| CPU2006 license: | 22 | Test date: | Apr-2007 |
|---|---|---|---|
| Test sponsor: | Fujitsu Siemens Computers | Hardware Availability: | Nov-2006 |
| Tested by: | Fujitsu Siemens Computers | Software Availability: | Feb-2007 |
| Hardware | |
|---|---|
| CPU Name: | Intel Xeon E5320 |
| CPU Characteristics: | 1067 MHz system bus |
| CPU MHz: | 1867 |
| FPU: | Integrated |
| CPU(s) enabled: | 8 cores, 2 chips, 4 cores/chip |
| CPU(s) orderable: | 1,2 chips |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 8 MB I+D on chip per chip, 4 MB shared / 2 cores |
| L3 Cache: | None |
| Other Cache: | None |
| Memory: | 16 GB (8x2 GB DDR2 PC2-5300F, 2 rank, CAS 5-5-5, with ECC) |
| Disk Subsystem: | SAS (73GB 15400 rpm) |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | 64-Bit SUSE LINUX Enterprise Server 10, Kernel 2.6.16.21-0.8-smp on an x86_64 |
| Compiler: | Intel C++ Compiler for IA32/EM64T application, Version 9.1 - Build 20070215, Package-ID: l_cc_p_9.1.047 |
| Auto Parallel: | No |
| File System: | ext2 |
| System State: | Multiuser, Runlevel 3 |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32/64-bit |
| Other Software: | Smart Heap Library, Version 8.1 |
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 | 8 | 806 | 96.9 | 810 | 96.5 | 809 | 96.6 | 8 | 744 | 105 | 741 | 105 | 741 | 106 |
| 401.bzip2 | 8 | 1375 | 56.1 | 1383 | 55.8 | 1382 | 55.9 | 8 | 1322 | 58.4 | 1323 | 58.3 | 1324 | 58.3 |
| 403.gcc | 8 | 999 | 64.5 | 999 | 64.5 | 1002 | 64.3 | 8 | 999 | 64.5 | 999 | 64.5 | 1002 | 64.3 |
| 429.mcf | 8 | 1469 | 49.7 | 1470 | 49.6 | 1467 | 49.7 | 8 | 1368 | 53.3 | 1372 | 53.2 | 1372 | 53.2 |
| 445.gobmk | 8 | 885 | 94.8 | 887 | 94.7 | 886 | 94.7 | 8 | 826 | 102 | 824 | 102 | 825 | 102 |
| 456.hmmer | 8 | 1239 | 60.2 | 1242 | 60.1 | 1239 | 60.2 | 8 | 1047 | 71.3 | 1046 | 71.4 | 1048 | 71.2 |
| 458.sjeng | 8 | 1067 | 90.7 | 1067 | 90.7 | 1069 | 90.6 | 8 | 979 | 98.9 | 980 | 98.7 | 976 | 99.2 |
| 462.libquantum | 8 | 7177 | 23.1 | 7188 | 23.1 | 7187 | 23.1 | 8 | 7104 | 23.3 | 7103 | 23.3 | 7103 | 23.3 |
| 464.h264ref | 8 | 1180 | 150 | 1179 | 150 | 1178 | 150 | 8 | 1168 | 152 | 1174 | 151 | 1165 | 152 |
| 471.omnetpp | 8 | 1067 | 46.9 | 1068 | 46.8 | 1073 | 46.6 | 8 | 1018 | 49.1 | 1018 | 49.1 | 1021 | 49.0 |
| 473.astar | 8 | 1114 | 50.4 | 1115 | 50.4 | 1113 | 50.5 | 8 | 1101 | 51.0 | 1101 | 51.0 | 1102 | 51.0 |
| 483.xalancbmk | 8 | 678 | 81.4 | 680 | 81.1 | 683 | 80.9 | 8 | 678 | 81.4 | 680 | 81.1 | 683 | 80.9 |
Operating System Notes
'ulimit -s unlimited' was used to set the stacksize to unlimited prior to run '/usr/bin/taskset' used to bind processes to CPUs
General Notes
The system bus runs at 1067 MHz All binaries were built with 32-bit Intel compiler except: 401.bzip2, 456.hmmer and 462.libquantum in peak were built with 64-bit Intel compiler by changing the path for include and library files. BIOS configuration: Hardware Prefetch = Disable, Adjacent Sector Prefetch = Disable The PRIMERGY RX300 S3 and the PRIMERGY TX300 S3 are electronically equivalent. For information about Fujitsu Siemens Computers in your country please see: http://www.fujitsu-siemens.com/countries
Base Portability Flags
| 400.perlbench: | -DSPEC_CPU_LINUX_X64 |
| 462.libquantum: | -DSPEC_CPU_LINUX |
| 483.xalancbmk: | -DSPEC_CPU_LINUX |
Base Optimization Flags
C benchmarks:
| -fast |
C++ benchmarks:
| -xP -O3 -ipo -no-prec-div -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_X64 |
| 401.bzip2: | -DSPEC_CPU_LP64 |
| 456.hmmer: | -DSPEC_CPU_LP64 |
| 462.libquantum: | -DSPEC_CPU_LP64 -DSPEC_CPU_LINUX |
| 483.xalancbmk: | -DSPEC_CPU_LINUX |
Peak Optimization Flags
C benchmarks:
| 400.perlbench: | -prof_gen(pass 1) -prof_use(pass 2) -fast |
| 401.bzip2: | -fast |
| 403.gcc: | basepeak = yes |
| 429.mcf: | -prof_gen(pass 1) -prof_use(pass 2) -fast -L/opt/SmartHeap_8_1/lib -lsmartheap |
| 445.gobmk: | Same as 429.mcf |
| 456.hmmer: | Same as 400.perlbench |
| 458.sjeng: | Same as 429.mcf |
| 462.libquantum: | Same as 400.perlbench |
| 464.h264ref: | Same as 429.mcf |
C++ benchmarks:
| 471.omnetpp: | -prof_gen(pass 1) -prof_use(pass 2) -xP -O3 -ipo -no-prec-div -L/opt/SmartHeap_8_1/lib -lsmartheap |
| 473.astar: | -prof_gen(pass 1) -prof_use(pass 2) -fast -L/opt/SmartHeap_8_1/lib -lsmartheap |
| 483.xalancbmk: | basepeak = yes |