| CPU2006 license: | 11 | Test date: | Oct-2010 |
|---|---|---|---|
| Test sponsor: | IBM Corporation | Hardware Availability: | Feb-2010 |
| Tested by: | IBM Corporation | Software Availability: | Nov-2010 |
| Hardware | |
|---|---|
| CPU Name: | POWER7 |
| CPU Characteristics: | Intelligent Energy Optimization enabled, up to 3.86 GHz |
| CPU MHz: | 3556 |
| FPU: | Integrated |
| CPU(s) enabled: | 32 cores, 4 chips, 8 cores/chip, 4 threads/core |
| CPU(s) orderable: | 8,16,24,32 cores |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 256 KB I+D on chip per core |
| L3 Cache: | 4 MB I+D on chip per core |
| Other Cache: | None |
| Memory: | 256 GB (32x8 GB) DDR3 1066 MHz |
| Disk Subsystem: | 6x146.8 GB Software RAID-0 SAS SFF 15K RPM |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Red Hat Enterprise Linux Server release 6.0 (ppc64), Kernel 2.6.32-71.el6.ppc64 |
| Compiler: | IBM XL C/C++ for Linux, V11.1 Updated with the Nov2010 PTF IBM XL Fortran for Linux, V13.1 Updated with the Nov2010 PTF |
| Auto Parallel: | No |
| File System: | ext2 |
| System State: | Run level 3 (multi-user) |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32/64-bit |
| Other Software: | -Post-Link Optimization for Linux on POWER, Version 5.5.0-3 -MicroQuill SmartHeap 9 -Apache C++ Standard Library 4.2.1 |
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 | 128 | 2143 | 812 | 2149 | 810 | 2147 | 810 | 128 | 2143 | 812 | 2149 | 810 | 2147 | 810 |
| 416.gamess | 128 | 2500 | 1000 | 2493 | 1010 | 2498 | 1000 | 128 | 2304 | 1090 | 2306 | 1090 | 2307 | 1090 |
| 433.milc | 128 | 1539 | 763 | 1550 | 758 | 1546 | 760 | 32 | 370 | 794 | 370 | 794 | 371 | 792 |
| 434.zeusmp | 128 | 1083 | 1080 | 1095 | 1060 | 1084 | 1070 | 128 | 1083 | 1080 | 1095 | 1060 | 1084 | 1070 |
| 435.gromacs | 128 | 1129 | 810 | 1122 | 815 | 1121 | 815 | 128 | 853 | 1070 | 845 | 1080 | 855 | 1070 |
| 436.cactusADM | 128 | 1156 | 1320 | 1157 | 1320 | 1152 | 1330 | 64 | 525 | 1460 | 524 | 1460 | 528 | 1450 |
| 437.leslie3d | 128 | 2333 | 516 | 2340 | 514 | 2338 | 515 | 32 | 551 | 546 | 550 | 547 | 551 | 546 |
| 444.namd | 128 | 778 | 1320 | 782 | 1310 | 776 | 1320 | 128 | 751 | 1370 | 751 | 1370 | 753 | 1360 |
| 447.dealII | 128 | 841 | 1740 | 852 | 1720 | 847 | 1730 | 128 | 640 | 2290 | 638 | 2290 | 642 | 2280 |
| 450.soplex | 128 | 2037 | 524 | 2039 | 524 | 2037 | 524 | 64 | 964 | 554 | 950 | 562 | 948 | 563 |
| 453.povray | 128 | 640 | 1060 | 639 | 1070 | 637 | 1070 | 128 | 487 | 1400 | 490 | 1390 | 489 | 1390 |
| 454.calculix | 128 | 1072 | 985 | 1104 | 956 | 1097 | 963 | 128 | 1096 | 964 | 1085 | 973 | 1084 | 974 |
| 459.GemsFDTD | 128 | 3153 | 431 | 3148 | 431 | 3147 | 431 | 128 | 3153 | 431 | 3148 | 431 | 3147 | 431 |
| 465.tonto | 128 | 1859 | 678 | 1865 | 675 | 1856 | 679 | 128 | 1067 | 1180 | 1067 | 1180 | 1066 | 1180 |
| 470.lbm | 128 | 1526 | 1150 | 1529 | 1150 | 1526 | 1150 | 128 | 1526 | 1150 | 1529 | 1150 | 1526 | 1150 |
| 481.wrf | 128 | 1688 | 847 | 1692 | 845 | 1690 | 846 | 128 | 1652 | 865 | 1650 | 867 | 1645 | 869 |
| 482.sphinx3 | 128 | 3228 | 773 | 3233 | 772 | 3228 | 773 | 32 | 706 | 884 | 700 | 891 | 704 | 886 |
Peak Tuning Notes
IBM Post-Link Optimization tool with options "-O4 -nodp" used for 433.milc 435.gromacs 450.soplex 482.sphinx3 options "-O4 -vrox -nodp" used for 434.zeusmp options "-O3 -lu -1 -nodp -sdp 9" used for 437.leslie3d 444.namd options "-O4" used for 465.tonto
Submit Notes
The config file option 'submit' was used. Benchmarks bound to a processor using numactl on the submit command.
Operating System Notes
ulimit -s (stack) set to 1048576. Large pages reserved as follows by root user: echo 9000 > /proc/sys/vm/nr_hugepages The following environment varibles were set before the runspec command: XLFRTEOPTS=intrinthds=1 HUGETLB_VERBOSE=0 HUGETLB_MORECORE=yes HUGETLB_ELFMAP=RW 447.dealII (peak): "apache_stdcxx_4_2_1" src.alt was used. 447.dealII (base): "apache_stdcxx_4_2_1" src.alt was used.
Base Compiler Invocation
C benchmarks:
| xlc -qlanglvl=extc99 |
C++ benchmarks:
| xlC |
Fortran benchmarks:
| xlf95 |
Benchmarks using both Fortran and C:
| xlc -qlanglvl=extc99 xlf95 |
Base Portability Flags
| 410.bwaves: | -qfixed |
| 416.gamess: | -qfixed |
| 434.zeusmp: | -qfixed |
| 435.gromacs: | -qfixed -qextname |
| 436.cactusADM: | -qfixed -qextname |
| 437.leslie3d: | -qfixed |
| 454.calculix: | -qfixed -qextname |
| 481.wrf: | -DNOUNDERSCORE |
| 482.sphinx3: | -qchars=signed |
Base Optimization Flags
C benchmarks:
| -O5 -qarch=pwr7 -qtune=pwr7 -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-align |
C++ benchmarks:
| -O5 -qarch=pwr7 -qtune=pwr7 -qrtti -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-align |
Fortran benchmarks:
| -O5 -qarch=pwr7 -qtune=pwr7 -qsmallstack=dynlenonheap -qalias=nostd -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-align |
Benchmarks using both Fortran and C:
| -O5 -qarch=pwr7 -qtune=pwr7 -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-align -qsmallstack=dynlenonheap -qalias=nostd |
Base Other Flags
C benchmarks:
| -qipa=threads |
C++ benchmarks:
| -qipa=threads |
Fortran benchmarks:
| -qipa=threads |
Benchmarks using both Fortran and C:
| -qipa=threads |
Peak Compiler Invocation
C benchmarks:
| xlc -qlanglvl=extc99 |
C++ benchmarks:
| xlC |
Fortran benchmarks:
| xlf95 |
Benchmarks using both Fortran and C:
| xlc -qlanglvl=extc99 xlf95 |
Peak Portability Flags
| 410.bwaves: | -qfixed |
| 416.gamess: | -qfixed |
| 434.zeusmp: | -qfixed |
| 435.gromacs: | -qfixed -qextname |
| 436.cactusADM: | -DSPEC_CPU_LP64 -qfixed -qextname |
| 437.leslie3d: | -qfixed |
| 453.povray: | -DSPEC_CPU_LP64 |
| 454.calculix: | -qfixed -qextname |
| 481.wrf: | -DNOUNDERSCORE |
| 482.sphinx3: | -qchars=signed |
Peak Optimization Flags
C benchmarks:
| 433.milc: | -Wl,-q -O5 -qarch=pwr7 -qtune=pwr7 -lhugetlbfs |
| 470.lbm: | basepeak = yes |
| 482.sphinx3: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qarch=pwr7 -qtune=pwr7 -lhugetlbfs |
C++ benchmarks:
| 444.namd: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qarch=pwr7 -qtune=pwr7 -lhugetlbfs |
| 447.dealII: | -O4 -qarch=pwr7 -qtune=pwr7 -qrtti -qcpp_stdinc=/autobench/sources/stdcxx-4.2.1/dist/include/ansi:/autobench/sources/stdcxx-4.2.1/dist/include:/opt/ibmcmp/vacpp/11.1/include -lsmartheap -L/autobench/sources/stdcxx-4.2.1/dist/lib -R/autobench/sources/stdcxx-4.2.1/dist/lib -lstd8d |
| 450.soplex: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O3 -qarch=pwr7 -qtune=pwr7 -q64 -lhugetlbfs |
| 453.povray: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qarch=pwr7 -qtune=pwr7 -qsimd -q64 -lsmartheap64 |
Fortran benchmarks:
| 410.bwaves: | basepeak = yes |
| 416.gamess: | -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qarch=pwr7 -qtune=pwr7 -qalias=nostd -lhugetlbfs |
| 434.zeusmp: | basepeak = yes |
| 437.leslie3d: | -Wl,-q -O5 -qarch=pwr7 -qtune=pwr7 -q64 -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-align |
| 459.GemsFDTD: | basepeak = yes |
| 465.tonto: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qarch=pwr7 -qtune=pwr7 -qsimd -lhugetlbfs |
Benchmarks using both Fortran and C:
| 435.gromacs: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -qarch=pwr7 -qtune=pwr7 -qsimd -lhugetlbfs |
| 436.cactusADM: | -O4 -qarch=pwr7 -qtune=pwr7 -qsimd -qnostrict -q64 -lhugetlbfs |
| 454.calculix: | -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qarch=pwr7 -qtune=pwr7 -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-align |
| 481.wrf: | -O3 -qarch=pwr7 -qtune=pwr7 -q64 -lhugetlbfs |