SPEC OMPM2001 Summary IBM Corporation IBM System p5 575 (2200 MHz, 8 CPU) Tue Dec 13 12:48:41 2005 SPEC License #HPG0005 Tester: IBM Test date: Dec-2005 Test Site: Austin, TX Hardware availability: Feb-2006 Software availability: Feb-2006 Base Base Base Peak Peak Peak Benchmarks Ref Time Run Time Ratio Ref Time Run Time Ratio ------------- -------- -------- -------- -------- -------- -------- 310.wupwise_m 6000 140 42930 6000 121 49743 310.wupwise_m 6000 138 43331 6000 121 49715 310.wupwise_m 6000 140 42983* 6000 121 49722* 312.swim_m 6000 163 36765* 6000 119 50222 312.swim_m 6000 163 36792 6000 120 50123 312.swim_m 6000 163 36730 6000 120 50178* 314.mgrid_m 7300 364 20042 7300 167 43720* 314.mgrid_m 7300 362 20145 7300 167 43841 314.mgrid_m 7300 363 20127* 7300 167 43701 316.applu_m 4000 82.0 48788 4000 66.3 60328* 316.applu_m 4000 81.8 48878* 4000 66.4 60199 316.applu_m 4000 81.8 48901 4000 66.1 60480 318.galgel_m 5100 117 43440* 5100 98.8 51625* 318.galgel_m 5100 118 43316 5100 98.5 51781 318.galgel_m 5100 117 43451 5100 98.8 51610 320.equake_m 2600 96.1 27041* 2600 81.2 32014 320.equake_m 2600 96.3 27005 2600 80.3 32373 320.equake_m 2600 95.9 27099 2600 80.7 32227* 324.apsi_m 3400 108 31594 3400 98.0 34698 324.apsi_m 3400 109 31299 3400 97.7 34818* 324.apsi_m 3400 108 31511* 3400 97.2 34990 326.gafort_m 8700 238 36486 8700 215 40543 326.gafort_m 8700 239 36440 8700 214 40693 326.gafort_m 8700 239 36468* 8700 214 40611* 328.fma3d_m 4600 265 17387* 4600 251 18310* 328.fma3d_m 4600 264 17394 4600 251 18303 328.fma3d_m 4600 265 17379 4600 250 18364 330.art_m 6400 76.7 83487 6400 77.7 82319 330.art_m 6400 76.6 83521* 6400 77.9 82188* 330.art_m 6400 76.5 83608 6400 77.9 82150 332.ammp_m 7000 355 19702* 7000 333 21004 332.ammp_m 7000 353 19810 7000 334 20979* 332.ammp_m 7000 358 19574 7000 334 20952 ======================================================================== 310.wupwise_m 6000 140 42983* 6000 121 49722* 312.swim_m 6000 163 36765* 6000 120 50178* 314.mgrid_m 7300 363 20127* 7300 167 43720* 316.applu_m 4000 81.8 48878* 4000 66.3 60328* 318.galgel_m 5100 117 43440* 5100 98.8 51625* 320.equake_m 2600 96.1 27041* 2600 80.7 32227* 324.apsi_m 3400 108 31511* 3400 97.7 34818* 326.gafort_m 8700 239 36468* 8700 214 40611* 328.fma3d_m 4600 265 17387* 4600 251 18310* 330.art_m 6400 76.6 83521* 6400 77.9 82188* 332.ammp_m 7000 355 19702* 7000 334 20979* SPECompMbase2001 33521 SPECompMpeak2001 40560 HARDWARE -------- Hardware Vendor: IBM Corporation Model Name: IBM System p5 575 (2200 MHz, 8 CPU) CPU: POWER5+ CPU MHz: 2200 FPU: Integrated CPU(s) enabled: 8 cores, 8 chips, 1 core/chip (SMT on) CPU(s) orderable: 8,16 Primary Cache: 64KBI+32KBD (on chip)/core Secondary Cache: 1920KB unified, shared (on chip)/chip L3 Cache: 36MB unified (off-chip)/DCM, 8 DCMs/SUT Other Cache: None Memory: 64x512MB Disk Subsystem: 2x73GB SCSI, 15K RPM Other Hardware: None SOFTWARE -------- OpenMP Threads: 16 Parallel: OpenMP 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 4.2.0.3 File System: AIX/JFS2 System State: Multi-user NOTES ----- Portability Flags & Environment Variables -qfixed used in: 310.wupwise_m, 312.swim_m, 314.mgrid_m, 316.applu_m, 324.apsi_m -qfixed=80 used in: 318.galgel_m -qsuffix=f=f90 used in: 318.galgel_m, 326.gafort_m, 328.fma3d_m Base Flags C: -qpdf1/pdf2 -q64 -O5 -qalign=natural -qhot=arraypad -Q -bdatapsize:64K -qsmp=omp FORTRAN: -O5 -qipa=noobject -qipa=partition=large -qmaxmem=-1 -qsmp=omp EXTRA_LDFLAGS=-bmaxdata:0x80000000 Base & Peak User Environment: OMP_NUM_THREADS=16 OMP_DYNAMIC=FALSE XLSMPOPTS=SPINS=0:YIELDS=0:STACK=8000000:SCHEDULE=STATIC:STARTPROC=0:STRIDE=1 MALLOCMULTIHEAP=1 Peak Flags: -qsmp=omp used in all cases 310.wupwise_m: -O5 -qhot=arraypad -qipa=noobject -qipa=partition=large -qmaxmem=-1 -q64 -btextpsize:64K -bdatapsize:64K fdpr -q -O3 312.swim_m: -O5 -qarch=pwr3 -qtune=pwr3 -q64 -btextpsize:64K -bdatapsize:64K -bstackpsize:64K 314.mgrid_m: -O5 -qipa=partition=large -qalign=struct=natural -q64 -btextpsize:64K -bdatapsize:64K 316.applu_m: -O3 -qarch=pwr4 -qtune=pwr4 -q64 -btextpsize:64K -bdatapsize:64K 318.galgel_m: -O5 -qarch=pwr3 -qtune=pwr3 -btextpsize:64K -bdatapsize:64K -bstackpsize:64K -lmass -qessl -lesslsmp EXTRA_LDFLAGS=-bmaxdata:0x80000000 320.equake_m: -qpdf1/pdf2 -O5 -qfdpr -q64 -bdatapsize:64K fdpr -q -O3 325.apsi_m: -O5 -qalign=struct=natural -bdatapsize:64K -bstackpsize:64K EXTRA_LDFLAGS=-bmaxdata:0x80000000 XLSMPOPTS=SPINS=0:YIELDS=0:STACK=8000000:SCHEDULE=STATIC:STARTPROC=0:STRIDE=2 326.gafort_m: -O5 -qhot=arraypad -qipa=noobject -qipa=partition=large -qmaxmem=-1 -qalign=struct=natural -btextpsize:64K -bdatapsize:64K -bstackpsize:64K -lhmu -lmass -qessl -lesslsmp EXTRA_LDFLAGS=-bmaxdata:0x80000000 328.fma3d_m: -O5 -qhot=arraypad -qipa=noobject -qipa=partition=large -qmaxmem=-1 -btextpsize:64K -bdatapsize:64K -bstackpsize:64K -lmass -qessl -lesslsmp EXTRA_LDFLAGS=-bmaxdata:0x80000000 330.art_m: -qpdf1/pdf2 -O5 -qfdpr -q64 -btextpsize:64K -bdatapsize:64K -lesslsmp fdpr -q -O3 EXTRA_CFLAGS= -DINTS_PER_CACHELINE=32 -DDBLS_PER_CACHELINE=16 332.ammp_m: -qpdf1/pdf2 -O5 -qipa=partition=large -qmaxmem=-1 -q64 -btextpsize:64K -bdatapsize:64K Alternate sources: Add critical region around update of linked list in parallel loop. Approved src.alt available as ompm-purdue1-20040324.tar.gz Used for 330.art_m, base and peak. Peak sources: SPEC OMPL2001 source for 32bit systems modified for SPEC OMPM2001 used with 312.swim_m, 316.applu_m, 320.equake_m, 326.gafort_m. The installed OS level is AIX 5L for POWER version 5.3 with the 5300-04 Recommended Technology Level. 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 ANSI C89: IBM XL C for AIX invoked as xlc_r Fortran 90: IBM XL Fortran for AIX invoked as xlf_r ulimits set to unlimited. Large page mode and memory affinity were set as follows: vmo -r -o lgpg_regions=1024 -o lgpg_size=16777216 chuser capabilities=CAP_BYPASS_RAC_VMM,CAP_PROPAGATE $USER shutdown -rF export MEMORY_AFFINITY=MCM 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. ----------------------------------------------------------------------------- For questions about this result, please contact the tester. For other inquiries, please contact webmaster@spec.org. Copyright 1999-2002 Standard Performance Evaluation Corporation Generated on Wed Mar 1 11:48:07 2006 by SPEC OMP2001 ASCII formatter v2.1