391	292
436.cactusADM	16	944	203	945	202	945	202	4	175	273	176	272	176	272
437.leslie3d	16	1401	107	1401	107	1402	107	16	1295	116	1297	116	1297	116
444.namd	16	619	207	619	207	619	207	16	535	240	535	240	536	239
447.dealII	16	663	276	665	275	667	274	16	528	347	536	342	532	344
450.soplex	16	1135	118	1135	118	1135	118	16	1037	129	1035	129	1034	129
453.povray	16	301	282	302	282	303	281	16	263	323	263	323	262	324
454.calculix	16	479	276	480	275	480	275	16	408	323	407	324	407	325
459.GemsFDTD	16	1612	105	1589	107	1590	107	16	1531	111	1527	111	1531	111
465.tonto	16	661	238	658	239	660	238	16	546	288	547	288	547	288
470.lbm	16	2115	104	2114	104	2115	104	16	2113	104	2114	104	2113	104
481.wrf	16	960	186	965	185	965	185	16	915	195	911	196	916	195
482.sphinx3	16	1427	219	1438	217	1435	217	16	1321	236	1319	236	1319	236

Submit Notes

The config file option 'submit' was used.
 'numactl' was used to bind copies to the cores

Operating System Notes

 The libhugetlbfs libraries were installed using the
 installation rpms that came with the distribution.

 '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=14336 in /etc/sysctl.conf
 mount -t hugetlbfs nodev /mnt/hugepages

General Notes

Environment variables set by runspec before the start of the run:
HUGETLB_MORECORE = "yes"
LD_LIBRARY_PATH = "/root/work/cpu2006v1.1/amd909gh-libs/64:/root/work/cpu2006v1.1/amd909gh-libs/32"
NCPUS = "4"

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:

-Mipa=jobs:4

C++ benchmarks:

-Mipa=jobs:4

Fortran benchmarks:

-Mipa=jobs:4

Benchmarks using both Fortran and C:

-Mipa=jobs:4

Peak Compiler Invocation

C benchmarks:

pgcc

C++ benchmarks (except as noted below):

	pathCC
444.namd:	pgcpp

Fortran benchmarks (except as noted below):

	pathf95
410.bwaves:	pgf95
434.zeusmp:	pgf95
437.leslie3d:	pgf95

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

	pgcc pgf95
435.gromacs:	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
436.cactusADM:	-DSPEC_CPU_LP64 -Mnomain
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:	basepeak = yes
470.lbm:	-Mvect=cachesize:6291456 -fastsse -Msmartalloc=huge -Mprefetch=t0 -Mloop32 -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi
482.sphinx3:	-Mpfi=indirect(pass 1) -Mpfo=indirect(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Mfprelaxed -Msmartalloc -tp barcelona-64 -Bstatic_pgi

C++ benchmarks:

444.namd:	-Mpfi(pass 1) -Mpfo(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Munroll=n:4 -Munroll=m:8 -Msmartalloc=huge -Mnodepchk -Mfprelaxed --zc_eh -tp barcelona-64 -Bstatic_pgi
447.dealII:	-march=barcelona -Ofast -static -INLINE:aggressive=on -fno-exceptions -m32
450.soplex:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -L/usr/lib -lhugetlbfs(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
453.povray:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -INLINE:aggressive=on

Fortran benchmarks:

410.bwaves:	-Mvect=cachesize:6291456 -fastsse -Msmartalloc -Mprefetch=nta -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi
416.gamess:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT(pass 2) -L/usr/lib64 -lhugetlbfs(pass 2) -O2 -OPT:Ofast -OPT:ro=3 -OPT:unroll_size=256
434.zeusmp:	-Mvect=cachesize:6291456 -fastsse -Mfprelaxed -Mprefetch=distance:8 -Mprefetch=t0 -Msmartalloc=huge -Msmartalloc=hugebss -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi
437.leslie3d:	-Mpfi=indirect(pass 1) -Mpfo=indirect(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Mvect=fuse -Msmartalloc=huge -Mprefetch=distance:8 -Mprefetch=t0 -Mfprelaxed -tp barcelona-64 -Bstatic_pgi
459.GemsFDTD:	-march=barcelona -Ofast -LNO:fission=2 -LNO:simd=2 -LNO:prefetch_ahead=1 -CG:load_exe=0 -CG:prefer_lru_reg=off -OPT:malloc_alg=1 -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT -L/usr/lib64 -lhugetlbfs
465.tonto:	-march=barcelona -Ofast -OPT:alias=no_f90_pointer_alias -LNO:blocking=off -CG:load_exe=1 -IPA:plimit=525 -OPT:malloc_alg=1 -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT -L/usr/lib64 -lhugetlbfs

Benchmarks using both Fortran and C:

435.gromacs:	-march=barcelona -Ofast -OPT:rsqrt=2 -OPT:malloc_alg=1 -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT -L/usr/lib64 -lhugetlbfs
436.cactusADM:	-Mvect=cachesize:6291456 -fastsse -Mconcur -Msmartalloc=huge -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi
454.calculix:	-Mpfi=indirect(pass 1) -Mpfo=indirect(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Msmartalloc=huge -Mprefetch=t0 -Mpre -Mfprelaxed -tp barcelona-64 -Bstatic_pgi
481.wrf:	-march=barcelona -Ofast -LNO:blocking=off -LNO:prefetch_ahead=10 -LANG:copyinout=off -IPA:callee_limit=5000 -GRA:prioritize_by_density=on -OPT:malloc_alg=1 -m3dnow -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT -L/usr/lib64 -lhugetlbfs

Peak Other Flags

C benchmarks:

-Mipa=jobs:4(pass 2)

C++ benchmarks:

444.namd:

-Mipa=jobs:4(pass 2)

Fortran benchmarks (except as noted below):

	-Mipa=jobs:4(pass 2)
416.gamess:	No flags used
459.GemsFDTD:	No flags used
465.tonto:	No flags used

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

	-Mipa=jobs:4(pass 2)
435.gromacs:	No flags used
481.wrf:	No flags used

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/pgi72_linux_flags.html,
http://www.spec.org/cpu2006/flags/CPU2006_flags.20090710.html,
http://www.spec.org/cpu2006/flags/amd-platform-amd909gh.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/pgi72_linux_flags.xml,
http://www.spec.org/cpu2006/flags/CPU2006_flags.20090710.xml,
http://www.spec.org/cpu2006/flags/amd-platform-amd909gh.xml.