SPEC Seal of Reviewal OMPM2001 Result
Copyright © 1999-2002 Standard Performance Evaluation Corporation
Hewlett-Packard Company
HP Integrity Superdome 16-way (1500 MHz Itanium 2)
SPECompMpeak2001 = 19281      
SPECompMbase2001 = 17953      
SPEC license # HPG2116 Tested by: Hewlett-Packard Company Test site: Richardson, Texas Test date: Sep-2003 Hardware Avail: Oct-2003 Software Avail: Oct-2003
Benchmark Reference
Graph Scale
310.wupwise_m 6000 266    22563       246    24410       310.wupwise_m base result bar (22563)
310.wupwise_m peak result bar (24410)
312.swim_m 6000 215    27877       215    27877       312.swim_m base result bar (27877)
312.swim_m peak result bar (27877)
314.mgrid_m 7300 342    21341       342    21341       314.mgrid_m base result bar (21341)
314.mgrid_m peak result bar (21341)
316.applu_m 4000 130    30748       111    35890       316.applu_m base result bar (30748)
316.applu_m peak result bar (35890)
318.galgel_m 5100 537    9489      444    11496       318.galgel_m base result bar (9489)
318.galgel_m peak result bar (11496)
320.equake_m 2600 197    13167       178    14582       320.equake_m base result bar (13167)
320.equake_m peak result bar (14582)
324.apsi_m 3400 136    25025       136    25025       324.apsi_m base result bar (25025)
324.apsi_m peak result bar (25025)
326.gafort_m 8700 552    15767       552    15767       326.gafort_m base result bar (15767)
326.gafort_m peak result bar (15767)
328.fma3d_m 4600 384    11992       309    14875       328.fma3d_m base result bar (11992)
328.fma3d_m peak result bar (14875)
330.art_m 6400 281    22737       281    22737       330.art_m base result bar (22737)
330.art_m peak result bar (22737)
332.ammp_m 7000 622    11257       596    11745       332.ammp_m base result bar (11257)
332.ammp_m peak result bar (11745)
SPECompMbase2001 17953        
  SPECompMpeak2001 19281        

Hardware Vendor: Hewlett-Packard Company
Model Name: HP Integrity Superdome 16-way (1500 MHz Itanium 2)
CPU: Intel Itanium 2
CPU MHz: 1500
FPU: Integrated
CPU(s) enabled: 16
CPU(s) orderable: 6 to 16 by 2
Primary Cache: L1 Inst/Data: 16 KB, associativity = 4
Secondary Cache: L2 Unified: 256 KB, associativity = 8
L3 Cache: L3 Unified: 6144 KB, associativity = 24
Other Cache: None
Memory: 64GB (128 * 512MB DIMMs)
Disk Subsystem: root disk 1x36 SCSI
Other Hardware: --
OpenMP Threads: 16
Parallel: OpenMP
Operating System: HPUX11i-TCOE B.11.23
Compiler: HP C/ANSI C Compiler B.11.23
HP aC++ Compiler B.11.23
HP Fortran 90 Compiler B.11.23
HP LIBF90 PHSS_29620
HP F90 Compiler PHSS_29663
HP aC++ Compiler PHSS_29655
HP C Compiler PHSS_29656
u2comp/be/plugin library PHSS_29657
File System: vxfs
System State: Multi-user
Notes / Tuning Information
  User environment:
  Portability Flags:
    318.galgel: +source=fixed +extend_source
     F90  +Ofaster +DSitanium2 +Oopenmp   
          +Oinfo +DD64 -minshared  
     cc   +Ofaster +Oopenmp +DD64 +Oinfo +DSitanium2
          -minshared -AOe +Onofltacc
    submit = chatr -s +id disable +pd 256k +pi 256k $commandexe;  \
         _M_ARENA_OPTS=64:32 _M_SBA_OPTS=16348:150:256 \
            mpsched -T FILL $command 
    310.wupwise_m:  +Ofaster +O3 +DSitanium2 +Oopenmp 
      +Oinfo +DD64 -minshared +cat -Wl,+pd256k -Wl,+pi256k
      ONESTEP = true 
      submit = chatr -s +id disable $commandexe; 
          _M_ARENA_OPTS=64:32 mpsched -T FILL $command

    312.swim_m:  basepeak=true
    314.mgrid_m: basepeak=true
    316.applu_m:  +Ofaster +Oopenmp +Oinfo +DSitanium
      +DD64 -minshared
      submit = chatr -s +id disable +pd 256k +pi 256k $commandexe; 
          _M_ARENA_OPTS=64:32 OMP_NUM_THREADS=15 
          mpsched -T FILL $command
    318.galgel_m: +Ofaster +DSitanium2 +Oopenmp +Oinfo
      +DD64 -minshared +Onodataprefetch +Oloop_unroll=14
      ONESTEP = true
      submit  = chatr -s +id disable +pd 256k +pi 256k $commandexe; 
      OMP_NUM_THREADS=9  _M_ARENA_OPTS=64:32 mpsched -T FILL $command

    320.equake_m:  +Ofaster +Oopenmp  +DD64  +Oinfo
      +DSitanium2 -minshared -AOe +Onofltacc +Onoparmsoverlap 
      submit  = chatr -s +id disable +pd 64k +pi 64k $commandexe; 
      _M_ARENA_OPTS=64:32 mpsched -T FILL $command
    324.apsi_m: basepeak=true

    326.gafort_m: basepeak=true
    328.fma3d_m: +Ofaster +DSitanium2  +Oopenmp +Oinfo +DD64 
      -minshared  +Oinline_budget=75 
      submit = chatr -s +id disable  +pd 1m +pi 1m $commandexe; 
         _M_ARENA_OPTS=64:32 mpsched -T FILL $command
    330.art_m: basepeak=true
    332.ammp_m: +Ofaster +Oopenmp  +DD64  +Oinfo 
      +DSitanium2 -minshared -AOe +Onofltacc
      submit = chatr -s +id disable +pd 16k +pi 16k $commandexe;  
           _M_ARENA_OPTS=64:32 mpsched -T FILL $command
 Alternate Sources:  
   hpg.1 C++ compiler compatible sources
   from SPEC Web site  ompm2001-isoc-20020619.tar.gz
     used for Base 320.equake_m 330.art_m 332.ammp_m 
     used for Peak 332.ammp_m 
   ompl.32 OMPL 32 bit compatible sources 
   from SPEC Web site ompm2001-srcl32bit-20020822.tar.gz 
     used for Peak 310.wupwise_m 328.fma3d_m
  Kernel Paramters (/stand/system):
     maxdsiz         0xc0000000
     maxdsiz_64bit   0x3ffbfffffff
     maxssiz         0x17f00000
     maxssiz_64bit   0x40000000
     maxtsiz         0x40000000
     maxtsiz_64bit   0x40000000
     vps_pagesize    4096
     vps_ceiling     16384
     dbc_min_pct     20
     dbc_max_pct     20
     swapmem_on      0

  System was configured with 1/2 of memory interleaved and
    1/2 of memory local to each cell

  System configured as a single partition with 4 cells and 
    4 processors per cell

  Threads were assigned to cpus using the FILL strategy
    from the HP-UX mpsched utility

  Memory tuning is documented in man page malloc(3C)
      64 malloc arenas, 32 4k pages expansion

      16384 maxfast size, 150 small blocks, 256 grain size

For questions about this result, please contact the tester.
For other inquiries, please contact webmaster@spec.org
Copyright © 1999-2002 Standard Performance Evaluation Corporation

First published at SPEC.org on 15-Oct-2003

Generated on Wed Oct 15 10:52:11 2003 by SPEC OMP2001 HTML formatter v1.01