| CPU2006 license: | 13 | Test date: | Jan-2009 |
|---|---|---|---|
| Test sponsor: | Intel Corporation | Hardware Availability: | Apr-2008 |
| Tested by: | Intel Corporation | Software Availability: | Nov-2008 |
| Hardware | |
|---|---|
| CPU Name: | AMD Phenom X4 9850 |
| CPU Characteristics: | |
| CPU MHz: | 2500 |
| FPU: | Integrated |
| CPU(s) enabled: | 4 cores, 1 chip, 4 cores/chip |
| CPU(s) orderable: | 1 chip |
| Primary Cache: | 64 KB I + 64 KB D on chip per core |
| Secondary Cache: | 512 KB I+D on chip per core |
| L3 Cache: | 2 MB I+D on chip per chip |
| Other Cache: | None |
| Memory: | 4 GB (4x1GB DDR2-800 CL5) |
| Disk Subsystem: | Seagate 320 GB SATA, 7200RPM |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Windows Vista Ultimate w/ SP1 (64-bit) |
| Compiler: | Intel C++ Compiler Professional 11.0 for IA32 Build 20080930 Package ID: w_cproc_p_11.0.054 Microsoft Visual Studio 2008 (for libraries) |
| Auto Parallel: | Yes |
| File System: | NTFS |
| System State: | Default |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32-bit |
| Other Software: | SmartHeap Library Version 8.1 from http://www.microquill.com/ |
Results Table
| Benchmark | Base | Peak | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | 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 | 715 | 13.7 | 714 | 13.7 | 717 | 13.6 | 556 | 17.6 | 557 | 17.5 | 555 | 17.6 |
| 401.bzip2 | 911 | 10.6 | 938 | 10.3 | 917 | 10.5 | 950 | 10.2 | 943 | 10.2 | 959 | 10.1 |
| 403.gcc | 634 | 12.7 | 635 | 12.7 | 638 | 12.6 | 601 | 13.4 | 599 | 13.4 | 622 | 12.9 |
| 429.mcf | 920 | 9.90 | 920 | 9.90 | 933 | 9.80 | 927 | 9.80 | 934 | 9.80 | 930 | 9.80 |
| 445.gobmk | 687 | 15.3 | 687 | 15.3 | 688 | 15.3 | 640 | 16.4 | 639 | 16.4 | 638 | 16.4 |
| 456.hmmer | 1924 | 4.80 | 1921 | 4.90 | 1933 | 4.80 | 1975 | 4.70 | 1975 | 4.70 | 1947 | 4.80 |
| 458.sjeng | 932 | 13.0 | 929 | 13.0 | 931 | 13.0 | 870 | 13.9 | 868 | 13.9 | 868 | 13.9 |
| 462.libquantum | 373 | 55.6 | 373 | 55.6 | 372 | 55.7 | 373 | 55.6 | 373 | 55.6 | 372 | 55.7 |
| 464.h264ref | 1028 | 21.5 | 1025 | 21.6 | 1022 | 21.7 | 1031 | 21.5 | 1047 | 21.1 | 1045 | 21.2 |
| 471.omnetpp | 573 | 10.9 | 569 | 11.0 | 570 | 11.0 | 503 | 12.4 | 511 | 12.2 | 510 | 12.3 |
| 473.astar | 719 | 9.80 | 723 | 9.70 | 722 | 9.70 | 696 | 10.1 | 686 | 10.2 | 681 | 10.3 |
| 483.xalancbmk | 538 | 12.8 | 534 | 12.9 | 542 | 12.7 | 538 | 12.8 | 534 | 12.9 | 542 | 12.7 |
General Notes
Tested systems can be used with Shin-G ATX case, Antec NeoPower 480W power supply Binaries were built on Windows Vista Ultimate (32-bit) OMP_NUM_THREADS set to number of logical processors as seen by the OS KMP_AFFINITY set to physical,0
Base Portability Flags
| 403.gcc: | -DSPEC_CPU_WIN32 |
| 464.h264ref: | -DSPEC_CPU_NO_INTTYPES -DWIN32 |
| 483.xalancbmk: | -Qoption,cpp,--no_wchar_t_keyword |
Base Optimization Flags
C benchmarks:
| /arch:SSE2 -Qipo -O3 -Qprec-div- -Qopt-prefetch -Qparallel -Qpar-runtime-control -Qvec-guard-write /F512000000 |
C++ benchmarks:
| /arch:SSE2 -Qipo -O3 -Qprec-div- -Qopt-prefetch -Qcxx-features /F512000000 shlw32m.lib -link /FORCE:MULTIPLE |
Peak Portability Flags
| 403.gcc: | -DSPEC_CPU_WIN32 |
| 464.h264ref: | -DSPEC_CPU_NO_INTTYPES -DWIN32 |
| 483.xalancbmk: | -Qoption,cpp,--no_wchar_t_keyword |
Peak Optimization Flags
C benchmarks:
| 400.perlbench: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qansi-alias -Qopt-prefetch /F512000000 shlw32m.lib -link /FORCE:MULTIPLE |
| 401.bzip2: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qopt-prefetch -Qansi-alias /F512000000 |
| 403.gcc: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- /F512000000 |
| 429.mcf: | /arch:SSE2 -Qipo -O3 -Qprec-div- -Qopt-prefetch /F512000000 |
| 445.gobmk: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O2 -Qprec-div- -Qansi-alias /F512000000 |
| 456.hmmer: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll2 -Qansi-alias /F512000000 |
| 458.sjeng: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll4 /F512000000 |
| 462.libquantum: | basepeak = yes |
| 464.h264ref: | Same as 456.hmmer |
C++ benchmarks:
| 471.omnetpp: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qansi-alias -Qopt-ra-region-strategy=block /F512000000 shlw32m.lib -link /FORCE:MULTIPLE |
| 473.astar: | /arch:SSE2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qansi-alias -Qopt-ra-region-strategy=routine /F512000000 shlw32m.lib -link /FORCE:MULTIPLE |
| 483.xalancbmk: | basepeak = yes |