| CPU2006 license: | 4 | Test date: | May-2008 |
|---|---|---|---|
| Test sponsor: | SGI | Hardware Availability: | Mar-2008 |
| Tested by: | SGI | Software Availability: | Apr-2008 |
| Hardware | |
|---|---|
| CPU Name: | Intel Xeon E5472 |
| CPU Characteristics: | Quad Core, 3.0 GHz |
| CPU MHz: | 2992 |
| 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: | 12 MB I+D on chip per chip, 6 MB shared / 2 cores |
| L3 Cache: | None |
| Other Cache: | None |
| Memory: | 16 GB (8*2GB PC2-6400 CL5-5-5 FB-DIMMs) |
| Disk Subsystem: | 16 TB RAID 6+1 32 x 500 GB SATA (Seagate Barracuda 7200 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++ and Fortran Compiler for Linux Version 10.1, Build 20070913 |
| Auto Parallel: | Yes |
| File System: | NFSv3 IPoIB |
| System State: | Multi-user, run level 3 |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32/64-bit |
| Other Software: | SGI ProPack 5 for Linux Service Pack 5 Binutils 2.17 SmartHeap library 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 | 8 | 524 | 149 | 518 | 151 | 520 | 150 | 8 | 436 | 179 | 435 | 180 | 437 | 179 |
| 401.bzip2 | 8 | 700 | 110 | 697 | 111 | 698 | 111 | 8 | 662 | 117 | 658 | 117 | 665 | 116 |
| 403.gcc | 8 | 612 | 105 | 605 | 106 | 612 | 105 | 8 | 607 | 106 | 606 | 106 | 610 | 106 |
| 429.mcf | 8 | 766 | 95.3 | 765 | 95.4 | 768 | 95.0 | 8 | 759 | 96.1 | 754 | 96.8 | 761 | 95.9 |
| 445.gobmk | 8 | 556 | 151 | 550 | 152 | 562 | 149 | 8 | 511 | 164 | 513 | 163 | 514 | 163 |
| 456.hmmer | 8 | 591 | 126 | 591 | 126 | 591 | 126 | 8 | 346 | 216 | 347 | 215 | 350 | 213 |
| 458.sjeng | 8 | 682 | 142 | 686 | 141 | 686 | 141 | 8 | 616 | 157 | 617 | 157 | 614 | 158 |
| 462.libquantum | 8 | 2225 | 74.5 | 2198 | 75.4 | 2199 | 75.4 | 1 | 85.1 | 244 | 89.5 | 232 | 86.5 | 239 |
| 464.h264ref | 8 | 705 | 251 | 705 | 251 | 705 | 251 | 8 | 675 | 262 | 709 | 250 | 681 | 260 |
| 471.omnetpp | 8 | 697 | 71.7 | 695 | 71.9 | 696 | 71.8 | 8 | 670 | 74.7 | 672 | 74.5 | 670 | 74.6 |
| 473.astar | 8 | 648 | 86.6 | 649 | 86.5 | 648 | 86.7 | 8 | 609 | 92.3 | 607 | 92.5 | 607 | 92.5 |
| 483.xalancbmk | 8 | 400 | 138 | 401 | 138 | 403 | 137 | 8 | 400 | 138 | 401 | 138 | 403 | 137 |
General Notes
BIOS settings: Snoop Filter: Enabled Hardware Prefetcher: Enabled Adjacent Sector Prefetch: Disabled All benchmarks compiled in 32-bit mode except 401.bzip2 and 456.hmmer, for peak, are compiled in 64-bit mode The taskset utility was used to bind processes to cores Parallel settings for 462.libquantum peak: OMP_NUM_THREADS = 8 KMP_AFFINITY = physical,0 KMP_STACKSIZE = 64M
Base Compiler Invocation
C benchmarks:
| /opt/intel/cc/10.1.008/bin/icc -L/opt/intel/cc/10.1.008/lib -I/opt/intel/cc/10.1.008/include |
C++ benchmarks:
| /opt/intel/cc/10.1.008/bin/icpc -L/opt/intel/cc/10.1.008/lib -I/opt/intel/cc/10.1.008/include |
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 -lsmartheap |
Peak Compiler Invocation
C benchmarks (except as noted below):
C++ benchmarks:
| /opt/intel/cc/10.1.008/bin/icpc -L/opt/intel/cc/10.1.008/lib -I/opt/intel/cc/10.1.008/include |
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 -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 -lsmartheap |
| 483.xalancbmk: | basepeak = yes |