SPEC® CINT2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

IBM Corporation

IBM Flex System p270 (3.4 GHz, 24 core, RHEL,
GCC)

CPU2006 license: 11 Test date: Jun-2013
Test sponsor: IBM Corporation Hardware Availability: Sep-2013
Tested by: IBM Corporation Software Availability: May-2013
Benchmark results graph
Hardware
CPU Name: POWER7+
CPU Characteristics: Intelligent Energy Optimization enabled,
up to 3.787 GHz
CPU MHz: 3416
FPU: Integrated
CPU(s) enabled: 24 cores, 4 chips, 6 cores/chip, 4 threads/core
CPU(s) orderable: 24 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: 256 GB (16 x 16 GB) DDR3 1066 MHz
Disk Subsystem: 2 x 177 GB Raid0 SATA SSD 1.8"
Other Hardware: None
Software
Operating System: Red Hat Enterprise Linux Server release 6.4
(ppc64) kernel 2.6.32-358.6.2.el6.ppc64
Compiler: C/C++: Version 4.7.3 of IBM
Advance Toolchain 6.0-4 gcc/g++ compiler
Auto Parallel: No
File System: ext4
System State: Run level 3 (multi-user)
Base Pointers: 32-bit
Peak Pointers: 32-bit
Other Software: -IBM Advance Toolchain 6.0-4
-IBM Mathematical Acceleration
Subsystem (MASS) libraries 7.1.0.2

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 96 1245 753 1252 749 1257 746 96 1245 753 1252 749 1257 746
401.bzip2 96 1116 830 1118 829 1114 832 96 1116 830 1118 829 1114 832
403.gcc 96 1058 731 1063 727 1065 725 96 1058 731 1063 727 1065 725
429.mcf 96 1425 614 1426 614 1429 613 96 1425 614 1426 614 1429 613
445.gobmk 96 1011 996 1010 997 1011 996 96 1011 996 1010 997 1011 996
456.hmmer 96 1425 628 1424 629 1424 629 96 1425 628 1424 629 1424 629
458.sjeng 96 1407 825 1409 824 1405 827 96 1407 825 1409 824 1405 827
462.libquantum 96 5708 348 5708 348 5708 348 96 5708 348 5708 348 5708 348
464.h264ref 96 1700 1250 1742 1220 1707 1240 96 1700 1250 1742 1220 1707 1240
471.omnetpp 96 1848 325 1847 325 1847 325 96 1848 325 1847 325 1847 325
473.astar 96 981 687 981 687 980 688 96 981 687 981 687 980 688
483.xalancbmk 96 709 934 710 933 710 933 96 709 934 710 933 710 933

Compiler Invocation Notes

For more information about IBM Advance Toolchain, including support, see
ftp://ftp.unicamp.br/pub/linuxpatch/toolchain/at/redhat/RHEL6/at6.0/release_notes.at6.0-6.0-4.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 6336 > /proc/sys/vm/nr_hugepages

  The Mathematical Acceleration Subsystem libraries
  are shipped with IBM XL C/C++ version 12.1 and
  IBM XL Fortran version 14.1 compiler products.

Platform Notes

   This Compute Node is housed in an "IBM Flex System Enterprise Chassis"

   The Maximum Power Limit for this Compute Node was set according to
   recommendation on "IBM Chassis Management Module"

General Notes

Environment variables set by runspec before the start of the run:
HUGETLB_ELFMAP = "RW"
HUGETLB_MORECORE = "yes"
HUGETLB_VERBOSE = "0"
TCMALLOC_MEMFS_MALLOC_PATH = "/libhugetlbfs"
XLFRTEOPTS = "intrinthds=1"

Base Compiler Invocation

C benchmarks:

 /opt/at6.0/bin/gcc 

C++ benchmarks:

 /opt/at6.0/bin/g++ 

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:

 -ffast-math   -O3   -mcpu=power7   -mtune=power7   -mrecip=rsqrt   -fpeel-loops   -funroll-loops   -mpopcntd   -m32   -flto   -fwhole-program   -fuse-linker-plugin   -Wl,-q   -Wl,-Map=link.map,--cref   -L /opt/at6.0/lib   -L /opt/ibmcmp/xlmass/7.1/lib   -Wl,-rpath,/opt/at6.0/lib   -Wl,-rpath,/opt/ibmcmp/xlmass/7.1/lib   -lhugetlbfs   -lmassvp7   -lmass_simdp7   -lmass 

C++ benchmarks:

 -ffast-math   -O3   -mcpu=power7   -mtune=power7   -mrecip=rsqrt   -fpeel-loops   -funroll-loops   -mpopcntd   -m32   --param max-inline-insns-auto=200   -Wl,-q   -Wl,-Map=link.map,--cref   -L /opt/at6.0/lib   -L /opt/ibmcmp/xlmass/7.1/lib   -Wl,-rpath,/opt/at6.0/lib   -Wl,-rpath,/opt/ibmcmp/xlmass/7.1/lib   -lhugetlbfs   -lmassvp7   -lmass_simdp7   -lmass   -ltcmalloc   -lstdc++ -lpthread 

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 

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/IBM-Power.20130828.html,
http://www.spec.org/cpu2006/flags/IBM-Linux-AT.20130813.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/IBM-Power.20130828.xml,
http://www.spec.org/cpu2006/flags/IBM-Linux-AT.20130813.xml.