SPEC® CFP2006 Result

Copyright 2006-2012 Standard Performance Evaluation Corporation

IBM Corporation

IBM System x3755 (AMD Opteron 8218)

CPU2006 license: 11 Test date: Jul-2007
Test sponsor: IBM Corporation Hardware Availability: Oct-2006
Tested by: IBM Corporation Software Availability: Mar-2007
Benchmark results graph
Hardware
CPU Name: AMD Opteron 8218
CPU Characteristics:
CPU MHz: 2600
FPU: Integrated
CPU(s) enabled: 8 cores, 4 chips, 2 cores/chip
CPU(s) orderable: 1, 2, 3, 4 chips
Primary Cache: 64 KB I + 64 KB D on chip per core
Secondary Cache: 1 MB I+D on chip per core
L3 Cache: None
Other Cache: None
Memory: 32 GB (16 x 2GB DDR2-5300 ECC)
Disk Subsystem: 1 x 36 GB SAS, 15000 RPM
Other Hardware: None
Software
Operating System: SLES 10 (x86_64), 2.6.16.21-0.8-smp
Compiler: QLogic PathScale
Compiler Suite, Release 3.0
Auto Parallel: No
File System: ext3
System State: Multi-user, run level 3
Base Pointers: 64-bit
Peak Pointers: 32/64-bit
Other Software: None

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.
410.bwaves 8 1192 91.2 1189 91.4 1190 91.3 8 1158 93.9 1304 83.4 1307 83.2
416.gamess 8 1494 105   1493 105   1493 105   8 1319 119   1318 119   1319 119  
433.milc 8 1229 59.7 1229 59.8 1229 59.7 8 1228 59.8 1228 59.8 1229 59.8
434.zeusmp 8 912 79.9 908 80.2 907 80.3 8 895 81.3 896 81.3 897 81.2
435.gromacs 8 618 92.4 621 92.1 618 92.4 8 548 104   546 105   547 104  
436.cactusADM 8 1089 87.8 1088 87.8 1086 88.0 8 1018 93.9 1014 94.3 1013 94.4
437.leslie3d 8 1091 69.0 1093 68.8 1094 68.7 8 1091 69.0 1093 68.8 1094 68.7
444.namd 8 709 90.5 709 90.5 709 90.5 8 669 95.9 669 95.9 668 96.0
447.dealII 8 793 115   791 116   793 115   8 635 144   635 144   635 144  
450.soplex 8 1186 56.3 1184 56.3 1186 56.2 8 1038 64.3 1038 64.3 1039 64.2
453.povray 8 352 121   354 120   354 120   8 322 132   322 132   325 131  
454.calculix 8 1206 54.7 1207 54.7 1207 54.7 8 1118 59.0 1117 59.1 1118 59.0
459.GemsFDTD 8 1354 62.7 1370 61.9 1341 63.3 8 1346 63.1 1352 62.8 1352 62.8
465.tonto 8 747 105   746 106   746 106   8 747 105   746 106   746 106  
470.lbm 8 1601 68.7 1568 70.1 1577 69.7 8 1601 68.7 1568 70.1 1577 69.7
481.wrf 8 906 98.7 903 99.0 905 98.8 8 906 98.7 903 99.0 905 98.8
482.sphinx3 8 1849 84.3 1845 84.5 1842 84.6 8 1849 84.3 1845 84.5 1842 84.6

General Notes

 taskset utility used to bind CPU(s) to processes
DSPEC_CPU_TABLE_WORKAROUND was used for portability when compiling 447.dealII
due to compilation being performed on SLES 9 SP3

Base Compiler Invocation

C benchmarks:

 pathcc 

C++ benchmarks:

 pathCC 

Fortran benchmarks:

 pathf95 

Benchmarks using both Fortran and C:

 pathcc   pathf95 

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

Base Optimization Flags

C benchmarks:

 -Ofast 

C++ benchmarks:

 -Ofast 

Fortran benchmarks:

 -Ofast   -OPT:malloc_alg=1 

Benchmarks using both Fortran and C:

 -Ofast   -OPT:malloc_alg=1 

Base Other Flags

C benchmarks:

 -IPA:max_jobs=2 

C++ benchmarks:

 -IPA:max_jobs=2 

Fortran benchmarks:

 -IPA:max_jobs=2 

Benchmarks using both Fortran and C:

 -IPA:max_jobs=2 

Peak Compiler Invocation

C benchmarks:

 pathcc 

C++ benchmarks:

 pathCC 

Fortran benchmarks:

 pathf95 

Benchmarks using both Fortran and C:

 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   -fno-second-underscore 
437.leslie3d:  -DSPEC_CPU_LP64 
444.namd:  -DSPEC_CPU_LP64 
447.dealII:  -DSPEC_CPU_TABLE_WORKAROUND 
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   -fno-second-underscore 
482.sphinx3:  -DSPEC_CPU_LP64 

Peak Optimization Flags

C benchmarks:

433.milc:  -Ofast   -CG:cflow=off   -LNO:prefetch=1   -OPT:malloc_alg=1 
470.lbm:  basepeak = yes 
482.sphinx3:  basepeak = yes 

C++ benchmarks:

444.namd:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -fno-exceptions 
447.dealII:  -Ofast   -INLINE:aggressive=on   -LNO:opt=0   -OPT:alias=disjoint   -m32   -fno-exceptions 
450.soplex:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -m32   -O3   -OPT:IEEE_arith=3   -CG:load_exe=0   -CG:movnti=1   -LNO:minvariant=off   -LNO:prefetch=1   -fno-exceptions 
453.povray:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -Ofast   -fno-fast-math 

Fortran benchmarks:

410.bwaves:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -OPT:Ofast   -OPT:IEEE_arith=3   -LNO:blocking=off   -LNO:ignore_feedback=off 
416.gamess:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O2   -OPT:Ofast   -OPT:ro=3   -OPT:unroll_size=256 
434.zeusmp:  -Ofast   -CG:local_fwd_sched=on   -LNO:blocking=off   -LNO:interchange=off   -LNO:fu=10   -LNO:full_unroll_outer=on 
437.leslie3d:  basepeak = yes 
459.GemsFDTD:  -Ofast   -LNO:fission=2   -LNO:prefetch=0 
465.tonto:  basepeak = yes 

Benchmarks using both Fortran and C:

435.gromacs:  -O3   -OPT:rsqrt=2   -OPT:ro=3 
436.cactusADM:  -fb_create fbdata(pass 1)   -fb_opt fbdata(pass 2)   -O3   -LNO:prefetch=3   -LNO:prefetch_ahead=5   -LNO:ou_prod_max=10   -LNO:full_unroll=5   -ipa 
454.calculix:  -Ofast   -LNO:simd=0   -WOPT:mem_opnds=on 
481.wrf:  basepeak = yes 

Peak Other Flags

C benchmarks:

 -IPA:max_jobs=2 

C++ benchmarks:

 -IPA:max_jobs=2 

Fortran benchmarks:

 -IPA:max_jobs=2 

Benchmarks using both Fortran and C:

 -IPA:max_jobs=2 

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/CPU2006_flags.20090714.13.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/CPU2006_flags.20090714.13.xml.