SPEC® CINT2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

IBM Corporation

IBM System x3755 (AMD Opteron 8356)

CPU2006 license: 11 Test date: Jun-2008
Test sponsor: IBM Corporation Hardware Availability: Jul-2008
Tested by: Advanced Micro Devices Software Availability: Jun-2008
Benchmark results graph
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: 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: 2 MB I+D on chip per chip
Other Cache: None
Memory: 32 GB (16 x 2 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: No
File System: ReiserFS
System State: Run level 3 (Full multiuser with network)
Base Pointers: 32/64-bit
Peak Pointers: 32/64-bit
Other Software: SmartHeap 8.0 32-bit Library for Linux

Results Table

Benchmark Base Peak
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 16 848 184   860 182   859 182   16 679 230 658 237 658 238
401.bzip2 16 1236 125   1245 124   1247 124   16 1207 128 1194 129 1194 129
403.gcc 16 1332 96.7 1336 96.4 1343 95.9 16 1012 127 1004 128 1011 127
429.mcf 16 1409 104   1409 104   1408 104   16 1081 135 1081 135 1079 135
445.gobmk 16 931 180   929 181   931 180   16 739 227 739 227 740 227
456.hmmer 16 637 234   630 237   633 236   16 435 343 437 341 437 341
458.sjeng 16 1007 192   1006 193   1005 193   16 921 210 922 210 923 210
462.libquantum 16 1466 226   1467 226   1466 226   16 1461 227 1468 226 1467 226
464.h264ref 16 1204 294   1203 294   1204 294   16 1166 304 1163 305 1163 304
471.omnetpp 16 942 106   941 106   942 106   16 923 108 919 109 924 108
473.astar 16 926 121   927 121   926 121   16 824 136 823 137 823 136
483.xalancbmk 16 748 148   751 147   750 147   16 629 176 630 175 628 176

Operating System Notes

 'numactl' was used to bind copies to the cores
 'ulimit -s unlimited' was used to set environment stack size
 'ulimit -l 2097152'  was used to set environment locked pages in memory limit
 Environment variable PGI_HUGE_PAGES set to 150
 Set vm/nr_hugepages=2400 in /etc/sysctl.conf
 mount -t hugetlbfs nodev /mnt/hugepages

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:

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

C++ benchmarks:

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

Base Other Flags

C benchmarks:

 -Mipa=jobs:4 

C++ benchmarks:

 -Mipa=jobs:4 

Peak Compiler Invocation

C benchmarks (except as noted below):

 pgcc 
400.perlbench:  pathcc 
403.gcc:  pathcc 
445.gobmk:  pathcc 
464.h264ref:  pathcc 

C++ benchmarks (except as noted below):

 pathCC 
473.astar:  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=indirect(pass 1)   -Mpfo=indirect(pass 2)   -fastsse   -O4   -Msmartalloc=huge:150   -Mprefetch=t0   -Mnounroll   -tp barcelona-64   -Bstatic_pgi 
403.gcc:  -march=barcelona   -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -OPT:Ofast   -m32 
429.mcf:  -fastsse   -Msmartalloc=huge:150   -Mipa=fast   -Mipa=inline:1   -tp barcelona   -Bstatic_pgi 
445.gobmk:  -march=barcelona   -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -OPT:alias=restrict   -LNO:prefetch=1   -LNO:ignore_feedback=off   -CG:p2align=on 
456.hmmer:  -fastsse   -Mvect=partial   -Munroll=n:8   -Msmartalloc=huge:150   -Msafeptr   -Mprefetch=t0   -Mfprelaxed   -Mipa=const   -Mipa=ptr   -Mipa=arg   -Mipa=inline   -tp barcelona-64   -Bstatic_pgi 
458.sjeng:  -Mpfi(pass 1)   -Mpfo(pass 2)   -Mipa=fast(pass 2)   -Mipa=inline:1(pass 2)   -Mipa=noarg(pass 2)   -fastsse   -Msmartalloc=huge:150   -Mfprelaxed   -tp barcelona-64   -Bstatic_pgi 
462.libquantum:  -fastsse   -Munroll=m:8   -Msmartalloc=huge:150   -Mprefetch=distance:4   -Mfprelaxed   -Mipa=fast   -Mipa=inline   -Mipa=noarg   -tp barcelona-64   -Bstatic_pgi 
464.h264ref:  -march=barcelona   -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -IPA:plimit=20000   -OPT:alias=disjoint   -LNO:prefetch=0   -CG:ptr_load_use=0   -CG:push_pop_int_saved_regs=off 

C++ benchmarks:

471.omnetpp:  -march=barcelona   -Ofast   -CG:gcm=off   -INLINE:aggressive=on   -OPT:alias=disjoint   -WOPT:if_conv=0   -m32   -lsmartheap 
473.astar:  -Mpfi(pass 1)   -Mpfo(pass 2)   -Mipa=fast(pass 2)   -Mipa=inline:6(pass 2)   -fastsse   -O4   -Msmartalloc=huge:150   -Msafeptr=global   -Mfprelaxed   --zc_eh   -tp barcelona   -Bstatic_pgi 
483.xalancbmk:  -march=barcelona   -Ofast   -OPT:unroll_times_max=8   -CG:push_pop_int_saved_regs=off   -CG:ptr_load_use=0   -m32   -lsmartheap 

Peak Other Flags

C benchmarks:

429.mcf:  -Mipa=jobs:4 
456.hmmer:  -Mipa=jobs:4 
458.sjeng:  -Mipa=jobs:4(pass 2) 
462.libquantum:  -Mipa=jobs:4 

C++ benchmarks (except as noted below):

 -L/root/work/cpu2006-amd421gh/amd421gh.libs/32 
473.astar:  -Mipa=jobs:4(pass 2) 

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/amd421GH-flags.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/amd421GH-flags.xml.