# Invocation command line: # /home/cpu2017/bin/harness/runcpu --configfile amd_speed_aocc320_milanx_A1.cfg --tune all --reportable --iterations 3 --nopower --runmode speed --tune base:peak --size test:train:refspeed intspeed # output_root was not used for this run ############################################################################ ################################################################################ # AMD AOCC 320 SPEC CPU2017 V1.1.8 Speed Configuration File for 64-bit Linux # # File name : amd_speed_aocc320_milanx_A1.cfg # Creation Date : February 11, 2022 # CPU2017 Version : 1.1.8 # Supported benchmarks : All Speed benchmarks (intspeed, fpspeed) # Compiler name/version : AOCC 3.2.0 # Operating system version : OpenSUSE 15.2 # Supported OS's : Ubuntu 20.04, RHEL 8.3, SLES 15 SP2 # Hardware : AMD Milan, Rome, (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_aocc320_milanx_A1.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-X/Milan/Rome-based # server platforms within Linux (AMD64). # # The binary package was built specifically for AMD Milan-X/Milan/Rome microprocessors and # is not intended to run on other products. # # Please install the binary package by following the instructions in # "Readme.amd_speed_aocc320_milanx_A1.txt" under the "How To Use the Binaries" section. # # The binary package is designed to work without alteration on two socket AMD # Milan-X/Milan/Rome-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-X/Milan/Rome configurations, please review # "Readme.amd_speed_aocc320_milanx_A1.txt". In general, Milan-X/Milan/Rome CPUs # should be autodetected with no action required by the user. # # In most cases, it should be unnecessary to edit "amd_speed_aocc320_milanx_A1.cfg" or any # other file besides "ini_amd_speed_aocc320_milanx_A1.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 aocc320 %define binary_package_name amd_speed_%{compiler_name}_milanx_A %define binary_package_revision 1 # build_path cannot contain SPEC variables or it will trigger rebuilds: %define build_path /sppo/bin/cpu2017v118-aocc32-milanx-speed %define flags_file_name %{compiler_name}-flags-A1.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 preENV_LIBOMP_NUM_HIDDEN_HELPER_THREADS = 0 # OpenMP environment variables: preENV_OMP_SCHEDULE = static preENV_OMP_DYNAMIC = false preENV_OMP_STACKSIZE = 128M # 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_aocc320_milanx_A1.inc' ############################################################################ ################################################################################ ################################################################################ # File name: amd_speed_aocc320_milanx_A1.inc # File generation code date: May 4, 2021 # File generation date/time: November 17, 2023 / 20:16:06 # # 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 16 %define physical_core_count 16 %define physical_core_max 15 %define logical_core_max 15 ################################################################################ ################################################################################ # 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 'milan8' section of CPU info ################################################################################ # default preENV thread settings: default: preENV_OMP_THREAD_LIMIT = 16 preENV_GOMP_CPU_AFFINITY = 0-15 ################################################################################ ################################################################################ # intspeed base thread counts: intspeed=base: threads = 16 ENV_GOMP_CPU_AFFINITY = 0-15 bind0 = numactl --physcpubind=0-15 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # fpspeed base thread counts: fpspeed=base: threads = 16 ENV_GOMP_CPU_AFFINITY = 0-15 bind0 = numactl --physcpubind=0-15 submit = echo "$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 ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 16 603.bwaves_s,607.cactuBSSN_s,627.cam4_s,628.pop2_s,638.imagick_s,649.fotonik3d_s,654.roms_s,657.xz_s=peak: threads = 16 ENV_GOMP_CPU_AFFINITY = 0-15 bind0 = numactl --physcpubind=0-15 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 16 619.lbm_s,621.wrf_s,644.nab_s=peak: threads = 16 ENV_GOMP_CPU_AFFINITY = 0-15 bind0 = numactl --physcpubind=0-15 submit = echo "$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 =3 tester =HPE test_sponsor =HPE hw_vendor =Hewlett Packard Enterprise hw_model000 =ProLiant DL385 Gen10 Plus v2 hw_model001 =(2.80 GHz, AMD EPYC 7203) #--------- If you install new compilers, edit this section -------------------- sw_compiler =C/C++/Fortran: Version 3.2.0 of AOCC ################################################################################ ################################################################################ # Hardware, firmware and software information ################################################################################ hw_avail =Nov-2023 sw_avail =May-2022 hw_cpu_name =AMD EPYC MILAN8 hw_cpu_nominal_mhz =2800 hw_cpu_max_mhz =3400 hw_ncores =16 hw_nthreadspercore =1 hw_ncpuorder =1,2 chips hw_other =None # Other perf-relevant hw, or "None" fw_bios000 =HPE BIOS Version v2.84 08/17/2023 released fw_bios001 = Aug-2023 sw_base_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 =64 MB I+D on chip per chip, hw_tcache001 = 16 MB shared / 2 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 notes_jemalloc_015 = 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. ################################################################################ intspeed: sw_peak_ptrsize =64-bit notes_os_thp_015 = ################################################################################ # The following fields must be set here for FP benchmarks. ################################################################################ fpspeed: sw_peak_ptrsize =64-bit notes_os_thp_003 =To enable THP only on request for peak runs of 628.pop2_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, 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. ################################################################################ intspeed,fpspeed: hw_disk =1 x 480 GB SATA SSD hw_memory =512 GB (16 x 32 GB 2Rx4 PC4-3200AA-R) hw_nchips =2 prepared_by =HPE Performance Engineering sw_file =xfs sw_os000 =Red Hat Enterprise Linux 9.0 (Plow) sw_os001 =Kernel 5.14.0-70.13.1.el9_0.x86_64 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_aocc320_milanx_A1.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/HPE-Platform-Flags-AMD-V1.3-EPYC-revS.xml flagsurl001 = http://www.spec.org/cpu2017/flags/aocc320-flags-A1.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: CC = clang -m64 CXX = clang++ -m64 FC = flang -m64 CLD = clang -m64 CXXLD = clang++ -m64 FLD = flang -m64 CC_VERSION_OPTION = --version CXX_VERSION_OPTION = --version FC_VERSION_OPTION = --version ################################################################################ ################################################################################ # Default Flags ################################################################################ default: # SPEC CPU flags: EXTRA_LIBS = -fopenmp=libomp -lomp -ljemalloc -lamdlibm -lm MATHLIBOPT = #clearing this variable or else SPEC will set it to -lm VECMATHLIB = -fveclib=AMDLIBM # AOCC option variables: OPT_ROOT = -march=znver3 $(VECMATHLIB) -ffast-math -fopenmp OPT_ROOT_BASE = -O3 $(OPT_ROOT) OPT_ROOT_PEAK = -Ofast $(OPT_ROOT) -flto ################################################################################ ################################################################################ # Portability Flags ################################################################################ default: # data model applies to all benchmarks: 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 \ -mllvm -enable-loopinterchange \ -mllvm -compute-interchange-order 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 -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 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 = -fvirtual-function-elimination -fvisibility=hidden LDCFLAGS = -Wl,-allow-multiple-definition -Wl,-mllvm \ -Wl,-enable-licm-vrp # LDCXXFLAGS is left empty as intspeed CPP bmks have to use VZEROUPPER # instruction which is the default. LDCXXFLAGS = LDFFLAGS = -Wl,-mllvm -Wl,-inline-recursion=4 \ -Wl,-mllvm -Wl,-lsr-in-nested-loop \ -Wl,-mllvm -Wl,-enable-iv-split # Setting submit in base and peak to identical values must be done due to a # quirk in the SPEC CPU harness. Do not try to move this assignment to intspeed # or default. 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 # ######################## # Setting submit in base and peak to identical values must be done due to a # quirk in the SPEC CPU harness. Do not try to move this assignment to fpspeed # or default. 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_CXXFLAGS += -mllvm -do-block-reorder=aggressive 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 \ -Wl,-mllvm -Wl,-do-block-reorder=aggressive 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 ######################################### # Benchmark specific peak tuning flags: # ######################################### ################################################################################ 600.perlbench_s=peak: # C submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 602.gcc_s=peak: # C submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 603.bwaves_s=peak: # Fortran 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 ################################################################################ ################################################################################ 605.mcf_s=peak: # C submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 607.cactuBSSN_s=peak: # C, C++, Fortran submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 620.omnetpp_s =peak: # C++ submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 621.wrf_s=peak: # Fortran, C FOPTIMIZE = -Hz,1,0x1 $(OPT_ROOT_PEAK) -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 \ -mllvm -enable-loopinterchange \ -mllvm -compute-interchange-order LDFFLAGS = -Wl,-mllvm -Wl,-enable-X86-prefetching \ -Wl,-mllvm -Wl,-enable-licm-vrp submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 623.xalancbmk_s=peak: # C++ EXTRA_CXXFLAGS = -mllvm -do-block-reorder=aggressive \ -fvirtual-function-elimination -fvisibility=hidden EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-function-specialize \ -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 \ -Wl,-mllvm -Wl,-do-block-reorder=aggressive submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 625.x264_s=peak: # C COPTIMIZE = $(OPT_ROOT_PEAK) -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 \ -mllvm -do-block-reorder=aggressive EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-do-block-reorder=aggressive \ -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 LDCFLAGS = -Wl,-allow-multiple-definition \ -Wl,-mllvm -Wl,-enable-licm-vrp submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 627.cam4_s=peak: # Fortran, C FOPTIMIZE = -Hz,1,0x1 $(OPT_ROOT_PEAK) -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 \ -mllvm -enable-loopinterchange \ -mllvm -compute-interchange-order LDFFLAGS = -Wl,-mllvm -Wl,-enable-X86-prefetching \ -Wl,-mllvm -Wl,-enable-licm-vrp submit = echo never > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 628.pop2_s=peak: # Fortran90, C 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 ################################################################################ ################################################################################ 631.deepsjeng_s=peak: # C++ 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 EXTRA_CXXFLAGS = -mllvm -do-block-reorder=aggressive \ -fvirtual-function-elimination -fvisibility=hidden EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-do-block-reorder=aggressive \ -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 # LDCXXFLAGS is left empty as intspeed CPP bmks have to use VZEROUPPER # instruction which is the default. LDCXXFLAGS = submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 638.imagick_s=peak: # C COPTIMIZE = $(OPT_ROOT_PEAK) -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 \ -mllvm -do-block-reorder=aggressive EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-do-block-reorder=aggressive \ -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 LDCFLAGS = -Wl,-allow-multiple-definition -Wl,-mllvm \ -Wl,-enable-licm-vrp submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 644.nab_s=peak: # C COPTIMIZE = $(OPT_ROOT_PEAK) -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 \ -mllvm -do-block-reorder=aggressive EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-do-block-reorder=aggressive \ -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 LDCFLAGS = -Wl,-allow-multiple-definition \ -Wl,-mllvm -Wl,-enable-licm-vrp submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 648.exchange2_s=peak: # Fortran submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 649.fotonik3d_s=peak: # Fortran 95 + OpenMP ENV_PGHPF_ZMEM =yes submit = echo never > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ ################################################################################ 654.roms_s=peak: # Fortran 2003 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 ################################################################################ ################################################################################ 657.xz_s=peak: # C99 COPTIMIZE = $(OPT_ROOT_PEAK) -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 \ -mllvm -do-block-reorder=aggressive EXTRA_LDFLAGS = -Wl,-mllvm -Wl,-do-block-reorder=aggressive \ -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 LDCFLAGS = -Wl,-allow-multiple-definition \ -Wl,-mllvm -Wl,-enable-licm-vrp ENV_LIBOMP_NUM_HIDDEN_HELPER_THREADS = 0 submit = echo always > /sys/kernel/mm/transparent_hugepage/enabled; $BIND $command ################################################################################ # The following settings were obtained by running the sysinfo_program # 'specperl $[top]/bin/sysinfo' (sysinfo:SHA:2eb381fc1a58eb8122e4a1b875c1e38b3489dac84088192aa0ec6d157b084d06) default: notes_plat_sysinfo_000 = notes_plat_sysinfo_005 = Sysinfo program /home/cpu2017/bin/sysinfo notes_plat_sysinfo_010 = Rev: r6732 of 2022-11-07 fe91c89b7ed5c36ae2c92cc097bec197 notes_plat_sysinfo_015 = running on localhost.localdomain Fri Nov 17 20:16:15 2023 notes_plat_sysinfo_020 = notes_plat_sysinfo_025 = SUT (System Under Test) info as seen by some common utilities. notes_plat_sysinfo_030 = notes_plat_sysinfo_035 = ------------------------------------------------------------ notes_plat_sysinfo_040 = Table of contents notes_plat_sysinfo_045 = ------------------------------------------------------------ notes_plat_sysinfo_050 = 1. uname -a notes_plat_sysinfo_055 = 2. w notes_plat_sysinfo_060 = 3. Username notes_plat_sysinfo_065 = 4. ulimit -a notes_plat_sysinfo_070 = 5. sysinfo process ancestry notes_plat_sysinfo_075 = 6. /proc/cpuinfo notes_plat_sysinfo_080 = 7. lscpu notes_plat_sysinfo_085 = 8. numactl --hardware notes_plat_sysinfo_090 = 9. /proc/meminfo notes_plat_sysinfo_095 = 10. who -r notes_plat_sysinfo_100 = 11. Systemd service manager version: systemd 250 (250-6.el9_0) notes_plat_sysinfo_105 = 12. Services, from systemctl list-unit-files notes_plat_sysinfo_110 = 13. Linux kernel boot-time arguments, from /proc/cmdline notes_plat_sysinfo_115 = 14. cpupower frequency-info notes_plat_sysinfo_120 = 15. sysctl notes_plat_sysinfo_125 = 16. /sys/kernel/mm/transparent_hugepage notes_plat_sysinfo_130 = 17. /sys/kernel/mm/transparent_hugepage/khugepaged notes_plat_sysinfo_135 = 18. OS release notes_plat_sysinfo_140 = 19. Disk information notes_plat_sysinfo_145 = 20. /sys/devices/virtual/dmi/id notes_plat_sysinfo_150 = 21. dmidecode notes_plat_sysinfo_155 = 22. BIOS notes_plat_sysinfo_160 = ------------------------------------------------------------ notes_plat_sysinfo_165 = notes_plat_sysinfo_170 = ------------------------------------------------------------ notes_plat_sysinfo_175 = 1. uname -a notes_plat_sysinfo_180 = Linux localhost.localdomain 5.14.0-70.13.1.el9_0.x86_64 #1 SMP PREEMPT Thu Apr 14 12:42:38 EDT 2022 x86_64 notes_plat_sysinfo_185 = x86_64 x86_64 GNU/Linux notes_plat_sysinfo_190 = notes_plat_sysinfo_195 = ------------------------------------------------------------ notes_plat_sysinfo_200 = 2. w notes_plat_sysinfo_205 = 20:16:15 up 3 min, 2 users, load average: 0.02, 0.06, 0.02 notes_plat_sysinfo_210 = USER TTY LOGIN@ IDLE JCPU PCPU WHAT notes_plat_sysinfo_215 = root tty1 07Apr22 589days 0.00s 0.00s -bash notes_plat_sysinfo_220 = root pts/0 07Apr22 15.00s 1.14s 0.03s /bin/bash ./amd_speed_aocc320_milanx_A1.sh notes_plat_sysinfo_225 = notes_plat_sysinfo_230 = ------------------------------------------------------------ notes_plat_sysinfo_235 = 3. Username notes_plat_sysinfo_240 = From environment variable $USER: root notes_plat_sysinfo_245 = notes_plat_sysinfo_250 = ------------------------------------------------------------ notes_plat_sysinfo_255 = 4. ulimit -a notes_plat_sysinfo_260 = real-time non-blocking time (microseconds, -R) unlimited notes_plat_sysinfo_265 = core file size (blocks, -c) 0 notes_plat_sysinfo_270 = data seg size (kbytes, -d) unlimited notes_plat_sysinfo_275 = scheduling priority (-e) 0 notes_plat_sysinfo_280 = file size (blocks, -f) unlimited notes_plat_sysinfo_285 = pending signals (-i) 2062709 notes_plat_sysinfo_290 = max locked memory (kbytes, -l) 2097152 notes_plat_sysinfo_295 = max memory size (kbytes, -m) unlimited notes_plat_sysinfo_300 = open files (-n) 1024 notes_plat_sysinfo_305 = pipe size (512 bytes, -p) 8 notes_plat_sysinfo_310 = POSIX message queues (bytes, -q) 819200 notes_plat_sysinfo_315 = real-time priority (-r) 0 notes_plat_sysinfo_320 = stack size (kbytes, -s) unlimited notes_plat_sysinfo_325 = cpu time (seconds, -t) unlimited notes_plat_sysinfo_330 = max user processes (-u) 2062709 notes_plat_sysinfo_335 = virtual memory (kbytes, -v) unlimited notes_plat_sysinfo_340 = file locks (-x) unlimited notes_plat_sysinfo_345 = notes_plat_sysinfo_350 = ------------------------------------------------------------ notes_plat_sysinfo_355 = 5. sysinfo process ancestry notes_plat_sysinfo_360 = /usr/lib/systemd/systemd --switched-root --system --deserialize 28 notes_plat_sysinfo_365 = sshd: /usr/sbin/sshd -D [listener] 0 of 10-100 startups notes_plat_sysinfo_370 = sshd: root [priv] notes_plat_sysinfo_375 = sshd: root@pts/0 notes_plat_sysinfo_380 = -bash notes_plat_sysinfo_385 = python3 ./run_intspeed_aocc320_milanx_A1.py notes_plat_sysinfo_390 = /bin/bash ./amd_speed_aocc320_milanx_A1.sh notes_plat_sysinfo_395 = runcpu --config amd_speed_aocc320_milanx_A1.cfg --tune all --reportable --iterations 3 intspeed notes_plat_sysinfo_400 = runcpu --configfile amd_speed_aocc320_milanx_A1.cfg --tune all --reportable --iterations 3 --nopower notes_plat_sysinfo_405 = --runmode speed --tune base:peak --size test:train:refspeed intspeed --nopreenv --note-preenv --logfile notes_plat_sysinfo_410 = $SPEC/tmp/CPU2017.107/templogs/preenv.intspeed.107.0.log --lognum 107.0 --from_runcpu 2 notes_plat_sysinfo_415 = specperl $SPEC/bin/sysinfo notes_plat_sysinfo_420 = $SPEC = /home/cpu2017 notes_plat_sysinfo_425 = notes_plat_sysinfo_430 = ------------------------------------------------------------ notes_plat_sysinfo_435 = 6. /proc/cpuinfo notes_plat_sysinfo_440 = model name : AMD EPYC 7203 8-Core Processor notes_plat_sysinfo_445 = vendor_id : AuthenticAMD notes_plat_sysinfo_450 = cpu family : 25 notes_plat_sysinfo_455 = model : 1 notes_plat_sysinfo_460 = stepping : 1 notes_plat_sysinfo_465 = microcode : 0xa0011d1 notes_plat_sysinfo_470 = bugs : sysret_ss_attrs spectre_v1 spectre_v2 spec_store_bypass notes_plat_sysinfo_475 = TLB size : 2560 4K pages notes_plat_sysinfo_480 = cpu cores : 8 notes_plat_sysinfo_485 = siblings : 8 notes_plat_sysinfo_490 = 2 physical ids (chips) notes_plat_sysinfo_495 = 16 processors (hardware threads) notes_plat_sysinfo_500 = physical id 0: core ids 0-7 notes_plat_sysinfo_505 = physical id 1: core ids 0-7 notes_plat_sysinfo_510 = physical id 0: apicids 0-7 notes_plat_sysinfo_515 = physical id 1: apicids 8-15 notes_plat_sysinfo_520 = Caution: /proc/cpuinfo data regarding chips, cores, and threads is not necessarily reliable, especially for notes_plat_sysinfo_525 = virtualized systems. Use the above data carefully. notes_plat_sysinfo_530 = notes_plat_sysinfo_535 = ------------------------------------------------------------ notes_plat_sysinfo_540 = 7. lscpu notes_plat_sysinfo_545 = notes_plat_sysinfo_550 = From lscpu from util-linux 2.37.4: notes_plat_sysinfo_555 = Architecture: x86_64 notes_plat_sysinfo_560 = CPU op-mode(s): 32-bit, 64-bit notes_plat_sysinfo_565 = Address sizes: 48 bits physical, 48 bits virtual notes_plat_sysinfo_570 = Byte Order: Little Endian notes_plat_sysinfo_575 = CPU(s): 16 notes_plat_sysinfo_580 = On-line CPU(s) list: 0-15 notes_plat_sysinfo_585 = Vendor ID: AuthenticAMD notes_plat_sysinfo_590 = BIOS Vendor ID: Advanced Micro Devices, Inc. notes_plat_sysinfo_595 = Model name: AMD EPYC 7203 8-Core Processor notes_plat_sysinfo_600 = BIOS Model name: AMD EPYC 7203 8-Core Processor notes_plat_sysinfo_605 = CPU family: 25 notes_plat_sysinfo_610 = Model: 1 notes_plat_sysinfo_615 = Thread(s) per core: 1 notes_plat_sysinfo_620 = Core(s) per socket: 8 notes_plat_sysinfo_625 = Socket(s): 2 notes_plat_sysinfo_630 = Stepping: 1 notes_plat_sysinfo_635 = Frequency boost: enabled notes_plat_sysinfo_640 = CPU max MHz: 2800.0000 notes_plat_sysinfo_645 = CPU min MHz: 1500.0000 notes_plat_sysinfo_650 = BogoMIPS: 5589.99 notes_plat_sysinfo_655 = Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 notes_plat_sysinfo_660 = clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm notes_plat_sysinfo_665 = constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl notes_plat_sysinfo_670 = pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes notes_plat_sysinfo_675 = xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a notes_plat_sysinfo_680 = misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core notes_plat_sysinfo_685 = perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single notes_plat_sysinfo_690 = hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 notes_plat_sysinfo_695 = erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt notes_plat_sysinfo_700 = xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local notes_plat_sysinfo_705 = clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock notes_plat_sysinfo_710 = nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter notes_plat_sysinfo_715 = pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes notes_plat_sysinfo_720 = vpclmulqdq rdpid overflow_recov succor smca fsrm notes_plat_sysinfo_725 = Virtualization: AMD-V notes_plat_sysinfo_730 = L1d cache: 512 KiB (16 instances) notes_plat_sysinfo_735 = L1i cache: 512 KiB (16 instances) notes_plat_sysinfo_740 = L2 cache: 8 MiB (16 instances) notes_plat_sysinfo_745 = L3 cache: 128 MiB (8 instances) notes_plat_sysinfo_750 = NUMA node(s): 8 notes_plat_sysinfo_755 = NUMA node0 CPU(s): 0,1 notes_plat_sysinfo_760 = NUMA node1 CPU(s): 2,3 notes_plat_sysinfo_765 = NUMA node2 CPU(s): 4,5 notes_plat_sysinfo_770 = NUMA node3 CPU(s): 6,7 notes_plat_sysinfo_775 = NUMA node4 CPU(s): 8,9 notes_plat_sysinfo_780 = NUMA node5 CPU(s): 10,11 notes_plat_sysinfo_785 = NUMA node6 CPU(s): 12,13 notes_plat_sysinfo_790 = NUMA node7 CPU(s): 14,15 notes_plat_sysinfo_795 = Vulnerability Itlb multihit: Not affected notes_plat_sysinfo_800 = Vulnerability L1tf: Not affected notes_plat_sysinfo_805 = Vulnerability Mds: Not affected notes_plat_sysinfo_810 = Vulnerability Meltdown: Not affected notes_plat_sysinfo_815 = Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl notes_plat_sysinfo_820 = Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization notes_plat_sysinfo_825 = Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP disabled, RSB notes_plat_sysinfo_830 = filling notes_plat_sysinfo_835 = Vulnerability Srbds: Not affected notes_plat_sysinfo_840 = Vulnerability Tsx async abort: Not affected notes_plat_sysinfo_845 = notes_plat_sysinfo_850 = From lscpu --cache: notes_plat_sysinfo_855 = NAME ONE-SIZE ALL-SIZE WAYS TYPE LEVEL SETS PHY-LINE COHERENCY-SIZE notes_plat_sysinfo_860 = L1d 32K 512K 8 Data 1 64 1 64 notes_plat_sysinfo_865 = L1i 32K 512K 8 Instruction 1 64 1 64 notes_plat_sysinfo_870 = L2 512K 8M 8 Unified 2 1024 1 64 notes_plat_sysinfo_875 = L3 16M 128M 16 Unified 3 16384 1 64 notes_plat_sysinfo_880 = notes_plat_sysinfo_885 = ------------------------------------------------------------ notes_plat_sysinfo_890 = 8. numactl --hardware notes_plat_sysinfo_895 = NOTE: a numactl 'node' might or might not correspond to a physical chip. notes_plat_sysinfo_900 = available: 8 nodes (0-7) notes_plat_sysinfo_905 = node 0 cpus: 0-1 notes_plat_sysinfo_910 = node 0 size: 64262 MB notes_plat_sysinfo_915 = node 0 free: 64142 MB notes_plat_sysinfo_920 = node 1 cpus: 2-3 notes_plat_sysinfo_925 = node 1 size: 64510 MB notes_plat_sysinfo_930 = node 1 free: 64380 MB notes_plat_sysinfo_935 = node 2 cpus: 4-5 notes_plat_sysinfo_940 = node 2 size: 64510 MB notes_plat_sysinfo_945 = node 2 free: 64421 MB notes_plat_sysinfo_950 = node 3 cpus: 6-7 notes_plat_sysinfo_955 = node 3 size: 64498 MB notes_plat_sysinfo_960 = node 3 free: 64360 MB notes_plat_sysinfo_965 = node 4 cpus: 8-9 notes_plat_sysinfo_970 = node 4 size: 64510 MB notes_plat_sysinfo_975 = node 4 free: 64162 MB notes_plat_sysinfo_980 = node 5 cpus: 10-11 notes_plat_sysinfo_985 = node 5 size: 64510 MB notes_plat_sysinfo_990 = node 5 free: 64324 MB notes_plat_sysinfo_995 = node 6 cpus: 12-13 notes_plat_sysinfo_1000= node 6 size: 64474 MB notes_plat_sysinfo_1005= node 6 free: 64376 MB notes_plat_sysinfo_1010= node 7 cpus: 14-15 notes_plat_sysinfo_1015= node 7 size: 64502 MB notes_plat_sysinfo_1020= node 7 free: 64408 MB notes_plat_sysinfo_1025= node distances: notes_plat_sysinfo_1030= node 0 1 2 3 4 5 6 7 notes_plat_sysinfo_1035= 0: 10 12 12 12 32 32 32 32 notes_plat_sysinfo_1040= 1: 12 10 12 12 32 32 32 32 notes_plat_sysinfo_1045= 2: 12 12 10 12 32 32 32 32 notes_plat_sysinfo_1050= 3: 12 12 12 10 32 32 32 32 notes_plat_sysinfo_1055= 4: 32 32 32 32 10 12 12 12 notes_plat_sysinfo_1060= 5: 32 32 32 32 12 10 12 12 notes_plat_sysinfo_1065= 6: 32 32 32 32 12 12 10 12 notes_plat_sysinfo_1070= 7: 32 32 32 32 12 12 12 10 notes_plat_sysinfo_1075= notes_plat_sysinfo_1080= ------------------------------------------------------------ notes_plat_sysinfo_1085= 9. /proc/meminfo notes_plat_sysinfo_1090= MemTotal: 528161252 kB notes_plat_sysinfo_1095= notes_plat_sysinfo_1100= ------------------------------------------------------------ notes_plat_sysinfo_1105= 10. who -r notes_plat_sysinfo_1110= run-level 3 Apr 7 05:30 notes_plat_sysinfo_1115= notes_plat_sysinfo_1120= ------------------------------------------------------------ notes_plat_sysinfo_1125= 11. Systemd service manager version: systemd 250 (250-6.el9_0) notes_plat_sysinfo_1130= Default Target Status notes_plat_sysinfo_1135= multi-user running notes_plat_sysinfo_1140= notes_plat_sysinfo_1145= ------------------------------------------------------------ notes_plat_sysinfo_1150= 12. Services, from systemctl list-unit-files notes_plat_sysinfo_1155= STATE UNIT FILES notes_plat_sysinfo_1160= enabled NetworkManager NetworkManager-dispatcher NetworkManager-wait-online auditd chronyd crond notes_plat_sysinfo_1165= dbus-broker firewalld getty@ irqbalance kdump lvm2-monitor mdmonitor microcode notes_plat_sysinfo_1170= nis-domainname rhsmcertd rsyslog selinux-autorelabel-mark sshd sssd notes_plat_sysinfo_1175= systemd-network-generator udisks2 notes_plat_sysinfo_1180= enabled-runtime systemd-remount-fs notes_plat_sysinfo_1185= disabled blk-availability chrony-wait console-getty cpupower debug-shell kvm_stat notes_plat_sysinfo_1190= man-db-restart-cache-update nftables rdisc rhsm rhsm-facts rpmdb-rebuild serial-getty@ notes_plat_sysinfo_1195= sshd-keygen@ systemd-boot-check-no-failures systemd-pstore systemd-sysext notes_plat_sysinfo_1200= indirect sssd-autofs sssd-kcm sssd-nss sssd-pac sssd-pam sssd-ssh sssd-sudo notes_plat_sysinfo_1205= notes_plat_sysinfo_1210= ------------------------------------------------------------ notes_plat_sysinfo_1215= 13. Linux kernel boot-time arguments, from /proc/cmdline notes_plat_sysinfo_1220= BOOT_IMAGE=(hd1,gpt2)/vmlinuz-5.14.0-70.13.1.el9_0.x86_64 notes_plat_sysinfo_1225= root=/dev/mapper/rhel-root notes_plat_sysinfo_1230= ro notes_plat_sysinfo_1235= resume=/dev/mapper/rhel-swap notes_plat_sysinfo_1240= rd.lvm.lv=rhel/root notes_plat_sysinfo_1245= rd.lvm.lv=rhel/swap notes_plat_sysinfo_1250= notes_plat_sysinfo_1255= ------------------------------------------------------------ notes_plat_sysinfo_1260= 14. cpupower frequency-info notes_plat_sysinfo_1265= analyzing CPU 0: notes_plat_sysinfo_1270= current policy: frequency should be within 1.50 GHz and 2.80 GHz. notes_plat_sysinfo_1275= The governor "performance" may decide which speed to use notes_plat_sysinfo_1280= within this range. notes_plat_sysinfo_1285= boost state support: notes_plat_sysinfo_1290= Supported: yes notes_plat_sysinfo_1295= Active: yes notes_plat_sysinfo_1300= Boost States: 0 notes_plat_sysinfo_1305= Total States: 3 notes_plat_sysinfo_1310= Pstate-P0: 2800MHz notes_plat_sysinfo_1315= notes_plat_sysinfo_1320= ------------------------------------------------------------ notes_plat_sysinfo_1325= 15. sysctl notes_plat_sysinfo_1330= kernel.numa_balancing 1 notes_plat_sysinfo_1335= kernel.randomize_va_space 0 notes_plat_sysinfo_1340= vm.compaction_proactiveness 20 notes_plat_sysinfo_1345= vm.dirty_background_bytes 0 notes_plat_sysinfo_1350= vm.dirty_background_ratio 10 notes_plat_sysinfo_1355= vm.dirty_bytes 0 notes_plat_sysinfo_1360= vm.dirty_expire_centisecs 3000 notes_plat_sysinfo_1365= vm.dirty_ratio 8 notes_plat_sysinfo_1370= vm.dirty_writeback_centisecs 500 notes_plat_sysinfo_1375= vm.dirtytime_expire_seconds 43200 notes_plat_sysinfo_1380= vm.extfrag_threshold 500 notes_plat_sysinfo_1385= vm.min_unmapped_ratio 1 notes_plat_sysinfo_1390= vm.nr_hugepages 0 notes_plat_sysinfo_1395= vm.nr_hugepages_mempolicy 0 notes_plat_sysinfo_1400= vm.nr_overcommit_hugepages 0 notes_plat_sysinfo_1405= vm.swappiness 1 notes_plat_sysinfo_1410= vm.watermark_boost_factor 15000 notes_plat_sysinfo_1415= vm.watermark_scale_factor 10 notes_plat_sysinfo_1420= vm.zone_reclaim_mode 1 notes_plat_sysinfo_1425= notes_plat_sysinfo_1430= ------------------------------------------------------------ notes_plat_sysinfo_1435= 16. /sys/kernel/mm/transparent_hugepage notes_plat_sysinfo_1440= defrag [always] defer defer+madvise madvise never notes_plat_sysinfo_1445= enabled [always] madvise never notes_plat_sysinfo_1450= hpage_pmd_size 2097152 notes_plat_sysinfo_1455= shmem_enabled always within_size advise [never] deny force notes_plat_sysinfo_1460= notes_plat_sysinfo_1465= ------------------------------------------------------------ notes_plat_sysinfo_1470= 17. /sys/kernel/mm/transparent_hugepage/khugepaged notes_plat_sysinfo_1475= alloc_sleep_millisecs 60000 notes_plat_sysinfo_1480= defrag 1 notes_plat_sysinfo_1485= max_ptes_none 511 notes_plat_sysinfo_1490= max_ptes_shared 256 notes_plat_sysinfo_1495= max_ptes_swap 64 notes_plat_sysinfo_1500= pages_to_scan 4096 notes_plat_sysinfo_1505= scan_sleep_millisecs 10000 notes_plat_sysinfo_1510= notes_plat_sysinfo_1515= ------------------------------------------------------------ notes_plat_sysinfo_1520= 18. OS release notes_plat_sysinfo_1525= From /etc/*-release /etc/*-version notes_plat_sysinfo_1530= os-release Red Hat Enterprise Linux 9.0 (Plow) notes_plat_sysinfo_1535= redhat-release Red Hat Enterprise Linux release 9.0 (Plow) notes_plat_sysinfo_1540= system-release Red Hat Enterprise Linux release 9.0 (Plow) notes_plat_sysinfo_1545= notes_plat_sysinfo_1550= ------------------------------------------------------------ notes_plat_sysinfo_1555= 19. Disk information notes_plat_sysinfo_1560= SPEC is set to: /home/cpu2017 notes_plat_sysinfo_1565= Filesystem Type Size Used Avail Use% Mounted on notes_plat_sysinfo_1570= /dev/mapper/rhel-home xfs 372G 25G 347G 7% /home notes_plat_sysinfo_1575= notes_plat_sysinfo_1580= ------------------------------------------------------------ notes_plat_sysinfo_1585= 20. /sys/devices/virtual/dmi/id notes_plat_sysinfo_1590= Vendor: HPE notes_plat_sysinfo_1595= Product: ProLiant DL385 Gen10 Plus notes_plat_sysinfo_1600= Product Family: ProLiant notes_plat_sysinfo_1605= Serial: CN7931050F notes_plat_sysinfo_1610= notes_plat_sysinfo_1615= ------------------------------------------------------------ notes_plat_sysinfo_1620= 21. dmidecode notes_plat_sysinfo_1625= Additional information from dmidecode 3.3 follows. WARNING: Use caution when you interpret this section. notes_plat_sysinfo_1630= The 'dmidecode' program reads system data which is "intended to allow hardware to be accurately notes_plat_sysinfo_1635= determined", but the intent may not be met, as there are frequent changes to hardware, firmware, and the notes_plat_sysinfo_1640= "DMTF SMBIOS" standard. notes_plat_sysinfo_1645= Memory: notes_plat_sysinfo_1650= 16x Hynix HMA84GR7DJR4N-XN 32 GB 2 rank 3200 notes_plat_sysinfo_1655= notes_plat_sysinfo_1660= notes_plat_sysinfo_1665= ------------------------------------------------------------ notes_plat_sysinfo_1670= 22. BIOS notes_plat_sysinfo_1675= (This section combines info from /sys/devices and dmidecode.) notes_plat_sysinfo_1680= BIOS Vendor: HPE notes_plat_sysinfo_1685= BIOS Version: A42 notes_plat_sysinfo_1690= BIOS Date: 08/17/2023 notes_plat_sysinfo_1695= BIOS Revision: 2.84 notes_plat_sysinfo_1700= Firmware Revision: 2.81 hw_cpu_name = AMD EPYC 7203 hw_disk = 372 GB add more disk info here hw_memory001 = 503.694 GB fixme: If using DDR4, the format is: hw_memory002 = 'N GB (N x N GB nRxn PC4-nnnnX-X)' hw_nchips = 2 hw_ncores = 16 hw_nthreadspercore = 1 prepared_by = root (is never output, only tags rawfile) sw_file = xfs sw_os001 = Red Hat Enterprise Linux 9.0 (Plow) sw_state = Run level 3 (add definition here) # End of settings added by sysinfo_program 648.exchange2_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 641.leela_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 631.deepsjeng_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 625.x264_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 620.omnetpp_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 605.mcf_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 602.gcc_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 600.perlbench_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 power_management001 = the cost of additional power usage notes_plat_000 = BIOS Configuration notes_plat_005 = Workload Profile set to General Peak Frequency Compute notes_plat_010 = Determinism Control set to Manual notes_plat_015 = Performance Determinism set to Power Deterministic notes_plat_020 = Memory Patrol Scrubbing set to Disabled notes_plat_025 = AMD SMT Option set to Disabled notes_plat_030 = NUMA memory domains per socket set to Four memory domains per socket notes_plat_035 = Last-Level Cache (LLC) as NUMA Node set to Enabled notes_plat_040 = Memory PStates set to Disabled notes_plat_045 = Thermal Configuration set to Maximum Cooling notes_plat_050 = Workload Profile set to Custom notes_plat_055 = Power Regulator set to OS Control Mode