| CPU2006 license: | 11 | Test date: | May-2008 |
|---|---|---|---|
| Test sponsor: | IBM Corporation | Hardware Availability: | May-2008 |
| Tested by: | IBM Corporation | Software Availability: | May-2008 |
| Hardware | |
|---|---|
| CPU Name: | POWER6 |
| CPU Characteristics: | |
| CPU MHz: | 4700 |
| FPU: | Integrated |
| CPU(s) enabled: | 32 cores, 16 chips, 2 cores/chip, 2 threads/core |
| CPU(s) orderable: | 32 cores |
| Primary Cache: | 64 KB I + 64 KB D on chip per core |
| Secondary Cache: | 4 MB I+D on chip per core |
| L3 Cache: | 32 MB I+D off chip per chip |
| Other Cache: | None |
| Memory: | 128 GB (64x2 GB) DDR2 533 MHz |
| Disk Subsystem: | 2x146 GB SFF SAS 10K RPM |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Red Hat Enterprise Linux Advanced Platform 5.2 for IBM POWER |
| Compiler: | IBM XL C/C++ Advanced Edition for Linux, V9.0 IBM XL Fortran Advanced Edition for Linux, V11.1 |
| Auto Parallel: | No |
| File System: | ext3 |
| System State: | Run level 3 (multi-user) |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32/64-bit |
| Other Software: | -IBM Post-Link Optimization for Linux on POWER, Version 5.4.0-17 -MicroQuill SmartHeap 8.1 -IBM Engineering and Scientific Subroutine Library for Linux on POWER, Version 4.3 |
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 | 64 | 786 | 1110 | 827 | 1050 | 832 | 1040 | 64 | 781 | 1110 | 752 | 1160 | 753 | 1160 |
| 416.gamess | 64 | 1768 | 709 | 1782 | 703 | 1764 | 710 | 64 | 1682 | 745 | 1681 | 746 | 1685 | 744 |
| 433.milc | 64 | 1389 | 423 | 1393 | 422 | 1393 | 422 | 64 | 1346 | 436 | 1345 | 437 | 1346 | 436 |
| 434.zeusmp | 64 | 943 | 618 | 943 | 617 | 944 | 617 | 64 | 558 | 1040 | 558 | 1040 | 576 | 1010 |
| 435.gromacs | 64 | 793 | 576 | 793 | 576 | 795 | 575 | 64 | 735 | 622 | 736 | 621 | 735 | 622 |
| 436.cactusADM | 64 | 1147 | 667 | 1146 | 667 | 1146 | 667 | 64 | 776 | 986 | 778 | 984 | 776 | 986 |
| 437.leslie3d | 64 | 879 | 684 | 886 | 679 | 877 | 686 | 32 | 388 | 776 | 388 | 775 | 389 | 773 |
| 444.namd | 64 | 678 | 757 | 679 | 756 | 678 | 757 | 64 | 654 | 785 | 654 | 785 | 654 | 785 |
| 447.dealII | 64 | 616 | 1190 | 637 | 1150 | 626 | 1170 | 64 | 599 | 1220 | 637 | 1150 | 603 | 1210 |
| 450.soplex | 64 | 1233 | 433 | 1237 | 431 | 1233 | 433 | 64 | 1233 | 433 | 1237 | 431 | 1233 | 433 |
| 453.povray | 64 | 619 | 550 | 639 | 533 | 624 | 546 | 64 | 538 | 633 | 511 | 666 | 539 | 632 |
| 454.calculix | 64 | 684 | 772 | 684 | 772 | 683 | 773 | 64 | 574 | 919 | 574 | 919 | 574 | 920 |
| 459.GemsFDTD | 64 | 1403 | 484 | 1402 | 484 | 1402 | 484 | 64 | 1403 | 484 | 1402 | 484 | 1402 | 484 |
| 465.tonto | 64 | 1598 | 394 | 1598 | 394 | 1571 | 401 | 64 | 680 | 926 | 689 | 914 | 693 | 909 |
| 470.lbm | 64 | 672 | 1310 | 672 | 1310 | 672 | 1310 | 64 | 670 | 1310 | 670 | 1310 | 670 | 1310 |
| 481.wrf | 64 | 1278 | 559 | 1279 | 559 | 1284 | 557 | 64 | 821 | 871 | 822 | 870 | 821 | 871 |
| 482.sphinx3 | 64 | 976 | 1280 | 978 | 1280 | 977 | 1280 | 64 | 954 | 1310 | 944 | 1320 | 943 | 1320 |
General Notes
kernel release 2.6.18-91.el5.
See flags file for details on following settings.
ulimit -s (stack) set to 1048576.
System set to Enhanced mode when defining partition on HMC
System set to "Chip affinity" mode using the HMC command
chsyscfg ... -i "addr_broadcast_perf_policy=chip_affinity"
Large pages reserved as follows by root user:
echo 4240 > /proc/sys/vm/nr_hugepages
System configured with libhugetlbfs library for application access to large pages
Environment variables set before executing benchmarks.
export HUGETLB_VERBOSE=0
export HUGETLB_MORECORE=yes
export XLFRTEOPTS=intrinthds=1
IBM Post-Link optimization tool used for
433.milc 435.gromacs 436.cactusADM 453.povray 465.tonto 482.sphinx3
Benchmarks bound to a processor using numactl on the submit command.
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 -qnoenablevmx -lhugetlbfs |
C++ benchmarks:
| -O5 -qrtti -qnoenablevmx -qstaticlink |
Fortran benchmarks:
| -O5 -qsmallstack=dynlenonheap -qalias=nostd -qnoenablevmx -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-link=BDT |
Benchmarks using both Fortran and C:
| -O5 -qnoenablevmx -qsmallstack=dynlenonheap -qalias=nostd -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-link=BDT |
Base Other Flags
C benchmarks:
| -qipa=noobject -qipa=threads |
C++ benchmarks:
| -qipa=noobject -qipa=threads |
Fortran benchmarks:
| -qipa=noobject -qipa=threads |
Benchmarks using both Fortran and C:
| -qipa=noobject -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: | -qfixed -qextname |
| 437.leslie3d: | -qfixed |
| 454.calculix: | -qfixed -qextname |
| 481.wrf: | -DNOUNDERSCORE |
| 482.sphinx3: | -qchars=signed |
Peak Optimization Flags
C benchmarks:
| 433.milc: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qnoenablevmx -lhugetlbfs |
| 470.lbm: | -O3 -qarch=pwr6e -qtune=pwr6 -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-link=BDT -q64 |
| 482.sphinx3: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O4 -lhugetlbfs |
C++ benchmarks:
| 444.namd: | -qpdf1(pass 1) -qpdf2(pass 2) -O3 -qarch=pwr6e -qtune=pwr6 |
| 447.dealII: | -O5 -qrtti -qnoenablevmx -qstaticlink -Wl,--whole-archive /usr/lib/libsmartheap.a -Wl,--no-whole-archive |
| 450.soplex: | basepeak = yes |
| 453.povray: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O5 -lsmartheap |
Fortran benchmarks:
| 410.bwaves: | -O5 -qsmallstack=dynlenonheap -lhugetlbfs |
| 416.gamess: | -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qalias=nostd -qnoenablevmx |
| 434.zeusmp: | -qpdf1(pass 1) -qpdf2(pass 2) -O3 -qarch=pwr6e -qtune=pwr6 -qxlf90=nosignedzero -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-link=BDT |
| 437.leslie3d: | -O3 -qarch=pwr6e -qtune=pwr6 -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-link=BDT -q64 |
| 459.GemsFDTD: | basepeak = yes |
| 465.tonto: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qessl -q64 -lessl -lsmartheap -lxlf90_r |
Benchmarks using both Fortran and C:
| 435.gromacs: | -Wl,-q -O2 -qarch=pwr6e -qtune=pwr6 -lhugetlbfs |
| 436.cactusADM: | -Wl,-q -qpdf1(pass 1) -qpdf2(pass 2) -O2 -qarch=pwr6e -qtune=pwr6 -qnostrict -lhugetlbfs |
| 454.calculix: | -qpdf1(pass 1) -qpdf2(pass 2) -O4 -B/usr/share/libhugetlbfs/ -tl -Wl,--hugetlbfs-link=BDT |
| 481.wrf: | -O5 -qnoenablevmx -q64 -lhugetlbfs |