CFP2000 Result: IBM Corporation IBM System p5 520 (2100 MHz, 2 CPU)

Benchmark	Base Copies	Base Runtime	Base Ratio	Copies	Runtime	Ratio
168.wupwise	4	95.0	78.2	4	86.6	85.8
171.swim	4	183	78.4	4	183	78.4
172.mgrid	4	143	58.4	4	135	61.9
173.applu	4	172	56.5	4	192	50.7
177.mesa	4	150	43.3	4	151	42.9
178.galgel	4	106	127	4	91.6	147
179.art	4	37.8	319	4	35.1	344
183.equake	4	40.6	149	4	39.9	151
187.facerec	4	106	82.8	4	106	83.1
188.ammp	4	249	41.1	4	248	41.1
189.lucas	4	136	68.0	4	137	67.7
191.fma3d	4	206	47.2	4	195	50.1
200.sixtrack	4	167	30.6	4	162	31.5
301.apsi	4	231	52.1	4	233	51.8
SPECfp_rate_base2000	71.6
SPECfp_rate2000	73.4

Benchmark

Base
Copies

Base
Runtime

Base
Ratio

Copies

Runtime

Ratio

168.wupwise

95.0

78.2

86.6

85.8

171.swim

183

78.4

183

78.4

172.mgrid

143

58.4

135

61.9

173.applu

172

56.5

192

50.7

177.mesa

150

43.3

151

42.9

178.galgel

106

127

91.6

147

179.art

37.8

319

35.1

344

183.equake

40.6

149

39.9

151

187.facerec

106

82.8

106

83.1

188.ammp

249

41.1

248

41.1

189.lucas

136

68.0

137

67.7

191.fma3d

206

47.2

195

50.1

200.sixtrack

167

30.6

162

31.5

301.apsi

231

52.1

233

51.8

SPECfp_rate_base2000

71.6

SPECfp_rate2000

73.4

Hardware

Hardware Vendor:

IBM Corporation

Model Name:

IBM System p5 520 (2100 MHz, 2 CPU)

CPU:

POWER5+

CPU MHz:

2100

FPU:

Integrated

CPU(s) enabled:

2 cores, 1 chip, 2 cores/chip (SMT on)

CPU(s) orderable:

1,2 core

Parallel:

Primary Cache:

64 KB I + 32 KB D on chip per core

Secondary Cache:

1920 KB I+D on chip per chip

L3 Cache:

36 MB I+D off chip per chip, 1 chip per SUT

Other Cache:

None

Memory:

16 GB (8x2 GB)

Disk Subsystem:

1x73GB SCSI, 15K RPM

Other Hardware:

None

Software

Operating System:

AIX 5L V5.3

Compiler:

XL C/C++ Enterprise Edition Version 8.0 for AIX
XL Fortran Enterprise Edition Version 10.1 for AIX
Other Software: ESSL 4.2.0.4

File System:

AIX/JFS2

System State:

Multi-user

Notes / Tuning Information
Portability Flags: -qfixed used in: 168.wupwise, 171.swim, 172.mgrid, 173.applu, 178.galgel, 200.sixtrack, 301.apsi -qsuffix=f=f90 used in: 178.galgel, 187.facerec, 189.lucas, 191.fma3d Base Optimization Flags: Fortran: -O5 -lhmu -blpdata -lmass C: -qpdf1/pdf2 -O5 -blpdata -qalign=natural Peak Optimization Flags 168.wupwise: -O5 -qsave -blpdata -lhmu -lmass 171.swim: basepeak=1 172.mgrid: -qpdf1/pdf2 -O4 -qipa=partition=large -q64 -blpdata 173.applu: -O5 -qarch=pwr3 -qtune=pwr3 -qalign=struct=natural -qfdpr -q64 -blpdata fdpr -q -O3 177.mesa: -qpdf1/pdf2 -O5 -qfdpr fdpr -q -O3 178.galgel: -qpdf1/pdf2 -O5 -qfdpr -qalign=struct=natural -lhmu -blpdata -lmass -qessl -lessl fdpr -q -O3 179.art: -O5 -lhmu -blpdata 183.equake: -qpdf1/pdf2 -O3 -qarch=auto -qtune=auto -qipa=level=2 -blpdata 187.facerec: -O5 -qsave -blpdata 188.ammp: -O5 -qalign=natural -qfdpr -blpdata -lhmu fdpr -q -O3 189.lucas: -O3 -qarch=auto -qtune=auto -qfdpr -blpdata -qessl -lessl fdpr -q -O3 191.fma3d: -qpdf1/pdf2 -O3 -qarch=auto -qtune=auto -qipa=level=2 -q64 -lhmu -blpdata -lmass 200.sixtrack: -O3 -qarch=auto -qtune=auto -qfdpr fdpr -q -O3 301.apsi: -O5 The installed OS level is AIX 5L for POWER Version 5.3 with the 5300-05 Recommended Technology Level. The installed C/C++ compiler is XL C/C++ Enterprise Edition Version 8.0 for AIX. The installed Fortran copiler is XL Fortran Enterprise Edition Version 10.1 with the May 2006 AIX PTF. SMT: Acronym for "Simultaneous Multi-Threading". A processor technology that allows the simultaneous execution of multiple thread contexts within a single processor core. (Enabled by default) SUT: Acronym for "System Under Test" ESSL: Engineering and Scientific Subroutine Library PTF: IBM identifier for "Program Fix Level" ANSI C89: IBM XL C for AIX invoked as xlc Fortran 77: IBM XL Fortran for AIX invoked as xlf90 Fortran 90: IBM XL Fortran for AIX invoked as xlf90 ulimits set to unlimited. Large page mode, memory affinity and MATMUL threading were set as follows: vmo -r -o lgpg_regions=512 -o lgpg_size=16777216 chuser capabilities=CAP_BYPASS_RAC_VMM,CAP_PROPAGATE $USER bosboot -aD shutdown -rF export MEMORY_AFFINITY=MCM export XLFRTEOPTS=intrinthds=1 The following config-file entry was used to assign each benchmark process to a core: submit = bindprocessor \$\$ \$SPECUSERNUM; $command The "bindprocessor" AIX command binds a process to a CPU core. This result was measured on an IBM System p5 510. IBM System p5 520 and IBM System p5 510 are electronically equivalent.

Notes / Tuning Information

  Portability Flags:
       -qfixed used in:        168.wupwise, 171.swim, 172.mgrid, 173.applu,
                               178.galgel, 200.sixtrack, 301.apsi
       -qsuffix=f=f90 used in: 178.galgel, 187.facerec, 189.lucas, 191.fma3d

  Base Optimization Flags:
    Fortran:    -O5 -lhmu -blpdata -lmass
    C:          -qpdf1/pdf2
                -O5 -blpdata -qalign=natural

  Peak Optimization Flags
    168.wupwise:  -O5 -qsave -blpdata -lhmu -lmass
    171.swim:     basepeak=1
    172.mgrid:    -qpdf1/pdf2
                  -O4 -qipa=partition=large -q64 -blpdata
    173.applu:    -O5 -qarch=pwr3 -qtune=pwr3 -qalign=struct=natural -qfdpr -q64 -blpdata
                   fdpr -q -O3
    177.mesa:     -qpdf1/pdf2
                   -O5 -qfdpr
                   fdpr -q -O3
    178.galgel:   -qpdf1/pdf2
                  -O5 -qfdpr -qalign=struct=natural -lhmu -blpdata -lmass -qessl -lessl
                  fdpr -q -O3
    179.art:      -O5 -lhmu -blpdata
    183.equake:   -qpdf1/pdf2
                  -O3 -qarch=auto -qtune=auto -qipa=level=2 -blpdata
    187.facerec:  -O5 -qsave -blpdata
    188.ammp:     -O5 -qalign=natural -qfdpr -blpdata -lhmu
                  fdpr -q -O3
    189.lucas:    -O3 -qarch=auto -qtune=auto -qfdpr -blpdata -qessl -lessl
                  fdpr -q -O3
    191.fma3d:    -qpdf1/pdf2
                  -O3 -qarch=auto -qtune=auto -qipa=level=2 -q64 -lhmu -blpdata -lmass
    200.sixtrack: -O3 -qarch=auto -qtune=auto -qfdpr
                  fdpr -q -O3
    301.apsi:     -O5


  The installed OS level is AIX 5L for POWER Version 5.3 with the 5300-05 Recommended Technology Level.
  The installed C/C++ compiler is XL C/C++ Enterprise Edition Version 8.0 for AIX.
  The installed Fortran copiler is XL Fortran Enterprise Edition Version 10.1 with the May 2006 AIX PTF.

  SMT:  Acronym for "Simultaneous Multi-Threading". A processor technology that allows
        the simultaneous execution of multiple thread contexts within a single processor
        core. (Enabled by default)
  SUT:  Acronym for "System Under Test"
  ESSL: Engineering and Scientific Subroutine Library
  PTF:  IBM identifier for "Program Fix Level"

  ANSI C89:       IBM XL C for AIX invoked as xlc
  Fortran 77:     IBM XL Fortran for AIX invoked as xlf90
  Fortran 90:     IBM XL Fortran for AIX invoked as xlf90

  ulimits set to unlimited.
  Large page mode, memory affinity and MATMUL threading were set as follows:
      vmo -r -o lgpg_regions=512 -o lgpg_size=16777216
      chuser capabilities=CAP_BYPASS_RAC_VMM,CAP_PROPAGATE $USER
      bosboot -aD
      shutdown -rF
      export MEMORY_AFFINITY=MCM
      export XLFRTEOPTS=intrinthds=1

  The following config-file entry was used to assign each benchmark process to a core:
       submit = bindprocessor \$\$ \$SPECUSERNUM; $command
  The "bindprocessor" AIX command binds a process to a CPU core.

  This result was measured on an IBM System p5 510. IBM System p5 520 and IBM System
  p5 510 are electronically equivalent.

First published at SPEC.org on 09-Aug-2006

Generated on Wed Aug 9 15:53:29 2006 by SPEC CPU2000 HTML formatter v1.01