SPEC OMPM2001 Summary SGI SGI Rackable C2112-4RP4 (Intel Xeon E5-2670, 2.6GHz) Wed Jul 18 17:08:54 2012 SPEC License #HPG0014 Tester: SGI Test date: Aug-2012 Test Site: SGI Hardware availability: Apr-2012 Software availability: May-2012 Base Base Base Peak Peak Peak Benchmarks Ref Time Run Time Ratio Ref Time Run Time Ratio ------------- -------- -------- -------- -------- -------- -------- 310.wupwise_m 6000 40.1 149447 6000 39.7 151226 310.wupwise_m 6000 39.9 150463* 6000 39.7 151230 310.wupwise_m 6000 39.9 150466 6000 39.7 151226* 312.swim_m 6000 81.9 73251 6000 72.7 82525* 312.swim_m 6000 81.9 73252 6000 72.5 82751 312.swim_m 6000 81.9 73251* 6000 72.7 82525 314.mgrid_m 7300 100 72658 7300 87.7 83266 314.mgrid_m 7300 101 72515* 7300 88.3 82695 314.mgrid_m 7300 101 72512 7300 87.7 83262* 316.applu_m 4000 45.9 87173 4000 44.7 89514* 316.applu_m 4000 45.7 87553* 4000 44.5 89916 316.applu_m 4000 45.7 87555 4000 44.7 89513 318.galgel_m 5100 76.2 66896 5100 65.3 78141 318.galgel_m 5100 76.4 66721* 5100 66.0 77227 318.galgel_m 5100 76.6 66546 5100 65.6 77699* 320.equake_m 2600 32.1 81076 2600 24.7 105471 320.equake_m 2600 32.1 81083* 2600 24.8 104633 320.equake_m 2600 32.1 81083 2600 24.8 104694* 324.apsi_m 3400 46.8 72609 3400 46.6 72919 324.apsi_m 3400 46.8 72608* 3400 47.0 72298 324.apsi_m 3400 46.8 72608 3400 46.8 72606* 326.gafort_m 8700 94.3 92234 8700 82.9 104915 326.gafort_m 8700 94.3 92235 8700 82.9 104917 326.gafort_m 8700 94.3 92234* 8700 82.9 104917* 328.fma3d_m 4600 95.5 48180* 4600 69.3 66408 328.fma3d_m 4600 95.3 48281 4600 69.5 66216 328.fma3d_m 4600 95.5 48180 4600 69.3 66407* 330.art_m 6400 30.3 211063 6400 30.1 212414 330.art_m 6400 30.3 211065 6400 30.3 211028 330.art_m 6400 30.3 211065* 6400 30.3 211028* 332.ammp_m 7000 124 56245 7000 128 54661 332.ammp_m 7000 125 56062 7000 125 56064* 332.ammp_m 7000 125 56064* 7000 124 56334 ======================================================================== 310.wupwise_m 6000 39.9 150463* 6000 39.7 151226* 312.swim_m 6000 81.9 73251* 6000 72.7 82525* 314.mgrid_m 7300 101 72515* 7300 87.7 83262* 316.applu_m 4000 45.7 87553* 4000 44.7 89514* 318.galgel_m 5100 76.4 66721* 5100 65.6 77699* 320.equake_m 2600 32.1 81083* 2600 24.8 104694* 324.apsi_m 3400 46.8 72608* 3400 46.8 72606* 326.gafort_m 8700 94.3 92234* 8700 82.9 104917* 328.fma3d_m 4600 95.5 48180* 4600 69.3 66407* 330.art_m 6400 30.3 211065* 6400 30.3 211028* 332.ammp_m 7000 125 56064* 7000 125 56064* SPECompMbase2001 83875 SPECompMpeak2001 93051 HARDWARE -------- Hardware Vendor: SGI Model Name: SGI Rackable C2112-4RP4 (Intel Xeon E5-2670, 2.6GHz) CPU: Intel(R) E5-2670 CPU MHz: 2600 FPU: Integrated CPU(s) enabled: 16 cores, 2 chips, 8 cores/chip, 2 threads/core CPU(s) orderable: 1-2 chips Primary Cache: 32 KB I +32 KB D on chip per core Secondary Cache: 256 KB I+D on chip per core L3 Cache: 20 MB I+D on chip Other Cache: N/A Memory: 128 GB (12 x 8 GB, 2Rx4 PC3-12800R-11, ECC) Disk Subsystem: 10 TB RAID 6 10 x 1 TB SAS (Seagate Constellation ES, 7200RPM) Other Hardware: None SOFTWARE -------- OpenMP Threads: 32 Parallel: OpenMP Operating System: SUSE Linux Enterprise Server 11 SP2, Kernel 3.0.26-0.7-default #1 SMP Compiler: Intel(R) C++ Composer XE , version 13.0 Beta, Build 20120425 Intel(R) Fortran Composer XE , version 13.0 Beta, Build 20120425 Intel(R) Math Kernel Library Version 10.3.9, Build 20120131 File System: NFSv3 IPoIB System State: Multi-user, run level 3 NOTES ----- BIOS settings notes: Intel Hyper-Threading Technology (SMT): Enabled (default is Enabled) Intel Turbo Boost Technology (Turbo) : Enabled (Max 3.3GHz) Portability Flags: 318.galgel_m: -FI -132 Extra Flags: 330.art_m: -DINTS_PER_CACHELINE=32 -DDBLS_PER_CACHELINE=16 General Notes and Environment variables export KMP_LIBRARY=turnaround export KMP_STACKSIZE=31M export KMP_BLOCKTIME=infinite export OMP_DYNAMIC=FALSE ONESTEP=yes ulimit -s unlimited For compiler/openmp flags description please refer: SGI-Linux-Intel12.1-intel64.html Base optimization flags and environment variables: ======================================================================== Medium: OPTIMIZE = -O2 -xAVX -ipo -openmp COPTIMIZE = -ansi-alias export KMP_AFFINITY=compact,0 Peak optimization flags and environment variables: ======================================================================== Medium: OPTIMIZE = -O3 -xAVX -ipo -openmp export KMP_AFFINITY=compact, 0 Peak per-benchmark optimization flags and environment variables: ======================================================================== 310.wupwise_m OPTIMIZE=-O3 -xSSE4.2 -ipo -openmp ======================================================================== 312.swim_m OPTIMIZE=-O3 -xSSE4.2 -ipo -openmp -opt-streaming-stores always -align srcalt = ompl.32 export OMP_NUM_THREADS=16 export KMP_AFFINITY=compact,1 ======================================================================== 314.mgrid_m OPTIMIZE=-O3 -xSSE4.2 -ipo -openmp -fno-alias export OMP_NUM_THREADS=16 export KMP_AFFINITY=compact,1 ======================================================================== 316.applu_m export KMP_AFFINITY=compact,1 ======================================================================== 318.galgel_m export OMP_NUM_THREADS=16 OPTIMIZE=-O2 -xAVX -ipo -openmp FOPTIMIZE=-mkl RM_SOURCES=lapak.f90 export KMP_AFFINITY=compact,1 ======================================================================== 320.equake_m export OMP_NUM_THREADS=16 export KMP_AFFINITY=compact,1 ======================================================================== 324.appsi_m OPTIMIZE=-O2 -xAVX -ipo -openmp ======================================================================== 326.gafort_m srcalt = ompl.32 OPTIMIZE=-O3 -xSSE4.2 -ipo -openmp export KMP_AFFINITY=scatter,0 ======================================================================== 328.fma3d_m FOPTIMIZE=-no-prec-sqrt -fp-model fast=2 export KMP_AFFINITY=compact,1 srcalt = ompl.32 ======================================================================== 330.art_m OPTIMIZE=-O2 -xSSE4.2 -ipo -openmp ======================================================================== 332.ammp_m OPTIMIZE=-O3 -xAVX -ipo -openmp ======================================================================== Additional notes for disk subsystem: The disk subsystem is mounted through NFS over IPoIB via 4x QDR InfiniBand network. The local disk on the system is only for the OS. ======================================================================== Additional notes for OS: Transparent Huge Page support is enabled on the system. ----------------------------------------------------------------------------- For questions about this result, please contact the tester. For other inquiries, please contact webmaster@spec.org. Copyright 1999-2008 Standard Performance Evaluation Corporation Generated on Wed Sep 5 13:17:35 2012 by SPEC OMP2001 ASCII formatter v2.1