SPEC® CFP2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

IBM Corporation

IBM Power 780 (3.7 GHz, 128 core)

CPU2006 license: 11 Test date: Sep-2012
Test sponsor: IBM Corporation Hardware Availability: Oct-2012
Tested by: IBM Corporation Software Availability: Nov-2012
Benchmark results graph
Hardware
CPU Name: POWER7+
CPU Characteristics: Intelligent Energy Optimization enabled,
up to 4.144 GHz
CPU MHz: 3724
FPU: Integrated
CPU(s) enabled: 128 cores, 16 chips, 8 cores/chip, 4 threads/core
CPU(s) orderable: 32,64,96,128 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: 1 TB (64 x 16 GB) DDR3 1066 MHz
Disk Subsystem: 8 x 387 GB Raid0 SFF-1 SSD
Other Hardware: None
Software
Operating System: IBM AIX V7.1
Compiler: C/C++: Version 12.1 of IBM XL C/C++ for AIX;
Fortran: Version 14.1 of IBM XL Fortran for AIX
Auto Parallel: No
File System: AIX/JFS2
System State: Multi-user
Base Pointers: 32-bit
Peak Pointers: 32/64-bit
Other Software: None

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 512 2385 2920 2384 2920 2384 2920 512 2295 3030 2299 3030 2296 3030
416.gamess 512 2315 4330 2317 4330 2316 4330 512 2235 4480 2227 4500 2249 4460
433.milc 512 1650 2850 1650 2850 1651 2850 128 402 2920 401 2930 401 2930
434.zeusmp 512 1446 3220 1438 3240 1333 3490 512 1440 3240 1251 3720 1255 3710
435.gromacs 512 982 3720 986 3710 990 3690 512 812 4500 814 4490 812 4500
436.cactusADM 512 1355 4520 1358 4510 1357 4510 512 920 6650 923 6630 928 6590
437.leslie3d 512 2427 1980 2431 1980 2428 1980 256 1070 2250 1073 2240 1070 2250
444.namd 512 729 5630 731 5620 730 5630 512 715 5740 715 5740 714 5750
447.dealII 512 633 9250 634 9240 633 9250 512 633 9250 634 9240 633 9250
450.soplex 512 1940 2200 1941 2200 1952 2190 256 809 2640 781 2730 783 2730
453.povray 512 594 4590 592 4600 595 4580 512 423 6440 428 6360 425 6410
454.calculix 512 932 4530 933 4530 901 4690 512 866 4880 868 4860 870 4860
459.GemsFDTD 512 3638 1490 3634 1500 3628 1500 128 847 1600 846 1600 849 1600
465.tonto 512 1098 4590 1101 4570 1099 4580 512 978 5150 977 5160 973 5180
470.lbm 512 4195 1680 4199 1680 4195 1680 128 428 4110 428 4110 428 4110
481.wrf 512 1636 3500 1645 3480 1611 3550 512 1636 3500 1645 3480 1611 3550
482.sphinx3 512 3014 3310 3007 3320 3010 3320 128 389 6410 390 6400 392 6360

Compiler Invocation Notes

C/C++ compiler updated to November 2012 PTF
      Version: 12.01.0000.0002
Fortran compiler updated to November 2012 PTF
      Version: 14.01.0000.0002

Peak Tuning Notes

 416.gamess fdpr options: -O4 -cbpth -1 -sdp -1
 433.milc fdpr options: -O3 -lu -1
 435.gromacs fdpr options: -O
 436.cactusADM fdpr options: -O3 -lu -1 -nodp -sdp 9
 437.leslie3d fdpr options: -O3
 453.povray fdpr options: -O3 -cbpth -1
 459.GemsFDTD fdpr options: -O3 -cbpth -1
 465.tonto fdpr options: -O4
 482.sphinx3 fdpr options: -O4 -rcctf 0 -sdp 9 -vrox

Submit Notes

 The config file option 'submit' was used
 to assign benchmark copy to specific kernel thread using
 the "bindprocessor" command (see flags file for details).

Operating System Notes

 AIX updated to V7.1 TL 2

 All ulimits set to unlimited.

 51200 16M large pages defined with vmo command

Platform Notes

 Service Processor Memory Mirroring Property Disabled

General Notes

Environment variables set by runspec before the start of the run:
MALLOCOPTIONS = "pool"
MEMORY_AFFINITY = "MCM"
XLFRTEOPTS = "intrinthds=1"

Base Compiler Invocation

C benchmarks:

 /usr/vac/bin/xlc   -qlanglvl=extc99 

C++ benchmarks:

 /usr/vacpp/bin/xlC 

Fortran benchmarks:

 /usr/bin/xlf95 

Benchmarks using both Fortran and C:

 /usr/vac/bin/xlc   -qlanglvl=extc99   /usr/bin/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:  -DSPEC_CPU_AIX   -DNOUNDERSCORE 
482.sphinx3:  -qchars=signed 

Base Optimization Flags

C benchmarks:

 -qipa=threads   -bmaxdata:0x40000000   -qlargepage   -O5   -D_ILS_MACROS   -blpdata 

C++ benchmarks:

 -qipa=threads   -bmaxdata:0x50000000   -qlargepage   -O5   -qsimd   -qvecnvol   -D_ILS_MACROS   -qrtti=all   -D__IBM_FAST_VECTOR   -D__IBM_FAST_SET_MAP_ITERATOR   -blpdata 

Fortran benchmarks:

 -qipa=threads   -bmaxdata:0x60000000   -qlargepage   -O5   -qsmallstack=dynlenonheap   -qalias=nostd   -blpdata 

Benchmarks using both Fortran and C:

 -qipa=threads   -bmaxdata:0x60000000   -qlargepage   -O5   -D_ILS_MACROS   -qsmallstack=dynlenonheap   -qalias=nostd   -blpdata 

Base Other Flags

C benchmarks:

 -qipa=noobject   -qsuppress=1500-036 

C++ benchmarks:

 -qipa=noobject   -qsuppress=1500-036 

Fortran benchmarks:

 -qipa=noobject   -qsuppress=1500-010   -qsuppress=cmpmsg   -qsuppress=1500-036 

Benchmarks using both Fortran and C:

 -qipa=noobject   -qsuppress=1500-010   -qsuppress=cmpmsg   -qsuppress=1500-036 

Peak Compiler Invocation

C benchmarks:

 /usr/vac/bin/xlc   -qlanglvl=extc99 

C++ benchmarks:

 /usr/vacpp/bin/xlC 

Fortran benchmarks:

 /usr/bin/xlf95 

Benchmarks using both Fortran and C:

 /usr/vac/bin/xlc   -qlanglvl=extc99   /usr/bin/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:  -DSPEC_CPU_AIX   -DNOUNDERSCORE 
482.sphinx3:  -qchars=signed 

Peak Optimization Flags

C benchmarks:

433.milc:  -qipa=threads   -bmaxdata:0x40000000   -O5   -qlargepage   -D_ILS_MACROS   -qprefetch=aggressive   -qalign=natural   -blpdata   -btextpsize:64K 
470.lbm:  -qipa=threads   -bmaxdata:0x30000000   -O5   -D_ILS_MACROS   -blpdata   -btextpsize:64K 
482.sphinx3:  -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qlargepage   -D_ILS_MACROS   -blpdata   -btextpsize:64K 

C++ benchmarks:

444.namd:  -qipa=threads   -O4   -q64   -qlargepage   -D_ILS_MACROS   -D__IBM_FAST_VECTOR   -D__IBM_FAST_SET_MAP_ITERATOR   -blpdata   -btextpsize:64K 
447.dealII:  basepeak = yes 
450.soplex:  -qipa=threads   -bmaxdata:0x40000000   -O5   -qsimd   -qvecnvol   -D_ILS_MACROS   -D__IBM_FAST_VECTOR   -D__IBM_FAST_SET_MAP_ITERATOR   -blpdata   -btextpsize:64K 
453.povray:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O4   -qsimd   -qvecnvol   -qlargepage   -D_ILS_MACROS   -qalign=natural   -blpdata   -btextpsize:64K 

Fortran benchmarks:

410.bwaves:  -qipa=threads   -bmaxdata:0x50000000   -O5   -qlargepage   -qsmallstack=dynlenonheap   -blpdata   -btextpsize:64K 
416.gamess:  -qipa=threads   -bmaxdata:0x40000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qarch=pwr5   -qlargepage   -qalias=nostd   -blpdata   -btextpsize:64K 
434.zeusmp:  -bmaxdata:0x40000000   -O5   -qlargepage   -qxlf90=nosignedzero   -blpdata   -btextpsize:64K 
437.leslie3d:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -blpdata   -btextpsize:64K 
459.GemsFDTD:  -qpdf1(pass 1)   -qpdf2(pass 2)   -O4   -q64   -qlargepage   -blpdata   -btextpsize:64K 
465.tonto:  -qipa=threads   -bmaxdata:0x50000000   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qsimd   -qvecnvol   -blpdata   -btextpsize:64K 

Benchmarks using both Fortran and C:

435.gromacs:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -D_ILS_MACROS   -blpdata   -btextpsize:64K 
436.cactusADM:  -qipa=threads   -bmaxdata:0x60000000   -O4   -qsimd   -qvecnvol   -D_ILS_MACROS   -qnostrict   -blpdata   -btextpsize:64K 
454.calculix:  -qipa=threads   -qpdf1(pass 1)   -qpdf2(pass 2)   -O5   -qsimd   -qvecnvol   -qlargepage   -D_ILS_MACROS   -blpdata   -btextpsize:64K 
481.wrf:  basepeak = yes 

Peak Other Flags

C benchmarks:

 -qipa=noobject   -qsuppress=1500-036 

C++ benchmarks (except as noted below):

 -qipa=noobject   -qsuppress=1500-036 
450.soplex:  -qsuppress=1500-036 

Fortran benchmarks (except as noted below):

 -qipa=noobject   -qsuppress=1500-010   -qsuppress=cmpmsg   -qsuppress=1500-036 
434.zeusmp:  -qsuppress=1500-010   -qsuppress=cmpmsg   -qsuppress=1500-036 

Benchmarks using both Fortran and C:

 -qipa=noobject   -qsuppress=1500-010   -qsuppress=cmpmsg   -qsuppress=1500-036 

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/IBM-XL.20110613.html,
http://www.spec.org/cpu2006/flags/IBM-AIX.20110613.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/IBM-XL.20110613.xml,
http://www.spec.org/cpu2006/flags/IBM-AIX.20110613.xml.