SPEC® CFP2006 Result

Copyright 2006-2014 Standard Performance Evaluation Corporation

Fujitsu Limited

Fujitsu SPARC Enterprise M8000

CPU2006 license: 19 Test date: Apr-2007
Test sponsor: Fujitsu Limited Hardware Availability: Apr-2007
Tested by: Sun Microsystems Software Availability: Jul-2007
Benchmark results graph
Hardware
CPU Name: SPARC64 VI
CPU Characteristics:
CPU MHz: 2280
FPU: Integrated
CPU(s) enabled: 32 cores, 16 chips, 2 cores/chip, 2 threads/core
CPU(s) orderable: 1 to 4 CMUs; each CMU contains 2 or 4 chips
Primary Cache: 128 KB I + 128 KB D on chip per core
Secondary Cache: 5 MB I+D on chip per chip
L3 Cache: None
Other Cache: None
Memory: 256 GB (128 x 2 GB)
Disk Subsystem: 400 GB Solaris Volume Manager RAID0
soft partition (see notes for details)
Other Hardware: None
Software
Operating System: Solaris 10 7/07 (build s10s_u4wos_03)
Compiler: Sun Studio 12 (build 44.0)
Auto Parallel: No
File System: ufs
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 63 1942 441 1941 441 1942 441 63 1926 444 1926 445 1927 444
416.gamess 63 4046 305 4044 305 4039 305 32 1907 329 1907 329 1906 329
433.milc 63 2668 217 2673 216 2672 216 63 2633 220 2633 220 2634 220
434.zeusmp 63 2494 230 2497 230 2495 230 63 2494 230 2497 230 2495 230
435.gromacs 63 1440 312 1436 313 1436 313 32 667 343 668 342 666 343
436.cactusADM 63 1696 444 1700 443 1699 443 63 1696 444 1700 443 1699 443
437.leslie3d 63 2032 292 2030 292 2029 292 63 1993 297 1992 297 1993 297
444.namd 63 1608 314 1608 314 1608 314 32 757 339 757 339 757 339
447.dealII 63 1658 435 1655 435 1655 435 63 1643 439 1652 436 1645 438
450.soplex 63 2465 213 2459 214 2459 214 63 2326 226 2316 227 2317 227
453.povray 63 1262 266 1260 266 1262 265 32 396 430 394 432 396 430
454.calculix 63 1356 383 1364 381 1359 382 63 1356 383 1364 381 1359 382
459.GemsFDTD 63 3229 207 3262 205 3273 204 63 3229 207 3262 205 3273 204
465.tonto 63 1851 335 1843 336 1840 337 32 807 390 807 390 807 390
470.lbm 63 3361 258 3361 258 3360 258 63 3200 271 3199 271 3200 270
481.wrf 63 1902 370 1899 371 1909 369 63 1902 370 1899 371 1909 369
482.sphinx3 63 4545 270 4543 270 4547 270 63 4545 270 4543 270 4547 270

Operating System Notes


Processes were bound to cores using "submit" and "pbind".
The SPEC toolset was bound to processor 0.

These shell commands request use of local 4MB pages:
      export LD_PRELOAD=madv.so.1:mpss.so.1
      export MPSSHEAP=4MB
      export MPSSSTACK=4MB
      export MADV=access_lwp
'access_lwp' means that the next light weight
process to touch the specified address range
will access it the most heavily.

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=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=1
       Set maximum percent memory for file system cache
    tune_t_fsflushr=3
       Controls how many seconds elapse between runs of the
       page flush daemon, fsflush.

 The "webconsole" service was turned off using
     svcadm disable webconsole

Platform Notes


Disk notes: The SPEC CPU tests use a 400 GB partition
created from 3x Sun StorageTek 6140 stripe sets.  The
partition was created in 3 steps: 1. Each 6140 stripe
set (RAID 0) is based on 8x 146 GB 15,000 RPM Seagate
ST3146954FC FC-AL disks.  2. Solaris views these as 3
logical units (LUNs) which are striped together (RAID
0) to make a 3 TB volume using Solaris Volume Manager
(SVM).  3. Lastly, SVM is then used to create one 400
GB soft partition for use by the CPU2006 output_root.

"CMU" = CPU/Memory Unit; each holds 2 or 4 CPU chips.

Memory was 8-way interleaved by filling all slots with
the same capacity DIMMs.

This result was measured using a Sun SPARC Enterprise
M8000 Server.  Note that the Fujitsu SPARC Enterprise
M8000 and Sun SPARC Enterprise M8000 are electrically
equivalent.

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   -xcache=128/64/2:5120/256/10   -xipo=2   -xpagesize=4M   -xprefetch_level=2   -xprefetch=latx:2   -xalias_level=std   -xprefetch_level=3   -xprefetch_auto_type=indirect_array_access 

C++ benchmarks:

 -xdepend   -library=stlport4   -fast   -fma=fused   -xcache=128/64/2:5120/256/10   -xipo=2   -xpagesize=4M   -xprefetch_level=2   -xprefetch=latx:2   -xalias_level=compatible 

Fortran benchmarks:

 -fast   -fma=fused   -xcache=128/64/2:5120/256/10   -xipo=2   -xpagesize=4M   -xprefetch_level=2   -xprefetch=latx:2 

Benchmarks using both Fortran and C:

 -fast(cc)   -fast(f90)   -fma=fused   -xcache=128/64/2:5120/256/10   -xipo=2   -xpagesize=4M   -xprefetch_level=2   -xprefetch=latx:2   -xalias_level=std   -xprefetch_level=3   -xprefetch_auto_type=indirect_array_access 

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:

433.milc:  -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xipo=2   -xprefetch_level=2   -fsimple=1   -xprefetch_auto_type=indirect_array_access   -W2,-Ainline:rs=400   -xalias_level=std   -fma=fused   -xprefetch=latx:3 
470.lbm:  -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xprefetch_level=3   -xipo=2   -xrestrict   -fma=fused   -Wc,-Qlp=1   -Wc,-Qlp-av=512   -Wc,-Qlp-t=1   -Wc,-Qlp-fa=1   -Wc,-Qms_pipe-prefolim=64   -xprefetch=latx:5 
482.sphinx3:  basepeak = yes 

C++ benchmarks:

444.namd:  -xdepend   -library=stlport4   -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xalias_level=compatible   -xprefetch_level=1   -fma=fused   -xprefetch=latx:3 
447.dealII:  -xdepend   -library=stlport4   -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xalias_level=compatible   -xipo=2   -xrestrict   -fma=fused   -xprefetch=latx:4.5 
450.soplex:  -xdepend   -library=stlport4   -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xalias_level=compatible   -xipo=2   -xprefetch_level=2   -fsimple=0   -xrestrict   -xprefetch_auto_type=indirect_array_access   -Qoption cg -Qlp-ol=1   -Qoption cg -Qlp-it=3   -Qoption cg -Qlp-imb=1   -Qoption iropt -Apf:pdl=3 
453.povray:  -xdepend   -library=stlport4   -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xalias_level=compatible   -xipo=2   -xrestrict   -fma=fused 

Fortran benchmarks:

410.bwaves:  -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xipo=2   -xprefetch_level=2   -fma=fused   -xprefetch=latx:3 
416.gamess:  -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xipo=2   -xprefetch_level=2   -fma=fused 
434.zeusmp:  basepeak = yes 
437.leslie3d:  -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xprefetch_level=3   -qoption cg -Qlp=1   -qoption cg -Qlp-fa=0   -qoption cg -Qlp-fl=1   -qoption cg -Qlp-av=448   -qoption cg -Qlp-t=4   -xprefetch=latx:3.5 
459.GemsFDTD:  basepeak = yes 
465.tonto:  -fast   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xipo=2   -xprefetch=latx:12   -lfast 

Benchmarks using both Fortran and C:

435.gromacs:  -xprofile=collect:./feedback(pass 1)   -xprofile=use:./feedback(pass 2)   -fast(cc)   -fast(f90)   -xcache=128/64/2:5120/256/10   -xpagesize=4M   -xipo=2   -xinline=   -xarch=generic   -xchip=generic   -fsimple=0   -fma=fused 
436.cactusADM:  basepeak = yes 
454.calculix:  basepeak = yes 
481.wrf:  basepeak = yes 

Peak 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 

The flags file that was used to format this result can be browsed at
http://www.spec.org/cpu2006/flags/Sun-Solaris-Studio12.20090714.02.html.

You can also download the XML flags source by saving the following link:
http://www.spec.org/cpu2006/flags/Sun-Solaris-Studio12.20090714.02.xml.