CINT2000 Result: IBM Corporation IBM System p5 575 (2200 Mhz, 8 CPU, SLES)

Benchmark	Base Copies	Base Runtime	Base Ratio	Copies	Runtime	Ratio
164.gzip	16	196	133	16	196	133
175.vpr	16	146	179	16	146	179
176.gcc	16	97.6	209	16	97.6	209
181.mcf	16	86.3	387	16	86.3	387
186.crafty	16	129	144	16	103	180
197.parser	16	223	150	16	206	162
252.eon	16	121	199	16	122	198
253.perlbmk	16	239	140	16	228	146
254.gap	16	113	181	16	113	181
255.vortex	16	119	297	16	119	297
256.bzip2	16	140	199	16	140	199
300.twolf	16	259	215	16	259	215
SPECint_rate_base2000	193
SPECint_rate2000	199

Benchmark

Base
Copies

Base
Runtime

Base
Ratio

Copies

Runtime

Ratio

164.gzip

196

133

196

133

175.vpr

146

179

146

179

176.gcc

97.6

209

97.6

209

181.mcf

86.3

387

86.3

387

186.crafty

129

144

103

180

197.parser

223

150

206

162

252.eon

121

199

122

198

253.perlbmk

239

140

228

146

254.gap

113

181

113

181

255.vortex

119

297

119

297

256.bzip2

140

199

140

199

300.twolf

259

215

259

215

SPECint_rate_base2000

193

SPECint_rate2000

199

Hardware

Hardware Vendor:

IBM Corporation

Model Name:

IBM System p5 575 (2200 Mhz, 8 CPU, SLES)

CPU:

POWER5+

CPU MHz:

2200

FPU:

Integrated

CPU(s) enabled:

8 cores, 8 chips, 1 core/chip (SMT on)

CPU(s) orderable:

8,16 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 unified off chip per chip

Other Cache:

None

Memory:

64 GB (32x2GB)

Disk Subsystem:

1x73GB SCSI, 15K RPM

Other Hardware:

Software

Operating System:

SLES
SUSE Linux Enterprise Server 10 (ppc) VERSION = 10
w/2.6.16.21-0.8-ppc64 Linux kernel

Compiler:

IBM XL C/C++ Advanced Edition V8.0.1 for Linux

File System:

reiserfs

System State:

Multi-User

Notes / Tuning Information
+FDO Feedback directed optimization enabled by: PASS1=-qpdf1 PASS2=-qpdf2 Integer suite C: invoked as cc C++: invoked as xlC Integer Portability Flags: 176.gcc: -DHOST_WORDS_BIG_ENDIAN 186.crafty: -DLINUX_PPC32 252.eon: -DHAS_ERRLIST 253.perlbmk: -DSPEC_CPU2000_LINUX_PPC32 -DSPEC_CPU2000_NEED_BOOL 254.gap: -DSYS_IS_USG -DSYS_HAS_IOCTL_PROTO -DSYS_HAS_CALLOC_PROTO 300.twolf: -DHAVE_SIGNED_CHAR Additional Peak Portability Flags: 252.eon: -DSPEC_CPU2000_LP64 (for 64-bit compilation) 253.perlbmk: -DSPEC_CPU2000_LP64 (for 64-bit compilation) Integer Base Optimization Flags: C: +FDO -O5 C++: +FDO -O5 Integer Peak Optimization Flags 164.gzip basepeak=1 175.vpr basepeak=1 176.gcc basepeak=1 181.mcf basepeak=1 186.crafty +FDO -O4 -qarch=pwr4 -qtune=pwr4 -q64 197.parser +FDO -O5 -qstaticlink 252.eon +FDO -O5 -q64 253.perlbmk: +FDO -O5 -q64 254.gap basepeak=1 255.vortex basepeak=1 256.bzip2 basepeak=1 300.twolf basepeak=1 System Settings: -- ulimit stack size set to unlimited SMT: Acronym for 'Simultaneous Multi-Threading'. A processor technology that allows the simultaneous execution of multiple thread contexts within a single processor core. SMT is enabled by default. Large pages reserved as follows by root user: echo 480 > /proc/sys/vm/nr_hugepages System configured with libhugetlbfs library for application access to large pages Environment variables set as follows: export HUGETLB_MORECORE=yes export LD_PRELOAD=libhugetlbfs.so (export LD_PRELOAD=libhugetlbfs.so not used for --action build.) Each process was bound to a cpu using submit= with the taskset command submit = taskset -p -c \$SPECUSERNUM \$\$ >/dev/null ; $command

Notes / Tuning Information

 +FDO
     Feedback directed optimization enabled by:  PASS1=-qpdf1  PASS2=-qpdf2

 Integer suite
   C:   invoked as cc
   C++: invoked as xlC

 Integer Portability Flags:
   176.gcc:     -DHOST_WORDS_BIG_ENDIAN
   186.crafty:  -DLINUX_PPC32
   252.eon:     -DHAS_ERRLIST 
   253.perlbmk: -DSPEC_CPU2000_LINUX_PPC32 -DSPEC_CPU2000_NEED_BOOL
   254.gap:     -DSYS_IS_USG -DSYS_HAS_IOCTL_PROTO -DSYS_HAS_CALLOC_PROTO
   300.twolf:   -DHAVE_SIGNED_CHAR

 Additional Peak Portability Flags:
    252.eon:     -DSPEC_CPU2000_LP64    (for 64-bit compilation)
    253.perlbmk: -DSPEC_CPU2000_LP64    (for 64-bit compilation)

 Integer Base Optimization Flags:
   C:   +FDO -O5
   C++: +FDO -O5


 Integer Peak Optimization Flags

 164.gzip 
     basepeak=1    
 175.vpr 
     basepeak=1
 176.gcc 
     basepeak=1
 181.mcf 
     basepeak=1
 186.crafty
     +FDO -O4 -qarch=pwr4 -qtune=pwr4 -q64
 197.parser 
     +FDO -O5 -qstaticlink
 252.eon
     +FDO -O5 -q64 
 253.perlbmk:  
     +FDO -O5 -q64 
 254.gap 
    basepeak=1
 255.vortex
     basepeak=1
 256.bzip2  
     basepeak=1
 300.twolf
     basepeak=1
 
 
 System Settings:
 -- ulimit stack size set to unlimited
 
 
 SMT: Acronym for 'Simultaneous Multi-Threading'.  A processor technology that allows
      the simultaneous execution of multiple thread contexts within a single processor
      core. SMT is enabled by default.
 
 Large pages reserved as follows by root user:
     echo 480 > /proc/sys/vm/nr_hugepages
 System configured with libhugetlbfs library for application access to large pages
 Environment variables set as follows:
     export HUGETLB_MORECORE=yes
     export LD_PRELOAD=libhugetlbfs.so
         (export LD_PRELOAD=libhugetlbfs.so not used for --action build.)
 
  
 Each process was bound to a cpu using submit= with the taskset command
    submit = taskset -p -c \$SPECUSERNUM \$\$ >/dev/null ; $command

First published at SPEC.org on 31-Oct-2006

Generated on Tue Oct 31 14:18:07 2006 by SPEC CPU2000 HTML formatter v1.01