SPEC® CINT2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

NEC Corporation

Express5800/120Lj
(Intel Xeon E5420)

CPU2006 license: 9006 Test date: May-2008
Test sponsor: NEC Corporation Hardware Availability: Apr-2008
Tested by: NEC Corporation Software Availability: Nov-2007
Benchmark results graph
Hardware
CPU Name: Intel Xeon E5420
CPU Characteristics: 2.50 GHz, 2x6 MB L2 shared, 1333 MHz bus
CPU MHz: 2500
FPU: Integrated
CPU(s) enabled: 4 cores, 1 chip, 4 cores/chip
CPU(s) orderable: 1,2 chips
Primary Cache: 32 KB I + 32 KB D on chip per core
Secondary Cache: 12 MB I+D on chip per chip, 6 MB shared / 2 cores
L3 Cache: None
Other Cache: None
Memory: 16 GB (8x2 GB PC2-5300F, 2 rank, CL5-5-5, ECC)
Disk Subsystem: 1x73.2 GB SAS, 15000RPM
Other Hardware: None
Software
Operating System: SUSE Linux Enterprise Server 10 (x86_64) SP1,
Kernel 2.6.16.46-0.12-smp
Compiler: Intel C++ Compiler for Linux32 and Linux64
version 10.1 Build 20070913 Package ID:
l_cc_p_10.1.008
Auto Parallel: Yes
File System: ReiserFS
System State: Run level 3 (multi-user)
Base Pointers: 32-bit
Peak Pointers: 32/64-bit
Other Software: MicroQuill SmartHeap library 8.1
binutils-2.17.tar.gz, Version 2.17

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 4 623 62.8 609 64.2 616 63.4 4 503 77.8 504 77.5 508 77.0
401.bzip2 4 772 50.0 770 50.1 769 50.2 4 733 52.6 723 53.4 724 53.3
403.gcc 4 642 50.2 638 50.5 632 50.9 4 635 50.7 637 50.6 634 50.8
429.mcf 4 694 52.5 696 52.4 697 52.4 4 712 51.2 711 51.3 714 51.1
445.gobmk 4 648 64.8 654 64.1 656 63.9 4 592 70.8 593 70.8 599 70.1
456.hmmer 4 709 52.6 710 52.6 709 52.6 4 414 90.2 414 90.2 419 89.1
458.sjeng 4 805 60.1 804 60.2 806 60.0 4 727 66.6 726 66.7 723 66.9
462.libquantum 4 2545 32.6 2547 32.5 2545 32.6 1 254 81.6 255 81.2 254 81.5
464.h264ref 4 838 106   838 106   839 105   4 803 110   802 110   813 109  
471.omnetpp 4 731 34.2 731 34.2 731 34.2 4 710 35.2 710 35.2 710 35.2
473.astar 4 730 38.5 736 38.2 729 38.5 4 681 41.2 682 41.2 683 41.1
483.xalancbmk 4 423 65.2 423 65.2 424 65.1 4 423 65.2 423 65.2 424 65.1

Operating System Notes

 'ulimit -s unlimited' was used to set the stacksize to unlimited prior to run
  OMP_NUM_THREADS set to number of cores

Platform Notes

Bios settings:
Hardware Prefetcher:          Enabled
Adjacent Cache Line Prefetch: Disabled
Intel SpeedStep Technology:   Disabled

General Notes

All benchmarks compiled in 32-bit mode except 401.bzip2,
456.hmmer, for peak, are compiled in 64-bit mode

 The NEC Express5800/120Lj(Intel Xeon E5420) and
 the Bull NovaScale T860 E1(Intel Xeon E5420,2.50GHz) models are electronically equivalent.
 The results have been measured on a NEC Express5800/120Lj(Intel Xeon E5420) model.

Base Compiler Invocation

C benchmarks:

 icc 

C++ benchmarks:

 icpc 

Base Portability Flags

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

Base Optimization Flags

C benchmarks:

 -fast   -inline-calloc   -opt-malloc-options=3 

C++ benchmarks:

 -xT   -ipo   -O3   -no-prec-div   -Wl,-z,muldefs   -L/opt/SmartHeap_8.1/lib -lsmartheap 

Base Other Flags

C benchmarks:

403.gcc:  -Dalloca=_alloca 

Peak Compiler Invocation

C benchmarks (except as noted below):

 icc 
401.bzip2:  /opt/intel/cce/10.1.008/bin/icc   -L/opt/intel/cce/10.1.008/lib   -I/opt/intel/cce/10.1.008/include 
456.hmmer:  /opt/intel/cce/10.1.008/bin/icc   -L/opt/intel/cce/10.1.008/lib   -I/opt/intel/cce/10.1.008/include 

C++ benchmarks:

 icpc 

Peak Portability Flags

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

Peak Optimization Flags

C benchmarks:

400.perlbench:  -prof-gen(pass 1)   -prof-use(pass 2)   -fast   -ansi-alias   -prefetch 
401.bzip2:  -prof-gen(pass 1)   -prof-use(pass 2)   -fast   -prefetch 
403.gcc:  -fast   -inline-calloc   -opt-malloc-options=3 
429.mcf:  -fast   -prefetch 
445.gobmk:  -prof-gen(pass 1)   -prof-use(pass 2)   -xT   -O2   -ipo   -no-prec-div   -ansi-alias 
456.hmmer:  -fast   -unroll2   -ansi-alias   -opt-multi-version-aggressive 
458.sjeng:  -prof-gen(pass 1)   -prof-use(pass 2)   -fast   -unroll4 
462.libquantum:  -fast   -unroll4   -Ob0   -prefetch   -opt-streaming-stores always   -vec-guard-write   -opt-malloc-options=3   -parallel   -par-runtime-control 
464.h264ref:  -prof-gen(pass 1)   -prof-use(pass 2)   -fast   -unroll2   -ansi-alias 

C++ benchmarks:

471.omnetpp:  -prof-gen(pass 1)   -prof-use(pass 2)   -xT   -O3   -ipo   -no-prec-div   -ansi-alias   -opt-ra-region-strategy=block   -Wl,-z,muldefs   -L/opt/SmartHeap_8.1/lib -lsmartheap 
473.astar:  -prof-gen(pass 1)   -prof-use(pass 2)   -xT   -O3   -ipo   -no-prec-div   -ansi-alias   -opt-ra-region-strategy=routine   -Wl,-z,muldefs   -L/opt/SmartHeap_8.1/lib -lsmartheap 
483.xalancbmk:  basepeak = yes 

Peak Other Flags

C benchmarks:

403.gcc:  -Dalloca=_alloca 

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/NEC-Intel-ic10.1-INT-ia32-linux-flags.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/NEC-Intel-ic10.1-INT-ia32-linux-flags.xml.