| CPU2006 license: | 19 | Test date: | Nov-2010 |
|---|---|---|---|
| Test sponsor: | Fujitsu | Hardware Availability: | Dec-2010 |
| Tested by: | Oracle Corporation | Software Availability: | Sep-2010 |
| Hardware | |
|---|---|
| CPU Name: | SPARC64 VII+ |
| CPU Characteristics: | |
| CPU MHz: | 3000 |
| FPU: | Integrated |
| CPU(s) enabled: | 256 cores, 64 chips, 4 cores/chip, 2 threads/core |
| CPU(s) orderable: | 1 to 16 CMUs; each CMU contains 2 or 4 CPU chips |
| Primary Cache: | 64 KB I + 64 KB D on chip per core |
| Secondary Cache: | 12 MB I+D on chip per chip |
| L3 Cache: | None |
| Other Cache: | None |
| Memory: | 2 TB (512 x 4 GB, 8-way interleaved) |
| Disk Subsystem: | 602 GB on 24 x 73 GB 10K RPM SAS disks, arranged as 8 x 3-way mirrors |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Oracle Solaris 10 9/10 |
| Compiler: | Oracle Solaris Studio 12.2 |
| Auto Parallel: | No |
| File System: | zfs |
| System State: | Default |
| Base Pointers: | 32-bit |
| Peak Pointers: | 32-bit |
| Other Software: | None |
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. | ||||||||||||||
| 410.bwaves | 511 | 5337 | 1300 | 5264 | 1320 | 5271 | 1320 | 511 | 5337 | 1300 | 5264 | 1320 | 5271 | 1320 |
| 416.gamess | 511 | 3123 | 3200 | 3109 | 3220 | 3131 | 3200 | 511 | 2908 | 3440 | 2877 | 3480 | 2879 | 3480 |
| 433.milc | 511 | 3387 | 1390 | 3388 | 1380 | 3390 | 1380 | 127 | 838 | 1390 | 838 | 1390 | 838 | 1390 |
| 434.zeusmp | 511 | 1763 | 2640 | 1763 | 2640 | 1764 | 2640 | 511 | 1738 | 2680 | 1736 | 2680 | 1737 | 2680 |
| 435.gromacs | 511 | 868 | 4200 | 870 | 4190 | 866 | 4210 | 511 | 826 | 4410 | 829 | 4400 | 828 | 4410 |
| 436.cactusADM | 511 | 1980 | 3080 | 1987 | 3070 | 1988 | 3070 | 255 | 832 | 3660 | 832 | 3660 | 871 | 3500 |
| 437.leslie3d | 511 | 4081 | 1180 | 4081 | 1180 | 4081 | 1180 | 255 | 1865 | 1290 | 1864 | 1290 | 1867 | 1280 |
| 444.namd | 511 | 916 | 4470 | 946 | 4330 | 917 | 4470 | 511 | 837 | 4900 | 838 | 4890 | 844 | 4850 |
| 447.dealII | 511 | 1154 | 5060 | 1140 | 5130 | 1179 | 4960 | 511 | 1154 | 5060 | 1140 | 5130 | 1179 | 4960 |
| 450.soplex | 511 | 5686 | 750 | 5691 | 749 | 5687 | 749 | 255 | 1770 | 1200 | 1759 | 1210 | 1758 | 1210 |
| 453.povray | 511 | 592 | 4590 | 591 | 4600 | 591 | 4600 | 511 | 439 | 6190 | 437 | 6220 | 439 | 6200 |
| 454.calculix | 511 | 782 | 5390 | 737 | 5720 | 756 | 5580 | 511 | 721 | 5850 | 722 | 5840 | 730 | 5770 |
| 459.GemsFDTD | 511 | 5795 | 936 | 5785 | 937 | 5796 | 935 | 511 | 5780 | 938 | 5796 | 935 | 5781 | 938 |
| 465.tonto | 511 | 1267 | 3970 | 1266 | 3970 | 1254 | 4010 | 511 | 1221 | 4120 | 1211 | 4150 | 1213 | 4150 |
| 470.lbm | 511 | 5499 | 1280 | 5501 | 1280 | 5500 | 1280 | 127 | 1034 | 1690 | 1034 | 1690 | 1037 | 1680 |
| 481.wrf | 511 | 3002 | 1900 | 3008 | 1900 | 3011 | 1900 | 255 | 1423 | 2000 | 1423 | 2000 | 1423 | 2000 |
| 482.sphinx3 | 511 | 7819 | 1270 | 7818 | 1270 | 7826 | 1270 | 127 | 1483 | 1670 | 1500 | 1650 | 1486 | 1670 |
Compiler Invocation Notes
Oracle Solaris Studio 12.2 is distributed with mandatory OS patches 118683-05 119963-20 120753-08 Oracle Solaris Studio 12.2 and patches are available at http://oracle.com/goto/solarisstudio 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
Processes were assigned to specific processors using 'pbind' commands. The config file option 'submit' was used, along with a list of processors in the 'BIND' variable, to generate the pbind commands. (For details, please see the config file.)
Operating System Notes
ulimit -s 131072 was used to limit the space
consumed by the stack (and therefore make more
space available to the heap).
/etc/system parameters
autoup=600
Causes pages older than the listed number of seconds to
be written by fsflush.
tune_t_fsflushr=10
Controls how many seconds elapse between runs of the
page flush daemon, fsflush.
lpg_alloc_prefer=1
Indicates that extra effort should be taken to ensure
that pages are created in the nearby lgroup (NUMA location).
kernel_cage_enable=0
Allows the kernel to use memory in any locality group.
In particular, allows ZFS file caches to be located on
any memory board.
zfs:zfs_arc_min=0x10000000
zfs:zfs_arc_max=0x10000000000
Limits the consumption of memory by the zfs file system
cache to 1 TB. (The arc_max sets the maximum cache
size; arc_min sets the minimum.)
The "webconsole" service was turned off using
svcadm disable webconsole
The system had 137 GB of swap space.
Platform Notes
Memory is 8-way interleaved by filling all slots with the same capacity DIMMs. This result is measured on a SPARC Enterprise M9000 server from Oracle. The SPARC Enterprise M9000 server from Oracle and from Fujitsu are electrically equivalent.
General Notes
447.dealII (peak): "apache_stdcxx_4_2_1" src.alt was used. 447.dealII (base): "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 -xipo=2 -xpagesize=4M -xlinkopt -xvector -xalias_level=std -xprefetch_auto_type=indirect_array_access -ll2amm |
C++ benchmarks:
Fortran benchmarks:
| -fast -fma=fused -xipo=2 -xpagesize=4M -xlinkopt -xvector -ll2amm |
Benchmarks using both Fortran and C:
| -fast(cc) -fast(f90) -fma=fused -xipo=2 -xpagesize=4M -xlinkopt -xvector -xalias_level=std -xprefetch_auto_type=indirect_array_access -ll2amm |
Base Other Flags
C benchmarks:
| -xjobs=32 -V -# |
C++ benchmarks:
| -xjobs=32 -verbose=diags,version |
Fortran benchmarks:
| -xjobs=32 -V -v |
Benchmarks using both Fortran and C:
| -xjobs=32 -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:
| 433.milc: | -fast -xpagesize=4M -fma=fused -xipo=2 -xprefetch_level=2 -xprefetch_auto_type=indirect_array_access -xalias_level=strong -xdepend -ll2amm |
| 470.lbm: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M |
| 482.sphinx3: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -fma=fused -xipo=2 -xinline= -xalias_level=strong -xprefetch_level=2 -lfast -ll2amm |
C++ benchmarks:
| 444.namd: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -xalias_level=any -xdepend -library=stlport4 -fma=fused -xipo=2 -xchip=generic -xunroll=2 |
| 447.dealII: | basepeak = yes |
| 450.soplex: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -xalias_level=compatible -xdepend -library=stlport4 -fma=fused -xipo=2 -xrestrict -xprefetch=no -ll2amm |
| 453.povray: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -xalias_level=compatible -xdepend -fma=fused -xipo=2 -xlinkopt=2 -xprefetch=no -xunroll=4 -xO4 -lfast |
Fortran benchmarks:
| 410.bwaves: | basepeak = yes |
| 416.gamess: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -fma=fused -xipo=2 -xprefetch=no%auto -xO3 |
| 434.zeusmp: | -fast -xpagesize=4M -fma=fused -xipo=2 -xprefetch_level=1 -ll2amm -xunroll=5 |
| 437.leslie3d: | -fast -xpagesize=4M -M /usr/lib/ld/map.bssalign -xprefetch=no |
| 459.GemsFDTD: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -fma=fused |
| 465.tonto: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -xipo=2 -xprefetch=no -lfast -ll2amm |
Benchmarks using both Fortran and C:
| 435.gromacs: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast(cc) -fast(f90) -xpagesize=4M -fma=fused -xtarget=generic -xinline= -fsimple=0 -xlinkopt -xvector -xdepend |
| 436.cactusADM: | -fast(cc) -fast(f90) -xpagesize=4M -fma=fused -xipo=2 |
| 454.calculix: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast(cc) -fast(f90) -xpagesize=4M -fma=fused -xipo=2 -xvector -xunroll=8 -xprefetch=latx:3 -xalias_level=std |
| 481.wrf: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast(cc) -fast(f90) -xpagesize=4M -fma=fused -xipo=2 -xprefetch=no -xcache=generic -ll2amm |