CPU2006 license: | 11 | Test date: | Sep-2016 |
---|---|---|---|
Test sponsor: | IBM Corporation | Hardware Availability: | Oct-2016 |
Tested by: | IBM Corporation | Software Availability: | Oct-2015 |
Hardware | |
---|---|
CPU Name: | POWER8 |
CPU Characteristics: | Intelligent Energy Optimization enabled, up to 4.32 GHz |
CPU MHz: | 4223 |
FPU: | Integrated |
CPU(s) enabled: | 32 cores, 8 chips, 4 cores/chip, 8 threads/core |
CPU(s) orderable: | 4 Modules |
Primary Cache: | 32 KB I + 64 KB D on chip per core |
Secondary Cache: | 512 KB I+D on chip per core |
L3 Cache: | 8 MB I+D on chip per core |
Other Cache: | 16 MB I+D off chip per CDIMM |
Memory: | 512 GB (32 x 16 GB CDIMMs) DDR4 1600 MHz |
Disk Subsystem: | 8 x 600 GB 15K RPM SAS SFF-2 Raid5 |
Other Hardware: | None |
Software | |
---|---|
Operating System: | Red Hat Enterprise Linux Server release 7.2 (ppc64) kernel <3.10.0-327> |
Compiler: | C/C++: Version 13.1 of IBM XL C/C++ for Linux |
Auto Parallel: | No |
File System: | xfs |
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 5.6.2-7 IBM Advance Toolchain 7.0-9 |
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 | 128 | 980 | 1280 | 942 | 1330 | 936 | 1340 | 128 | 901 | 1390 | 889 | 1410 | 859 | 1460 |
401.bzip2 | 128 | 893 | 1380 | 830 | 1490 | 830 | 1490 | 192 | 1180 | 1570 | 1169 | 1580 | 1125 | 1650 |
403.gcc | 128 | 547 | 1880 | 546 | 1890 | 544 | 1890 | 224 | 783 | 2300 | 781 | 2310 | 779 | 2310 |
429.mcf | 128 | 461 | 2530 | 460 | 2540 | 461 | 2530 | 128 | 438 | 2660 | 439 | 2660 | 441 | 2640 |
445.gobmk | 128 | 740 | 1810 | 739 | 1820 | 739 | 1820 | 256 | 1246 | 2160 | 1242 | 2160 | 1245 | 2160 |
456.hmmer | 128 | 672 | 1780 | 672 | 1780 | 674 | 1770 | 128 | 367 | 3250 | 369 | 3230 | 367 | 3260 |
458.sjeng | 128 | 907 | 1710 | 906 | 1710 | 906 | 1710 | 256 | 1672 | 1850 | 1669 | 1860 | 1674 | 1850 |
462.libquantum | 128 | 571 | 4640 | 571 | 4650 | 572 | 4640 | 128 | 140 | 19000 | 141 | 18800 | 142 | 18700 |
464.h264ref | 128 | 991 | 2860 | 993 | 2850 | 989 | 2860 | 128 | 949 | 2990 | 947 | 2990 | 962 | 2940 |
471.omnetpp | 128 | 582 | 1370 | 581 | 1380 | 582 | 1370 | 256 | 1053 | 1520 | 1054 | 1520 | 1053 | 1520 |
473.astar | 128 | 527 | 1710 | 526 | 1710 | 529 | 1700 | 224 | 867 | 1810 | 863 | 1820 | 867 | 1810 |
483.xalancbmk | 128 | 391 | 2260 | 382 | 2320 | 382 | 2310 | 192 | 549 | 2420 | 548 | 2420 | 534 | 2480 |
400.perlbench fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 401.bzip2 fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 403.gcc fdpr options: -O4 -m power8 -A 2 -sls -dir -vrox 429.mcf fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 456.hmmer fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 458.sjeng fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 462.libquantum fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 464.h264ref fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 471.omnetpp fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 473.astar fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox 483.xalancbmk fdpr options: -O4 -m power8 -A 2 -rcl 2 -sls -dir -vrox
The config file option 'submit' was used to assign benchmark copy to specific kernel thread using the "numactl" command (see flags file for details).
ulimit -s (stack) set to unlimited 16000 16M large pages defined with sysctl command Transparent huge page disabled with echo never > /sys/kernel/mm/transparent_hugepage/enabled sysctl vm.nr_hugepages=N and reboot to set large page pool
Environment variables set by runspec before the start of the run: HUGETLB_MORECORE = "yes" HUGETLB_VERBOSE = "0" TCMALLOC_MEMFS_MALLOC_PATH = "/dev/hugepages/" XLFRTEOPTS = "intrinthds=1"
/opt/ibm/xlC/13.1.0/bin/xlc_at -qlanglvl=extc99 |
/opt/ibm/xlC/13.1.0/bin/xlC_at |
400.perlbench: | -DSPEC_CPU_LINUX_PPC |
462.libquantum: | -DSPEC_CPU_LINUX |
464.h264ref: | -qchars=signed |
483.xalancbmk: | -DSPEC_CPU_LINUX |
-qinline=40 -qipa=threads -qlargepage -O5 -qalias=noansi -qalloca -lhugetlbfs |
-qinline=40 -qipa=threads -qlargepage -O5 -qrtti -ltcmalloc |
-qipa=noobject -qsuppress=1500-036 |
-qipa=noobject -qsuppress=1500-036 |
/opt/ibm/xlC/13.1.0/bin/xlc_at -qlanglvl=extc99 |
/opt/ibm/xlC/13.1.0/bin/xlC_at |
400.perlbench: | -DSPEC_CPU_LINUX_PPC |
403.gcc: | -DSPEC_CPU_LP64 |
462.libquantum: | -DSPEC_CPU_LINUX |
464.h264ref: | -qchars=signed |
483.xalancbmk: | -DSPEC_CPU_LINUX |
471.omnetpp: | -qinline=40 -qipa=threads -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qsimd=noauto -qarch=pwr7 -qtune=pwr7 -qprefetch=dscr=0x54 -qfdpr -qrtti -lhugetlbfs -Wl,-q -ltcmalloc |
473.astar: | -qinline=40 -qipa=threads -qpdf1(pass 1) -qpdf2(pass 2) -O5 -qlargepage -qprefetch=dscr=0x93 -qfdpr -lhugetlbfs -Wl,-q -ltcmalloc |
483.xalancbmk: | -qinline=40 -qipa=threads -qpdf1(pass 1) -qpdf2(pass 2) -O3 -qarch=auto -qtune=auto -qsimd -qlargepage -qprefetch=dscr=0x93 -qipa=partition=large -qfdpr -lhugetlbfs -Wl,-q -ltcmalloc |
-qsuppress=1586-476(pass 2) -qipa=noobject -qsuppress=1500-036 | |
400.perlbench: | -qsuppress=1586-476(pass 2) -qsuppress=1500-036 |
456.hmmer: | -qipa=noobject -qsuppress=1500-036 |
-qsuppress=1586-476(pass 2) -qipa=noobject -qsuppress=1500-036 |