# Invocation command line: # /home/cpu2017/bin/harness/runcpu --nobuild --action validate --configfile amd_speed_aocc300_milan_B2.cfg --define cores=24 --tune all --output_format all --define intspeedaffinity --define drop_caches --nopower --runmode speed --size refspeed --nopower --runmode speed --tune base:peak --size refspeed intspeed # output_root was not used for this run ############################################################################ ################################################################################ # AMD AOCC 300 SPEC CPU2017 V1.1.5 Speed Configuration File for 64-bit Linux # # File name : amd_speed_aocc300_milan_B2.cfg # Creation Date : May 4, 2021 # CPU2017 Version : 1.1.8 # Supported benchmarks : All Speed benchmarks (intspeed, fpspeed) # Compiler name/version : AOCC 3.0.0 # Operating system version : OpenSUSE 15.2 # Supported OS's : Ubuntu 20.04, RHEL 8.3, SLES 15 SP2 # Hardware : AMD Milan, Rome, Naples (AMD64) # FP Base Pointer Size : 64-bit # FP Peak Pointer Size : 64-bit # INT Base Pointer Size : 64-bit # INT Peak Pointer Size : 64-bit # Auto Parallization : No # # Note: DO NOT EDIT THIS FILE, the only edits required to properly run these # binaries are made in the ini Python file. Please consult Readme.amd_speed_aocc300_milan_B2.txt # for a few uncommon exceptions which require edits to this file. # # Description: # # This binary package automates away many of the complexities necessary to set # up and run SPEC CPU2017 under optimized conditions on AMD Milan/Rome/Naples-based # server platforms within Linux (AMD64). # # The binary package was built specifically for AMD Milan/Rome/Naples microprocessors and # is not intended to run on other products. # # Please install the binary package by following the instructions in # "Readme.amd_speed_aocc300_milan_B2.txt" under the "How To Use the Binaries" section. # # The binary package is designed to work without alteration on two socket AMD # Milan/Rome/Naples-based servers with 64 cores per socket, SMT enabled and 1 TiB of DDR4 # memory distributed evenly among all 16 channels using 32 GiB DIMMs. # # To run the binary package on other Milan/Rome/Naples configurations, please review # "Readme.amd_speed_aocc300_milan_B2.txt". In general, Milan/Rome or Naples CPUs # should be autodetected with no action required by the user. # # In most cases, it should be unnecessary to edit "amd_speed_aocc300_milan_B2.cfg" or any # other file besides "ini_amd_speed_aocc300_milan_B2.py" where reporting fields # and run conditions are set. # # The run script automatically sets the optimal number of speed copies and binds # them appropriately. # # The run script and accompanying binary package are designed to work on Ubuntu # 20.04, RHEL 8.3 and SLES 15 SP2. # # Important! If you write your own run script, please set the stack size to # "unlimited" when executing this binary package. Failure to do so may cause # some benchmarks to overflow the stack. For example, to set stack size within # the bash shell, include the following line somewhere at the top of your run # script before the runcpu invocation: # # ulimit -s unlimited # # Modification of this config file should only be necessary if you intend to # rebuild the binaries. General instructions for rebuilding the binaries are # found in-line below. # ################################################################################ # Modifiable macros: ################################################################################ # Change the following line to true if you intend to REBUILD the binaries (AMD # does not support this). Valid values are "true" or "false" (no quotes). %define allow_build false # Only change these macros if you are rebuilding the binary package: %define compiler_name aocc300 %define binary_package_name amd_speed_%{compiler_name}_milan_B %define binary_package_revision 2 %define build_path /sppo/bin/cpu2017v115aocc3-b1/ %define flags_file_name %{compiler_name}-flags-B2.xml # To enable the platform file, be sure to uncomment the flagsurl02 header line # below. %define platform_file_name INVALID_platform_%{binary_package_name}.xml # You should never have to change binary_package_full_name: %define binary_package_full_name %{binary_package_name}%{binary_package_revision} ################################################################################ # Include file name ################################################################################ # The include file contains fields that are commonly changed. This file is auto- # generated based upon INI file settings and should not need user modification # for runs. %define inc_file_name %{binary_package_full_name}.inc ################################################################################ # Binary label extension and "allow_build"" switch ################################################################################ # Only modify the binary label extension if you plan to rebuild the binaries. %define ext %{binary_package_name} # If you plan to recompile these CPU2017 binaries, please choose a new extension # name (ext above) to avoid confusion with the current binary set on your system # under test, and to avoid confusion for SPEC submission reviewers. You will # also need to set "allow_build" to true below. Finally, you must modify the # Paths section below to point to your library locations if the paths are not # already set up in your build environment. ################################################################################ # Paths and Environment Variables # ** MODIFY AS NEEDED (modification should not be necessary for runs) ** ################################################################################ # Allow environment variables to be set before runs: preenv = 1 # Necessary to avoid gcc out-of-memory exceptions on certain SUTs: preENV_MALLOC_CONF = retain:true # OpenMP environment variables: preENV_OMP_SCHEDULE = static preENV_OMP_DYNAMIC = false preENV_OMP_STACKSIZE = 16G # Define the name of the directory that holds AMD library files: %define lib_dir %{binary_package_name}_lib %define build_lib_dir %{binary_package_name}_lib # Set the shared object library path for runs and builds: preENV_LD_LIBRARY_PATH = $[top]/%{lib_dir}/lib;$[top]/%{lib_dir}/lib32:%{ENV_LD_LIBRARY_PATH} # Define 32-bit library build paths: # Do not use $[top] with the 32-bit libraries because doing so will cause an # options checksum error triggering a xalanc recompile attempt on SUTs having # different file paths. # NOTE: no 32-bit libraries are currently needed with Speed. JEMALLOC_LIB32_PATH = %{build_path}%{build_lib_dir}/lib32 %if '%{allow_build}' eq 'false' # The include file is only needed for runs, but not for builds. # include: %{inc_file_name} # ----- Begin inclusion of 'amd_speed_aocc300_milan_B2.inc' ############################################################################ ################################################################################ ################################################################################ # File name: amd_speed_aocc300_milan_B2.inc # File generation code date: January 25, 2021 # File generation date/time: December 03, 2021 / 15:00:58 # # This file is automatically generated during a SPEC CPU2017 run. # # To modify inc file generation, please consult the readme file or the run # script. ################################################################################ ################################################################################ ################################################################################ ################################################################################ # The following macros are generated for use in the cfg file. ################################################################################ ################################################################################ %define logical_core_count 48 %define physical_core_count 48 %define physical_core_max 47 %define logical_core_max 47 ################################################################################ ################################################################################ # The following inc blocks set the speed thread counts and affinity settings. # # intspeed benchmarks: 600.perlbench_s,602.gcc_s,605.mcf_s,620.omnetpp_s, # 623.xalancbmk_s,625.x264_s,631.deepsjeng_s,641.leela_s,648.exchange2_s, # 657.xz_s # fpspeed benchmarks: 603.bwaves_s,607.cactuBSSN_s,619.lbm_s,621.wrf_s, # 627.cam4_s,628.pop2_s,638.imagick_s,644.nab_s,649.fotonik3d_s, # 654.roms_s # # Selected thread counts from default section of CPU info (nothing for 7643, epyc6n, 48p, or 48l) ################################################################################ # default preENV thread settings: default: preENV_OMP_THREAD_LIMIT = 48 preENV_GOMP_CPU_AFFINITY = 0-47 ################################################################################ ################################################################################ # intspeed base thread counts: intspeed=base: threads = 48 ENV_GOMP_CPU_AFFINITY = 0-47 bind0 = numactl --physcpubind=0-47 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # fpspeed base thread counts: fpspeed=base: threads = 48 ENV_GOMP_CPU_AFFINITY = 0-47 bind0 = numactl --physcpubind=0-47 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 1 600.perlbench_s,602.gcc_s,605.mcf_s,620.omnetpp_s,623.xalancbmk_s,625.x264_s,631.deepsjeng_s,641.leela_s,648.exchange2_s=peak: threads = 1 ENV_GOMP_CPU_AFFINITY = 0 bind0 = numactl --physcpubind=0 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 48 603.bwaves_s,619.lbm_s,627.cam4_s,638.imagick_s,644.nab_s=peak: threads = 48 ENV_GOMP_CPU_AFFINITY = 0 24 1 25 2 26 3 27 4 28 5 29 6 30 7 31 8 32 9 33 10 34 11 35 12 36 13 37 14 38 15 39 16 40 17 41 18 42 19 43 20 44 21 45 22 46 23 47 bind0 = numactl --physcpubind=0-47 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 48 607.cactuBSSN_s,621.wrf_s,628.pop2_s,649.fotonik3d_s,654.roms_s,657.xz_s=peak: threads = 48 ENV_GOMP_CPU_AFFINITY = 0-47 bind0 = numactl --physcpubind=0-47 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ ################################################################################ # Switch back to default: default: ################################################################################ ################################################################################ ################################################################################ # The remainder of this file defines CPU2017 report parameters. ################################################################################ ################################################################################ ################################################################################ # SPEC CPU 2017 report header ################################################################################ license_num =9019 tester =Cisco Systems test_sponsor =Cisco Systems hw_vendor =Cisco Systems hw_model000 =Cisco UCS C225 M6 (AMD EPYC 7643 48-Core) #--------- If you install new compilers, edit this section -------------------- sw_compiler =C/C++/Fortran: Version 3.0.0 of AOCC ################################################################################ ################################################################################ # Hardware, firmware and software information ################################################################################ hw_avail =Jun-2021 sw_avail =Jun-2021 hw_cpu_name =AMD EPYC 7643 hw_cpu_nominal_mhz =2300 hw_cpu_max_mhz =3600 hw_ncores =48 hw_nthreadspercore =1 hw_ncpuorder =1 chips hw_other =None # Other perf-relevant hw, or "None" fw_bios =Version 4.2.1c released Aug-2021 sw_base_ptrsize =64-bit sw_peak_ptrsize = 64-bit hw_pcache =32 KB I + 32 KB D on chip per core hw_scache =512 KB I+D on chip per core hw_tcache000 =256 MB I+D on chip per chip, hw_tcache001 = 32 MB shared / 6 cores hw_ocache =None ################################################################################ # Notes ################################################################################ # Enter notes_000 through notes_100 here. notes_000 =Binaries were compiled on a system with 2x AMD EPYC 7742 CPU + 1TiB Memory using openSUSE 15.2 notes_005 = notes_010 =NA: The test sponsor attests, as of date of publication, that CVE-2017-5754 (Meltdown) notes_015 =is mitigated in the system as tested and documented. notes_020 =Yes: The test sponsor attests, as of date of publication, that CVE-2017-5753 (Spectre variant 1) notes_025 =is mitigated in the system as tested and documented. notes_030 =Yes: The test sponsor attests, as of date of publication, that CVE-2017-5715 (Spectre variant 2) notes_035 =is mitigated in the system as tested and documented. notes_040 = notes_submit_000 ='numactl' was used to bind copies to the cores. notes_submit_005 =See the configuration file for details. notes_os_000 ='ulimit -s unlimited' was used to set environment stack size limit notes_os_005 ='ulimit -l 2097152' was used to set environment locked pages in memory limit notes_os_010 = notes_os_015 =runcpu command invoked through numactl i.e.: notes_os_020 =numactl --interleave=all runcpu notes_os_025 = notes_os_030 =To limit dirty cache to 8% of memory, 'sysctl -w vm.dirty_ratio=8' run as root. notes_os_035 =To limit swap usage to minimum necessary, 'sysctl -w vm.swappiness=1' run as root. notes_os_040 =To free node-local memory and avoid remote memory usage, notes_os_045 ='sysctl -w vm.zone_reclaim_mode=1' run as root. notes_os_050 =To clear filesystem caches, 'sync; sysctl -w vm.drop_caches=3' run as root. notes_os_055 =To disable address space layout randomization (ASLR) to reduce run-to-run notes_os_060 =variability, 'sysctl -w kernel.randomize_va_space=0' run as root. notes_os_065 = notes_os_thp_000 =To enable Transparent Hugepages (THP) for all allocations, notes_os_thp_005 ='echo always > /sys/kernel/mm/transparent_hugepage/enabled' and notes_os_thp_010 ='echo always > /sys/kernel/mm/transparent_hugepage/defrag' run as root. notes_comp_000 =The AMD64 AOCC Compiler Suite is available at notes_comp_005 =http://developer.amd.com/amd-aocc/ notes_comp_010 = notes_jemalloc_000 =jemalloc: configured and built with GCC v4.8.2 in RHEL 7.4 (No options specified) notes_jemalloc_005 =jemalloc 5.1.0 is available here: notes_jemalloc_010 =https://github.com/jemalloc/jemalloc/releases/download/5.1.0/jemalloc-5.1.0.tar.bz2 sw_other =jemalloc: jemalloc memory allocator library v5.1.0 ################################################################################ # The following note fields describe platorm settings. ################################################################################ # example: (uncomment as necessary) # notes_plat_000 =BIOS settings: # notes_plat_002 = cTDP: 280 # notes_plat_004 = Determinism Slider set to Power # notes_plat_006 = Package Power: 280 # notes_plat_008 = EDC: 300 # notes_plat_010 = NPS: 1 # notes_plat_014 = 4-link xGMI max speed: 16Gbps # notes_plat_015 = Fan Speed: Maximum ################################################################################ # The following are custom fields: ################################################################################ # Use custom_fields to enter lines that are not listed here. For example: # notes_plat_100 = Energy Bias set to Max Performance # new_field = Ambient temperature set to 10C ################################################################################ # The following fields must be set here for only Int benchmarks. ################################################################################ intrate: sw_peak_ptrsize =64-bit notes_os_thp_003 = ################################################################################ # The following fields must be set here for FP benchmarks. ################################################################################ fprate: sw_peak_ptrsize =64-bit notes_os_thp_003 =To enable THP only on request for peak runs of 628.pop2_s, and 638.imagick_s, notes_os_thp_004 ='echo madvise > /sys/kernel/mm/transparent_hugepage/enabled' run as root. notes_os_thp_005 =To disable THP for peak runs of 627.cam4_s, 644.nab_s, 649.fotonik3d_s, and 654.roms_s, notes_os_thp_006 ='echo never > /sys/kernel/mm/transparent_hugepage/enabled' run as root. notes_os_thp_007 = ################################################################################ # The following fields must be set here or they will be overwritten by sysinfo. ################################################################################ intrate,fprate: hw_disk =unknown hw_memory000 =1 TB (16 x 64 GB 4Rx4 PC4-3200V-L) hw_memory001 =running at 2933 hw_memory002 = hw_nchips =1 prepared_by =prepared by unknown sw_file =unknown file sw_os000 =unknown os000 sw_os001 =kernel version # ex: Kernel 4.4.0-87-generic sw_state =Run level 3 (multi-user) ################################################################################ # End of inc file ################################################################################ # Switch back to the default block after the include file: default: # ---- End inclusion of '/home/cpu2017/config/amd_speed_aocc300_milan_B2.inc' # Switch back to default block after the include file: default: fail_build = 1 %elif '%{allow_build}' eq 'true' # If you intend to rebuild, be sure to set the library paths either in the # build script or here: preENV_LIBRARY_PATH = $[top]/%{build_lib_dir}/lib;$[top]/%{build_lib_dir}/lib32:%{ENV_LIBRARY_PATH} % define build_ncpus 64 # controls number of simultaneous compiles fail_build = 0 makeflags = --jobs=%{build_ncpus} --load-average=%{build_ncpus} %else % error The value of "allow_build" is %{allow_build}, but it can only be "true" or "false". This error was generated %endif ################################################################################ # Enable automated data collection per benchmark ################################################################################ # Data collection is not enabled for reportable runs. # teeout is necessary to get data collection stdout into the logs. Best # practices for the individual data collection items would be to have # them store important output in separate files. Filenames could be # constructed from $SPEC (environment), $lognum (result number from runcpu), # and benchmark name/number. teeout = yes # Run runcpu with '-v 35' (or greater) to log lists of variables which can # be used in substitutions as below. # For CPU2006, change $label to $ext %define data-collection-parameters benchname='$name' benchnum='$num' benchmark='$benchmark' iteration=$iter size='$size' tune='$tune' label='$label' log='$log' lognum='$lognum' from_runcpu='$from_runcpu' %define data-collection-start $[top]/data-collection/data-collection start %{data-collection-parameters} %define data-collection-stop $[top]/data-collection/data-collection stop %{data-collection-parameters} monitor_specrun_wrapper = %{data-collection-start} ; $command ; %{data-collection-stop} ################################################################################ # Header settings ################################################################################ backup_config = 0 # set to 0 if you do not want backup files bench_post_setup = sync # command_add_redirect: If set, the generated ${command} will include # redirection operators (stdout, stderr), which are passed along to the shell # that executes the command. If this variable is not set, specinvoke does the # redirection. command_add_redirect = yes env_vars = yes flagsurl000 = http://www.spec.org/cpu2017/flags/aocc300-flags-B2.xml flagsurl001 = http://www.spec.org/cpu2017/flags/Cisco-Platform-Settings-AMD-v2-revC.xml #flagsurl02 = $[top]/%{platform_file_name} # label: User defined extension string that tags your binaries & directories: label = %{ext} line_width = 1020 log_line_width = 1020 mean_anyway = yes output_format = all reportable = yes size = test,train,ref teeout = yes teerunout = yes tune = base,peak use_submit_for_speed = yes ################################################################################ # Compilers ################################################################################ default: CROSSPLAT_PORT_OPTS = -mno-adx -mno-sse4a CC = clang -m64 $[CROSSPLAT_PORT_OPTS] CXX = clang++ -m64 -std=c++98 $[CROSSPLAT_PORT_OPTS] FC = flang -m64 $[CROSSPLAT_PORT_OPTS] CLD = clang -m64 CXXLD = clang++ -m64 FLD = flang -m64 CC_VERSION_OPTION = --version CXX_VERSION_OPTION = --version FC_VERSION_OPTION = --version ################################################################################ # Portability Flags ################################################################################ default:# data model applies to all benchmarks ################################################################################ # Default Flags ################################################################################ EXTRA_LIBS = -fopenmp=libomp -lomp -ljemalloc -lamdlibm -lm MATHLIBOPT = #clearing this variable or else SPEC will set it to -lm VECMATHLIB = -fveclib=AMDLIBM OPT_ROOT = -march=znver3 $(VECMATHLIB) -ffast-math OPT_ROOT_BASE = -O3 $(OPT_ROOT) OPT_ROOT_PEAK = -Ofast $(OPT_ROOT) -flto ################################################################################ # Portability Flags ################################################################################ default: EXTRA_PORTABILITY = -DSPEC_LP64 # *** Benchmark-specific portability *** # Anything other than the data model is only allowed where a need is proven. # (ordered by last 2 digits of benchmark number) 600.perlbench_s: #lang='C' PORTABILITY = -DSPEC_LINUX_X64 621.wrf_s: #lang='F,C' CPORTABILITY = -DSPEC_CASE_FLAG FPORTABILITY = -Mbyteswapio 623.xalancbmk_s: #lang='CXX' PORTABILITY = -DSPEC_LINUX 627.cam4_s: #lang='F,C' PORTABILITY = -DSPEC_CASE_FLAG 628.pop2_s: #lang='F,C' CPORTABILITY = -DSPEC_CASE_FLAG FPORTABILITY = -Mbyteswapio ################################################################################ # Tuning Flags ################################################################################ ##################### # Base tuning flags # ##################### default=base: COPTIMIZE = $(OPT_ROOT_BASE) -flto -fstruct-layout=5 \ -mllvm -unroll-threshold=50 \ -mllvm -inline-threshold=1000 -fremap-arrays \ -mllvm -function-specialize -flv-function-specialization \ -mllvm -enable-gvn-hoist \ -mllvm -global-vectorize-slp=true \ -mllvm -enable-licm-vrp \ -mllvm -reduce-array-computations=3 \ -Wno-unused-command-line-argument CXXOPTIMIZE = $(OPT_ROOT_BASE) -flto \ -mllvm -enable-partial-unswitch \ -mllvm -unroll-threshold=100 \ -finline-aggressive -flv-function-specialization \ -mllvm -loop-unswitch-threshold=200000 \ -mllvm -reroll-loops \ -mllvm -aggressive-loop-unswitch \ -mllvm -extra-vectorizer-passes \ -mllvm -reduce-array-computations=3 \ -mllvm -global-vectorize-slp=true \ -Wno-unused-command-line-argument \ -mllvm -convert-pow-exp-to-int=false FOPTIMIZE = -Hz,1,0x1 $(OPT_ROOT_BASE) -Mrecursive \ -mllvm -fuse-tile-inner-loop -funroll-loops \ -mllvm -extra-vectorizer-passes \ -mllvm -lsr-in-nested-loop \ -mllvm -enable-licm-vrp \ -mllvm -reduce-array-computations=3 \ -mllvm -global-vectorize-slp=true \ -Wno-unused-command-line-argument LDCXXFLAGS = -Wl,-mllvm -Wl,-x86-use-vzeroupper=false EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-region-vectorize \ -Wl,-mllvm -Wl,-function-specialize \ -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 LDFFLAGS = -Wl,-mllvm -Wl,-enable-X86-prefetching \ -Wl,-mllvm -Wl,-enable-licm-vrp #other libraries # Put OpenMP and math libraries here: # -lm needed at the end for some transcendental functions: EXTRA_LIBS = -fopenmp=libomp -lomp -lamdlibm -ljemalloc -lflang -lflangrti -lm EXTRA_FLIBS = # Don't put the AMD and mvec math libraries in MATHLIBOPT because it will trigger a reporting issue # because GCC won't use them. Forcefeed all benchmarks the math libraries in EXTRA_LIBS and clear # out MATHLIBOPT. MATHLIBOPT = # The following is necessary for 502/602 gcc: LDOPTIMIZE = -z muldefs # The following is necessary for 502/602 gcc: EXTRA_OPTIMIZE = -DSPEC_OPENMP -fopenmp -Wno-return-type ######################## # intspeed tuning flags # ######################## intspeed: FOPTIMIZE = $(OPT_ROOT_BASE) -flto EXTRA_FFLAGS = -mllvm -unroll-aggressive \ -mllvm -unroll-threshold=150 EXTRA_CXXFLAGS = -mllvm -do-block-reorder=aggressive \ -fvirtual-function-elimination -fvisibility=hidden LDCFLAGS = -Wl,-allow-multiple-definition -Wl,-mllvm \ -Wl,-enable-licm-vrp LDCXXFLAGS = -Wl,-mllvm -Wl,-do-block-reorder=aggressive LDFFLAGS = -Wl,-mllvm -Wl,-inline-recursion=4 \ -Wl,-mllvm -Wl,-lsr-in-nested-loop \ -Wl,-mllvm -Wl,-enable-iv-split intspeed=base: submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command intspeed=peak: submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ######################## # fpspeed tuning flags # ######################## fpspeed: CXX = clang++ -m64 -std=c++98 $[CROSSPLAT_PORT_OPTS] fpspeed=base: submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command fpspeed=peak: submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ##################### # Peak tuning flags # ##################### default=peak: COPTIMIZE = $(OPT_ROOT_PEAK) -fstruct-layout=5 \ -mllvm -unroll-threshold=50 -fremap-arrays \ -flv-function-specialization -mllvm \ -inline-threshold=1000 -mllvm -enable-gvn-hoist \ -mllvm -global-vectorize-slp=true -mllvm \ -function-specialize -mllvm -enable-licm-vrp \ -mllvm -reduce-array-computations=3 \ -Wno-unused-command-line-argument CXXOPTIMIZE = $(OPT_ROOT_PEAK) -finline-aggressive \ -mllvm -unroll-threshold=100 \ -flv-function-specialization -mllvm -enable-licm-vrp \ -mllvm -reroll-loops -mllvm \ -aggressive-loop-unswitch -mllvm \ -reduce-array-computations=3 -mllvm \ -global-vectorize-slp=true \ -Wno-unused-command-line-argument FOPTIMIZE = $(OPT_ROOT_PEAK) -Mrecursive \ -mllvm -reduce-array-computations=3 \ -mllvm -global-vectorize-slp=true \ -mllvm -enable-licm-vrp \ -Wno-unused-command-line-argument EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-function-specialize \ -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 LDFFLAGS = -Wl,-mllvm -Wl,-enable-X86-prefetching \ -Wl,-mllvm -Wl,-enable-licm-vrp LDCXXFLAGS = -Wl,-mllvm -Wl,-x86-use-vzeroupper=false \ -Wl,-mllvm -Wl,-enable-licm-vrp EXTRA_LIBS = -fopenmp=libomp -lomp -lamdlibm -ljemalloc -lflang -lm EXTRA_OPTIMIZE = -DSPEC_OPENMP -fopenmp -Wno-return-type feedback = 0 PASS1_CFLAGS = -fprofile-instr-generate PASS2_CFLAGS = -fprofile-instr-use PASS1_FFLAGS = -fprofile-generate PASS2_FFLAGS = -fprofile-use PASS1_CXXFLAGS = -fprofile-instr-generate PASS2_CXXFLAGS = -fprofile-instr-use PASS1_LDFLAGS = -fprofile-instr-generate PASS2_LDFLAGS = -fprofile-instr-use fdo_run1 = $command ; llvm-profdata merge --output=default.profdata *.profraw # Int benchmark specific peak tuning flags: # FP benchmark specific peak tuning flags: 603.bwaves_s=peak: FOPTIMIZE = -Ofast $(OPT_ROOT) -Mrecursive \ -mllvm -reduce-array-computations=3 \ -mllvm -global-vectorize-slp=true \ -mllvm -enable-licm-vrp \ -Wno-unused-command-line-argument submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command 607.cactuBSSN_s=peak: submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command 621.wrf_s=peak: FOPTIMIZE = -Hz,1,0x1 $(OPT_ROOT_BASE) -Mrecursive \ -mllvm -fuse-tile-inner-loop -funroll-loops \ -mllvm -extra-vectorizer-passes \ -mllvm -lsr-in-nested-loop \ -mllvm -enable-licm-vrp \ -mllvm -reduce-array-computations=3 \ -mllvm -global-vectorize-slp=true \ -Wno-unused-command-line-argument submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; numactl --interleave=all --physcpubind=0-%{physical_core_max} $command 627.cam4_s=peak: submit = echo never > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command 628.pop2_s=peak: FOPTIMIZE = $(OPT_ROOT) -Ofast -Mrecursive \ -mllvm -reduce-array-computations=3 \ -mllvm -global-vectorize-slp=true \ -mllvm -enable-licm-vrp \ -Wno-unused-command-line-argument submit = echo madvise > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command 638.imagick_s=peak: submit = echo madvise > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command 644.nab_s=peak: EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-region-vectorize \ -Wl,-mllvm -Wl,-function-specialize submit = echo never > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command 649.fotonik3d_s=peak: ENV_PGHPF_ZMEM =yes submit = echo never > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command 654.roms_s=peak: FOPTIMIZE = -Ofast $(OPT_ROOT) -Mrecursive \ -mllvm -reduce-array-computations=3 \ -mllvm -global-vectorize-slp=true \ -mllvm -enable-licm-vrp \ -Wno-unused-command-line-argument submit = echo never > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command # The following settings were obtained by running the sysinfo_program # 'specperl $[top]/bin/sysinfo' (sysinfo:SHA:679c83684f6f4fc369a093999b6661d0a378911de2a006d3245423ad80d3fb9a) default: notes_plat_sysinfo_000 = notes_plat_sysinfo_005 = Sysinfo program /home/cpu2017/bin/sysinfo notes_plat_sysinfo_010 = Rev: r6622 of 2021-04-07 982a61ec0915b55891ef0e16acafc64d notes_plat_sysinfo_015 = running on localhost Fri Dec 3 18:47:10 2021 notes_plat_sysinfo_020 = notes_plat_sysinfo_025 = SUT (System Under Test) info as seen by some common utilities. notes_plat_sysinfo_030 = For more information on this section, see notes_plat_sysinfo_035 = https://www.spec.org/cpu2017/Docs/config.html#sysinfo notes_plat_sysinfo_040 = notes_plat_sysinfo_045 = From /proc/cpuinfo notes_plat_sysinfo_050 = model name : AMD EPYC 7643 48-Core Processor notes_plat_sysinfo_055 = 1 "physical id"s (chips) notes_plat_sysinfo_060 = 48 "processors" notes_plat_sysinfo_065 = cores, siblings (Caution: counting these is hw and system dependent. The following notes_plat_sysinfo_070 = excerpts from /proc/cpuinfo might not be reliable. Use with caution.) notes_plat_sysinfo_075 = cpu cores : 48 notes_plat_sysinfo_080 = siblings : 48 notes_plat_sysinfo_085 = physical 0: cores 0 1 2 3 4 5 8 9 10 11 12 13 16 17 18 19 20 21 24 25 26 27 28 29 notes_plat_sysinfo_090 = 32 33 34 35 36 37 40 41 42 43 44 45 48 49 50 51 52 53 56 57 58 59 60 61 notes_plat_sysinfo_095 = notes_plat_sysinfo_100 = From lscpu from util-linux 2.36.2: notes_plat_sysinfo_105 = Architecture: x86_64 notes_plat_sysinfo_110 = CPU op-mode(s): 32-bit, 64-bit notes_plat_sysinfo_115 = Byte Order: Little Endian notes_plat_sysinfo_120 = Address sizes: 48 bits physical, 48 bits virtual notes_plat_sysinfo_125 = CPU(s): 48 notes_plat_sysinfo_130 = On-line CPU(s) list: 0-47 notes_plat_sysinfo_135 = Thread(s) per core: 1 notes_plat_sysinfo_140 = Core(s) per socket: 48 notes_plat_sysinfo_145 = Socket(s): 1 notes_plat_sysinfo_150 = NUMA node(s): 8 notes_plat_sysinfo_155 = Vendor ID: AuthenticAMD notes_plat_sysinfo_160 = CPU family: 25 notes_plat_sysinfo_165 = Model: 1 notes_plat_sysinfo_170 = Model name: AMD EPYC 7643 48-Core Processor notes_plat_sysinfo_175 = Stepping: 1 notes_plat_sysinfo_180 = Frequency boost: enabled notes_plat_sysinfo_185 = CPU MHz: 1496.431 notes_plat_sysinfo_190 = CPU max MHz: 2300.0000 notes_plat_sysinfo_195 = CPU min MHz: 1500.0000 notes_plat_sysinfo_200 = BogoMIPS: 4591.26 notes_plat_sysinfo_205 = Virtualization: AMD-V notes_plat_sysinfo_210 = L1d cache: 1.5 MiB notes_plat_sysinfo_215 = L1i cache: 1.5 MiB notes_plat_sysinfo_220 = L2 cache: 24 MiB notes_plat_sysinfo_225 = L3 cache: 256 MiB notes_plat_sysinfo_230 = NUMA node0 CPU(s): 0-5 notes_plat_sysinfo_235 = NUMA node1 CPU(s): 6-11 notes_plat_sysinfo_240 = NUMA node2 CPU(s): 12-17 notes_plat_sysinfo_245 = NUMA node3 CPU(s): 18-23 notes_plat_sysinfo_250 = NUMA node4 CPU(s): 24-29 notes_plat_sysinfo_255 = NUMA node5 CPU(s): 30-35 notes_plat_sysinfo_260 = NUMA node6 CPU(s): 36-41 notes_plat_sysinfo_265 = NUMA node7 CPU(s): 42-47 notes_plat_sysinfo_270 = Vulnerability Itlb multihit: Not affected notes_plat_sysinfo_275 = Vulnerability L1tf: Not affected notes_plat_sysinfo_280 = Vulnerability Mds: Not affected notes_plat_sysinfo_285 = Vulnerability Meltdown: Not affected notes_plat_sysinfo_290 = Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via notes_plat_sysinfo_295 = prctl and seccomp notes_plat_sysinfo_300 = Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user notes_plat_sysinfo_305 = pointer sanitization notes_plat_sysinfo_310 = Vulnerability Spectre v2: Mitigation; Full AMD retpoline, IBPB conditional, notes_plat_sysinfo_315 = IBRS_FW, STIBP disabled, RSB filling notes_plat_sysinfo_320 = Vulnerability Srbds: Not affected notes_plat_sysinfo_325 = Vulnerability Tsx async abort: Not affected notes_plat_sysinfo_330 = Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr notes_plat_sysinfo_335 = pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt notes_plat_sysinfo_340 = pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid notes_plat_sysinfo_345 = aperfmperf pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes notes_plat_sysinfo_350 = xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a notes_plat_sysinfo_355 = misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb notes_plat_sysinfo_360 = bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs notes_plat_sysinfo_365 = ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid cqm rdt_a rdseed adx smap notes_plat_sysinfo_370 = clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc notes_plat_sysinfo_375 = cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd amd_ppin arat npt lbrv notes_plat_sysinfo_380 = svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter notes_plat_sysinfo_385 = pfthreshold v_vmsave_vmload vgif umip pku ospke vaes vpclmulqdq rdpid overflow_recov notes_plat_sysinfo_390 = succor smca notes_plat_sysinfo_395 = notes_plat_sysinfo_400 = From lscpu --cache: notes_plat_sysinfo_405 = NAME ONE-SIZE ALL-SIZE WAYS TYPE LEVEL SETS PHY-LINE COHERENCY-SIZE notes_plat_sysinfo_410 = L1d 32K 1.5M 8 Data 1 64 1 64 notes_plat_sysinfo_415 = L1i 32K 1.5M 8 Instruction 1 64 1 64 notes_plat_sysinfo_420 = L2 512K 24M 8 Unified 2 1024 1 64 notes_plat_sysinfo_425 = L3 32M 256M 16 Unified 3 32768 1 64 notes_plat_sysinfo_430 = notes_plat_sysinfo_435 = /proc/cpuinfo cache data notes_plat_sysinfo_440 = cache size : 512 KB notes_plat_sysinfo_445 = notes_plat_sysinfo_450 = From numactl --hardware notes_plat_sysinfo_455 = WARNING: a numactl 'node' might or might not correspond to a physical chip. notes_plat_sysinfo_460 = available: 8 nodes (0-7) notes_plat_sysinfo_465 = node 0 cpus: 0 1 2 3 4 5 notes_plat_sysinfo_470 = node 0 size: 128838 MB notes_plat_sysinfo_475 = node 0 free: 125995 MB notes_plat_sysinfo_480 = node 1 cpus: 6 7 8 9 10 11 notes_plat_sysinfo_485 = node 1 size: 129022 MB notes_plat_sysinfo_490 = node 1 free: 128817 MB notes_plat_sysinfo_495 = node 2 cpus: 12 13 14 15 16 17 notes_plat_sysinfo_500 = node 2 size: 129022 MB notes_plat_sysinfo_505 = node 2 free: 128342 MB notes_plat_sysinfo_510 = node 3 cpus: 18 19 20 21 22 23 notes_plat_sysinfo_515 = node 3 size: 129022 MB notes_plat_sysinfo_520 = node 3 free: 128453 MB notes_plat_sysinfo_525 = node 4 cpus: 24 25 26 27 28 29 notes_plat_sysinfo_530 = node 4 size: 128988 MB notes_plat_sysinfo_535 = node 4 free: 128631 MB notes_plat_sysinfo_540 = node 5 cpus: 30 31 32 33 34 35 notes_plat_sysinfo_545 = node 5 size: 129022 MB notes_plat_sysinfo_550 = node 5 free: 128477 MB notes_plat_sysinfo_555 = node 6 cpus: 36 37 38 39 40 41 notes_plat_sysinfo_560 = node 6 size: 129022 MB notes_plat_sysinfo_565 = node 6 free: 127919 MB notes_plat_sysinfo_570 = node 7 cpus: 42 43 44 45 46 47 notes_plat_sysinfo_575 = node 7 size: 116908 MB notes_plat_sysinfo_580 = node 7 free: 114897 MB notes_plat_sysinfo_585 = node distances: notes_plat_sysinfo_590 = node 0 1 2 3 4 5 6 7 notes_plat_sysinfo_595 = 0: 10 11 11 11 11 11 11 11 notes_plat_sysinfo_600 = 1: 11 10 11 11 11 11 11 11 notes_plat_sysinfo_605 = 2: 11 11 10 11 11 11 11 11 notes_plat_sysinfo_610 = 3: 11 11 11 10 11 11 11 11 notes_plat_sysinfo_615 = 4: 11 11 11 11 10 11 11 11 notes_plat_sysinfo_620 = 5: 11 11 11 11 11 10 11 11 notes_plat_sysinfo_625 = 6: 11 11 11 11 11 11 10 11 notes_plat_sysinfo_630 = 7: 11 11 11 11 11 11 11 10 notes_plat_sysinfo_635 = notes_plat_sysinfo_640 = From /proc/meminfo notes_plat_sysinfo_645 = MemTotal: 1044322708 kB notes_plat_sysinfo_650 = HugePages_Total: 0 notes_plat_sysinfo_655 = Hugepagesize: 2048 kB notes_plat_sysinfo_660 = notes_plat_sysinfo_665 = /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor has notes_plat_sysinfo_670 = ondemand notes_plat_sysinfo_675 = notes_plat_sysinfo_680 = From /etc/*release* /etc/*version* notes_plat_sysinfo_685 = os-release: notes_plat_sysinfo_690 = NAME="SLES" notes_plat_sysinfo_695 = VERSION="15-SP3" notes_plat_sysinfo_700 = VERSION_ID="15.3" notes_plat_sysinfo_705 = PRETTY_NAME="SUSE Linux Enterprise Server 15 SP3" notes_plat_sysinfo_710 = ID="sles" notes_plat_sysinfo_715 = ID_LIKE="suse" notes_plat_sysinfo_720 = ANSI_COLOR="0;32" notes_plat_sysinfo_725 = CPE_NAME="cpe:/o:suse:sles:15:sp3" notes_plat_sysinfo_730 = notes_plat_sysinfo_735 = uname -a: notes_plat_sysinfo_740 = Linux localhost 5.3.18-57-default #1 SMP Wed Apr 28 10:54:41 UTC 2021 (ba3c2e9) x86_64 notes_plat_sysinfo_745 = x86_64 x86_64 GNU/Linux notes_plat_sysinfo_750 = notes_plat_sysinfo_755 = Kernel self-reported vulnerability status: notes_plat_sysinfo_760 = notes_plat_sysinfo_765 = CVE-2018-12207 (iTLB Multihit): Not affected notes_plat_sysinfo_770 = CVE-2018-3620 (L1 Terminal Fault): Not affected notes_plat_sysinfo_775 = Microarchitectural Data Sampling: Not affected notes_plat_sysinfo_780 = CVE-2017-5754 (Meltdown): Not affected notes_plat_sysinfo_785 = CVE-2018-3639 (Speculative Store Bypass): Mitigation: Speculative Store notes_plat_sysinfo_790 = Bypass disabled via prctl and notes_plat_sysinfo_795 = seccomp notes_plat_sysinfo_800 = CVE-2017-5753 (Spectre variant 1): Mitigation: usercopy/swapgs notes_plat_sysinfo_805 = barriers and __user pointer notes_plat_sysinfo_810 = sanitization notes_plat_sysinfo_815 = CVE-2017-5715 (Spectre variant 2): Mitigation: Full AMD retpoline, notes_plat_sysinfo_820 = IBPB: conditional, IBRS_FW, STIBP: notes_plat_sysinfo_825 = disabled, RSB filling notes_plat_sysinfo_830 = CVE-2020-0543 (Special Register Buffer Data Sampling): Not affected notes_plat_sysinfo_835 = CVE-2019-11135 (TSX Asynchronous Abort): Not affected notes_plat_sysinfo_840 = notes_plat_sysinfo_845 = run-level 3 Dec 3 15:03 notes_plat_sysinfo_850 = notes_plat_sysinfo_855 = SPEC is set to: /home/cpu2017 notes_plat_sysinfo_860 = Filesystem Type Size Used Avail Use% Mounted on notes_plat_sysinfo_865 = /dev/nvme0n1p3 xfs 1.5T 18G 1.5T 2% / notes_plat_sysinfo_870 = notes_plat_sysinfo_875 = From /sys/devices/virtual/dmi/id notes_plat_sysinfo_880 = Vendor: Cisco Systems Inc notes_plat_sysinfo_885 = Product: UCSC-C225-M6N notes_plat_sysinfo_890 = Serial: WZP25230TMY notes_plat_sysinfo_895 = notes_plat_sysinfo_900 = Additional information from dmidecode 3.2 follows. WARNING: Use caution when you notes_plat_sysinfo_905 = interpret this section. The 'dmidecode' program reads system data which is "intended to notes_plat_sysinfo_910 = allow hardware to be accurately determined", but the intent may not be met, as there are notes_plat_sysinfo_915 = frequent changes to hardware, firmware, and the "DMTF SMBIOS" standard. notes_plat_sysinfo_920 = Memory: notes_plat_sysinfo_925 = 8x 0xCE00 M386AAG40AM3-CWE 128 GB 4 rank 3200 notes_plat_sysinfo_930 = notes_plat_sysinfo_935 = BIOS: notes_plat_sysinfo_940 = BIOS Vendor: Cisco Systems, Inc. notes_plat_sysinfo_945 = BIOS Version: C225M6.4.2.1c.0.0806211349 notes_plat_sysinfo_950 = BIOS Date: 08/06/2021 notes_plat_sysinfo_955 = BIOS Revision: 5.22 notes_plat_sysinfo_960 = notes_plat_sysinfo_965 = (End of data from sysinfo program) hw_cpu_name = AMD EPYC 7643 hw_disk = 1 x 1.6 TB SSD SATA hw_memory000 = 1 TB (8 x 128 GB 4Rx4 PC4-3200V-L) hw_nchips = 1 prepared_by = Cisco Systems sw_file = xfs sw_os000 = SUSE Linux Enterprise Server 15 SP3 (x86_64) sw_os001 = 5.3.18-57-default sw_state = Run level 3 (multi-user) # End of settings added by sysinfo_program 657.xz_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 # 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: power_management000 = BIOS and OS set to prefer performance at the cost power_management001 = of additional power usage notes_plat_000 = SMT Mode set to Disabled notes_plat_005 = NUMA nodes per socket set to NPS1 notes_plat_010 = ACPI SRAT L3 Cache As NUMA Domain set to Enabled notes_plat_015 = DRAM Scrub Time set to Disabled notes_plat_020 = Determinism Slider set to Power notes_plat_025 = L1 Stream HW Prefetcher set to Enabled notes_plat_030 = APBDIS set to 1