SPEC Seal of Reviewal CINT2000 Result
Copyright © 1999-2004 Standard Performance Evaluation Corporation
Compaq Computer Corporation
AlphaServer DS20E Model 68/833
SPECint_rate2000 = 13.1  
SPECint_rate_base2000 = 12.0  
SPEC license # 2 Tested by: Compaq NH Test date: Jun-2001 Hardware Avail: Jun-2001 Software Avail: Aug-2001
Graph Scale Benchmark Base
Copies
Base
Runtime
Base
Ratio
Copies Runtime Ratio
164.gzip base result bar (9.10)
164.gzip peak result bar (9.22)
164.gzip 2 357    9.10  2 352    9.22 
175.vpr base result bar (10.2)
175.vpr peak result bar (10.2)
175.vpr 2 319    10.2   2 317    10.2  
176.gcc base result bar (13.5)
176.gcc peak result bar (15.3)
176.gcc 2 189    13.5   2 167    15.3  
181.mcf base result bar (10.6)
181.mcf peak result bar (13.8)
181.mcf 2 393    10.6   2 303    13.8  
186.crafty base result bar (15.5)
186.crafty peak result bar (15.5)
186.crafty 2 149    15.5   2 149    15.5  
197.parser base result bar (8.37)
197.parser peak result bar (10.3)
197.parser 2 499    8.37  2 406    10.3  
252.eon base result bar (15.5)
252.eon peak result bar (15.8)
252.eon 2 194    15.5   2 191    15.8  
253.perlbmk base result bar (12.0)
253.perlbmk peak result bar (12.9)
253.perlbmk 2 348    12.0   2 324    12.9  
254.gap base result bar (8.31)
254.gap peak result bar (9.78)
254.gap 2 307    8.31  2 261    9.78 
255.vortex base result bar (16.2)
255.vortex peak result bar (17.9)
255.vortex 2 273    16.2   2 247    17.9  
256.bzip2 base result bar (12.6)
256.bzip2 peak result bar (13.6)
256.bzip2 2 275    12.6   2 256    13.6  
300.twolf base result bar (15.7)
300.twolf peak result bar (16.1)
300.twolf 2 443    15.7   2 432    16.1  
  SPECint_rate_base2000 12.0    
  SPECint_rate2000 13.1  

Hardware
Hardware Vendor: Compaq Computer Corporation
Model Name: AlphaServer DS20E Model 68/833
CPU: Alpha 21264B
CPU MHz: 833
FPU: Integrated
CPU(s) enabled: 2 cores, 2 chips, 1 core/chip
CPU(s) orderable: 1 to 2
Parallel: No
Primary Cache: 64KB(I)+64KB(D) on chip
Secondary Cache: 8MB off chip per CPU
L3 Cache: None
Other Cache: None
Memory: 4GB
Disk Subsystem: 1x18GB
Other Hardware: None
Software
Operating System: Tru64 UNIX V5.1
+Patch Kit 2
Compiler: Compaq C V6.4-214-46B59
Program Analysis Tools V2.0
Spike V5.2 DTK (1.461 46B5P)
Compaq C++ V6.3-010-46B2F
File System: AdvFS
System State: Multi-user
Notes / Tuning Information
 Baseline C  : cc  -arch ev6 -fast +CFB ONESTEP
          C++: cxx -arch ev6 -O2        ONESTEP
 Peak:
   All but 252.eon: cc -g3 -arch ev6 ONESTEP
      164.gzip: -fast -O4 -non_shared +CFB
       175.vpr: -fast -O4 -assume restricted_pointers +CF
       176.gcc: -fast -O4 -xtaso_short -all -ldensemalloc
                +CFB +IFB
       181.mcf: -fast -xtaso_short +CFB +IFB +PFB
    186.crafty: same as base
    197.parser: -fast -O4 -xtaso_short -non_shared +CFB
       252.eon: cxx -arch ev6 -O2 -all -ldensemalloc -non
   253.perlbmk: -fast -non_shared +CFB +IFB
       254.gap: -fast -O4 -non_shared +CFB +IFB +PFB
    255.vortex: -fast -non_shared +CFB +IFB
     256.bzip2: -fast -O4 -non_shared +CFB
     300.twolf: -fast -O4 -assume restricted_pointers -al
                -ldensemalloc -none +CFB +IFB
 Most benchmarks are built using one or more types of
 profile-driven feedback.  The types used are designated
 by abbreviations in the notes:
 +CFB: Code generation is optimized by the compiler, usin
       feedback from a training run.  These commands are
       done before the first compile (in phase "fdo_pre0"
            mkdir /tmp/pp
            rm -f /tmp/pp/${baseexe}*
       and these flags are added to the first and second
            PASS1_CFLAGS = -prof_gen_noopt -prof_dir /tmp
            PASS2_CFLAGS = -prof_use       -prof_dir /tmp
      (Peak builds use /tmp/pp above; base builds use /tm
 +IFB: Icache usage is improved by the post-link-time opt
       Spike, using feedback from a training run.  These
       are used (in phase "fdo_postN"):
            mv ${baseexe} oldexe
            spike oldexe -feedback oldexe -o ${baseexe}
 +PFB: Prefetches are improved by the post-link-time opti
       Spike, using feedback from a training run.  These
       commands are used (in phase "fdo_post_makeN"):
            rm -f *Counts*
            mv ${baseexe} oldexe
            pixie -stats dstride oldexe 1>pixie.out 2>pix
            mv oldexe.pixie ${baseexe}
       A training run is carried out (in phase "fdo_runN"
       then this command (in phase "fdo_postN"):
            spike oldexe -fb oldexe -stride_prefetch -o $
 When Spike is used for both Icache and Prefetch improvem
 only one spike command is actually issued, with the Icac
 options followed by the Prefetch options.
 Portability: gcc: -Dalloca=__builtin_alloca; crafty: -DA
 perlbmk: -DSPEC_CPU2000_DUNIX; vortex: -DSPEC_CPU2000_LP
 gap: -DSYS_HAS_CALLOC_PROTO -DSYS_IS_BSD -DSYS_HAS_IOCTL
      -DSPEC_CPU2000_LP64
 Information on UNIX V5.1 Patches can be found at
 http://ftp1.service.digital.com/public/unix/v5.1/
 Spike, and the Program Analysis Tools, are part of the D
 Tool Kit Supplement, http://www.tru64unix.compaq.com/dtk
 features used in this SPEC submission will be available
 site as a beta kit in August, 2001, and as a production
 October, 2001.  The C compiler for this SPEC submission
 available at the same location, as a production release,
 May, 2001.


For questions about this result, please contact the tester.
For other inquiries, please contact webmaster@spec.org
Copyright © 1999-2004 Standard Performance Evaluation Corporation

First published at SPEC.org on 09-Jul-2001

Generated on Wed Apr 13 13:09:15 2005 by SPEC CPU2000 HTML formatter v1.01