CPU2006 license: | 19 | Test date: | Sep-2009 |
---|---|---|---|
Test sponsor: | Fujitsu | Hardware Availability: | Nov-2009 |
Tested by: | Sun Microsystems | Software Availability: | Oct-2009 |
Hardware | |
---|---|
CPU Name: | SPARC64 VII |
CPU Characteristics: | |
CPU MHz: | 2530 |
FPU: | Integrated |
CPU(s) enabled: | 32 cores, 8 chips, 4 cores/chip, 2 threads/core |
CPU(s) orderable: | 1 to 4 CPUMs; each CPUM contains 2 CPU chips |
Primary Cache: | 64 KB I + 64 KB D on chip per core |
Secondary Cache: | 5632 KB I+D on chip per chip |
L3 Cache: | None |
Other Cache: | None |
Memory: | 128 GB (64 x 2 GB), 8-way interleaved |
Disk Subsystem: | 536 GB (zfs 8 x 3-way mirrors) on 24x 73GB 15000RPM FC-AL disks in 2x SE3510 enclosures |
Other Hardware: | None |
Software | |
---|---|
Operating System: | Solaris 10 10/09 (s10s_u8wos_06) |
Compiler: | Sun Studio 12 Update 1 plus patches (see notes) |
Auto Parallel: | No |
File System: | zfs |
System State: | Default |
Base Pointers: | 32-bit |
Peak Pointers: | 32-bit |
Other Software: | None |
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. | ||||||||||||||
400.perlbench | 64 | 1601 | 390 | 1598 | 391 | 1596 | 392 | 64 | 1163 | 537 | 1144 | 547 | 1151 | 543 |
401.bzip2 | 64 | 4630 | 133 | 4651 | 133 | 4640 | 133 | 32 | 1561 | 198 | 1558 | 198 | 1548 | 199 |
403.gcc | 64 | 2647 | 195 | 2687 | 192 | 2651 | 194 | 64 | 2647 | 195 | 2687 | 192 | 2651 | 194 |
429.mcf | 64 | 2890 | 202 | 2889 | 202 | 2898 | 201 | 32 | 1215 | 240 | 1218 | 240 | 1217 | 240 |
445.gobmk | 64 | 1452 | 462 | 1450 | 463 | 1453 | 462 | 64 | 1341 | 501 | 1354 | 496 | 1349 | 498 |
456.hmmer | 64 | 2099 | 284 | 2099 | 285 | 2102 | 284 | 63 | 2025 | 290 | 2023 | 291 | 2032 | 289 |
458.sjeng | 64 | 2234 | 347 | 2232 | 347 | 2232 | 347 | 64 | 2088 | 371 | 2088 | 371 | 2090 | 370 |
462.libquantum | 64 | 2272 | 584 | 2267 | 585 | 2268 | 585 | 64 | 2258 | 587 | 2257 | 587 | 2257 | 587 |
464.h264ref | 64 | 2269 | 624 | 2266 | 625 | 2275 | 623 | 64 | 2118 | 669 | 2125 | 667 | 2120 | 668 |
471.omnetpp | 64 | 4316 | 92.7 | 4313 | 92.7 | 4319 | 92.6 | 64 | 4252 | 94.1 | 4253 | 94.0 | 4255 | 94.0 |
473.astar | 64 | 2863 | 157 | 2892 | 155 | 2862 | 157 | 32 | 1305 | 172 | 1314 | 171 | 1308 | 172 |
483.xalancbmk | 64 | 1660 | 266 | 1662 | 266 | 1643 | 269 | 64 | 1660 | 266 | 1662 | 266 | 1643 | 269 |
Sun Studio 12 Update 1 was used, plus patch 119963-17 Sun Studio compiler patches are available at http://developers.sun.com/sunstudio/downloads/patches/ss12u1_patches.jsp
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.)
ulimit -s 131072 was used to allow the stack to grow up to 131072 KB (aka 128 MB). Note that saying "131072" is preferable to "unlimited", because there is a tradeoff between space for the stack vs. space 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=600 Causes pages older than the listed number of seconds to be written by fsflush. zfs:zfs_arc_max = 0x10000000 Control the amount of memory used by ZFS for caching lpg_alloc_prefer=1 Prefer local pages, even if not easily available Other System Settings: The webconsole service was turned off using svcadm disable webconsole The system had 50 GB of swap space
Memory is 8-way interleaved by filling all slots with the same capacity DIMMs. This result is measured on a Sun SPARC Enterprise M5000 Server. The Sun SPARC Enterprise M5000 and the Fujitsu SPARC Enterprise M5000 are electrically equivalent.
Environment variables set by runspec before the start of the run: OMP_NUM_THREADS = "64" SUNW_MP_PROCBIND = "true" SUNW_MP_THR_IDLE = "SPIN" (Although these variables were set prior to the run they did not affect performance, since the benchmarks were compiled in serial mode.)
400.perlbench: | -DSPEC_CPU_SOLARIS_SPARC |
403.gcc: | -DSPEC_CPU_SOLARIS |
462.libquantum: | -DSPEC_CPU_SOLARIS |
483.xalancbmk: | -DSPEC_CPU_SOLARIS |
-fast -fma=fused -xipo=2 -xpagesize=4M -xarch=sparcfmaf -xalias_level=std -ll2amm |
-xdepend -fast -fma=fused -xipo=2 -xpagesize=4M -xarch=sparcfmaf -xalias_level=compatible -library=stlport4 -lfast |
400.perlbench: | -DSPEC_CPU_SOLARIS_SPARC |
403.gcc: | -DSPEC_CPU_SOLARIS |
462.libquantum: | -DSPEC_CPU_SOLARIS |
483.xalancbmk: | -DSPEC_CPU_SOLARIS |
471.omnetpp: | -xdepend -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -xalias_level=compatible -library=stlport4 -fma=fused -xipo=2 -xprefetch_level=2 -Qoption cg -Qlp-av=0 -lfast |
473.astar: | -xdepend -xprofile=collect:./feedback(pass 1) -xprofile=use:./feedback(pass 2) -fast -xpagesize=4M -xalias_level=compatible -library=stlport4 -M /usr/lib/ld/map.bssalign -fma=fused -xipo=2 -xprefetch=no%auto -lfast -lbsdmalloc |
483.xalancbmk: | basepeak = yes |