| CPU2006 license: | 11 | Test date: | Oct-2010 |
|---|---|---|---|
| Test sponsor: | IBM Corporation | Hardware Availability: | Mar-2010 |
| Tested by: | IBM Corporation | Software Availability: | Nov-2010 |
| Hardware | |
|---|---|
| CPU Name: | POWER7 |
| CPU Characteristics: | Intelligent Energy Optimization enabled, up to 3.94 GHz |
| CPU MHz: | 3860 |
| FPU: | Integrated |
| CPU(s) enabled: | 64 cores, 8 chips, 8 cores/chip, 4 threads/core |
| CPU(s) orderable: | 8,16,24,32,48,64 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: | 512 GB (64x8 GB) DDR3 1066 MHz |
| Disk Subsystem: | 3x146.8 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 | 256 | 1084 | 3210 | 1112 | 3130 | 1121 | 3100 | 256 | 1084 | 3210 | 1112 | 3130 | 1121 | 3100 |
| 416.gamess | 256 | 2469 | 2030 | 2466 | 2030 | 2478 | 2020 | 256 | 2266 | 2210 | 2272 | 2210 | 2266 | 2210 |
| 433.milc | 256 | 752 | 3120 | 774 | 3040 | 766 | 3070 | 64 | 188 | 3130 | 187 | 3140 | 187 | 3140 |
| 434.zeusmp | 256 | 1046 | 2230 | 1042 | 2240 | 1053 | 2210 | 256 | 1046 | 2230 | 1042 | 2240 | 1053 | 2210 |
| 435.gromacs | 256 | 1087 | 1680 | 1094 | 1670 | 1106 | 1650 | 256 | 834 | 2190 | 853 | 2140 | 841 | 2170 |
| 436.cactusADM | 256 | 1107 | 2760 | 1109 | 2760 | 1115 | 2740 | 128 | 487 | 3140 | 483 | 3170 | 483 | 3160 |
| 437.leslie3d | 256 | 1227 | 1960 | 1275 | 1890 | 1279 | 1880 | 256 | 1227 | 1960 | 1275 | 1890 | 1279 | 1880 |
| 444.namd | 256 | 761 | 2700 | 761 | 2700 | 762 | 2690 | 256 | 738 | 2780 | 737 | 2790 | 736 | 2790 |
| 447.dealII | 256 | 794 | 3690 | 804 | 3640 | 806 | 3640 | 256 | 601 | 4870 | 602 | 4860 | 600 | 4880 |
| 450.soplex | 256 | 1099 | 1940 | 1148 | 1860 | 1152 | 1850 | 256 | 1099 | 1940 | 1148 | 1860 | 1152 | 1850 |
| 453.povray | 256 | 740 | 1840 | 742 | 1840 | 732 | 1860 | 256 | 567 | 2400 | 573 | 2380 | 568 | 2400 |
| 454.calculix | 256 | 1075 | 1960 | 1067 | 1980 | 1071 | 1970 | 256 | 1066 | 1980 | 1049 | 2010 | 1050 | 2010 |
| 459.GemsFDTD | 256 | 1616 | 1680 | 1627 | 1670 | 1631 | 1670 | 256 | 1616 | 1680 | 1627 | 1670 | 1631 | 1670 |
| 465.tonto | 256 | 1708 | 1480 | 1725 | 1460 | 1722 | 1460 | 256 | 913 | 2760 | 911 | 2770 | 914 | 2760 |
| 470.lbm | 256 | 805 | 4370 | 886 | 3970 | 888 | 3960 | 256 | 805 | 4370 | 886 | 3970 | 888 | 3960 |
| 481.wrf | 256 | 1378 | 2080 | 1432 | 2000 | 1433 | 2000 | 256 | 1266 | 2260 | 1253 | 2280 | 1270 | 2250 |
| 482.sphinx3 | 256 | 1881 | 2650 | 1983 | 2520 | 2020 | 2470 | 256 | 1881 | 2650 | 1983 | 2520 | 2020 | 2470 |
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 18000 > /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: | basepeak = yes |
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: | basepeak = yes |
| 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: | basepeak = yes |
| 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 |