| CPU2006 license: | 11 | Test date: | Jan-2013 |
|---|---|---|---|
| Test sponsor: | IBM Corporation | Hardware Availability: | Mar-2013 |
| Tested by: | IBM Corporation | Software Availability: | Nov-2012 |
| Hardware | |
|---|---|
| CPU Name: | POWER7+ |
| CPU Characteristics: | Intelligent Energy Optimization enabled, up to 3.787 GHz |
| CPU MHz: | 3416 |
| FPU: | Integrated |
| CPU(s) enabled: | 48 cores, 8 chips, 6 cores/chip, 4 threads/core |
| CPU(s) orderable: | 12, 24, 36, 48 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: | 10 MB I+D on chip per core |
| Other Cache: | None |
| Memory: | 512 GB (64 x 8 GB) DDR3 1066 MHz |
| Disk Subsystem: | 3 x 146.8 GB Raid0 SAS SFF 15K RPM |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | SUSE Linux Enterprise Server 11 SP2 (ppc64) kernel 3.0.42-0.7-ppc64 |
| Compiler: | C/C++: Version 4.7.3 of IBM Advance Toolchain 6.0-1 gcc/g++ compiler |
| Auto Parallel: | No |
| File System: | ext3 |
| System State: | Run level 3 (multi-user) |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32-bit |
| Other Software: | -IBM Advance Toolchain 6.0-1 |
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. | ||||||||||||||
| 400.perlbench | 192 | 1356 | 1380 | 1272 | 1470 | 1261 | 1490 | 192 | 1356 | 1380 | 1272 | 1470 | 1261 | 1490 |
| 401.bzip2 | 192 | 1136 | 1630 | 1115 | 1660 | 1114 | 1660 | 192 | 1136 | 1630 | 1115 | 1660 | 1114 | 1660 |
| 403.gcc | 192 | 1046 | 1480 | 1045 | 1480 | 1046 | 1480 | 192 | 1046 | 1480 | 1045 | 1480 | 1046 | 1480 |
| 429.mcf | 192 | 1415 | 1240 | 1414 | 1240 | 1413 | 1240 | 192 | 1415 | 1240 | 1414 | 1240 | 1413 | 1240 |
| 445.gobmk | 192 | 1010 | 1990 | 1015 | 1980 | 1011 | 1990 | 192 | 1010 | 1990 | 1015 | 1980 | 1011 | 1990 |
| 456.hmmer | 192 | 1424 | 1260 | 1423 | 1260 | 1423 | 1260 | 192 | 1424 | 1260 | 1423 | 1260 | 1423 | 1260 |
| 458.sjeng | 192 | 1394 | 1670 | 1392 | 1670 | 1394 | 1670 | 192 | 1394 | 1670 | 1392 | 1670 | 1394 | 1670 |
| 462.libquantum | 192 | 5795 | 686 | 5769 | 690 | 5789 | 687 | 192 | 5795 | 686 | 5769 | 690 | 5789 | 687 |
| 464.h264ref | 192 | 1705 | 2490 | 1706 | 2490 | 1718 | 2470 | 192 | 1705 | 2490 | 1706 | 2490 | 1718 | 2470 |
| 471.omnetpp | 192 | 1857 | 646 | 1855 | 647 | 1857 | 646 | 192 | 1857 | 646 | 1855 | 647 | 1857 | 646 |
| 473.astar | 192 | 978 | 1380 | 980 | 1380 | 979 | 1380 | 192 | 978 | 1380 | 980 | 1380 | 979 | 1380 |
| 483.xalancbmk | 192 | 705 | 1880 | 705 | 1880 | 707 | 1870 | 192 | 705 | 1880 | 705 | 1880 | 707 | 1870 |
Compiler Invocation Notes
For more information about IBM Advance Toolchain, including support, see ftp://linuxpatch.ncsa.uiuc.edu/toolchain/at/suse/SLES_11/at6.0/release_notes.at6.0-6.0-1.html
Submit Notes
The config file option 'submit' was used to assign benchmark copy to specific kernel thread using the "numactl" command (see flags file for details).
Operating System Notes
ulimit -s (stack) set to 1048576.
Large pages reserved as follows by root user:
echo 12672 > /proc/sys/vm/nr_hugepages
The following environment varibles were set before the runspec command:
export HUGETLB_VERBOSE=0
export HUGETLB_MORECORE=yes
Base Portability Flags
| 400.perlbench: | -DSPEC_CPU_LINUX_PPC |
| 462.libquantum: | -DSPEC_CPU_LINUX |
| 464.h264ref: | -fsigned-char |
| 483.xalancbmk: | -DSPEC_CPU_LINUX |
Base Optimization Flags
C benchmarks:
| -O3 -mcpu=power7 -mtune=power7 -m32 -ffast-math -fpeel-loops -funroll-loops -mvsx -maltivec -ftree-vectorize -mpopcntd -mrecip=rsqrt -flto -fwhole-program -fuse-linker-plugin -lhugetlbfs |
C++ benchmarks:
| -O3 -mcpu=power7 -mtune=power7 -m32 -ffast-math -fpeel-loops -funroll-loops -mvsx -maltivec -ftree-vectorize -mpopcntd -mrecip=rsqrt -flto -fwhole-program -fuse-linker-plugin -ltcmalloc |
Peak Optimization Flags
C benchmarks:
| 400.perlbench: | basepeak = yes |
| 401.bzip2: | basepeak = yes |
| 403.gcc: | basepeak = yes |
| 429.mcf: | basepeak = yes |
| 445.gobmk: | basepeak = yes |
| 456.hmmer: | basepeak = yes |
| 458.sjeng: | basepeak = yes |
| 462.libquantum: | basepeak = yes |
| 464.h264ref: | basepeak = yes |
C++ benchmarks:
| 471.omnetpp: | basepeak = yes |
| 473.astar: | basepeak = yes |
| 483.xalancbmk: | basepeak = yes |