SPEC® CFP2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

NEC Corporation

Express5800/A1080a-D (Intel Xeon E7-8870)

SPECfp®2006 = 45.4

CPU2006 license: 9006 Test date: Nov-2011
Test sponsor: NEC Corporation Hardware Availability: Nov-2011
Tested by: NEC Corporation Software Availability: May-2011
Benchmark results graph
Hardware
CPU Name: Intel Xeon E7-8870
CPU Characteristics: Intel Turbo Boost Technology up to 2.80 GHz
CPU MHz: 2400
FPU: Integrated
CPU(s) enabled: 20 cores, 2 chips, 10 cores/chip, 2 threads/core
CPU(s) orderable: 1,2,3,4 chips
Primary Cache: 32 KB I + 32 KB D on chip per core
Secondary Cache: 256 KB I+D on chip per core
L3 Cache: 30 MB I+D on chip per chip
Other Cache: None
Memory: 128 GB (32 x 4 GB 2Rx4 PC3-8500R-7, ECC)
Disk Subsystem: 2x300 GB SAS, 10000 RPM, RAID 0
Other Hardware: None
Software
Operating System: Red Hat Enterprise Linux Server release 6.1,
Kernel 2.6.32-131.0.15.el6.x86_64 on an x86_64
Compiler: C/C++/Fortran: Version 12.0.4.191 of Intel
Compiler XE Build 20110427
Auto Parallel: Yes
File System: ext4
System State: Run level 3 (multi-user)
Base Pointers: 64-bit
Peak Pointers: 32/64-bit
Other Software: None

Results Table

Benchmark Base Peak
Seconds Ratio Seconds Ratio Seconds Ratio 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 104   131   105   130   105   130   105   130   106   128   103   132  
416.gamess 1464   13.4 1456   13.4 1460   13.4 825   23.7 828   23.7 826   23.7
433.milc 317   29.0 290   31.6 289   31.7 296   31.0 296   31.0 296   31.0
434.zeusmp 117   78.0 117   77.6 117   77.7 117   78.0 117   77.6 117   77.7
435.gromacs 393   18.2 391   18.3 391   18.3 357   20.0 358   20.0 356   20.1
436.cactusADM 46.4 257   45.2 264   44.4 269   46.4 257   45.2 264   44.4 269  
437.leslie3d 79.7 118   77.7 121   78.5 120   79.7 118   77.7 121   78.5 120  
444.namd 492   16.3 492   16.3 492   16.3 483   16.6 483   16.6 483   16.6
447.dealII 348   32.9 348   32.9 348   32.9 348   32.9 348   32.9 348   32.9
450.soplex 313   26.6 313   26.7 311   26.8 313   26.6 313   26.7 311   26.8
453.povray 205   26.0 207   25.7 204   26.1 163   32.6 163   32.7 163   32.6
454.calculix 364   22.7 368   22.4 364   22.7 298   27.7 298   27.7 298   27.7
459.GemsFDTD 214   49.6 206   51.4 210   50.5 181   58.5 179   59.4 177   59.9
465.tonto 703   14.0 695   14.2 703   14.0 352   27.9 353   27.9 353   27.9
470.lbm 73.9 186   74.1 186   74.1 186   80.1 172   78.5 175   81.5 169  
481.wrf 433   25.8 439   25.4 433   25.8 433   25.8 439   25.4 433   25.8
482.sphinx3 626   31.1 627   31.1 626   31.1 603   32.3 601   32.4 603   32.3

Operating System Notes

 'ulimit -s unlimited' was used to set the stack size to unlimited prior to run
 echo 1 > /proc/sys/vm/zone_reclaim_mode
 'mount -t hugetlbfs nodev /mnt/hugepages' was used to enable large pages
 echo 900 > /proc/sys/vm/nr_hugepages
 export HUGETLB_MORECORE=yes
 export LD_PRELOAD=/usr/lib64/libhugetlbfs.so

Platform Notes

 Patrol Scrubbing set to disabled in Maintenance Console

General Notes

 The Express5800/A1080a-S and the Express5800/A1080a-D models are electronically equivalent.
 The results have been measured on the Express5800/A1080a-S model.
 Binaries were compiled on RHEL 5.6

Base Compiler Invocation

C benchmarks:

 icc -m64 

C++ benchmarks:

 icpc -m64 

Fortran benchmarks:

 ifort -m64 

Benchmarks using both Fortran and C:

 icc -m64   ifort -m64 

Base Portability Flags

410.bwaves:  -DSPEC_CPU_LP64 
416.gamess:  -DSPEC_CPU_LP64 
433.milc:  -DSPEC_CPU_LP64 
434.zeusmp:  -DSPEC_CPU_LP64 
435.gromacs:  -DSPEC_CPU_LP64   -nofor_main 
436.cactusADM:  -DSPEC_CPU_LP64   -nofor_main 
437.leslie3d:  -DSPEC_CPU_LP64 
444.namd:  -DSPEC_CPU_LP64 
447.dealII:  -DSPEC_CPU_LP64 
450.soplex:  -DSPEC_CPU_LP64 
453.povray:  -DSPEC_CPU_LP64 
454.calculix:  -DSPEC_CPU_LP64   -nofor_main 
459.GemsFDTD:  -DSPEC_CPU_LP64 
465.tonto:  -DSPEC_CPU_LP64 
470.lbm:  -DSPEC_CPU_LP64 
481.wrf:  -DSPEC_CPU_LP64   -DSPEC_CPU_CASE_FLAG   -DSPEC_CPU_LINUX 
482.sphinx3:  -DSPEC_CPU_LP64 

Base Optimization Flags

C benchmarks:

 -xSSE4.2   -ipo   -O3   -no-prec-div   -static   -parallel   -opt-prefetch   -ansi-alias 

C++ benchmarks:

 -xSSE4.2   -ipo   -O3   -no-prec-div   -static   -opt-prefetch   -ansi-alias 

Fortran benchmarks:

 -xSSE4.2   -ipo   -O3   -no-prec-div   -static   -parallel   -opt-prefetch 

Benchmarks using both Fortran and C:

 -xSSE4.2   -ipo   -O3   -no-prec-div   -static   -parallel   -opt-prefetch   -ansi-alias 

Peak Compiler Invocation

C benchmarks:

 icc -m64 

C++ benchmarks:

 icpc -m64 

Fortran benchmarks:

 ifort -m64 

Benchmarks using both Fortran and C:

 icc -m64   ifort -m64 

Peak Portability Flags

Same as Base Portability Flags

Peak Optimization Flags

C benchmarks:

433.milc:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -static   -auto-ilp32   -ansi-alias 
470.lbm:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -parallel   -ansi-alias   -static   -auto-ilp32 
482.sphinx3:  -xSSE4.2   -ipo   -O3   -no-prec-div   -unroll2   -ansi-alias   -parallel 

C++ benchmarks:

444.namd:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -fno-alias   -auto-ilp32 
447.dealII:  basepeak = yes 
450.soplex:  basepeak = yes 
453.povray:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -unroll4   -ansi-alias   -B /usr/share/libhugetlbfs/ -Wl,-melf_x86_64 -Wl,-hugetlbfs-link=BDT 

Fortran benchmarks:

410.bwaves:  -xSSE4.2   -ipo   -O3   -no-prec-div   -opt-prefetch   -parallel   -static 
416.gamess:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -unroll2   -inline-level=0   -scalar-rep-   -static 
434.zeusmp:  basepeak = yes 
437.leslie3d:  basepeak = yes 
459.GemsFDTD:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -unroll2   -inline-level=0   -opt-prefetch   -parallel   -B /usr/share/libhugetlbfs/ -Wl,-melf_x86_64 -Wl,-hugetlbfs-link=BDT 
465.tonto:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -inline-calloc   -opt-malloc-options=3   -auto   -unroll4   -B /usr/share/libhugetlbfs/ -Wl,-melf_x86_64 -Wl,-hugetlbfs-link=BDT 

Benchmarks using both Fortran and C:

435.gromacs:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -static   -auto-ilp32   -ansi-alias 
436.cactusADM:  basepeak = yes 
454.calculix:  -xSSE4.2   -ipo   -O3   -no-prec-div   -auto-ilp32   -ansi-alias 
481.wrf:  basepeak = yes 

The flags files that were used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/Intel-ic12.0-linux64-revB.20110705.html,
http://www.spec.org/cpu2006/flags/NEC-platform-linux64-revC.html.

You can also download the XML flags sources by saving the following links:
http://www.spec.org/cpu2006/flags/Intel-ic12.0-linux64-revB.20110705.xml,
http://www.spec.org/cpu2006/flags/NEC-platform-linux64-revC.xml.