# Invocation command line: # /mnt/shm/cpu2006-ic16/bin/runspec --define invoke_with_interleave --rate 576 -c sgi-linux-HSW-46xx-IC16.0.0.109.cfg -define smt --define cores=288 --define physicalfirst --define invoke_with_interleave --define drop_caches --define THP_enabled -T all -o asc,csv,cfg,pdf int # output_root was not used for this run ############################################################################ ############################################################################ # This is a sample config file. It was tested with: # # Compiler name/version: Intel Compiler 16.0 # Operating system version: 64-Bit RedHat Enterprise Linux64 7.1 # Hardware: Intel processors supporting AVX2 # ############################################################################ # SPEC CPU2006 Intel Linux64 config file # 20150812 Intel Compiler 16.0 for Linux64 ############################################################################ action = validate tune = base,peak # ######################################################## # ATTENTION ATTENTION ATTENTION ######################################################## # # NOTE If you change fail_build then PLEASE also # change the line 'define version', because # SPEC review tools use 'ext' to track binaries. # ######################################################## %define version 20151214 ext = cpu2006-1.2-ic16.0-lin64-ws-avx2-rate-%{version} # # vvvvvvvvvvvv # do not change unless you read NOTE above fail_build=0 # do not change unless you read NOTE above # ^^^^^^^^^^^^ # do not change unless you read NOTE above # ######################################################## # ##################################################################################### # You can't change the line with fail_build=1 without changing the line ext= # to reflect the data on which you re-built the binaries. # In addition, the sw_compiler lines below, must be modified to match the description # of the compiler being used to build the binaries ##################################################################################### PATHSEP = / check_md5=1 reportable=1 bench_post_setup=sync parallel_test=0 mean_anyway=1 sysinfo_program = specperl $[top]/config/sysinfo.rev6914 -f -p flagsurl000=http://www.spec.org/cpu2006/flags/Intel-ic16.0-official-linux64.xml flagsurl001=http://www.spec.org/cpu2006/flags/SGI-UV300-Platform-Flags.20160112.xml # Set some environment variables preENV_LD_LIBRARY_PATH = $[top]/libs/32:$[top]/libs/64:$[top]/sh # # These are listed as benchmark-tuning-extension-machine # int=default=default=default: CC= icc -m32 -L/sw/sdev/intel/parallel_studio_xe_2016/compilers_and_libraries/linux/lib/ia32_lin CXX= icpc -m32 -L/sw/sdev/intel/parallel_studio_xe_2016/compilers_and_libraries/linux/lib/ia32_lin OBJ = .o SMARTHEAP32_DIR = /root/cpu2006-ic16/sh SMARTHEAP64_DIR = /root/cpu2006-ic16/sh PORTABILITY = -D_FILE_OFFSET_BITS=64 fp=default=default=default: CC= icc -m64 CXX= icpc -m64 FC= ifort -m64 OBJ = .o # For UP systems, we need to know if the processors are ordered across cores first or in order # If across cores, processors 0, 1, 2 and 3 are on distinct physical cores # Otherwise, processors 0, 2, 4 and 6 are on distinct physical cores default: submit = numactl --localalloc --physcpubind=$SPECCOPYNUM $command parallel_setup = 18 parallel_setup_type = fork parallel_setup_prefork = taskset -pc $SPECCOPYNUM $$ %ifdef %{no-numa} submit = taskset -c $SPECCOPYNUM $command %endif #################################################################### # Compiler options # for Nehalem use -xSSE4.2 # for processors prior to dunnington, replace -xSSE4.1 with -xSSSE3 #################################################################### default: SSE = -xCORE-AVX2 FASTNOSTATIC = $(SSE) -ipo -O3 -no-prec-div FAST = $(SSE) -ipo -O3 -no-prec-div ################################################################ # # portability & libraries # #################### Portability Flags and Notes ############################ 400.perlbench=default: CPORTABILITY= -DSPEC_CPU_LINUX_IA32 403.gcc=default: EXTRA_CFLAGS= -Dalloca=_alloca 462.libquantum=default: CPORTABILITY= -DSPEC_CPU_LINUX 483.xalancbmk=default: CXXPORTABILITY= -DSPEC_CPU_LINUX fp=default: PORTABILITY = -DSPEC_CPU_LP64 435.gromacs=default=default=default: LDPORTABILITY = -nofor_main 436.cactusADM=default=default=default: LDPORTABILITY = -nofor_main 454.calculix=default=default=default: LDPORTABILITY = -nofor_main 481.wrf=default=default=default: CPORTABILITY = -DSPEC_CPU_CASE_FLAG -DSPEC_CPU_LINUX ################################################################ # Tuning Flags ################################################################ # # Base tuning default optimization # Feedback directed optimization not allowed in baseline for CPU2006 # However there is no limit on the number of flags as long as the same # flags are used in the same order for all benchmarks of a given language 471.omnetpp,473.astar,483.xalancbmk=default: EXTRA_LIBS= -L$(SMARTHEAP32_DIR) -lsmartheap EXTRA_LDFLAGS= -Wl,-z,muldefs int=base=default=default: COPTIMIZE= $(FASTNOSTATIC) -opt-prefetch -opt-mem-layout-trans=3 CXXOPTIMIZE= $(FASTNOSTATIC) -opt-prefetch -opt-mem-layout-trans=3 fp=base=default=default: OPTIMIZE= $(FAST) -opt-prefetch COPTIMIZE= -auto-p32 -ansi-alias -opt-mem-layout-trans=3 CXXOPTIMIZE= -auto-p32 -ansi-alias -opt-mem-layout-trans=3 ################################################################ # Peak Tuning Flags int 2006 fast ################################################################ int=peak=default: COPTIMIZE= -ansi-alias -opt-mem-layout-trans=3 CXXOPTIMIZE= -ansi-alias -opt-mem-layout-trans=3 PASS1_CFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_CFLAGS = $(FASTNOSTATIC) -prof-use PASS1_CXXFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_CXXFLAGS = $(FASTNOSTATIC) -prof-use PASS1_LDCFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_LDCFLAGS = $(FASTNOSTATIC) -prof-use PASS1_LDCXXFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_LDCXXFLAGS = $(FASTNOSTATIC) -prof-use 400.perlbench=peak=default: CC= icc -m64 CPORTABILITY= -DSPEC_CPU_LP64 -DSPEC_CPU_LINUX_X64 COPTIMIZE= -auto-ilp32 401.bzip2=peak=default: CC= icc -m64 CPORTABILITY= -DSPEC_CPU_LP64 COPTIMIZE= -opt-prefetch -auto-ilp32 -ansi-alias 403.gcc=peak=default: COPTIMIZE = $(FASTNOSTATIC) feedback=0 429.mcf=peak=default: basepeak=yes 445.gobmk=peak=default: PASS1_CFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_CFLAGS = $(SSE) -prof-use PASS1_LDCFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_LDCFLAGS = $(SSE) -prof-use 456.hmmer=peak=default: CC= icc -m64 CPORTABILITY= -DSPEC_CPU_LP64 COPTIMIZE= $(FASTNOSTATIC) -unroll2 -auto-ilp32 feedback=no 458.sjeng=peak=default: CC= icc -m64 CPORTABILITY= -DSPEC_CPU_LP64 COPTIMIZE= -unroll4 -auto-ilp32 462.libquantum=peak=default: basepeak=yes 464.h264ref=peak=default: COPTIMIZE= -unroll2 -ansi-alias 471.omnetpp=peak=default: CXXOPTIMIZE= -ansi-alias -opt-ra-region-strategy=block 473.astar=peak=default: basepeak=yes 483.xalancbmk=peak=default: basepeak=yes ################################################################ # Peak Tuning Flags for FP ################################################################ fp=peak=default: COPTIMIZE= -auto-ilp32 CXXOPTIMIZE= -auto-ilp32 PASS1_CFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_CFLAGS = $(FASTNOSTATIC) -opt-mem-layout-trans=3 -prof-use PASS1_CXXFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_CXXFLAGS = $(FASTNOSTATIC) -opt-mem-layout-trans=3 -prof-use PASS1_FFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_FFLAGS = $(FASTNOSTATIC) -prof-use PASS1_LDFLAGS = -prof-gen:threadsafe -par-num-threads=1 PASS2_LDFLAGS = $(FASTNOSTATIC) -prof-use 410.bwaves=peak=default: basepeak=yes #################################################################################################################################### %ifdef %{smt} copies=%{cores} %ifdef %{physicallogical} submit = numactl --localalloc --physcpubind=`expr 2 \\* $SPECCOPYNUM` $command %ifdef %{no-numa} submit = taskset -c `expr 2 \\* $SPECCOPYNUM` $command %endif %endif %endif #################################################################################################################################### 416.gamess=peak=default: OPTIMIZE= -unroll2 -inline-level=0 -scalar-rep- 433.milc=peak=default: basepeak=yes 434.zeusmp=peak=default: basepeak=yes feedback=0 435.gromacs=peak=default: OPTIMIZE= -opt-prefetch 436.cactusADM=peak=default: basepeak=yes 437.leslie3d=peak=default: basepeak=yes #################################################################################################################################### %ifdef %{smt} copies=%{cores} %ifdef %{physicallogical} submit = numactl --localalloc --physcpubind=`expr 2 \\* $SPECCOPYNUM` $command %ifdef %{no-numa} submit = taskset -c `expr 2 \\* $SPECCOPYNUM` $command %endif %endif %endif #################################################################################################################################### 444.namd=peak=default: CXXOPTIMIZE= -fno-alias -auto-ilp32 447.dealII=peak=default: basepeak=yes 450.soplex=peak=default: PORTABILITY = -D_FILE_OFFSET_BITS=64 CXX= icpc -m32 -L/sw/sdev/intel/parallel_studio_xe_2016/compilers_and_libraries/linux/lib/ia32_lin OPTIMIZE= -opt-malloc-options=3 CXXOPTIMIZE= #################################################################################################################################### %ifdef %{smt} copies=%{cores} %ifdef %{physicallogical} submit = numactl --localalloc --physcpubind=`expr 2 \\* $SPECCOPYNUM` $command %ifdef %{no-numa} submit = taskset -c `expr 2 \\* $SPECCOPYNUM` $command %endif %endif %endif #################################################################################################################################### 453.povray=peak=default: CXXOPTIMIZE= -unroll4 -ansi-alias 454.calculix=peak=default: basepeak=yes 459.GemsFDTD=peak=default: basepeak=yes #################################################################################################################################### %ifdef %{smt} copies=%{cores} %ifdef %{physicallogical} submit = numactl --localalloc --physcpubind=`expr 2 \\* $SPECCOPYNUM` $command %ifdef %{no-numa} submit = taskset -c `expr 2 \\* $SPECCOPYNUM` $command %endif %endif %endif #################################################################################################################################### 465.tonto=peak=default: OPTIMIZE= -unroll4 -auto -inline-calloc -opt-malloc-options=3 470.lbm=peak=default: basepeak=yes 481.wrf=peak=default: basepeak=yes 482.sphinx3=peak=default: basepeak=yes ################################################################# # (Edit this to match your system) ################################################################# default=default=default=default: license_num = 4 test_sponsor = SGI hw_avail = Sep-2015 sw_avail = Nov-2015 tester = SGI hw_cpu_name = Intel Xeon E7-8890 v3 hw_cpu_char = Intel Turbo Boost Technology up to 3.30 GHz hw_cpu_mhz = 2500 hw_disk = 8 TB tmpfs hw_fpu = Integrated hw_memory000 = 8 TB (256 x 32 GB 2Rx4 PC4-2133P-R, hw_memory001 = running at 1600 MHz) hw_model = SGI UV 300 (Intel Xeon E7-8890 v3, 2.5 GHz) hw_ncpuorder = 4-64 chips hw_ncores = 288 hw_nchips = 16 hw_ncoresperchip = 18 hw_nthreadspercore = 2 hw_other = None hw_pcache = 32 KB I + 32 KB D on chip per core hw_scache = 256 KB I+D on chip per core hw_tcache = 45 MB I+D on chip per chip hw_ocache = None hw_vendor = SGI prepared_by = Dave Raddatz sw_file = tmpfs sw_os000 = SUSE Linux Enterprise Server 11 (x86_64) SP4, sw_os001 = Kernel 3.0.101-65.1.9552.0.PTF-default sw_state = Run level 3 (multi-user) notes_submit_000 = The numactl mechanism was used to bind copies to processors. The config file option 'submit' notes_submit_005 = was used to generate numactl commands to bind each copy to a specific processor. notes_submit_010 = For details, please see the config file. %ifdef %{no-numa} notes_submit_000 = The taskset mechanism was used to bind copies to processors. The config file option 'submit' notes_submit_001 = was used to generate taskset commands to bind each copy to a specific processor. notes_submit_002 = For details, please see the config file. %endif #notes_001 = Binaries compiled on a system with 32x Intel Xeon E7-8890 v3 CPU + 16TB #notes_002 = memory using SLES 11 SP4 notes_os_000 = Stack size set to unlimited using "ulimit -s unlimited" notes_os_005 = notes_os_010 = Tmpfs filesystem set up with: notes_os_015 = mkdir -p /mnt/shm/cpu2006-ic16 notes_os_020 = mount -t tmpfs -o size=8192G,rw tmpfs /mnt/shm/cpu2006-ic16 notes_os_025 = notes_os_030 = Turbo mode activated with: notes_os_035 = modprobe acpi_cpufreq notes_os_040 = cpupower frequency-set -u 3300MHz -d 3300MHz -g performance notes_plat_000 = BT Mode set to Auto-select int=default=default=default: sw_compiler000 = C/C++: Version 16.0.0.109 of Intel C++ Studio XE sw_compiler001 = for Linux sw_base_ptrsize = 32-bit sw_peak_ptrsize = 32/64-bit sw_other = Microquill SmartHeap V10.2 default: %ifdef %{THP_enabled} notes_015 = Transparent Huge Pages enabled with: notes_020 = echo always > /sys/kernel/mm/transparent_hugepage/enabled %endif %ifdef %{THP_disabled} notes_200 = Transparent Huge Pages disabled with: notes_201 = echo never > /sys/kernel/mm/transparent_hugepage/enabled %endif %ifdef %{drop_caches} notes_025 = Filesystem page cache cleared with: notes_030 = echo 1 > /proc/sys/vm/drop_caches %endif %ifdef %{invoke_with_interleave} notes_035 = runspec command invoked through numactl i.e.: notes_040 = numactl --interleave=all runspec %endif fp=default=default=default: sw_compiler001 = C/C++: Version 16.0.0.109 of Intel C++ Studio XE sw_compiler002 = for Linux; sw_compiler004 = Fortran: Version 16.0.0.109 of Intel Fortran sw_compiler005 = Studio XE for Linux sw_base_ptrsize = 32/64-bit sw_peak_ptrsize = 32/64-bit # The following settings were obtained by running 'specperl $[top]/config/sysinfo.rev6914 -f -p' default: # Sysinfo program /mnt/shm/cpu2006-ic16/config/sysinfo.rev6914 # $Rev: 6914 $ $Date:: 2014-06-25 #$ e3fbb8667b5a285932ceab81e28219e1 # running on uv300-or Mon Dec 21 08:26:53 2015 # # This section contains SUT (System Under Test) info as seen by # some common utilities. To remove or add to this section, see: # http://www.spec.org/cpu2006/Docs/config.html#sysinfo # # From /proc/cpuinfo # model name : Intel(R) Xeon(R) CPU E7-8890 v3 @ 2.50GHz # 16 "physical id"s (chips) # 576 "processors" # cores, siblings (Caution: counting these is hw and system dependent. The # following excerpts from /proc/cpuinfo might not be reliable. Use with # caution.) # cpu cores : 18 # siblings : 36 # physical 0: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 1: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 2: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 3: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 4: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 5: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 6: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 7: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 8: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 9: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 10: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 11: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 12: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 13: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 14: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # physical 15: cores 0 1 2 3 4 8 9 10 11 16 17 18 19 20 24 25 26 27 # cache size : 46080 KB # # From /proc/meminfo # MemTotal: 8207146788 kB # HugePages_Total: 0 # Hugepagesize: 2048 kB # # /usr/bin/lsb_release -d # SUSE Linux Enterprise Server 11 (x86_64) # # From /etc/*release* /etc/*version* # SuSE-release: # SUSE Linux Enterprise Server 11 (x86_64) # VERSION = 11 # PATCHLEVEL = 4 # os-release: # NAME="SLES" # VERSION="11.4" # VERSION_ID="11.4" # PRETTY_NAME="SUSE Linux Enterprise Server 11 SP4" # ID="sles" # ANSI_COLOR="0;32" # CPE_NAME="cpe:/o:suse:sles:11:4" # sgi-accelerate-release: SGI Accelerate 1.11, Build # 713r44.sles11sp4-1511252000 # sgi-foundation-release: SGI Foundation Software 2.13, Build # 713r44.sles11sp4-1511252000 # sgi-mpi-release: SGI MPI 1.11, Build 713r44.sles11sp4-1511252000 # sgi-release: SGI Performance Suite 1.11 # # uname -a: # Linux uv300-or 3.0.101-65.1.9552.0.PTF-default #1 SMP Mon Sep 7 19:21:52 UTC # 2015 (bef9feb) x86_64 x86_64 x86_64 GNU/Linux # # run-level 3 Dec 21 07:40 last=S # # SPEC is set to: /mnt/shm/cpu2006-ic16 # Filesystem Type Size Used Avail Use% Mounted on # tmpfs tmpfs 8.0T 2.0G 8.0T 1% /mnt/shm/cpu2006-ic16 # Additional information from dmidecode: # # Warning: Use caution when you interpret this section. The 'dmidecode' program # reads system data which is "intended to allow hardware to be accurately # determined", but the intent may not be met, as there are frequent changes to # hardware, firmware, and the "DMTF SMBIOS" standard. # # BIOS Silicon Graphics International Corp. SGI UV 300 series BIOS 09/24/2015 # Memory: # 256x Samsung M393A4K40BB0-CPB 32 GB 1600 MHz # # (End of data from sysinfo program) # hw_cpu_name = Intel Xeon E7-8890 v3 # hw_disk = 8.0 TB add more disk info here # hw_memory001 = 7826.945 GB fixme: If using DDR3, format is: # hw_memory002 = 'N GB (M x N GB nRxn PCn-nnnnnR-n, ECC)' # hw_nchips = 16 # prepared_by = root (is never output, only tags rawfile) # sw_file = tmpfs # sw_os001 = SUSE Linux Enterprise Server 11 (x86_64) # sw_os002 = 3.0.101-65.1.9552.0.PTF-default # sw_state = Run level 3 (add definition here) # The following section was added automatically, and contains settings that # did not appear in the original configuration file, but were added to the # raw file after the run. default: notes_000 =Environment variables set by runspec before the start of the run: notes_005 =LD_LIBRARY_PATH = "/mnt/shm/cpu2006-ic16/libs/32:/mnt/shm/cpu2006-ic16/libs/64:/mnt/shm/cpu2006-ic16/sh" notes_010 =