| CPU2006 license: | 13 | Test date: | Mar-2010 |
|---|---|---|---|
| Test sponsor: | Intel Corporation | Hardware Availability: | Mar-2010 |
| Tested by: | Intel Corporation | Software Availability: | Nov-2009 |
| Hardware | |
|---|---|
| CPU Name: | Intel Xeon X5677 |
| CPU Characteristics: | Intel Turbo Boost Technology up to 3.73 GHz |
| CPU MHz: | 3467 |
| FPU: | Integrated |
| CPU(s) enabled: | 8 cores, 2 chips, 4 cores/chip, 2 threads/core |
| CPU(s) orderable: | 1,2 chips |
| Primary Cache: | 32 KB I + 32 KB D on chip per core |
| Secondary Cache: | 256 KB I+D on chip per core |
| L3 Cache: | 12 MB I+D on chip per chip |
| Other Cache: | None |
| Memory: | 24 GB (6x 4GB DDR3-1333, ECC, CL9) |
| Disk Subsystem: | 1 x 300 GB SATA, 10000 RPM |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Windows 7 Enterprise (64-bit) |
| Compiler: | Intel C++ Compiler Professional 11.1 for Intel 64 Build 20090903 Package ID: w_cproc_p_11.1.045 Intel Visual Fortran Compiler Professional 11.1 for Intel 64 Build 20090903 Package ID: w_cprof_p_11.1.045 Microsoft Visual Studio 2008 Professional SP1 (for libraries) |
| Auto Parallel: | Yes |
| File System: | NTFS |
| System State: | Default |
| Base Pointers: | 64-bit |
| Peak Pointers: | 64-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. | ||||||||||||
| 410.bwaves | 135 | 101 | 119 | 114 | 133 | 102 | 135 | 101 | 119 | 114 | 133 | 102 |
| 416.gamess | 726 | 27.0 | 724 | 27.1 | 724 | 27.0 | 670 | 29.2 | 670 | 29.2 | 671 | 29.2 |
| 433.milc | 309 | 29.7 | 310 | 29.6 | 325 | 28.3 | 309 | 29.7 | 310 | 29.6 | 325 | 28.3 |
| 434.zeusmp | 249 | 36.6 | 253 | 35.9 | 249 | 36.5 | 249 | 36.6 | 253 | 35.9 | 249 | 36.5 |
| 435.gromacs | 271 | 26.4 | 270 | 26.4 | 271 | 26.4 | 269 | 26.5 | 268 | 26.6 | 269 | 26.6 |
| 436.cactusADM | 110 | 109 | 110 | 109 | 109 | 109 | 108 | 111 | 108 | 111 | 108 | 111 |
| 437.leslie3d | 268 | 35.1 | 268 | 35.1 | 268 | 35.0 | 268 | 35.1 | 268 | 35.1 | 268 | 35.0 |
| 444.namd | 364 | 22.0 | 365 | 22.0 | 364 | 22.0 | 364 | 22.0 | 365 | 22.0 | 364 | 22.0 |
| 447.dealII | 363 | 31.5 | 362 | 31.6 | 361 | 31.7 | 320 | 35.8 | 320 | 35.7 | 320 | 35.8 |
| 450.soplex | 257 | 32.5 | 250 | 33.4 | 250 | 33.3 | 236 | 35.4 | 235 | 35.4 | 237 | 35.2 |
| 453.povray | 166 | 32.0 | 166 | 32.0 | 166 | 32.0 | 131 | 40.8 | 131 | 40.7 | 130 | 41.0 |
| 454.calculix | 259 | 31.8 | 260 | 31.7 | 261 | 31.7 | 249 | 33.1 | 249 | 33.1 | 249 | 33.1 |
| 459.GemsFDTD | 199 | 53.3 | 213 | 49.8 | 198 | 53.7 | 148 | 71.5 | 148 | 71.6 | 148 | 71.5 |
| 465.tonto | 368 | 26.7 | 368 | 26.8 | 368 | 26.7 | 303 | 32.5 | 303 | 32.5 | 303 | 32.5 |
| 470.lbm | 205 | 67.0 | 204 | 67.4 | 204 | 67.3 | 205 | 67.0 | 204 | 67.4 | 204 | 67.3 |
| 481.wrf | 237 | 47.1 | 236 | 47.3 | 237 | 47.2 | 223 | 50.0 | 224 | 49.8 | 263 | 42.5 |
| 482.sphinx3 | 380 | 51.3 | 383 | 50.8 | 380 | 51.3 | 371 | 52.5 | 369 | 52.8 | 370 | 52.7 |
General Notes
Tested systems is used with tower case, PC Power and Cooling dual 865W power supplys OMP_NUM_THREADS set to number of processors cores KMP_AFFINITY set to granularity=fine,scatter System was configured with nVidia Quadro FX 370 discrete graphics card
Base Compiler Invocation
C benchmarks:
| icl -Qvc9 -Qstd=c99 |
C++ benchmarks:
| icl -Qvc9 |
Fortran benchmarks:
| ifort |
Benchmarks using both Fortran and C:
| icl -Qvc9 -Qstd=c99 ifort |
Base Portability Flags
| 410.bwaves: | -DSPEC_CPU_P64 /Qlowercase |
| 416.gamess: | -DSPEC_CPU_P64 |
| 433.milc: | -DSPEC_CPU_P64 |
| 434.zeusmp: | -DSPEC_CPU_P64 |
| 435.gromacs: | -DSPEC_CPU_P64 |
| 436.cactusADM: | -DSPEC_CPU_P64 -Qlowercase /assume:underscore |
| 437.leslie3d: | -DSPEC_CPU_P64 |
| 444.namd: | -DSPEC_CPU_P64 /TP |
| 447.dealII: | -DSPEC_CPU_P64 -DDEAL_II_MEMBER_VAR_SPECIALIZATION_BUG |
| 450.soplex: | -DSPEC_CPU_P64 |
| 453.povray: | -DSPEC_CPU_P64 -DSPEC_CPU_WINDOWS_ICL |
| 454.calculix: | -DSPEC_CPU_P64 -DSPEC_CPU_NOZMODIFIER -Qlowercase |
| 459.GemsFDTD: | -DSPEC_CPU_P64 |
| 465.tonto: | -DSPEC_CPU_P64 |
| 470.lbm: | -DSPEC_CPU_P64 |
| 481.wrf: | -DSPEC_CPU_P64 -DSPEC_CPU_WINDOWS_ICL |
| 482.sphinx3: | -DSPEC_CPU_P64 |
Base Optimization Flags
C benchmarks:
| -QxSSE4.2 -Qipo -O3 -Qprec-div- -Qparallel -Qopt-prefetch -Qauto-ilp32 /F1000000000 |
C++ benchmarks:
| -QxSSE4.2 -Qipo -O3 -Qprec-div- -Qparallel -Qopt-prefetch -Qcxx-features -Qauto-ilp32 /F1000000000 shlW64M.lib -link /FORCE:MULTIPLE |
Fortran benchmarks:
| -QxSSE4.2 -Qipo -O3 -Qprec-div- -Qparallel -Qopt-prefetch /F1000000000 |
Benchmarks using both Fortran and C:
| -QxSSE4.2 -Qipo -O3 -Qprec-div- -Qparallel -Qopt-prefetch -Qauto-ilp32 /F1000000000 |
Peak Compiler Invocation
C benchmarks:
| icl -Qvc9 -Qstd=c99 |
C++ benchmarks:
| icl -Qvc9 |
Fortran benchmarks:
| ifort |
Benchmarks using both Fortran and C:
| icl -Qvc9 -Qstd=c99 ifort |
Peak Portability Flags
Same as Base Portability Flags
Peak Optimization Flags
C benchmarks:
| 433.milc: | basepeak = yes |
| 470.lbm: | basepeak = yes |
| 482.sphinx3: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll2 -Qauto-ilp32 /F1000000000 |
C++ benchmarks:
| 444.namd: | basepeak = yes |
| 447.dealII: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll2 -Qopt-prefetch -Qansi-alias -Qscalar-rep- -Qauto-ilp32 /F1000000000 shlW64M.lib -link /FORCE:MULTIPLE |
| 450.soplex: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qauto-ilp32 /F1000000000 shlW64M.lib -link /FORCE:MULTIPLE |
| 453.povray: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll4 -Qansi-alias -Qauto-ilp32 /F1000000000 shlW64M.lib -link /FORCE:MULTIPLE |
Fortran benchmarks:
| 410.bwaves: | basepeak = yes |
| 416.gamess: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll2 -Ob0 -Qansi-alias -Qscalar-rep- /F1000000000 |
| 434.zeusmp: | basepeak = yes |
| 437.leslie3d: | basepeak = yes |
| 459.GemsFDTD: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll2 -Qopt-prefetch -Qparallel /F1000000000 |
| 465.tonto: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qunroll4 -Qauto -Qinline-calloc /F1000000000 |
Benchmarks using both Fortran and C:
| 435.gromacs: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qopt-prefetch -Qauto-ilp32 /F1000000000 |
| 436.cactusADM: | -QxSSE4.2(pass 2) -Qprof_gen(pass 1) -Qprof_use(pass 2) -Qipo -O3 -Qprec-div- -Qopt-prefetch -Qparallel -Qunroll2 -Qauto-ilp32 /F1000000000 |
| 454.calculix: | -QxSSE4.2 -Qipo -O3 -Qprec-div- -Qauto-ilp32 /F1000000000 |
| 481.wrf: | Same as 454.calculix |