SPEC CFP2000 Summary IBM Corporation IBM eServer p5 575 (1500 MHz, 16 CPU) Sat Jul 30 18:27:18 2005 SPEC License #11 Test date: Jul-2005 Hardware availability: Oct-2005 Tester: IBM Software availability: Oct-2005 Base Base Base Peak Peak Peak Benchmarks # Copies Run Time Rate # Copies Run Time Rate ------------ -------- -------- -------- -------- -------- -------- 168.wupwise 32 155 383 32 119 499 168.wupwise 32 154 385 32 119 500* 168.wupwise 32 155 384* 32 119 501 171.swim 32 281 410 32 281 410 171.swim 32 282 409 32 282 409 171.swim 32 281 410* 32 281 410* 172.mgrid 32 206 324 16 96.5 346* 172.mgrid 32 206 324* 16 96.6 346 172.mgrid 32 206 324 16 96.5 346 173.applu 32 286 273 32 264 296 173.applu 32 266 293 32 268 291* 173.applu 32 280 278* 32 271 288 177.mesa 32 226 230 32 215 241 177.mesa 32 227 228 32 214 243 177.mesa 32 227 229* 32 215 242* 178.galgel 32 145 741 16 61.3 878 178.galgel 32 146 739* 16 60.9 884* 178.galgel 32 147 734 16 60.1 896 179.art 32 83.1 1161* 16 40.5 1192 179.art 32 82.9 1164 16 40.8 1184 179.art 32 83.2 1161 16 40.5 1191* 183.equake 32 84.0 575 16 41.3 584 183.equake 32 85.1 567 16 41.4 583* 183.equake 32 84.3 573* 16 41.8 577 187.facerec 32 173 407* 32 168 420 187.facerec 32 173 407 32 165 428* 187.facerec 32 174 406 32 162 434 188.ammp 32 364 224 32 364 224 188.ammp 32 363 225 32 363 225 188.ammp 32 364 225* 32 364 225* 189.lucas 32 201 369 16 95.8 387* 189.lucas 32 201 369* 16 96.1 386 189.lucas 32 201 369 16 95.8 388 191.fma3d 32 315 248* 32 298 261 191.fma3d 32 310 251 32 302 258 191.fma3d 32 319 245 32 302 259* 200.sixtrack 32 236 173 32 229 178 200.sixtrack 32 237 172 32 230 178* 200.sixtrack 32 237 172* 32 230 178 301.apsi 32 368 262* 32 310 311 301.apsi 32 368 262 32 332 291 301.apsi 32 365 264 32 323 299* ======================================================================== 168.wupwise 32 155 384* 32 119 500* 171.swim 32 281 410* 32 281 410* 172.mgrid 32 206 324* 16 96.5 346* 173.applu 32 280 278* 32 268 291* 177.mesa 32 227 229* 32 215 242* 178.galgel 32 146 739* 16 60.9 884* 179.art 32 83.1 1161* 16 40.5 1191* 183.equake 32 84.3 573* 16 41.4 583* 187.facerec 32 173 407* 32 165 428* 188.ammp 32 364 225* 32 364 225* 189.lucas 32 201 369* 16 95.8 387* 191.fma3d 32 315 248* 32 302 259* 200.sixtrack 32 237 172* 32 230 178* 301.apsi 32 368 262* 32 323 299* SPECfp_rate_base2000 359 SPECfp_rate2000 385 HARDWARE -------- Hardware Vendor: IBM Corporation Model Name: IBM eServer p5 575 (1500 MHz, 16 CPU) CPU: POWER5 CPU MHz: 1500 FPU: Integrated CPU(s) enabled: 16 cores, 8 chips, 2 cores/chip (SMT on) CPU(s) orderable: 16 Parallel: No Primary Cache: 64KBI+32KBD (on chip)/core Secondary Cache: 1920KB unified (on chip)/chip L3 Cache: 36MB unified (off-chip)/DCM, 8 DCM/SUT Other Cache: None Memory: 64x1GB Disk Subsystem: 2x36GB SCSI, 15K RPM Other Hardware: None SOFTWARE -------- Operating System: AIX 5L V5.3 Compiler: XL C/C++ Enterprise Edition Version 7.0 for AIX XL Fortran Enterprise Edition V9.1 for AIX Other Software: ESSL 4.2.0.2 File System: AIX/JFS2 System State: Multi-user NOTES ----- 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 -blpdata -lmass C: -qpdf1/pdf2 -O5 -blpdata -qalign=natural Peak Optimization Flags 168.wupwise: F77=xlf90 -q64 -O5 -lmass -qalign=struct=natural -qfdpr fdpr -q -O3 171.swim: basepeak=1 172.mgrid: -O5 -lmass -qessl -lessl -blpdata -qsave users=16 173.applu: F77=xlf90 -q64 -O5 -qarch=pwr3 -qtune=pwr3 -blpdata -lmass -qalign=struct=natural -qfdpr fdpr -q -O3 177.mesa: -qpdf1/pdf2 -O3 -qarch=auto -qtune=auto -qipa=level=2 178.galgel: -O5 -blpdata -lmass -qessl -lessl -qfdpr fdpr -q -O3 users=16 179.art: -O5 -lhmu -blpdata -lmass users=16 183.equake: -qpdf1/pdf2 -O5 -blpdata -qalign=natural -D_ILS_MACROS users=16 187.facerec: -O5 -blpdata -qfdpr -qalign=struct=natural fdpr -q -O3 188.ammp: basepeak=1 189.lucas: -O5 -lmass -qessl -lessl -blpdata -qsave users=16 191.fma3d: -qpdf1/pdf2 -O5 -blpdata -qfdpr -qalign=struct=natural fdpr -q -O3 200.sixtrack: F77=xlf90 -q64 -O5 -blpdata -lmass -qalign=struct=natural -qfdpr fdpr -q -O3 301.apsi: F77=xlf90 -O5 -lmass -qessl -lessl -blpdata -qsave The installed OS level is AIX 5L for POWER version 5.3 with the 5300-03 Recommended Maintenance package. 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) DCM: Acronym for "Dual-Chip Module" (one dual-core processor chip + one L3-cache chip) SUT: Acronym for "System Under Test" ESSL: Engineering and Scientific Subroutine Library C: IBM XL C for AIX invoked as xlc Fortran 77: IBM XL Fortran for AIX invoked as xlf90 unless explicitly reassigned Fortran 90: IBM XL Fortran for AIX invoked as xlf ulimits set to unlimited. Large page mode and memory affinity were set as follows: vmo -r -o lgpg_regions=2048 -o lgpg_size=16777216 chuser capabilities=CAP_BYPASS_RAC_VMM,CAP_PROPAGATE $USER reboot -q export MEMORY_AFFINITY=MCM export LDR_CNTRL=LARGE_PAGE_DATA=M The following config-file entry was used to assign each benchmark process to a core: submit = let "MYCPU=2*\$SPECUSERNUM"; if (("\$MYCPU > 31")) then let "MYCPU-=31"; fi; bindprocessor \$\$ \$MYCPU; $command The "bindprocessor" AIX command binds a process to a CPU core. Use flags-description file IBM-20050822-AIX.txt. ----------------------------------------------------------------------------- For questions about this result, please contact the tester. For other inquiries, please contact webmaster@spec.org. Copyright 1999-2005 Standard Performance Evaluation Corporation Generated on Wed Aug 24 17:58:53 2005 by SPEC CPU2000 ASCII formatter v2.1