| CPU2006 license: | 20 | Test date: | May-2008 |
|---|---|---|---|
| Test sponsor: | Bull SAS | Hardware Availability: | Apr-2008 |
| Tested by: | NEC Corporation | Software Availability: | Nov-2007 |
| Hardware | |
|---|---|
| CPU Name: | Intel Xeon E5440 |
| CPU Characteristics: | 2.83 GHz, 2x6 MB L2 shared, 1333 MHz bus |
| CPU MHz: | 2833 |
| 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 | 546 | 71.6 | 547 | 71.4 | 550 | 71.1 | 4 | 456 | 85.7 | 456 | 85.8 | 458 | 85.4 |
| 401.bzip2 | 4 | 695 | 55.5 | 712 | 54.2 | 696 | 55.4 | 4 | 656 | 58.8 | 654 | 59.0 | 653 | 59.1 |
| 403.gcc | 4 | 603 | 53.4 | 600 | 53.6 | 600 | 53.7 | 4 | 605 | 53.2 | 606 | 53.2 | 608 | 52.9 |
| 429.mcf | 4 | 702 | 51.9 | 697 | 52.3 | 696 | 52.4 | 4 | 710 | 51.4 | 707 | 51.6 | 714 | 51.1 |
| 445.gobmk | 4 | 580 | 72.4 | 589 | 71.2 | 578 | 72.6 | 4 | 530 | 79.2 | 530 | 79.2 | 529 | 79.4 |
| 456.hmmer | 4 | 626 | 59.6 | 626 | 59.6 | 626 | 59.6 | 4 | 369 | 101 | 368 | 101 | 370 | 101 |
| 458.sjeng | 4 | 718 | 67.4 | 718 | 67.4 | 723 | 67.0 | 4 | 651 | 74.4 | 656 | 73.8 | 655 | 73.9 |
| 462.libquantum | 4 | 2497 | 33.2 | 2498 | 33.2 | 2497 | 33.2 | 1 | 248 | 83.6 | 249 | 83.3 | 248 | 83.5 |
| 464.h264ref | 4 | 742 | 119 | 741 | 119 | 742 | 119 | 4 | 711 | 124 | 709 | 125 | 710 | 125 |
| 471.omnetpp | 4 | 741 | 33.7 | 740 | 33.8 | 739 | 33.8 | 4 | 722 | 34.6 | 721 | 34.7 | 722 | 34.6 |
| 473.astar | 4 | 683 | 41.1 | 685 | 41.0 | 684 | 41.0 | 4 | 640 | 43.9 | 637 | 44.1 | 638 | 44.0 |
| 483.xalancbmk | 4 | 395 | 69.9 | 395 | 69.9 | 395 | 69.8 | 4 | 395 | 69.9 | 395 | 69.9 | 395 | 69.8 |
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 E5440) and the Bull NovaScale T860 E1(Intel Xeon E5440,2.83GHz) models are electronically equivalent. The results have been measured on a NEC Express5800/120Lj(Intel Xeon E5440) model.
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 |
Peak Compiler Invocation
C benchmarks (except as noted below):
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 |