SPEC CFP2000 Summary IBM Corporation IBM eServer p5 595 (1900 MHz, 64 CPU) Mon Nov 1 17:06:51 2004 SPEC License #11 Test date: Nov-2004 Hardware availability: Nov-2004 Tester: IBM Software availability: Dec-2004 Base Base Base Peak Peak Peak Benchmarks # Copies Run Time Rate # Copies Run Time Rate ------------ -------- -------- -------- -------- -------- -------- 168.wupwise 128 134 1769* 128 124 1919 168.wupwise 128 135 1755 128 125 1894* 168.wupwise 128 133 1789 128 126 1890 171.swim 128 277 1664* 128 277 1664* 171.swim 128 277 1661 128 277 1661 171.swim 128 276 1669 128 276 1669 172.mgrid 128 171 1564 128 171 1567* 172.mgrid 128 173 1549 128 171 1560 172.mgrid 128 172 1558* 128 171 1567 173.applu 128 256 1218* 64 117 1335 173.applu 128 255 1224 64 121 1286 173.applu 128 258 1210 64 117 1331* 177.mesa 128 209 993 128 212 980 177.mesa 128 211 984* 128 213 974* 177.mesa 128 212 981 128 214 970 178.galgel 128 119 3626 128 119 3626 178.galgel 128 122 3528 128 122 3528 178.galgel 128 119 3613* 128 119 3613* 179.art 128 67.9 5689 128 68.0 5679* 179.art 128 68.1 5667* 128 68.2 5660 179.art 128 68.1 5666 128 67.9 5688 183.equake 128 81.4 2370 128 82.0 2354 183.equake 128 81.6 2366 128 81.6 2364 183.equake 128 81.5 2369* 128 81.8 2360* 187.facerec 128 126 2238 128 126 2238 187.facerec 128 125 2257* 128 125 2257* 187.facerec 128 125 2263 128 125 2263 188.ammp 128 291 1122 128 289 1129 188.ammp 128 291 1122* 128 287 1137 188.ammp 128 290 1125 128 288 1136* 189.lucas 128 182 1633* 64 88.6 1675 189.lucas 128 182 1631 64 88.5 1679 189.lucas 128 182 1635 64 88.6 1677* 191.fma3d 128 221 1409* 128 213 1463* 191.fma3d 128 222 1406 128 213 1465 191.fma3d 128 220 1416 128 213 1461 200.sixtrack 128 206 792 128 201 814 200.sixtrack 128 205 795* 128 200 817* 200.sixtrack 128 205 797 128 199 821 301.apsi 128 316 1223 128 239 1617 301.apsi 128 325 1186 128 239 1613* 301.apsi 128 325 1189* 128 245 1578 ======================================================================== 168.wupwise 128 134 1769* 128 125 1894* 171.swim 128 277 1664* 128 277 1664* 172.mgrid 128 172 1558* 128 171 1567* 173.applu 128 256 1218* 64 117 1331* 177.mesa 128 211 984* 128 213 974* 178.galgel 128 119 3613* 128 119 3613* 179.art 128 68.1 5667* 128 68.0 5679* 183.equake 128 81.5 2369* 128 81.8 2360* 187.facerec 128 125 2257* 128 125 2257* 188.ammp 128 291 1122* 128 288 1136* 189.lucas 128 182 1633* 64 88.6 1677* 191.fma3d 128 221 1409* 128 213 1463* 200.sixtrack 128 205 795* 128 200 817* 301.apsi 128 325 1189* 128 239 1613* SPECfp_rate_base2000 1684 SPECfp_rate2000 1752 HARDWARE -------- Hardware Vendor: IBM Corporation Model Name: IBM eServer p5 595 (1900 MHz, 64 CPU) CPU: POWER5 CPU MHz: 1900 FPU: Integrated CPU(s) enabled: 64 cores, 32 chips, 2 cores/chip (SMT on) CPU(s) orderable: 16,24,32,40,48,56,64 Parallel: No Primary Cache: 64KBI+32KBD (on chip)/core Secondary Cache: 1920KB unified (on chip)/chip L3 Cache: 36MB unified (off-chip)/chip, 4 chips/MCM, 8 MCMs/SUT Other Cache: None Memory: 256 GB DDR2 Disk Subsystem: 3x36GB SCSI, 15K RPM Other Hardware: None SOFTWARE -------- Operating System: AIX 5L V5.3 ML_1 Compiler: XL C/C++ Enterprise Edition V7.0 for AIX XL Fortran Enterprise Edition V9.1 for AIX Other Software: ESSL for AIX V4.2 File System: AIX/JFS2 System State: Multi-user NOTES ----- Tested by IBM 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: C: -qpdf1/pdf2 -O5 -blpdata -qalign=natural Fortran: -qpdf1/pdf2 -O5 -blpdata -lmass Peak Optimization Flags: 168.wupwise: -O5 -qarch=pwr3 -qtune=pwr3 -blpdata -lmass 171.swim: basepeak=1 172.mgrid: -qpdf1/pdf2 -O5 -blpdata -lmass 173.applu: -O5 -blpdata -lmass F77=xlf users=64 177.mesa: -qpdf1/pdf2 -O5 -blpdata -lmass -qalign=natural 178.galgel: basepeak=1 179.art: -qpdf1/pdf2 -O5 -blpdata -lmass -qalign=natural 183.equake: -qpdf1/pdf2 -O5 -blpdata -lmass -qalign=natural 187.facerec: basepeak=1 188.ammp: -qpdf1/pdf2 -O5 -blpdata -qalign=natural -D_ILS_MACROS 189.lucas: -O5 -blpdata -lmass users=64 191.fma3d: -qpdf1/pdf2 -O5 -blpdata -qalign=natural -qhot=arraypad -Q 200.sixtrack: -O3 -qhot -qarch=pwr5 -qtune=pwr5 -qfdpr fdpr -R3 301.apsi: -O5 -lmass -qessl -lessl -blpdata -qsave 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) MCM: Acronym for "Multi-Chip Module" (four dual-core processor chips + four L3-cache chips). This system contains 8 MCMs. SUT: Acronym for "System Under Test" ESSL: Engineering and Scientific Subroutine Library C: IBM XL C for AIX invoked as xlc Fortran: IBM XL Fortran for AIX invoked as xlf90 APAR IY62267 was applied to AIX 53 to achieve Mantainence 1 Level. ulimits set to unlimited. Large page mode and memory affinity were set as follows: vmo -r -o lgpg_regions=8192 -o lgpg_size=16777216 -o memory_affinity=1 -o v_pinshm=1 chuser capabilities=CAP_BYPASS_RAC_VMM,CAP_PROPAGATE $USER shutdown -r export MEMORY_AFFINITY=MCM The following config-file entry was used to assign each benchmark process to a core: submit = schedule.128 \$SPECUSERNUM $command with the "schedule.128" function defined as follows: #!/bin/ksh index=$1 shift 1 # Strip off the residual arguments; the rest is the command. if [[ $index -ge 64 ]] then target=$((1+2*(index-64))) else target=$((2*index)) fi bindprocessor $$ $target # Schedule this job to the corresponding core. $* # Now run the command. The "bindprocessor" AIX command binds a process to a CPU core. ----------------------------------------------------------------------------- For questions about this result, please contact the tester. For other inquiries, please contact webmaster@spec.org. Copyright 1999-2004 Standard Performance Evaluation Corporation Generated on Tue Nov 16 17:01:12 2004 by SPEC CPU2000 ASCII formatter v2.1