| CPU2006 license: | 6 | Test date: | Jul-2009 |
|---|---|---|---|
| Test sponsor: | Sun Microsystems | Hardware Availability: | Nov-2009 |
| Tested by: | Fujitsu Limited | Software Availability: | Jun-2009 |
| Hardware | |
|---|---|
| CPU Name: | SPARC64 VII |
| CPU Characteristics: | |
| CPU MHz: | 2880 |
| FPU: | Integrated |
| CPU(s) enabled: | 64 cores, 16 chips, 4 cores/chip, 2 threads/core |
| CPU(s) orderable: | 1 to 4 CMUs; each CMU contains 2 or 4 chips |
| Primary Cache: | 64 KB I + 64 KB D on chip per core |
| Secondary Cache: | 6 MB I+D on chip per chip |
| L3 Cache: | None |
| Other Cache: | None |
| Memory: | 384 GB (64 x 2 GB + 64 x 4 GB), 8-way interleaved |
| Disk Subsystem: | 1 x Seagate Savvio 10K.2 (146 GB 10,000 RPM SAS) |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Solaris 10 5/09 with patches 119963-13, 120753-06, 118683-03 |
| Compiler: | Sun Studio 12 Update 1 |
| Auto Parallel: | Yes |
| File System: | ufs |
| System State: | Default |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32-bit |
| Other Software: | Apache C++ Standard Library V4.2.1 |
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 | 34.0 | 400 | 34.5 | 394 | 34.8 | 391 | 26.3 | 516 | 26.2 | 518 | 26.3 | 516 |
| 416.gamess | 1649 | 11.9 | 1649 | 11.9 | 1649 | 11.9 | 1481 | 13.2 | 1481 | 13.2 | 1480 | 13.2 |
| 433.milc | 1059 | 8.67 | 1056 | 8.70 | 1055 | 8.70 | 700 | 13.1 | 699 | 13.1 | 699 | 13.1 |
| 434.zeusmp | 253 | 35.9 | 253 | 36.0 | 253 | 36.0 | 253 | 36.0 | 253 | 36.0 | 253 | 35.9 |
| 435.gromacs | 1350 | 5.29 | 1348 | 5.30 | 1348 | 5.30 | 534 | 13.4 | 534 | 13.4 | 534 | 13.4 |
| 436.cactusADM | 48.5 | 246 | 48.4 | 247 | 47.5 | 252 | 48.3 | 248 | 49.4 | 242 | 47.8 | 250 |
| 437.leslie3d | 131 | 71.9 | 129 | 72.9 | 129 | 72.9 | 131 | 71.9 | 129 | 72.9 | 129 | 72.9 |
| 444.namd | 638 | 12.6 | 638 | 12.6 | 638 | 12.6 | 627 | 12.8 | 627 | 12.8 | 627 | 12.8 |
| 447.dealII | 732 | 15.6 | 731 | 15.6 | 732 | 15.6 | 527 | 21.7 | 526 | 21.7 | 526 | 21.7 |
| 450.soplex | 932 | 8.95 | 931 | 8.96 | 932 | 8.95 | 630 | 13.2 | 630 | 13.2 | 630 | 13.2 |
| 453.povray | 411 | 12.9 | 411 | 13.0 | 411 | 12.9 | 337 | 15.8 | 337 | 15.8 | 337 | 15.8 |
| 454.calculix | 594 | 13.9 | 594 | 13.9 | 594 | 13.9 | 540 | 15.3 | 540 | 15.3 | 540 | 15.3 |
| 459.GemsFDTD | 140 | 75.8 | 140 | 76.0 | 140 | 76.0 | 135 | 78.4 | 136 | 77.7 | 135 | 78.8 |
| 465.tonto | 838 | 11.7 | 840 | 11.7 | 838 | 11.7 | 633 | 15.5 | 633 | 15.5 | 633 | 15.5 |
| 470.lbm | 36.7 | 374 | 36.7 | 374 | 36.6 | 375 | 36.1 | 380 | 35.3 | 390 | 35.4 | 388 |
| 481.wrf | 728 | 15.3 | 728 | 15.3 | 728 | 15.3 | 697 | 16.0 | 697 | 16.0 | 698 | 16.0 |
| 482.sphinx3 | 1003 | 19.4 | 1009 | 19.3 | 1004 | 19.4 | 990 | 19.7 | 991 | 19.7 | 987 | 19.7 |
Compiler Invocation Notes
Sun Studio compiler patches are available at http://developers.sun.com/sunstudio/downloads/patches/ss12u1_patches.jsp The Apache C++ Standard Library V4.2.1 was installed from http://stdcxx.apache.org/download.html using: alias gmake=specmake gmake BUILDTYPE=8d CONFIG=sunpro.config
Submit Notes
The config file option 'submit' was used. Processes were assigned to specific processors using 'pbind' commands. The list of processors to use was provided in the 'BIND' variable, to generate the pbind commands. (For details, please see the config file.)
Operating System Notes
Shell Environments:
The maximum number of threads a program can create was set with:
OMP_NUM_THREADS=64
Program threads were bound to processors with:
SUNW_MP_PROCBIND=" 1 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34
36 38 40 42 44 46 48 50 52 54 56 58 60 62 64 66 68 70
72 74 76 78 80 82 84 86 88 90 92 94 96 98 100 102 104
106 108 110 112 114 116 118 120 122 124 126"
Behavior of parallel threads was set with:
SUNW_MP_THR_IDLE=SPIN
SPIN specifies that an idle thread should spin while waiting at barrier
or waiting for new parallel regions to work on.
ulimit -s 131072 was used to limit the space consumed
by the stack (making more space available for the heap)
System Tunables:
(/etc/system parameters)
tune_t_fsflushr=10
Controls how many seconds elapse between runs of the
page flush daemon, fsflush.
autoup=300
Causes pages older than the listed number of seconds to
be written by fsflush.
bufhwm=3000
Memory byte limit for caching I/O buffers.
segmap_percent=3
Set maximum percent memory for file system cache.
lpg_alloc_prefer=1
Set lgroup page allocation to strongly prefer local pages.
Other System Settings:
The webconsole service was turned off using svcadm disable webconsole.
Platform Notes
Memory is 8-way interleaved by filling each CMU's slots with the same capacity DIMMs. This result is measured on a Fujitsu SPARC Enterprise M8000 Server. Note that the Fujitsu SPARC Enterprise M8000 and Sun SPARC Enterprise M8000 are electrically equivalent.
General Notes
447.dealII (peak): "apache_stdcxx_4_2_1" src.alt was used.
Base Compiler Invocation
C benchmarks:
| cc |
C++ benchmarks:
| CC |
Fortran benchmarks:
| f90 |
Benchmarks using both Fortran and C:
| cc f90 |
Base Optimization Flags
C benchmarks:
| -fast -fma=fused -xpagesize=4M -xipo=2 -xprefetch=latx:2 -xautopar -xreduction -xprefetch_level=3 -xprefetch_auto_type=indirect_array_access |
C++ benchmarks:
| -fast -fma=fused -xpagesize=4M -xipo=2 -xprefetch=latx:2 -xautopar -xreduction -xprefetch_level=2 -xalias_level=compatible -library=stlport4 |
Fortran benchmarks:
| -fast -fma=fused -xpagesize=4M -xipo=2 -xprefetch=latx:2 -xautopar -xreduction -xprefetch_level=2 |
Benchmarks using both Fortran and C:
| -fast(cc) -fast(f90) -fma=fused -xpagesize=4M -xipo=2 -xprefetch=latx:2 -xautopar -xreduction -xprefetch_level=3 -xprefetch_auto_type=indirect_array_access -xprefetch_level=2 |
Base Other Flags
C benchmarks:
| -xjobs=16 -V -# |
C++ benchmarks:
| -xjobs=16 -verbose=diags,version |
Fortran benchmarks:
| -xjobs=16 -V -v |
Benchmarks using both Fortran and C:
| -xjobs=16 -V -# -v |
Peak Compiler Invocation
C benchmarks:
| cc |
C++ benchmarks:
| CC |
Fortran benchmarks:
| f90 |
Benchmarks using both Fortran and C:
| cc f90 |
Peak Optimization Flags
C benchmarks:
C++ benchmarks:
Fortran benchmarks:
| 410.bwaves: | -fast -fma=fused -xpagesize=512K -xipo=2 -xprefetch=latx:2 -xprefetch_level=2 -xautopar -xreduction |
| 416.gamess: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -fma=fused -xpagesize=4M -xipo=2 -xprefetch_level=3 |
| 434.zeusmp: | -fast -fma=fused -xpagesize=4M -xipo=2 -xprefetch=latx:2 -xautopar -xreduction |
| 437.leslie3d: | basepeak = yes |
| 459.GemsFDTD: | -fast -fma=fused -xpagesize=4M -xipo=2 -xprefetch=latx:2 -fsimple=1 -xprefetch_level=2 -xautopar -xreduction |
| 465.tonto: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -xipo=2 -xprefetch=no -xarch=generic -lfast |
Benchmarks using both Fortran and C:
| 435.gromacs: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast(cc) -fast(f90) -fma=fused -xipo=2 -xalias_level=std |
| 436.cactusADM: | -fast(cc) -fast(f90) -fma=fused -xpagesize=4M -xipo=2 -xprefetch=latx:2 -xalias_level=std -xprefetch_level=3 -xprefetch_auto_type=indirect_array_access -xautopar -xreduction |
| 454.calculix: | -fast(cc) -fast(f90) -fma=fused -xpagesize=4M -xipo=2 -xprefetch_level=3 -xprefetch=latx:3.0 -xalias_level=std |
| 481.wrf: | -fast(cc) -fast(f90) -fma=fused -xpagesize=4M -xipo=2 -xprefetch_level=3 -xunroll=8 |