| CPU2006 license: | 3 | Test date: | Feb-2007 |
|---|---|---|---|
| Test sponsor: | Hewlett-Packard Company | Hardware Availability: | Sep-2006 |
| Tested by: | Hewlett-Packard Company | Software Availability: | Jan-2007 |
| Hardware | |
|---|---|
| CPU Name: | AMD Opteron 8220 SE |
| CPU Characteristics: | |
| CPU MHz: | 2800 |
| FPU: | Integrated |
| CPU(s) enabled: | 8 cores, 4 chips, 2 cores/chip |
| CPU(s) orderable: | 2,4 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 (16x2 GB, PC2-5300P CL5) |
| Disk Subsystem: | 72 GB 10K SAS |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Solaris 10 6/06 |
| Compiler: | Sun Studio 11 with Patches |
| Auto Parallel: | No |
| File System: | ufs |
| System State: | Default |
| 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 | 1138 | 95.5 | 1135 | 95.8 | 1135 | 95.8 | 8 | 1092 | 99.6 | 1093 | 99.5 | 1092 | 99.6 |
| 416.gamess | 8 | 1364 | 115 | 1364 | 115 | 1363 | 115 | 8 | 1363 | 115 | 1362 | 115 | 1364 | 115 |
| 433.milc | 8 | 1149 | 63.9 | 1150 | 63.9 | 1149 | 63.9 | 8 | 1149 | 63.9 | 1150 | 63.9 | 1149 | 63.9 |
| 434.zeusmp | 8 | 928 | 78.5 | 926 | 78.6 | 928 | 78.4 | 8 | 923 | 78.9 | 925 | 78.7 | 923 | 78.8 |
| 435.gromacs | 8 | 830 | 68.8 | 829 | 68.9 | 829 | 68.9 | 8 | 541 | 106 | 542 | 105 | 541 | 106 |
| 436.cactusADM | 8 | 1297 | 73.7 | 1297 | 73.7 | 1324 | 72.2 | 8 | 1305 | 73.2 | 1300 | 73.6 | 1303 | 73.3 |
| 437.leslie3d | 8 | 1072 | 70.2 | 1071 | 70.2 | 1069 | 70.3 | 8 | 1043 | 72.1 | 1043 | 72.1 | 1043 | 72.1 |
| 444.namd | 8 | 645 | 99.5 | 643 | 99.8 | 643 | 99.8 | 8 | 631 | 102 | 632 | 101 | 631 | 102 |
| 447.dealII | 8 | 853 | 107 | 852 | 107 | 855 | 107 | 8 | 784 | 117 | 787 | 116 | 785 | 117 |
| 450.soplex | 8 | 1178 | 56.7 | 1148 | 58.1 | 1147 | 58.2 | 8 | 1097 | 60.8 | 1104 | 60.4 | 1091 | 61.2 |
| 453.povray | 8 | 331 | 129 | 331 | 129 | 331 | 129 | 8 | 331 | 129 | 331 | 129 | 331 | 129 |
| 454.calculix | 8 | 778 | 84.8 | 778 | 84.8 | 779 | 84.8 | 8 | 726 | 90.9 | 726 | 91.0 | 726 | 90.9 |
| 459.GemsFDTD | 8 | 1362 | 62.3 | 1372 | 61.9 | 1370 | 62.0 | 8 | 1362 | 62.3 | 1372 | 61.9 | 1370 | 62.0 |
| 465.tonto | 8 | 962 | 81.9 | 964 | 81.6 | 962 | 81.9 | 8 | 846 | 93.1 | 850 | 92.7 | 846 | 93.1 |
| 470.lbm | 8 | 1861 | 59.1 | 1859 | 59.1 | 1859 | 59.1 | 8 | 1676 | 65.6 | 1691 | 65.0 | 1682 | 65.3 |
| 481.wrf | 8 | 1189 | 75.1 | 1195 | 74.8 | 1201 | 74.4 | 8 | 1189 | 75.1 | 1195 | 74.8 | 1201 | 74.4 |
| 482.sphinx3 | 8 | 1784 | 87.4 | 1784 | 87.4 | 1783 | 87.4 | 8 | 1720 | 90.7 | 1719 | 90.7 | 1720 | 90.7 |
Operating System Notes
Processes were bound to cores using "submit" and "pbind". ulimit -s unlimited (shell): increases stack The following patches were applied to Sun Studio 11 compiler: 120759-09 : x86/x64 121016-05 : x86 C 121020-04 : x86 F90 121022-02 : x86 F90 121018-08 : x86 C++
Platform Notes
Node Interleaving was disabled in BIOS
Base Compiler Invocation
C benchmarks:
| cc |
C++ benchmarks:
| CC |
Fortran benchmarks:
| f90 |
Benchmarks using both Fortran and C:
| cc f90 |
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 |
| 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 |
| 459.GemsFDTD: | -DSPEC_CPU_LP64 |
| 465.tonto: | -DSPEC_CPU_LP64 |
| 470.lbm: | -DSPEC_CPU_LP64 |
| 481.wrf: | -DSPEC_CPU_LP64 -DSPEC_CPU_WORDS_LITTLEENDIAN |
| 482.sphinx3: | -DSPEC_CPU_LP64 |
Base Optimization Flags
C benchmarks:
| -fast -xipo=2 -xarch=amd64a |
C++ benchmarks:
| -fast -xipo=2 -xarch=amd64a -library=stlport4 |
Fortran benchmarks:
| -fast -xipo=2 -xarch=amd64a |
Benchmarks using both Fortran and C:
| -fast(cc) -fast(f90) -xipo=2 -xarch=amd64a |
Base Other Flags
C benchmarks:
| -V |
C++ benchmarks:
| -verbose=version |
Fortran benchmarks:
| -V |
Benchmarks using both Fortran and C:
| -V |
Peak Compiler Invocation
C benchmarks:
| cc |
C++ benchmarks:
| CC |
Fortran benchmarks:
| f90 |
Benchmarks using both Fortran and C:
| cc f90 |
Peak Portability Flags
| 433.milc: | -DSPEC_CPU_LP64 |
| 436.cactusADM: | -DSPEC_CPU_LP64 |
| 453.povray: | -DSPEC_CPU_LP64 |
| 459.GemsFDTD: | -DSPEC_CPU_LP64 |
| 481.wrf: | -DSPEC_CPU_LP64 -DSPEC_CPU_WORDS_LITTLEENDIAN |
Peak Optimization Flags
C benchmarks:
| 433.milc: | basepeak = yes |
| 470.lbm: | -fast -xarch=amd64a -xpagesize=2m -W2,-Ainline:inc=200 -W2,-Ainline:cs=500 -xprefetch_level=3 |
| 482.sphinx3: | -fast -xarch=amd64a -xrestrict -xipo=2 -xprefetch=auto -xpagesize=2m -Wd,-iropt-prof -W2,-Ashort_ldst:ldld -W2,-Ainline:rs=50 -M /usr/lib/ld/map.bssalign |
C++ benchmarks:
| 444.namd: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xarch=amd64a -xipo=2 -library=stlport4 |
| 447.dealII: | -fast -xarch=amd64a -xipo=2 -xvector -Qoption iropt -Abcopy -xalias_level -xrestrict -xregs=frameptr -library=stlport4 |
| 450.soplex: | -fast -xipo=2 -xarch=sse2a -library=stlport4 |
| 453.povray: | basepeak = yes |
Fortran benchmarks:
| 410.bwaves: | -fast -xarch=amd64a -unroll=5 -stackvar -xO4 -xipo=2 -xprefetch_level=3 -Qoption iropt -Rloop_dist |
| 416.gamess: | -fast -xarch=amd64a -xipo=2 -xprefetch_level=3 |
| 434.zeusmp: | -fast -xarch=amd64a -xipo=2 -xregs=frameptr |
| 437.leslie3d: | -fast -xipo=2 -xarch=sse2a |
| 459.GemsFDTD: | basepeak = yes |
| 465.tonto: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xarch=amd64a -xipo=2 -xvector=lib -xalias -xdepend -lbsdmalloc |
Benchmarks using both Fortran and C:
| 435.gromacs: | -fast(cc) -fast(f90) -xipo=2 -xarch=amd64a -Wu,-fsimple=3 -Qoption ube -fsimple=3 |
| 436.cactusADM: | -fast(cc) -fast(f90) -xipo=2 -xarch=amd64a |
| 454.calculix: | -fast(cc) -fast(f90) -xarch=amd64a -xpagesize=2m -xprefetch=auto -xprefetch_level=3 -W2,-Ainline:inc=200 -W2,-Ainline:cs=500 -unroll=5 -stackvar -xO4 -xipo=2 -Qoption iropt -Rloop_dist |
| 481.wrf: | basepeak = yes |