SPEC® CINT2006 Result

Dell Inc.

PowerEdge M905 (AMD Opteron 8356, 2.3 GHz)

SPECint®_rate2006 = 182

SPECint_rate_base2006 = 154

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:	32/64-bit
Peak Pointers:	32/64-bit
Other Software:	Microquill SmartHeap V8.1

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	16	859	182	886	176	894	175	16	653	239	642	244	644	243
401.bzip2	16	1207	128	1244	124	1244	124	16	1199	129	1195	129	1195	129
403.gcc	16	1270	101	1296	99.4	1294	99.5	16	966	133	968	133	978	132
429.mcf	16	1466	99.5	1473	99.1	1470	99.3	16	1112	131	1112	131	1112	131
445.gobmk	16	921	182	922	182	920	182	16	740	227	739	227	740	227
456.hmmer	16	633	236	631	237	631	236	16	445	336	437	342	437	342
458.sjeng	16	1050	184	1048	185	1051	184	16	959	202	957	202	958	202
462.libquantum	16	1421	233	1419	234	1411	235	16	1439	230	1431	232	1433	231
464.h264ref	16	1229	288	1230	288	1228	288	16	1180	300	1183	299	1180	300
471.omnetpp	16	1032	96.9	1032	96.9	1032	96.9	16	1032	96.9	1032	96.9	1032	96.9
473.astar	16	1005	112	1006	112	1005	112	16	882	127	877	128	879	128
483.xalancbmk	16	768	144	771	143	768	144	16	627	176	628	176	626	176

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

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:

-fast -Mipa=fast -Mipa=inline -Mfprelaxed -Msmartalloc=huge:150 -tp barcelona-64 -Bstatic_pgi

C++ benchmarks:

-fastsse -Mipa=fast -Mipa=inline -Mfprelaxed -Msmartalloc=huge:150 --zc_eh -tp barcelona -Bstatic_pgi

Base Other Flags

C benchmarks:

-w -Mipa=jobs:4

C++ benchmarks:

-w -Mipa=jobs:4

Peak Compiler Invocation

C benchmarks (except as noted below):

	pgcc
400.perlbench:	pathcc
403.gcc:	pathcc
445.gobmk:	pathcc

C++ benchmarks (except as noted below):

	pathCC
471.omnetpp:	pgcpp

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 -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -IPA:plimit=20000 -LNO:opt=0 -WOPT:if_conv=0 -CG:local_sched_alg=1
401.bzip2:	-Mpfi(pass 1) -Mpfo(pass 2) -fast -O4 -Msmartalloc=huge:150 -Mnounroll -tp barcelona-64 -Bstatic_pgi
403.gcc:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -m32 -O3 -OPT:Ofast
429.mcf:	-fastsse -Mipa=fast -Mipa=inline:1 -Msmartalloc=huge:150 -tp barcelona -Bstatic_pgi
445.gobmk:	-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -O3 -OPT:alias=restrict -LNO:opt=0 -CG:p2align=on
456.hmmer:	-fastsse -Munroll=n:8 -Msmartalloc=huge:150 -Mfprelaxed -Mvect=partial -Msafeptr -Mipa=const -Mipa=ptr -Mipa=arg -Mipa=inline -tp barcelona-64 -Bstatic_pgi
458.sjeng:	-Mpfi(pass 1) -Mipa=fast(pass 2) -Mipa=inline:1(pass 2) -Mipa=noarg(pass 2) -Mpfo(pass 2) -fastsse -Msmartalloc=huge:150 -Mfprelaxed -tp barcelona-64 -Bstatic_pgi
462.libquantum:	-fastsse -Mfprelaxed -Msmartalloc=huge:150 -Munroll=m:8 -Mipa=fast -Mipa=inline -Mipa=noarg -tp barcelona-64 -Bstatic_pgi
464.h264ref:	-Mpfi=indirect(pass 1) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mpfo=indirect(pass 2) -fastsse -Msmartalloc=huge:150 -Mfprelaxed -tp barcelona-64 -Bstatic_pgi

C++ benchmarks:

471.omnetpp:	basepeak = yes
473.astar:	-march=barcelona -Ofast -TENV:frame_pointer=off -WOPT:if_conv=0 -GRA:optimize_boundary=on -IPA:plimit=525 -m32 -lsmartheap
483.xalancbmk:	-march=barcelona -Ofast -m32 -OPT:unroll_times_max=8 -CG:push_pop_int_saved_regs=off -CG:ptr_load_use=0 -lsmartheap

Peak Other Flags

C benchmarks (except as noted below):

	-w -Mipa=jobs:4(pass 2)
400.perlbench:	No flags used
401.bzip2:	-w
403.gcc:	No flags used
445.gobmk:	No flags used

C++ benchmarks (except as noted below):

	-L/root/work/cpu2006/amd123GH.libs/32
471.omnetpp:	-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.