# Invocation command line: # /mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/bin/harness/runcpu --configfile amd_speed_aocc400_znver4_A1.cfg --tune all --reportable --iterations 2 --define DL-BIOS-L3NUMA=1 --define DL-BIOS-NPS=2 --define DL-BIOSinc=Dell-BIOS_EPYC-4.inc --define DL-BIOS-adddcD=1 --define DL-VERS=v4.8.1 --output_format html,pdf,txt --nopower --runmode speed --tune base:peak --size test:train:refspeed intspeed # output_root was not used for this run ############################################################################ ################################################################################ # AMD AOCC 400 SPEC CPU 2017 V1.1.9 Speed Configuration File for 64-bit Linux # # File name : amd_speed_aocc400_znver4_A1.cfg # Creation Date : April 16, 2023 # CPU 2017 Version : 1.1.9 # Supported benchmarks : All Speed benchmarks (intspeed, fpspeed) # Compiler name/version : AOCC 4.0.0 # Operating system version : RHEL 8.6 # Supported OS's : Ubuntu 22.04, RHEL 8.6/9, SLE 15 SP4 # Hardware : AMD znver4 (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 Parallelization : 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_aocc400_znver4_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 CPU 2017 under optimized conditions on AMD znver4-based # server platforms within Linux (AMD64). # # The binary package was built specifically for AMD znver4 microprocessors and # is not intended to run on other products. # # Please install the binary package by following the instructions in # "Readme.amd_speed_aocc400_znver4_A1.txt" under the "How To Use the Binaries" section. # # The binary package is designed to work without alteration on one socket AMD # znver4-based servers with 96 cores, SMT enabled and 768 (64x12) GB of DDR5 # memory distributed evenly among all 12 channels using 64 GiB DIMMs. # # To run the binary package on other znver4 configurations, please review # "Readme.amd_speed_aocc400_znver4_A1.txt". In general, znver4 CPUs # should be autodetected with no action required by the user. # # In most cases, it should be unnecessary to edit "amd_speed_aocc400_znver4_A1.cfg" or any # other file besides "ini_amd_speed_aocc400_znver4_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 # 22.04, RHEL 8.6/9, and SLE 15 SP4. # # 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: ################################################################################ # "allow_build"" switch: # 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 aocc400 %define binary_package_name amd_speed_%{compiler_name}_znver4_A %define binary_package_ext %{binary_package_name} %define binary_package_revision 1 %define build_path ${SPEC} %define flags_file_name %{compiler_name}-flags_A1.1.xml # Do NOT change build_lib_dir after the build or it will trigger a # rebuild of the xalanc. It should also remain literal: %define build_lib_dir amd_speed_aocc400_znver4_A_lib # To enable the platform file, be sure to uncomment the flagsurl02 header line # below in the Header settings. %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 %define flags_inc_file_name %{binary_package_full_name}_flags.inc # Binary label extension: # Only modify the binary label extension if you plan to rebuild the binaries. # If you plan to recompile these CPU 2017 binaries, please choose a new extension # name below 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 above. 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. # Note that AMD calls an external script to set up the compiler and library # paths before initiating the build. %define ext %{binary_package_ext} ################################################################################ # Paths and Environment Variables # ** MODIFY AS NEEDED (modification should not be necessary for runs) ** ################################################################################ # Allow environment variables to be set before runs: preenv = 1 # retain:true is necessary to avoid gcc out-of-memory exceptions on certain SUTs: # oversize_threshold is required to support jemalloc 5.2.x+ preENV_MALLOC_CONF = oversize_threshold:0,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 # Set the shared object library path for runs and builds: preENV_LD_LIBRARY_PATH = $[top]/%{lib_dir}/lib:%{ENV_LD_LIBRARY_PATH} %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_aocc400_znver4_A1.inc' ############################################################################ ################################################################################ ################################################################################ # File name: amd_speed_aocc400_znver4_A1.inc # File generation code date: October 11, 2022 # File generation date/time: November 10, 2023 / 00:55:32 # # 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 128 %define physical_core_count 128 %define physical_core_max 127 %define logical_core_max 127 ################################################################################ ################################################################################ # 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 '9554' section of CPU info ################################################################################ # default preENV thread settings: default: preENV_OMP_THREAD_LIMIT = 128 preENV_GOMP_CPU_AFFINITY = 0-127 ################################################################################ ################################################################################ # intspeed base thread counts: intspeed=base: threads = 128 ENV_GOMP_CPU_AFFINITY = 0-127 bind0 = numactl --physcpubind=0-127 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # fpspeed base thread counts: fpspeed=base: threads = 128 ENV_GOMP_CPU_AFFINITY = 0-127 bind0 = numactl --physcpubind=0-127 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 1 600.perlbench_s,602.gcc_s,605.mcf_s,620.omnetpp_s,623.xalancbmk_s,625.x264_s,631.deepsjeng_s,641.leela_s,648.exchange2_s=peak: threads = 1 ENV_GOMP_CPU_AFFINITY = 15 bind0 = numactl --physcpubind=15 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 128 603.bwaves_s,619.lbm_s,621.wrf_s,628.pop2_s,649.fotonik3d_s=peak: threads = 128 ENV_GOMP_CPU_AFFINITY = 0-127 bind0 = numactl --physcpubind=0-127 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 128 607.cactuBSSN_s,627.cam4_s,638.imagick_s,644.nab_s,657.xz_s=peak: threads = 128 ENV_GOMP_CPU_AFFINITY = 0-127 bind0 = numactl --physcpubind=0-127 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 128 654.roms_s=peak: threads = 128 ENV_GOMP_CPU_AFFINITY = 0 64 1 65 2 66 3 67 4 68 5 69 6 70 7 71 8 72 9 73 10 74 11 75 12 76 13 77 14 78 15 79 16 80 17 81 18 82 19 83 20 84 21 85 22 86 23 87 24 88 25 89 26 90 27 91 28 92 29 93 30 94 31 95 32 96 33 97 34 98 35 99 36 100 37 101 38 102 39 103 40 104 41 105 42 106 43 107 44 108 45 109 46 110 47 111 48 112 49 113 50 114 51 115 52 116 53 117 54 118 55 119 56 120 57 121 58 122 59 123 60 124 61 125 62 126 63 127 bind0 = numactl --physcpubind=0-127 submit = echo "$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 =9999 # (Your SPEC license number) tester =unknown tester test_sponsor =unknown sponsor hw_vendor =unknown vendor #--------- If you install new compilers, edit this section -------------------- sw_compiler =C/C++/Fortran: Version 4.0.0 of AOCC ################################################################################ ################################################################################ # Hardware, firmware and software information ################################################################################ hw_avail =Nov-2022 sw_avail =Nov-2022 hw_cpu_name =AMD EPYC 9554 hw_cpu_nominal_mhz =3100 hw_cpu_max_mhz =3750 hw_ncores =128 hw_nthreadspercore =1 hw_ncpuorder =1,2 chips hw_other =None # Other perf-relevant hw, or "None" fw_bios =Version 0.0.0 released Dec-2022 sw_base_ptrsize =64-bit hw_pcache =32 KB I + 32 KB D on chip per core hw_scache =1 MB I+D on chip per core hw_tcache000 =256 MB I+D on chip per chip, 32 MB shared / 8 hw_tcache001 = cores hw_ocache =None sw_other =None ################################################################################ # Notes ################################################################################ # Enter notes_000 through notes_100 here. notes_000 =Binaries were compiled on a system with 2x AMD EPYC 9174F CPU + 1.5TiB Memory using RHEL 8.6 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_submit_010 = 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_other000 =jemalloc: jemalloc memory allocator library v5.1.0 ################################################################################ # The following note fields describe platorm settings. ################################################################################ # example: (edit and uncomment as necessary) # notes_plat_000 =BIOS settings: # notes_plat_002 = TDP: 400 # notes_plat_004 = Determinism Slider set to Power # notes_plat_006 = PPT: 400 # notes_plat_010 = NPS: 4 # notes_plat_011 = Workload Profile = CPU Intensive # notes_plat_012 = TSME = Disabled # notes_plat_014 = SEV Control = Disabled # 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 always enable THP for peak runs of: notes_os_thp_004 =603.bwaves_s, 607.cactuBSSN_s, 619.lbm_s, 627.cam4_s, 628.pop2_s, 638.imagick_s, 644.nab_s, 649.fotonik3d_s: notes_os_thp_005 ='echo madvise > /sys/kernel/mm/transparent_hugepage/enabled; echo always > /sys/kernel/mm/transparent_hugepage/defrag' notes_os_thp_006 =run as root. notes_os_thp_007 =To disable THP for peak runs of 621.wrf_s: notes_os_thp_008 ='echo never > /sys/kernel/mm/transparent_hugepage/enabled; echo always > /sys/kernel/mm/transparent_hugepage/defrag' notes_os_thp_009 =run as root. notes_os_thp_010 =To enable THP only on request for peak runs of 654.roms_s: notes_os_thp_011 ='echo madvise > /sys/kernel/mm/transparent_hugepage/enabled; echo madvise > /sys/kernel/mm/transparent_hugepage/defrag' notes_os_thp_012 =run as root. ################################################################################ # The following fields must be set here or they will be overwritten by sysinfo. ################################################################################ intspeed,fpspeed: hw_disk =unknown hw_nchips =2 prepared_by =prepared by unknown sw_file =unknown file 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 '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/amd_speed_aocc400_znver4_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:%{ENV_LIBRARY_PATH} % define build_ncpus 16 # 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/aocc400-flags_A1.1.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 ################################################################################ # Include the flags file: ################################################################################ #include: %{flags_inc_file_name} # ----- Begin inclusion of 'amd_speed_aocc400_znver4_A1_flags.inc' ############################################################################ ################################################################################ # AMD AOCC 4.0.0 SPEC CPU2017 V1.1.8 Speed Configuration Flags for AMD64 Linux ################################################################################ # 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 ################################################################################ # 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 ################################################################################ # Default libraries and variables ################################################################################ default: # Libraries: EXTRA_LIBS = -fopenmp=libomp \ -lomp \ -lamdalloc \ -lamdlibm \ -lm MATHLIBOPT = #clearing this variable or else SPEC will set it to -lm VECMATHLIB = -fveclib=AMDLIBM # Variables: OPT_ROOT = -march=znver4 \ $(VECMATHLIB) \ -ffast-math \ -fopenmp OPT_ROOT_BASE = -O3 \ $(OPT_ROOT) OPT_ROOT_PEAK = -Ofast \ $(OPT_ROOT) \ -flto THP_ALWAYS = echo always > /sys/kernel/mm/transparent_hugepage/enabled; echo always > /sys/kernel/mm/transparent_hugepage/defrag THP_NEVER = echo never > /sys/kernel/mm/transparent_hugepage/enabled; echo never > /sys/kernel/mm/transparent_hugepage/defrag THP_MADVISE = echo madvise > /sys/kernel/mm/transparent_hugepage/enabled; echo madvise > /sys/kernel/mm/transparent_hugepage/defrag DEFAULT_SUBMIT = echo "$command" > run.sh ; $BIND bash run.sh ############################################################################### # AOCC 4.0.0 workarounds that do not count as PORTABILITY ################################################################################ # The workarounds in this section would not qualify under the SPEC CPU # PORTABILITY rule. # - In peak, they can be set as needed for individual benchmarks. # - In base, individual settings are not allowed; set for whole suite. # Use EXTRA_CFLAGS, EXTRA_CXXFLAGS, and EXTRA_FFLAGS for them. # # See: # https://www.spec.org/cpu2017/Docs/runrules.html#portability # https://www.spec.org/cpu2017/Docs/runrules.html#BaseFlags ####################### # Default workarounds # ####################### default: # Allow unused compile/link arguments without triggering warnings during build: EXTRA_CFLAGS = -Wno-unused-command-line-argument EXTRA_CXXFLAGS = -Wno-unused-command-line-argument EXTRA_FFLAGS = -Wno-unused-command-line-argument LDOPTIONS = -Wno-unused-command-line-argument #################### # Base workarounds # #################### # # *** NONE *** # ############################## # Integer workarounds - base # ############################## intrate=base: # The following is necessary for 602 gcc: EXTRA_LDFLAGS = -z muldefs ######################### # FP workarounds - base # ######################### # # *** NONE *** # #################### # Peak workarounds # #################### # # *** NONE *** # ############################## # Integer workarounds - peak # ############################## 602.gcc_s=peak: #lang='C' EXTRA_LDFLAGS = -z muldefs ##################################### # Floating Point workarounds - peak # ##################################### # # *** NONE *** # ################################################################################ # Tuning Flags ################################################################################ ##################### # Base tuning flags # ##################### default=base: COPTIMIZE = $(OPT_ROOT_BASE) \ -flto \ -fstruct-layout=7 \ -mllvm -unroll-threshold=50 \ -mllvm -inline-threshold=1000 \ -fremap-arrays \ -fstrip-mining \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -Wno-return-type \ -zopt CXXOPTIMIZE = $(OPT_ROOT_BASE) \ -flto \ -mllvm -unroll-threshold=100 \ -finline-aggressive \ -mllvm -loop-unswitch-threshold=200000 \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -zopt FOPTIMIZE = $(OPT_ROOT_BASE) \ -flto \ -Mrecursive \ -funroll-loops \ -mllvm -lsr-in-nested-loop \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -zopt LDCXXFLAGS = -Wl,-mllvm -Wl,-x86-use-vzeroupper=false LDFLAGS = -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 LDFFLAGS = -Wl,-mllvm -Wl,-enable-X86-prefetching #other libraries # Put OpenMP and math libraries here: # -lm needed at the end for some transcendental functions: EXTRA_LIBS = -fopenmp=libomp \ -lomp \ -lamdlibm \ -lamdalloc \ -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 = ######################### # intspeed tuning flags # ######################### intspeed: FOPTIMIZE = $(OPT_ROOT_BASE) \ -flto \ -mllvm -optimize-strided-mem-cost EXTRA_FFLAGS = -mllvm -unroll-aggressive \ -mllvm -unroll-threshold=150 EXTRA_CXXFLAGS = -fvirtual-function-elimination \ -fvisibility=hidden LDFLAGS = -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 LDCFLAGS = -Wl,-allow-multiple-definition LDCXXFLAGS = LDFFLAGS = -Wl,-mllvm -Wl,-inline-recursion=4 \ -Wl,-mllvm -Wl,-lsr-in-nested-loop \ -Wl,-mllvm -Wl,-enable-iv-split ############################## # intspeed base tuning flags # ############################## intspeed=base: EXTRA_LIBS = -fopenmp=libomp \ -lomp \ -lamdlibm \ -lflang \ -lm EXTRA_CLIBS = -lamdalloc EXTRA_CXXLIBS = -lamdalloc-ext EXTRA_FLIBS = -lamdalloc submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} ############################## # intspeed peak tuning flags # ############################## intspeed=peak: submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} ############################# # fpspeed base tuning flags # ############################# fpspeed=base: submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} ############################# # fpspeed peak tuning flags # ############################# fpspeed=peak: submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} ##################### # Peak tuning flags # ##################### default=peak: COPTIMIZE = $(OPT_ROOT_PEAK) -fstruct-layout=9 \ -mllvm -unroll-threshold=50 \ -fremap-arrays \ -fstrip-mining \ -mllvm -inline-threshold=1000 \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP -Wno-return-type \ -zopt CXXOPTIMIZE = $(OPT_ROOT_PEAK) -finline-aggressive \ -mllvm -unroll-threshold=100 \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -zopt FOPTIMIZE = $(OPT_ROOT_PEAK) -Mrecursive \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -zopt LDFLAGS = -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 LDFFLAGS = -Wl,-mllvm -Wl,-enable-X86-prefetching LDCXXFLAGS = -Wl,-mllvm -Wl,-x86-use-vzeroupper=false EXTRA_LIBS = -fopenmp=libomp \ -lomp \ -lamdlibm \ -lamdalloc \ -lflang \ -lm 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: 603.bwaves_s=peak: #lang='F' FOPTIMIZE = -Ofast \ $(OPT_ROOT) \ -Mrecursive \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -fvector-transform \ -fscalar-transform submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 607.cactuBSSN_s=peak: #lang='CXX,C,F' submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 619.lbm_s=peak: submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 620.omnetpp_s=peak: #lang='CXX' EXTRA_LIBS = -fopenmp=libomp \ -lomp \ -lamdlibm \ -lamdalloc-ext \ -lflang -lm 621.wrf_s=peak: #lang='F,C' FOPTIMIZE = $(OPT_ROOT_BASE) \ -Mrecursive \ -funroll-loops \ -mllvm -lsr-in-nested-loop \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -zopt submit = ${THP_NEVER}; ${DEFAULT_SUBMIT} 623.xalancbmk_s=peak: #lang='CXX' EXTRA_CXXFLAGS = -mllvm -do-block-reorder=aggressive \ -fvirtual-function-elimination -fvisibility=hidden LDFLAGS = -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 \ -Wl,-mllvm -Wl,-do-block-reorder=aggressive EXTRA_LIBS = -fopenmp=libomp \ -lomp \ -lamdlibm \ -lamdalloc-ext \ -lflang \ -lm 627.cam4_s=peak: #lang='F,C' LDFLAGS = -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 628.pop2_s=peak: #lang='F,C' FOPTIMIZE = $(OPT_ROOT) \ -Ofast \ -Mrecursive \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -fvector-transform \ -fscalar-transform submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 638.imagick_s=peak: #lang='C' LDFLAGS = -Wl,-mllvm -Wl,-align-all-nofallthru-blocks=6 \ -Wl,-mllvm -Wl,-reduce-array-computations=3 submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 644.nab_s=peak: #lang='C' LDFLAGS = -Wl,-mllvm -Wl,-region-vectorize submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 649.fotonik3d_s=peak: #lang='F' ENV_PGHPF_ZMEM = yes submit = ${THP_ALWAYS}; ${DEFAULT_SUBMIT} 654.roms_s=peak: #lang='F' FOPTIMIZE = -Ofast \ $(OPT_ROOT) \ -Mrecursive \ -mllvm -reduce-array-computations=3 \ -DSPEC_OPENMP \ -fvector-transform \ -fscalar-transform submit = ${THP_MADVISE}; ${DEFAULT_SUBMIT} 657.xz_s=peak: #lang='C' ENV_LIBOMP_NUM_HIDDEN_HELPER_THREADS = 8 # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/amd_speed_aocc400_znver4_A1_flags.inc' # Dell #include: Dell.inc # ----- Begin inclusion of 'Dell.inc' ############################################################################ #---------------------------- # Dell #--------------------------- # #------------------------------------------- # **** DO NOT EDIT BELOW HERE!!! #------------------------------------------- # Defined only if called from Automation %ifdef %{DL-BIOSinc} fprate,fpspeed,intrate,intspeed: power_management000 = BIOS and OS set to prefer performance power_management001 = at the cost of additional power usage. # #include: Dell-flags.inc # ----- Begin inclusion of 'Dell-flags.inc' ############################################################################ #------------------------------------------------------- # Dell platform flags (Auto) #------------------------------------------------------- default: flagsurl001=http://www.spec.org/cpu2017/flags/Dell-Platform-Flags-PowerEdge-AMD-EPYC-v1.2.xml # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/Dell-flags.inc' #include: %{DL-BIOSinc} # ----- Begin inclusion of 'Dell-BIOS_EPYC-4.inc' ############################################################################ #------------------------------------------------------- # Dell # # AMD EPYC 4 (Genoa) #------------------------------------------------------- # # BIOS Settings # fprate,fpspeed,intrate,intspeed: notes_plat_form_000 = notes_plat_form_005 = BIOS settings: notes_plat_form_010 = DRAM Refresh Delay : Performance notes_plat_form_015 = DIMM Self Healing on notes_plat_form_020 = Uncorrectable Memory Error : Disabled notes_plat_form_025 = %ifndef %{DL-BIOS-LogProc} notes_plat_form_030 = Logical Processor : Disabled %endif notes_plat_form_035 = Virtualization Technology : Disabled fprate: notes_plat_form_215 = L1 Stride Prefetcher: : Disabled fprate,fpspeed,intrate,intspeed: %ifdef %{DL-BIOS-NPS} notes_plat_form_040 = NUMA Nodes per Socket : 2 %endif %ifdef %{DL-BIOS-L3NUMA} %endif notes_plat_form_045 = notes_plat_form_050 = System Profile : Custom fpspeed,intspeed: notes_plat_form_055 = C-States : Disabled fprate,fpspeed,intrate,intspeed: notes_plat_form_060 = Memory Patrol Scrub : Disabled notes_plat_form_065 = PCI ASPM L1 Link notes_plat_form_070 = Power Management : Disabled notes_plat_form_075 = Determinism Slider : Power Determinism fpspeed,intspeed: notes_plat_form_080 = Algorithm Performance notes_plat_form_085 = Boost Disable (ApbDis) : Enabled # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/Dell-BIOS_EPYC-4.inc' #include: Dell-LIC.inc # ----- Begin inclusion of 'Dell-LIC.inc' ############################################################################ #------------------------------------------------------- # Dell (Dell Inc.) # # SPEC Licensing Info #------------------------------------------------------- fprate,fpspeed,intrate,intspeed: hw_vendor = Dell Inc. tester = Dell Inc. test_sponsor = Dell Inc. prepared_by = Dell v4.8.1 # Old number 55 license_num = 6573 # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/Dell-LIC.inc' #include: Dell-cleanup.inc # ----- Begin inclusion of 'Dell-cleanup.inc' ############################################################################ #------------------------------------------------------- # Dell EMC (Dell Inc.) # # AMD #------------------------------------------------------- # cleanup - sysinfo/AMD scripts fprate,fpspeed,intspeed,intrate: #sw_os000 = %undef% #sw_os001 = %undef% sw_os002 = %undef% #hw_memory000 = %undef% hw_memory001 = %undef% hw_memory002 = %undef% #hw_model000 = %undef% #hw_model001 = %undef% # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/Dell-cleanup.inc' # #include: Dell-Autogen.inc # ----- Begin inclusion of 'Dell-Autogen.inc' ############################################################################ fprate,fpspeed,intrate,intspeed: hw_model = PowerEdge R6625 (AMD EPYC 9554 64-Core Processor) hw_cpu_name = AMD EPYC 9554 hw_cpu_max_mhz = 3750 hw_ncpuorder = 1,2 chips hw_ncores = 128 hw_nthreadspercore = 1 fw_bios = Version 1.4.6 released Jul-2023 sw_state = Run level 5 (graphical multi-user) sw_file = tmpfs hw_disk = 80 GB on tmpfs notes_tmpfs_000 = notes_tmpfs_005 = Benchmark run from a 80 GB ramdisk created with the cmd: "mount -t tmpfs -o size=80G tmpfs /mnt/ramdisk" sw_os000 = Ubuntu 22.04.3 LTS sw_os001 = 5.15.0-84-generic hw_cpu_nominal_mhz = 3100 hw_memory000 = 1536 GB (24 x 64 GB 2Rx4 PC5-4800B-R) sw_avail = Sep-2023 hw_avail = May-2023 # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/Dell-Autogen.inc' %endif # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/config/Dell.inc' # 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 /mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1/bin/sysinfo notes_plat_sysinfo_010 = Rev: r6732 of 2022-11-07 fe91c89b7ed5c36ae2c92cc097bec197 notes_plat_sysinfo_015 = running on amd-spa Fri Nov 10 00:55:41 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 249 (249.11-0ubuntu3.10) 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. tuned-adm active notes_plat_sysinfo_125 = 16. sysctl notes_plat_sysinfo_130 = 17. /sys/kernel/mm/transparent_hugepage notes_plat_sysinfo_135 = 18. /sys/kernel/mm/transparent_hugepage/khugepaged notes_plat_sysinfo_140 = 19. OS release notes_plat_sysinfo_145 = 20. Disk information notes_plat_sysinfo_150 = 21. /sys/devices/virtual/dmi/id notes_plat_sysinfo_155 = 22. dmidecode notes_plat_sysinfo_160 = 23. BIOS notes_plat_sysinfo_165 = ------------------------------------------------------------ notes_plat_sysinfo_170 = notes_plat_sysinfo_175 = ------------------------------------------------------------ notes_plat_sysinfo_180 = 1. uname -a notes_plat_sysinfo_185 = Linux amd-spa 5.15.0-84-generic #93-Ubuntu SMP Tue Sep 5 17:16:10 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux notes_plat_sysinfo_190 = notes_plat_sysinfo_195 = ------------------------------------------------------------ notes_plat_sysinfo_200 = 2. w notes_plat_sysinfo_205 = 00:55:41 up 2 min, 2 users, load average: 0.26, 0.10, 0.03 notes_plat_sysinfo_210 = USER TTY FROM LOGIN@ IDLE JCPU PCPU WHAT notes_plat_sysinfo_215 = root tty1 - 00:54 1:01 0.19s 0.14s sudo su notes_plat_sysinfo_220 = root pts/0 - 00:54 37.00s 1.20s 0.30s /bin/bash ./amd_speed_aocc400_znver4_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 = time(seconds) unlimited notes_plat_sysinfo_265 = file(blocks) unlimited notes_plat_sysinfo_270 = data(kbytes) unlimited notes_plat_sysinfo_275 = stack(kbytes) unlimited notes_plat_sysinfo_280 = coredump(blocks) 0 notes_plat_sysinfo_285 = memory(kbytes) unlimited notes_plat_sysinfo_290 = locked memory(kbytes) 2097152 notes_plat_sysinfo_295 = process 6190361 notes_plat_sysinfo_300 = nofiles 1024 notes_plat_sysinfo_305 = vmemory(kbytes) unlimited notes_plat_sysinfo_310 = locks unlimited notes_plat_sysinfo_315 = rtprio 0 notes_plat_sysinfo_320 = notes_plat_sysinfo_325 = ------------------------------------------------------------ notes_plat_sysinfo_330 = 5. sysinfo process ancestry notes_plat_sysinfo_335 = /sbin/init notes_plat_sysinfo_340 = /bin/login -p -- notes_plat_sysinfo_345 = -bash notes_plat_sysinfo_350 = sudo su notes_plat_sysinfo_355 = sudo su notes_plat_sysinfo_360 = su notes_plat_sysinfo_365 = bash notes_plat_sysinfo_370 = /bin/bash ./DELL_speed.sh notes_plat_sysinfo_375 = /bin/bash ./dell-run-main.sh speed notes_plat_sysinfo_380 = /bin/bash ./dell-run-main.sh speed notes_plat_sysinfo_385 = /bin/bash ./dell-run-speccpu.sh speed --define DL-BIOSinc=Dell-BIOS_EPYC-4.inc --define DL-BIOS-adddcD=1 notes_plat_sysinfo_390 = --define DL-VERS=v4.8.1 --output_format html,pdf,txt notes_plat_sysinfo_395 = python3 ./run_amd_speed_aocc400_znver4_A1.py notes_plat_sysinfo_400 = /bin/bash ./amd_speed_aocc400_znver4_A1.sh notes_plat_sysinfo_405 = runcpu --config amd_speed_aocc400_znver4_A1.cfg --tune all --reportable --iterations 2 --define notes_plat_sysinfo_410 = DL-BIOS-L3NUMA=1 --define DL-BIOS-NPS=2 --define DL-BIOSinc=Dell-BIOS_EPYC-4.inc --define DL-BIOS-adddcD=1 notes_plat_sysinfo_415 = --define DL-VERS=v4.8.1 --output_format html,pdf,txt intspeed notes_plat_sysinfo_420 = runcpu --configfile amd_speed_aocc400_znver4_A1.cfg --tune all --reportable --iterations 2 --define notes_plat_sysinfo_425 = DL-BIOS-L3NUMA=1 --define DL-BIOS-NPS=2 --define DL-BIOSinc=Dell-BIOS_EPYC-4.inc --define DL-BIOS-adddcD=1 notes_plat_sysinfo_430 = --define DL-VERS=v4.8.1 --output_format html,pdf,txt --nopower --runmode speed --tune base:peak --size notes_plat_sysinfo_435 = test:train:refspeed intspeed --nopreenv --note-preenv --logfile notes_plat_sysinfo_440 = $SPEC/tmp/CPU2017.001/templogs/preenv.intspeed.001.0.log --lognum 001.0 --from_runcpu 2 notes_plat_sysinfo_445 = specperl $SPEC/bin/sysinfo notes_plat_sysinfo_450 = $SPEC = /mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1 notes_plat_sysinfo_455 = notes_plat_sysinfo_460 = ------------------------------------------------------------ notes_plat_sysinfo_465 = 6. /proc/cpuinfo notes_plat_sysinfo_470 = model name : AMD EPYC 9554 64-Core Processor notes_plat_sysinfo_475 = vendor_id : AuthenticAMD notes_plat_sysinfo_480 = cpu family : 25 notes_plat_sysinfo_485 = model : 17 notes_plat_sysinfo_490 = stepping : 1 notes_plat_sysinfo_495 = microcode : 0xa10113e notes_plat_sysinfo_500 = bugs : sysret_ss_attrs spectre_v1 spectre_v2 spec_store_bypass notes_plat_sysinfo_505 = TLB size : 3584 4K pages notes_plat_sysinfo_510 = cpu cores : 64 notes_plat_sysinfo_515 = siblings : 64 notes_plat_sysinfo_520 = 2 physical ids (chips) notes_plat_sysinfo_525 = 128 processors (hardware threads) notes_plat_sysinfo_530 = physical id 0: core ids 0-7,16-23,32-39,48-55,64-71,80-87,96-103,112-119 notes_plat_sysinfo_535 = physical id 1: core ids 0-7,16-23,32-39,48-55,64-71,80-87,96-103,112-119 notes_plat_sysinfo_540 = physical id 0: apicids 0-7,16-23,32-39,48-55,64-71,80-87,96-103,112-119 notes_plat_sysinfo_545 = physical id 1: apicids 128-135,144-151,160-167,176-183,192-199,208-215,224-231,240-247 notes_plat_sysinfo_550 = Caution: /proc/cpuinfo data regarding chips, cores, and threads is not necessarily reliable, especially for notes_plat_sysinfo_555 = virtualized systems. Use the above data carefully. notes_plat_sysinfo_560 = notes_plat_sysinfo_565 = ------------------------------------------------------------ notes_plat_sysinfo_570 = 7. lscpu notes_plat_sysinfo_575 = notes_plat_sysinfo_580 = From lscpu from util-linux 2.37.2: notes_plat_sysinfo_585 = Architecture: x86_64 notes_plat_sysinfo_590 = CPU op-mode(s): 32-bit, 64-bit notes_plat_sysinfo_595 = Address sizes: 52 bits physical, 57 bits virtual notes_plat_sysinfo_600 = Byte Order: Little Endian notes_plat_sysinfo_605 = CPU(s): 128 notes_plat_sysinfo_610 = On-line CPU(s) list: 0-127 notes_plat_sysinfo_615 = Vendor ID: AuthenticAMD notes_plat_sysinfo_620 = Model name: AMD EPYC 9554 64-Core Processor notes_plat_sysinfo_625 = CPU family: 25 notes_plat_sysinfo_630 = Model: 17 notes_plat_sysinfo_635 = Thread(s) per core: 1 notes_plat_sysinfo_640 = Core(s) per socket: 64 notes_plat_sysinfo_645 = Socket(s): 2 notes_plat_sysinfo_650 = Stepping: 1 notes_plat_sysinfo_655 = BogoMIPS: 6202.07 notes_plat_sysinfo_660 = Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 notes_plat_sysinfo_665 = clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp notes_plat_sysinfo_670 = lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf notes_plat_sysinfo_675 = rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic notes_plat_sysinfo_680 = movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic notes_plat_sysinfo_685 = cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce notes_plat_sysinfo_690 = topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 notes_plat_sysinfo_695 = cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall notes_plat_sysinfo_700 = fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq notes_plat_sysinfo_705 = rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw notes_plat_sysinfo_710 = avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc notes_plat_sysinfo_715 = cqm_mbm_total cqm_mbm_local avx512_bf16 clzero irperf xsaveerptr rdpru notes_plat_sysinfo_720 = wbnoinvd amd_ppin cppc arat npt lbrv svm_lock nrip_save tsc_scale notes_plat_sysinfo_725 = vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic notes_plat_sysinfo_730 = v_vmsave_vmload vgif v_spec_ctrl avx512vbmi umip pku ospke avx512_vbmi2 notes_plat_sysinfo_735 = gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 notes_plat_sysinfo_740 = rdpid overflow_recov succor smca fsrm flush_l1d notes_plat_sysinfo_745 = Virtualization: AMD-V notes_plat_sysinfo_750 = L1d cache: 4 MiB (128 instances) notes_plat_sysinfo_755 = L1i cache: 4 MiB (128 instances) notes_plat_sysinfo_760 = L2 cache: 128 MiB (128 instances) notes_plat_sysinfo_765 = L3 cache: 512 MiB (16 instances) notes_plat_sysinfo_770 = NUMA node(s): 8 notes_plat_sysinfo_775 = NUMA node0 CPU(s): 0-15 notes_plat_sysinfo_780 = NUMA node1 CPU(s): 16-31 notes_plat_sysinfo_785 = NUMA node2 CPU(s): 32-47 notes_plat_sysinfo_790 = NUMA node3 CPU(s): 48-63 notes_plat_sysinfo_795 = NUMA node4 CPU(s): 64-79 notes_plat_sysinfo_800 = NUMA node5 CPU(s): 80-95 notes_plat_sysinfo_805 = NUMA node6 CPU(s): 96-111 notes_plat_sysinfo_810 = NUMA node7 CPU(s): 112-127 notes_plat_sysinfo_815 = Vulnerability Gather data sampling: Not affected notes_plat_sysinfo_820 = Vulnerability Itlb multihit: Not affected notes_plat_sysinfo_825 = Vulnerability L1tf: Not affected notes_plat_sysinfo_830 = Vulnerability Mds: Not affected notes_plat_sysinfo_835 = Vulnerability Meltdown: Not affected notes_plat_sysinfo_840 = Vulnerability Mmio stale data: Not affected notes_plat_sysinfo_845 = Vulnerability Retbleed: Not affected notes_plat_sysinfo_850 = Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp notes_plat_sysinfo_855 = Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization notes_plat_sysinfo_860 = Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP disabled, RSB notes_plat_sysinfo_865 = filling, PBRSB-eIBRS Not affected notes_plat_sysinfo_870 = Vulnerability Srbds: Not affected notes_plat_sysinfo_875 = Vulnerability Tsx async abort: Not affected notes_plat_sysinfo_880 = notes_plat_sysinfo_885 = From lscpu --cache: notes_plat_sysinfo_890 = NAME ONE-SIZE ALL-SIZE WAYS TYPE LEVEL SETS PHY-LINE COHERENCY-SIZE notes_plat_sysinfo_895 = L1d 32K 4M 8 Data 1 64 1 64 notes_plat_sysinfo_900 = L1i 32K 4M 8 Instruction 1 64 1 64 notes_plat_sysinfo_905 = L2 1M 128M 8 Unified 2 2048 1 64 notes_plat_sysinfo_910 = L3 32M 512M 16 Unified 3 32768 1 64 notes_plat_sysinfo_915 = notes_plat_sysinfo_920 = ------------------------------------------------------------ notes_plat_sysinfo_925 = 8. numactl --hardware notes_plat_sysinfo_930 = NOTE: a numactl 'node' might or might not correspond to a physical chip. notes_plat_sysinfo_935 = available: 8 nodes (0-7) notes_plat_sysinfo_940 = node 0 cpus: 0-15 notes_plat_sysinfo_945 = node 0 size: 193077 MB notes_plat_sysinfo_950 = node 0 free: 192645 MB notes_plat_sysinfo_955 = node 1 cpus: 16-31 notes_plat_sysinfo_960 = node 1 size: 193530 MB notes_plat_sysinfo_965 = node 1 free: 193115 MB notes_plat_sysinfo_970 = node 2 cpus: 32-47 notes_plat_sysinfo_975 = node 2 size: 193530 MB notes_plat_sysinfo_980 = node 2 free: 193148 MB notes_plat_sysinfo_985 = node 3 cpus: 48-63 notes_plat_sysinfo_990 = node 3 size: 193514 MB notes_plat_sysinfo_995 = node 3 free: 193154 MB notes_plat_sysinfo_1000= node 4 cpus: 64-79 notes_plat_sysinfo_1005= node 4 size: 193530 MB notes_plat_sysinfo_1010= node 4 free: 189526 MB notes_plat_sysinfo_1015= node 5 cpus: 80-95 notes_plat_sysinfo_1020= node 5 size: 193530 MB notes_plat_sysinfo_1025= node 5 free: 193095 MB notes_plat_sysinfo_1030= node 6 cpus: 96-111 notes_plat_sysinfo_1035= node 6 size: 193483 MB notes_plat_sysinfo_1040= node 6 free: 193066 MB notes_plat_sysinfo_1045= node 7 cpus: 112-127 notes_plat_sysinfo_1050= node 7 size: 193504 MB notes_plat_sysinfo_1055= node 7 free: 193168 MB notes_plat_sysinfo_1060= node distances: notes_plat_sysinfo_1065= node 0 1 2 3 4 5 6 7 notes_plat_sysinfo_1070= 0: 10 12 12 12 32 32 32 32 notes_plat_sysinfo_1075= 1: 12 10 12 12 32 32 32 32 notes_plat_sysinfo_1080= 2: 12 12 10 12 32 32 32 32 notes_plat_sysinfo_1085= 3: 12 12 12 10 32 32 32 32 notes_plat_sysinfo_1090= 4: 32 32 32 32 10 12 12 12 notes_plat_sysinfo_1095= 5: 32 32 32 32 12 10 12 12 notes_plat_sysinfo_1100= 6: 32 32 32 32 12 12 10 12 notes_plat_sysinfo_1105= 7: 32 32 32 32 12 12 12 10 notes_plat_sysinfo_1110= notes_plat_sysinfo_1115= ------------------------------------------------------------ notes_plat_sysinfo_1120= 9. /proc/meminfo notes_plat_sysinfo_1125= MemTotal: 1584848568 kB notes_plat_sysinfo_1130= notes_plat_sysinfo_1135= ------------------------------------------------------------ notes_plat_sysinfo_1140= 10. who -r notes_plat_sysinfo_1145= run-level 5 Nov 10 00:53 notes_plat_sysinfo_1150= notes_plat_sysinfo_1155= ------------------------------------------------------------ notes_plat_sysinfo_1160= 11. Systemd service manager version: systemd 249 (249.11-0ubuntu3.10) notes_plat_sysinfo_1165= Default Target Status notes_plat_sysinfo_1170= graphical running notes_plat_sysinfo_1175= notes_plat_sysinfo_1180= ------------------------------------------------------------ notes_plat_sysinfo_1185= 12. Services, from systemctl list-unit-files notes_plat_sysinfo_1190= STATE UNIT FILES notes_plat_sysinfo_1195= enabled ModemManager apparmor blk-availability console-setup cron dmesg e2scrub_reap finalrd notes_plat_sysinfo_1200= getty@ gpu-manager grub-common grub-initrd-fallback irqbalance keyboard-setup lm-sensors notes_plat_sysinfo_1205= lvm2-monitor lxd-agent multipathd networkd-dispatcher open-vm-tools pollinate rsyslog notes_plat_sysinfo_1210= secureboot-db setvtrgb ssh systemd-networkd systemd-pstore systemd-resolved notes_plat_sysinfo_1215= systemd-timesyncd thermald tuned ua-reboot-cmds ubuntu-advantage udisks2 ufw vgauth notes_plat_sysinfo_1220= enabled-runtime netplan-ovs-cleanup systemd-fsck-root systemd-remount-fs notes_plat_sysinfo_1225= disabled console-getty debug-shell iscsid nftables open-iscsi rsync serial-getty@ notes_plat_sysinfo_1230= systemd-boot-check-no-failures systemd-network-generator systemd-sysext notes_plat_sysinfo_1235= systemd-time-wait-sync upower notes_plat_sysinfo_1240= generated apport notes_plat_sysinfo_1245= indirect uuidd notes_plat_sysinfo_1250= masked cryptdisks cryptdisks-early hwclock lvm2 multipath-tools-boot rc rcS screen-cleanup sudo notes_plat_sysinfo_1255= systemd-networkd-wait-online x11-common notes_plat_sysinfo_1260= notes_plat_sysinfo_1265= ------------------------------------------------------------ notes_plat_sysinfo_1270= 13. Linux kernel boot-time arguments, from /proc/cmdline notes_plat_sysinfo_1275= BOOT_IMAGE=/vmlinuz-5.15.0-84-generic notes_plat_sysinfo_1280= root=/dev/mapper/ubuntu--vg-ubuntu--lv notes_plat_sysinfo_1285= ro notes_plat_sysinfo_1290= notes_plat_sysinfo_1295= ------------------------------------------------------------ notes_plat_sysinfo_1300= 14. cpupower frequency-info notes_plat_sysinfo_1305= analyzing CPU 0: notes_plat_sysinfo_1310= Unable to determine current policy notes_plat_sysinfo_1315= boost state support: notes_plat_sysinfo_1320= Supported: yes notes_plat_sysinfo_1325= Active: yes notes_plat_sysinfo_1330= Boost States: 0 notes_plat_sysinfo_1335= Total States: 3 notes_plat_sysinfo_1340= Pstate-P0: 3100MHz notes_plat_sysinfo_1345= notes_plat_sysinfo_1350= ------------------------------------------------------------ notes_plat_sysinfo_1355= 15. tuned-adm active notes_plat_sysinfo_1360= Current active profile: latency-performance notes_plat_sysinfo_1365= notes_plat_sysinfo_1370= ------------------------------------------------------------ notes_plat_sysinfo_1375= 16. sysctl notes_plat_sysinfo_1380= kernel.numa_balancing 1 notes_plat_sysinfo_1385= kernel.randomize_va_space 0 notes_plat_sysinfo_1390= vm.compaction_proactiveness 20 notes_plat_sysinfo_1395= vm.dirty_background_bytes 0 notes_plat_sysinfo_1400= vm.dirty_background_ratio 3 notes_plat_sysinfo_1405= vm.dirty_bytes 0 notes_plat_sysinfo_1410= vm.dirty_expire_centisecs 3000 notes_plat_sysinfo_1415= vm.dirty_ratio 8 notes_plat_sysinfo_1420= vm.dirty_writeback_centisecs 500 notes_plat_sysinfo_1425= vm.dirtytime_expire_seconds 43200 notes_plat_sysinfo_1430= vm.extfrag_threshold 500 notes_plat_sysinfo_1435= vm.min_unmapped_ratio 1 notes_plat_sysinfo_1440= vm.nr_hugepages 0 notes_plat_sysinfo_1445= vm.nr_hugepages_mempolicy 0 notes_plat_sysinfo_1450= vm.nr_overcommit_hugepages 0 notes_plat_sysinfo_1455= vm.swappiness 1 notes_plat_sysinfo_1460= vm.watermark_boost_factor 15000 notes_plat_sysinfo_1465= vm.watermark_scale_factor 10 notes_plat_sysinfo_1470= vm.zone_reclaim_mode 1 notes_plat_sysinfo_1475= notes_plat_sysinfo_1480= ------------------------------------------------------------ notes_plat_sysinfo_1485= 17. /sys/kernel/mm/transparent_hugepage notes_plat_sysinfo_1490= defrag [always] defer defer+madvise madvise never notes_plat_sysinfo_1495= enabled [always] madvise never notes_plat_sysinfo_1500= hpage_pmd_size 2097152 notes_plat_sysinfo_1505= shmem_enabled always within_size advise [never] deny force notes_plat_sysinfo_1510= notes_plat_sysinfo_1515= ------------------------------------------------------------ notes_plat_sysinfo_1520= 18. /sys/kernel/mm/transparent_hugepage/khugepaged notes_plat_sysinfo_1525= alloc_sleep_millisecs 60000 notes_plat_sysinfo_1530= defrag 1 notes_plat_sysinfo_1535= max_ptes_none 511 notes_plat_sysinfo_1540= max_ptes_shared 256 notes_plat_sysinfo_1545= max_ptes_swap 64 notes_plat_sysinfo_1550= pages_to_scan 4096 notes_plat_sysinfo_1555= scan_sleep_millisecs 10000 notes_plat_sysinfo_1560= notes_plat_sysinfo_1565= ------------------------------------------------------------ notes_plat_sysinfo_1570= 19. OS release notes_plat_sysinfo_1575= From /etc/*-release /etc/*-version notes_plat_sysinfo_1580= os-release Ubuntu 22.04.3 LTS notes_plat_sysinfo_1585= notes_plat_sysinfo_1590= ------------------------------------------------------------ notes_plat_sysinfo_1595= 20. Disk information notes_plat_sysinfo_1600= SPEC is set to: /mnt/ramdisk/cpu2017-1.1.9-aocc400-znver4-A1.1 notes_plat_sysinfo_1605= Filesystem Type Size Used Avail Use% Mounted on notes_plat_sysinfo_1610= tmpfs tmpfs 80G 3.4G 77G 5% /mnt/ramdisk notes_plat_sysinfo_1615= notes_plat_sysinfo_1620= ------------------------------------------------------------ notes_plat_sysinfo_1625= 21. /sys/devices/virtual/dmi/id notes_plat_sysinfo_1630= Vendor: Dell Inc. notes_plat_sysinfo_1635= Product: PowerEdge R6625 notes_plat_sysinfo_1640= Product Family: PowerEdge notes_plat_sysinfo_1645= Serial: BGP4016 notes_plat_sysinfo_1650= notes_plat_sysinfo_1655= ------------------------------------------------------------ notes_plat_sysinfo_1660= 22. dmidecode notes_plat_sysinfo_1665= Additional information from dmidecode 3.3 follows. WARNING: Use caution when you interpret this section. notes_plat_sysinfo_1670= The 'dmidecode' program reads system data which is "intended to allow hardware to be accurately notes_plat_sysinfo_1675= determined", but the intent may not be met, as there are frequent changes to hardware, firmware, and the notes_plat_sysinfo_1680= "DMTF SMBIOS" standard. notes_plat_sysinfo_1685= Memory: notes_plat_sysinfo_1690= 22x 802C0000802C MTC40F2046S1RC48BA1 64 GB 2 rank 4800 notes_plat_sysinfo_1695= 2x 80AD000080AD HMCG94MEBRA109N 64 GB 2 rank 4800 notes_plat_sysinfo_1700= notes_plat_sysinfo_1705= notes_plat_sysinfo_1710= ------------------------------------------------------------ notes_plat_sysinfo_1715= 23. BIOS notes_plat_sysinfo_1720= (This section combines info from /sys/devices and dmidecode.) notes_plat_sysinfo_1725= BIOS Vendor: Dell Inc. notes_plat_sysinfo_1730= BIOS Version: 1.4.6 notes_plat_sysinfo_1735= BIOS Date: 07/06/2023 notes_plat_sysinfo_1740= BIOS Revision: 1.4 hw_cpu_name = AMD EPYC 9554 hw_disk = 80 GB add more disk info here hw_nchips = 2 hw_ncores = 128 hw_nthreadspercore = 1 prepared_by = root (is never output, only tags rawfile) sw_file = tmpfs sw_os001 = Ubuntu 22.04.3 LTS sw_state = Run level 5 (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 = 1 620.omnetpp_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