| CPU2006 license: | 6 | Test date: | Aug-2008 |
|---|---|---|---|
| Test sponsor: | Sun Microsystems | Hardware Availability: | Sep-2008 |
| Tested by: | Sun Microsystems | Software Availability: | Nov-2007 |
| Hardware | |
|---|---|
| CPU Name: | Intel Xeon E7338 |
| CPU Characteristics: | |
| CPU MHz: | 2400 |
| FPU: | Integrated |
| CPU(s) enabled: | 16 cores, 4 chips, 4 cores/chip |
| CPU(s) orderable: | 2,4 chips |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 6 MB I+D on chip per chip, 3 MB shared / 2 cores |
| L3 Cache: | None |
| Other Cache: | None |
| Memory: | 128 GB (32x4 GB PC2-5300F, 2 rank, CL5-5-5, ECC) |
| Disk Subsystem: | SAS, 146 GB, 10K RPM |
| 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 |
| Auto Parallel: | Yes |
| File System: | ReiserFS |
| System State: | Multi-user, run level 3 |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32/64-bit |
| Other Software: | Binutils 2.17.10.50 Microquill SmartHeap V8.1 |
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 | 16 | 700 | 223 | 708 | 221 | 700 | 223 | 16 | 594 | 263 | 596 | 262 | 596 | 262 |
| 401.bzip2 | 16 | 1369 | 113 | 1356 | 114 | 1352 | 114 | 16 | 1306 | 118 | 1314 | 118 | 1311 | 118 |
| 403.gcc | 16 | 973 | 132 | 971 | 133 | 969 | 133 | 16 | 969 | 133 | 957 | 135 | 973 | 132 |
| 429.mcf | 16 | 1564 | 93.3 | 1572 | 92.8 | 1573 | 92.8 | 16 | 1565 | 93.2 | 1552 | 94.0 | 1581 | 92.3 |
| 445.gobmk | 16 | 748 | 225 | 740 | 227 | 750 | 224 | 16 | 676 | 248 | 678 | 247 | 683 | 246 |
| 456.hmmer | 16 | 822 | 182 | 825 | 181 | 824 | 181 | 16 | 599 | 249 | 601 | 248 | 599 | 249 |
| 458.sjeng | 16 | 904 | 214 | 903 | 214 | 905 | 214 | 16 | 811 | 239 | 815 | 238 | 811 | 239 |
| 462.libquantum | 16 | 6018 | 55.1 | 6164 | 53.8 | 6187 | 53.6 | 1 | 97.5 | 212 | 91.8 | 226 | 100 | 207 |
| 464.h264ref | 16 | 975 | 363 | 973 | 364 | 974 | 364 | 16 | 928 | 381 | 948 | 373 | 929 | 381 |
| 471.omnetpp | 16 | 1120 | 89.3 | 1122 | 89.1 | 1119 | 89.4 | 16 | 1097 | 91.1 | 1091 | 91.6 | 1105 | 90.5 |
| 473.astar | 16 | 1086 | 103 | 1090 | 103 | 1084 | 104 | 16 | 1023 | 110 | 1020 | 110 | 1039 | 108 |
| 483.xalancbmk | 16 | 719 | 153 | 723 | 153 | 721 | 153 | 16 | 719 | 153 | 723 | 153 | 721 | 153 |
Operating System Notes
taskset was used to bind processes to cores except for 462.libquantum peak 'ulimit -s unlimited' was used to set the stacksize to unlimited OMP_NUM_THREADS set to number of cores. KMP_STACKSIZE set to 64M KMP_AFFINITY set to physical,0
Platform Notes
Default BIOS configuration used (includes this settings): Hardware Prefetch = Disable; Adjacent Sector Prefetch = Disable
General Notes
All benchmarks compiled in 32-bit mode except 401.bzip2 and 456.hmmer, and 462.libquantum for peak, are compiled in 64-bit mode
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/data2/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 -auto-ilp32 -unroll4 -ansi-alias -opt-multi-version-aggressive -vec-guard-write |
| 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 -O3 -auto-ilp32 -unroll8 -Ob0 -opt-streaming-stores always -vec-guard-write -opt-malloc-options=3 -parallel -par-runtime-control -no-prec-div -opt-ra-region-strategy=routine |
| 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/data2/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/data2/SmartHeap_8.1/lib -lsmartheap |
| 483.xalancbmk: | basepeak = yes |