SPEC Seal of Reviewal OMPM2001 Result
Copyright © 1999-2002 Standard Performance Evaluation Corporation
Hewlett-Packard Company
ProLiant DL585 (AMD Opteron (TM) 880)
SPECompMpeak2001 = 17948      
SPECompMbase2001 = 16621      
SPEC license # HPG0001 Tested by: Hewlett-Packard Company Test site: Austin, Texas Test date: Oct-2005 Hardware Avail: Sep-2005 Software Avail: Oct-2005
Benchmark Reference
Time
Base
Runtime
Base
Ratio
Peak
Runtime
Peak
Ratio
Graph Scale
310.wupwise_m 6000 233    25723       224    26830       310.wupwise_m base result bar (25723)
310.wupwise_m peak result bar (26830)
312.swim_m 6000 441    13606       375    15992       312.swim_m base result bar (13606)
312.swim_m peak result bar (15992)
314.mgrid_m 7300 425    17181       418    17457       314.mgrid_m base result bar (17181)
314.mgrid_m peak result bar (17457)
316.applu_m 4000 423    9460      302    13241       316.applu_m base result bar (9460)
316.applu_m peak result bar (13241)
318.galgel_m 5100 334    15281       314    16249       318.galgel_m base result bar (15281)
318.galgel_m peak result bar (16249)
320.equake_m 2600 135    19249       127    20513       320.equake_m base result bar (19249)
320.equake_m peak result bar (20513)
324.apsi_m 3400 165    20613       161    21095       324.apsi_m base result bar (20613)
324.apsi_m peak result bar (21095)
326.gafort_m 8700 538    16183       512    16978       326.gafort_m base result bar (16183)
326.gafort_m peak result bar (16978)
328.fma3d_m 4600 428    10744       399    11536       328.fma3d_m base result bar (10744)
328.fma3d_m peak result bar (11536)
330.art_m 6400 136    47031       136    47031       330.art_m base result bar (47031)
330.art_m peak result bar (47031)
332.ammp_m 7000 738    9482      722    9694      332.ammp_m base result bar (9482)
332.ammp_m peak result bar (9694)
SPECompMbase2001 16621        
  SPECompMpeak2001 17948        

Hardware
Hardware Vendor: Hewlett-Packard Company
Model Name: ProLiant DL585 (AMD Opteron (TM) 880)
CPU: AMD Opteron (TM) 880
CPU MHz: 2400
FPU: Integrated
CPU(s) enabled: 8 cores, 4 chips, 2 cores/chip
CPU(s) orderable: 1,2,4
Primary Cache: 64KBI + 64KBD on chip
Secondary Cache: 1024KB (I+D) on chip
L3 Cache: None
Other Cache: None
Memory: 16x1GB, PC3200 CL3 DDR SDRAM ECC Registered
Disk Subsystem: SCSI, 36GB, 15K RPM
Other Hardware: None
Software
OpenMP Threads: 8
Parallel: OpenMP
Operating System: RedHat Enterprise Linux, Advanced Server version 4 (2)
Compiler: PathScale EKO Compiler Suite, Release 2.2.1
File System: ext3
System State: Multi-User
Notes / Tuning Information

 Environemnt Settings:
  export PSC_OMP_AFFINITY=TRUE
  export PSC_OMP_AFFINITY_MAP=0,1,2,3,4,5,6,7
  export PSC_OMP_STATIC_FAIR=TRUE
  export PSC_OMP_THREAD_SPIN=1000000000
  export OMP_DYNAMIC=FALSE
  export OMP_NUM_THREADS=8
  ONESTEP=yes for base and peak
  ulimit -s unlimited

 Machine Configuration
  DL585 BIOS version 4.12 A01 - 8/26/2005
  chkconfig --levels 12345 cpuspeed off

 Baseline optimization flags:
  COPTIMIZE = -mp -Ofast
  FOPTIMIZE = -mp -Ofast -OPT:early_mp=on -mcmodel=medium

 Peak optimization flags:
    310.wupwise_m: -mp -Ofast -msse3 -LNO:prefetch_ahead=5:prefetch=3 
             -OPT:unroll_times_max=8:unroll_size=128:IEEE_NaN_Inf=off:ro=3 
             -IPA:linear=on:plimit=50000:callee_limit=5000 
             -INLINE:aggressive=on
    312.swim_m: -mp -O3 -OPT:Ofast -m3dnow -mcmodel=medium -LNO:simd=0
    314.mgrid_m: -mp -Ofast -CG:gcm=off:cflow=off -LNO:fusion=2:prefetch=0 
             -msse3 -OPT:early_mp=on:unroll_times_max=8:unroll_size=256:ro=3
             -mcmodel=medium
    316.applu_m: -mp -Ofast -mcmodel=medium -CG:local_fwd_sched=on 
             -LNO:fusion=2:fission=2:full_unroll_size=10000:prefetch=3 
             -TENV:X=3 
           use_submit_for_speed=1
             submit= numactl --interleave=0,1,2,3 $command
    318.galgel_m: -mp -Ofast -OPT:early_mp=on -OPT:fast_complex=on +ACML
     RM_SOURCES=lapak.f90
     -L/pathscale64_mp/lib -lacml
     -I/pathscale64_mp/include 
    320.equake_m: -Ofast -mp -OPT:alias=disjoint
    324.apsi_m: -mp -O3 -OPT:Ofast -TENV:x=4 -LNO:fusion=2:prefetch=0
    326.gafort_m: -Ofast -OPT:early_mp=on -mp -LNO:vintr=0
    328.fma3d_m: -mp -O2 -ipa -CG:load_exe=1 -OPT:Ofast:IEEE_arith=3:ro=3 
             -WOPT:mem_opnds=on:retype_expr=on -IPA:pu_reorder=1
    330.art_m: basepeak=yes
    332.ammp_m: -mp -O3 -OPT:alias=disjoint:unroll_times_max=8:Ofast:ro=3 
             -fno-math-errno -TENV:X=4 -LNO:prefetch=0
           use_submit_for_speed=1
              submit= PSC_OMP_GUIDED_CHUNK_MAX=700 $command

    Portability Flags:
        318.galgel_m: -fixedform -extend_source

    Extra Flags:
        330.art_m: -DINTS_PER_CACHELINE=16 -DDBLS_PER_CACHELINE=8

 Alternate Source:      
       330.art_m         : Required srcalt purdue1 used for base and peak
       310.wupwise_m     : Approved srcalt ompl.32 used for peak
       312.swim_m        : Approved srcalt ompl.32 used for peak
       314.mgrid_m       : Approved srcalt ompl    used for peak
       320.equake_m      : Approved srcalt ompl.32 used for peak
       324.apsi_m        : Approved srcalt ompl    used for peak

Math library acml2.7.0 available via download
    http://developer.amd.com/acml.aspx
        file = acml-2-7-0-pathscale-64bit.tgz
    Use the +ACML option to select this library. 

For a description of Pathscale Compiler and portability
flags and system parameters used to generate this result,
please refer to HP-Pathscale-20051026.txt file in the flags directory.



For questions about this result, please contact the tester.
For other inquiries, please contact [email protected]
Copyright © 1999-2002 Standard Performance Evaluation Corporation

First published at SPEC.org on 27-Oct-2005

Generated on Mon Oct 31 11:05:31 2005 by SPEC OMP2001 HTML formatter v1.01