| CPU2006 license: | 19 | Test date: | Mar-2014 |
|---|---|---|---|
| Test sponsor: | Fujitsu | Hardware Availability: | Apr-2014 |
| Tested by: | Fujitsu | Software Availability: | Feb-2014 |
| Hardware | |
|---|---|
| CPU Name: | SPARC64 X+ |
| CPU Characteristics: | |
| CPU MHz: | 3700 |
| FPU: | Integrated |
| CPU(s) enabled: | 64 cores, 4 chips, 16 cores/chip, 2 threads/core |
| CPU(s) orderable: | 1 to 16 BBs; each BB contains 2 or 4 CPU chips; each CPU chip contains 4, 8, 12, 16 cores |
| Primary Cache: | 64 KB I + 64 KB D on chip per core |
| Secondary Cache: | 24 MB I+D on chip per chip |
| L3 Cache: | None |
| Other Cache: | None |
| Memory: | 512 GB (32 x 16 GB 2Rx4 PC3L-12800R-11, ECC) |
| Disk Subsystem: | tmpfs 600 GB 10,025 RPM Toshiba MBF2600RC SAS (for system disk) |
| Other Hardware: | None |
| Software | |
|---|---|
| Operating System: | Solaris 11.1 SRU 15.4 |
| Compiler: | C/C++/Fortran: Version 12.3 of Oracle Solaris Studio 10/13 Patch Set |
| Auto Parallel: | No |
| File System: | tmpfs (output_root was used to put run directories in /tmp/cpu2006) 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 | 128 | 1004 | 1730 | 1005 | 1730 | 1005 | 1730 | 64 | 482 | 1800 | 482 | 1800 | 482 | 1800 |
| 416.gamess | 128 | 1546 | 1620 | 1534 | 1630 | 1547 | 1620 | 128 | 1519 | 1650 | 1526 | 1640 | 1518 | 1650 |
| 433.milc | 128 | 741 | 1590 | 741 | 1590 | 741 | 1590 | 128 | 735 | 1600 | 736 | 1600 | 735 | 1600 |
| 434.zeusmp | 128 | 713 | 1630 | 717 | 1620 | 713 | 1630 | 128 | 713 | 1630 | 717 | 1620 | 713 | 1630 |
| 435.gromacs | 128 | 565 | 1620 | 558 | 1640 | 558 | 1640 | 128 | 565 | 1620 | 558 | 1640 | 558 | 1640 |
| 436.cactusADM | 128 | 543 | 2820 | 544 | 2810 | 544 | 2810 | 128 | 513 | 2980 | 513 | 2980 | 514 | 2970 |
| 437.leslie3d | 128 | 1096 | 1100 | 1099 | 1100 | 1098 | 1100 | 64 | 498 | 1210 | 497 | 1210 | 498 | 1210 |
| 444.namd | 128 | 632 | 1620 | 633 | 1620 | 631 | 1630 | 128 | 465 | 2210 | 465 | 2210 | 465 | 2210 |
| 447.dealII | 128 | 463 | 3170 | 464 | 3150 | 464 | 3160 | 128 | 412 | 3550 | 412 | 3550 | 411 | 3560 |
| 450.soplex | 128 | 1145 | 932 | 1144 | 933 | 1145 | 932 | 128 | 1053 | 1010 | 1054 | 1010 | 1054 | 1010 |
| 453.povray | 128 | 445 | 1530 | 445 | 1530 | 444 | 1530 | 128 | 337 | 2020 | 337 | 2020 | 341 | 2000 |
| 454.calculix | 128 | 423 | 2500 | 424 | 2490 | 424 | 2490 | 128 | 402 | 2630 | 402 | 2630 | 401 | 2630 |
| 459.GemsFDTD | 128 | 1506 | 902 | 1506 | 902 | 1506 | 902 | 64 | 670 | 1010 | 671 | 1010 | 671 | 1010 |
| 465.tonto | 128 | 701 | 1800 | 697 | 1810 | 698 | 1800 | 128 | 615 | 2050 | 615 | 2050 | 613 | 2060 |
| 470.lbm | 128 | 875 | 2010 | 873 | 2010 | 875 | 2010 | 64 | 367 | 2390 | 368 | 2390 | 368 | 2390 |
| 481.wrf | 128 | 951 | 1500 | 952 | 1500 | 950 | 1500 | 128 | 795 | 1800 | 797 | 1800 | 797 | 1790 |
| 482.sphinx3 | 128 | 1574 | 1580 | 1570 | 1590 | 1572 | 1590 | 128 | 1477 | 1690 | 1477 | 1690 | 1475 | 1690 |
Compiler Invocation Notes
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
Shell Environments:
ulimit -s 131072 was used to limit the space consumed by the stack
(and therefore make more space available to the heap).
The "Logical Domains Manager" service was turned off using the command "svcadm disable ldmd".
System Tunables:
(/etc/system parameters)
autoup = 1555200
Causes pages older than the listed number of seconds to be written by fsflush.
tune_t_fsflushr = 259200
Controls how many seconds elapse between runs of the page flush daemon, fsflush.
Platform Notes
Sysinfo program /export/cpu2006-v1.2/config/sysinfo $Rev: 6874 $ $Date:: 2013-11-20 #$ 654bd3fcf53b06faef0efe54ed011998 running on spec-bb02 Mon Mar 3 08:51:13 2014 This section contains SUT (System Under Test) info as seen by some common utilities. To remove or add to this section, see: http://www.spec.org/cpu2006/Docs/config.html#sysinfo From /usr/sbin/psrinfo SPARC64-X+ (chipid 0, clock 3700 MHz) SPARC64-X+ (chipid 1, clock 3700 MHz) SPARC64-X+ (chipid 2, clock 3700 MHz) SPARC64-X+ (chipid 3, clock 3700 MHz) 4 chips 128 threads 3700 MHz From kstat: 64 cores From prtconf: 522240 Megabytes /etc/release: Oracle Solaris 11.1 SPARC uname -a: SunOS spec-bb02 5.11 11.1 sun4v sparc sun4v disk: df -h $SPEC Filesystem Size Used Available Capacity Mounted on rpool/export 547G 18G 450G 4% /export (End of data from sysinfo program)
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 -xtarget=sparc64x -fma=fused -xpagesize=4M -xipo=2 -xalias_level=std -xprefetch_level=2 -M map.bssalign -lbsdmalloc |
C++ benchmarks:
Fortran benchmarks:
| -fast -xtarget=sparc64x -fma=fused -xpagesize=4M -xipo=2 -xvector=%none -M map.bssalign |
Benchmarks using both Fortran and C:
| -fast(cc) -fast(f90) -xtarget=sparc64x -fma=fused -xpagesize=4M -xipo=2 -xalias_level=std -xprefetch_level=2 -xvector=%none -M map.bssalign |
Base Other Flags
C benchmarks:
| -xjobs=8 |
C++ benchmarks:
| -xjobs=8 |
Fortran benchmarks:
| -xjobs=8 |
Benchmarks using both Fortran and C:
| -xjobs=8 |
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: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xtarget=sparc64x -fma=fused -xpagesize=4M -xipo=2 -xunroll=4 -xvector=%none -xprefetch=no%auto -M map.bssalign |
| 416.gamess: | -fast -xtarget=sparc64x -fma=fused -xpagesize=4M -xipo=1 -xprefetch=no%auto -xunroll=6 -M map.bssalign |
| 434.zeusmp: | basepeak = yes |
| 437.leslie3d: | -fast -xtarget=sparc64x -fma=fused -xpagesize=4M -xunroll=2 -xvector=%none -xprefetch=latx:0.8 -Qoption cg -Qms_pipe+alldoall -M map.bssalign |
| 459.GemsFDTD: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xtarget=sparc64x -fma=fused -xpagesize=4M -xunroll=9 -xprefetch=latx:0.2 -xprefetch_level=3 -Qoption cg -Qlp-av=128 -Qoption iropt -Rujam -M map.bssalign |
| 465.tonto: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xtarget=sparc64x -fma=fused -xpagesize=4M -xipo=1 -xO4 -xunroll=3 -xprefetch=no%auto -M map.bssalign -lbsdmalloc |
Benchmarks using both Fortran and C:
| 435.gromacs: | basepeak = yes |
| 436.cactusADM: | -fast(cc) -fast(f90) -xtarget=sparc64x -fma=fused -xpagesize=4M -xO4 -xunroll=16 -xprefetch=latx:1.4 -Wc,-Qpeep-Ex:minmax_use_cmov=2 -Wc,-Qms_pipe+ulmscc=1 -W2,-Asac -M map.256M.align -lbsdmalloc |
| 454.calculix: | -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast(cc) -fast(f90) -xtarget=sparc64x -fma=fused -xpagesize=4M -xipo=1 -xalias_level=strong -xprefetch=latx:2.0 -stackvar -M map.bssalign |
| 481.wrf: | -fast(cc) -fast(f90) -xtarget=sparc64x -fma=fused -xpagesize=4M -xunroll=9 -xprefetch=latx:0.4 -Qoption iropt -Rujam -xO4 -M map.bssalign |