CINT2000 Result: IBM Corporation IBM System p5 550Q (1650 Mhz, 8 CPU, SLES)

Benchmark	Base Copies	Base Runtime	Base Ratio	Copies	Runtime	Ratio
164.gzip	16	273	95.2	16	273	95.2
175.vpr	16	221	118	16	221	118
176.gcc	16	135	152	16	135	152
181.mcf	16	173	193	16	173	193
186.crafty	16	177	105	16	143	130
197.parser	16	310	108	16	288	116
252.eon	16	168	144	16	172	140
253.perlbmk	16	322	104	16	326	102
254.gap	16	155	132	16	155	132
255.vortex	16	166	212	16	166	212
256.bzip2	16	197	141	16	197	141
300.twolf	16	408	137	16	408	137
SPECint_rate_base2000	133
SPECint_rate2000	136

Benchmark

Base
Copies

Base
Runtime

Base
Ratio

Copies

Runtime

Ratio

164.gzip

273

95.2

273

95.2

175.vpr

221

118

221

118

176.gcc

135

152

135

152

181.mcf

173

193

173

193

186.crafty

177

105

143

130

197.parser

310

108

288

116

252.eon

168

144

172

140

253.perlbmk

322

104

326

102

254.gap

155

132

155

132

255.vortex

166

212

166

212

256.bzip2

197

141

197

141

300.twolf

408

137

408

137

SPECint_rate_base2000

133

SPECint_rate2000

136

Hardware

Hardware Vendor:

IBM Corporation

Model Name:

IBM System p5 550Q (1650 Mhz, 8 CPU, SLES)

CPU:

POWER5+

CPU MHz:

1650

FPU:

Integrated

CPU(s) enabled:

8 cores, 4 chips, 2 cores/chip (SMT on)

CPU(s) orderable:

4,8 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

Other Cache:

None

Memory:

32 GB (16x2GB)

Disk Subsystem:

1x73GB SCSI, 15K RPM

Other Hardware:

None

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 14:18:03 2006 by SPEC CPU2000 HTML formatter v1.01