SPEC® CINT2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

NEC Corporation

Express5800/A1080a-S (Intel Xeon E7-4820)

CPU2006 license: 9006 Test date: Aug-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 E7-4820
CPU Characteristics: Intel Turbo Boost Technology up to 2.26 GHz
CPU MHz: 2000
FPU: Integrated
CPU(s) enabled: 32 cores, 4 chips, 8 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: 18 MB I+D on chip per chip
Other Cache: None
Memory: 256 GB (64 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++: Version 12.0.4.191 of Intel Compiler XE
for applications on IA-32 Build 20110427
Auto Parallel: No
File System: ext4
System State: Run level 3 (multi-user)
Base Pointers: 32-bit
Peak Pointers: 32/64-bit
Other Software: Microquill SmartHeap V9.01

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 64 1087 575 1096 570 1091 573 64 914 684 917 682 913 685
401.bzip2 64 1574 392 1575 392 1574 392 64 1491 414 1499 412 1495 413
403.gcc 64 898 574 896 575 898 574 64 898 574 893 577 898 574
429.mcf 64 664 880 666 876 662 881 64 648 901 648 901 650 898
445.gobmk 64 1044 643 1045 642 1044 643 64 948 708 948 708 948 708
456.hmmer 64 665 899 662 901 663 901 64 530 1130 529 1130 531 1130
458.sjeng 64 1252 619 1250 619 1250 619 64 1165 664 1165 664 1165 665
462.libquantum 64 393 3370 394 3360 393 3370 64 393 3370 394 3360 393 3370
464.h264ref 64 1625 872 1615 877 1584 894 64 1643 862 1635 866 1641 863
471.omnetpp 64 959 417 958 418 959 417 64 888 451 888 450 888 450
473.astar 64 1032 435 1030 436 1031 436 64 1032 435 1030 436 1031 436
483.xalancbmk 64 625 707 624 707 625 706 64 625 707 624 707 625 706

Submit Notes

The config file option 'submit' was used.
 numactl was used to bind copies to the cores

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
 Huge pages were not configured for this run

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 -m32 

C++ benchmarks:

 icpc -m32 

Base Portability Flags

400.perlbench:  -DSPEC_CPU_LINUX_IA32 
462.libquantum:  -DSPEC_CPU_LINUX 
483.xalancbmk:  -DSPEC_CPU_LINUX 

Base Optimization Flags

C benchmarks:

 -xSSE4.2   -ipo   -O3   -no-prec-div   -opt-prefetch   -B /usr/share/libhugetlbfs/ -Wl,-hugetlbfs-link=BDT 

C++ benchmarks:

 -xSSE4.2   -ipo   -O3   -no-prec-div   -opt-prefetch   -Wl,-z,muldefs   -L/opt/SmartHeap_9/lib -lsmartheap   -B /usr/share/libhugetlbfs/ -Wl,-hugetlbfs-link=BDT 

Base Other Flags

C benchmarks:

403.gcc:  -Dalloca=_alloca 

Peak Compiler Invocation

C benchmarks (except as noted below):

 icc -m32 
401.bzip2:  icc -m64 
456.hmmer:  icc -m64 
458.sjeng:  icc -m64 

C++ benchmarks:

 icpc -m32 

Peak Portability Flags

400.perlbench:  -DSPEC_CPU_LINUX_IA32 
401.bzip2:  -DSPEC_CPU_LP64 
456.hmmer:  -DSPEC_CPU_LP64 
458.sjeng:  -DSPEC_CPU_LP64 
462.libquantum:  -DSPEC_CPU_LINUX 
483.xalancbmk:  -DSPEC_CPU_LINUX 

Peak Optimization Flags

C benchmarks:

400.perlbench:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -static(pass 2)   -prof-use(pass 2)   -ansi-alias 
401.bzip2:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -static(pass 2)   -prof-use(pass 2)   -opt-prefetch   -ansi-alias   -auto-ilp32 
403.gcc:  -xSSE4.2   -ipo   -O3   -no-prec-div   -B /usr/share/libhugetlbfs/ -Wl,-hugetlbfs-link=BDT 
429.mcf:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -ansi-alias   -auto-ilp32 
445.gobmk:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -prof-use(pass 2)   -O2   -ipo   -no-prec-div   -ansi-alias 
456.hmmer:  -xSSE4.2   -ipo   -O3   -no-prec-div   -unroll2   -auto-ilp32   -B /usr/share/libhugetlbfs/ -Wl,-melf_x86_64 -Wl,-hugetlbfs-link=BDT 
458.sjeng:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -unroll4   -auto-ilp32   -B /usr/share/libhugetlbfs/ -Wl,-melf_x86_64 -Wl,-hugetlbfs-link=BDT 
462.libquantum:  basepeak = yes 
464.h264ref:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -unroll2   -ansi-alias 

C++ benchmarks:

471.omnetpp:  -xSSE4.2(pass 2)   -prof-gen(pass 1)   -ipo(pass 2)   -O3(pass 2)   -no-prec-div(pass 2)   -prof-use(pass 2)   -ansi-alias   -opt-ra-region-strategy=block   -Wl,-z,muldefs   -L/opt/SmartHeap_9/lib -lsmartheap 
473.astar:  basepeak = yes 
483.xalancbmk:  basepeak = yes 

Peak Other Flags

C benchmarks:

403.gcc:  -Dalloca=_alloca 

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-revB.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-revB.xml.