# Invocation command line: # /root/speccpu/bin/harness/runcpu --configfile amd_speed_aocc400_znver4_A1.cfg --tune base --reportable --iterations 2 --nopower --runmode speed --tune base --size test:train:refspeed fpspeed # 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-A1.2.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: October 12, 2023 / 11:12:58 # # This file is automatically generated during a SPEC CPU2017 run. # # To modify inc file generation, please consult the readme file or the run # script. ################################################################################ ################################################################################ ################################################################################ ################################################################################ # The following macros are generated for use in the cfg file. ################################################################################ ################################################################################ %define logical_core_count 192 %define physical_core_count 192 %define physical_core_max 191 %define logical_core_max 191 ################################################################################ ################################################################################ # 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 '9654' section of CPU info ################################################################################ # default preENV thread settings: default: preENV_OMP_THREAD_LIMIT = 192 preENV_GOMP_CPU_AFFINITY = 0-191 ################################################################################ ################################################################################ # intspeed base thread counts: intspeed=base: threads = 192 ENV_GOMP_CPU_AFFINITY = 0-191 bind0 = numactl --physcpubind=0-191 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # fpspeed base thread counts: fpspeed=base: threads = 192 ENV_GOMP_CPU_AFFINITY = 0-191 bind0 = numactl --physcpubind=0-191 submit = echo "$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 ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 192 603.bwaves_s,619.lbm_s,621.wrf_s,628.pop2_s,649.fotonik3d_s=peak: threads = 192 ENV_GOMP_CPU_AFFINITY = 0-191 bind0 = numactl --physcpubind=0-191 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 192 607.cactuBSSN_s,627.cam4_s,638.imagick_s,644.nab_s,657.xz_s=peak: threads = 192 ENV_GOMP_CPU_AFFINITY = 0-191 bind0 = numactl --physcpubind=0-191 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 192 654.roms_s=peak: threads = 192 ENV_GOMP_CPU_AFFINITY = 0 96 1 97 2 98 3 99 4 100 5 101 6 102 7 103 8 104 9 105 10 106 11 107 12 108 13 109 14 110 15 111 16 112 17 113 18 114 19 115 20 116 21 117 22 118 23 119 24 120 25 121 26 122 27 123 28 124 29 125 30 126 31 127 32 128 33 129 34 130 35 131 36 132 37 133 38 134 39 135 40 136 41 137 42 138 43 139 44 140 45 141 46 142 47 143 48 144 49 145 50 146 51 147 52 148 53 149 54 150 55 151 56 152 57 153 58 154 59 155 60 156 61 157 62 158 63 159 64 160 65 161 66 162 67 163 68 164 69 165 70 166 71 167 72 168 73 169 74 170 75 171 76 172 77 173 78 174 79 175 80 176 81 177 82 178 83 179 84 180 85 181 86 182 87 183 88 184 89 185 90 186 91 187 92 188 93 189 94 190 95 191 bind0 = numactl --physcpubind=0-191 submit = echo "$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 =9050 tester =Quanta Computer Inc. test_sponsor =Quanta Computer Inc. hw_vendor =Quanta Cloud Technology hw_model000 =QuantaGrid D44N-1U hw_model001 =(2.40 GHz,AMD EPYC 9654) #--------- 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-2023 sw_avail =Sep-2023 hw_cpu_name =AMD EPYC 9654 hw_cpu_nominal_mhz =2400 hw_cpu_max_mhz =3700 hw_ncores =192 hw_nthreadspercore =1 hw_ncpuorder =1,2 chips hw_other =None # Other perf-relevant hw, or "None" fw_bios =Version 3A02 released Sep-2023 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 =384 MB I+D on chip per chip, hw_tcache001 = 32 MB shared / 8 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_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_003 = ################################################################################ # The following fields must be set here for FP benchmarks. ################################################################################ fpspeed: sw_peak_ptrsize =Not Applicable notes_os_thp_015 =To always enable THP for peak runs of: notes_os_thp_020 =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_025 ='echo madvise > /sys/kernel/mm/transparent_hugepage/enabled; echo always > /sys/kernel/mm/transparent_hugepage/defrag' notes_os_thp_030 =run as root. notes_os_thp_035 =To disable THP for peak runs of 621.wrf_s: notes_os_thp_040 ='echo never > /sys/kernel/mm/transparent_hugepage/enabled; echo always > /sys/kernel/mm/transparent_hugepage/defrag' notes_os_thp_045 =run as root. notes_os_thp_050 =To enable THP only on request for peak runs of 654.roms_s: notes_os_thp_055 ='echo madvise > /sys/kernel/mm/transparent_hugepage/enabled; echo madvise > /sys/kernel/mm/transparent_hugepage/defrag' notes_os_thp_060 =run as root. ################################################################################ # The following fields must be set here or they will be overwritten by sysinfo. ################################################################################ intspeed,fpspeed: hw_disk =1 x 3.84 TB NVMe SSD hw_memory000 =1536 GB (24 x 64 GB 2Rx4 PC5-4800B-R) hw_memory002 = hw_nchips =2 prepared_by =prepared by Quanta Computer Inc. sw_file =xfs sw_os000 =SUSE Linux Enterprise Server 15 SP4 sw_os001 =Kernel 5.14.21-150400.22-default 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 '/root/speccpu/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-A1.2.xml flagsurl001 = http://www.spec.org/cpu2017/flags/Quanta-Computer-Inc-amd-speccpu-setting-v1.1_AMD_Genoa.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 '/root/speccpu/config/amd_speed_aocc400_znver4_A1_flags.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 /root/speccpu/bin/sysinfo notes_plat_sysinfo_010 = Rev: r6732 of 2022-11-07 fe91c89b7ed5c36ae2c92cc097bec197 notes_plat_sysinfo_015 = running on localhost Thu Oct 12 11:13:33 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+suse.124.g2bc0b2c447) 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 localhost 5.14.21-150400.22-default #1 SMP PREEMPT_DYNAMIC Wed May 11 06:57:18 UTC 2022 (49db222/lp) notes_plat_sysinfo_190 = x86_64 x86_64 x86_64 GNU/Linux notes_plat_sysinfo_195 = notes_plat_sysinfo_200 = ------------------------------------------------------------ notes_plat_sysinfo_205 = 2. w notes_plat_sysinfo_210 = 11:13:33 up 19 min, 2 users, load average: 60.16, 133.27, 99.56 notes_plat_sysinfo_215 = USER TTY FROM LOGIN@ IDLE JCPU PCPU WHAT notes_plat_sysinfo_220 = root tty1 - 10:54 37.00s 1.14s 0.08s /bin/bash ./amd_speed_aocc400_znver4_A1.sh notes_plat_sysinfo_225 = root tty2 - 11:08 20.00s 0.17s 0.01s vim notes_plat_sysinfo_230 = CPU2017-D44N-9654-2.40GHz-3A02-1.5TB_4800MHz-suse15sp4-amd_speed_aocc400_znver4_A1-20231012_1056/CPU2017.00 notes_plat_sysinfo_235 = 1.fpspeed.txt notes_plat_sysinfo_240 = notes_plat_sysinfo_245 = ------------------------------------------------------------ notes_plat_sysinfo_250 = 3. Username notes_plat_sysinfo_255 = From environment variable $USER: root notes_plat_sysinfo_260 = notes_plat_sysinfo_265 = ------------------------------------------------------------ notes_plat_sysinfo_270 = 4. ulimit -a notes_plat_sysinfo_275 = core file size (blocks, -c) unlimited notes_plat_sysinfo_280 = data seg size (kbytes, -d) unlimited notes_plat_sysinfo_285 = scheduling priority (-e) 0 notes_plat_sysinfo_290 = file size (blocks, -f) unlimited notes_plat_sysinfo_295 = pending signals (-i) 6189302 notes_plat_sysinfo_300 = max locked memory (kbytes, -l) 2097152 notes_plat_sysinfo_305 = max memory size (kbytes, -m) unlimited notes_plat_sysinfo_310 = open files (-n) 1024000 notes_plat_sysinfo_315 = pipe size (512 bytes, -p) 8 notes_plat_sysinfo_320 = POSIX message queues (bytes, -q) 819200 notes_plat_sysinfo_325 = real-time priority (-r) 0 notes_plat_sysinfo_330 = stack size (kbytes, -s) unlimited notes_plat_sysinfo_335 = cpu time (seconds, -t) unlimited notes_plat_sysinfo_340 = max user processes (-u) 6189302 notes_plat_sysinfo_345 = virtual memory (kbytes, -v) unlimited notes_plat_sysinfo_350 = file locks (-x) unlimited notes_plat_sysinfo_355 = notes_plat_sysinfo_360 = ------------------------------------------------------------ notes_plat_sysinfo_365 = 5. sysinfo process ancestry notes_plat_sysinfo_370 = /usr/lib/systemd/systemd --switched-root --system --deserialize 30 notes_plat_sysinfo_375 = login -- root notes_plat_sysinfo_380 = -bash notes_plat_sysinfo_385 = python3 ./run_amd_speed_aocc400_znver4_A1.py notes_plat_sysinfo_390 = /bin/bash ./amd_speed_aocc400_znver4_A1.sh notes_plat_sysinfo_395 = runcpu --config amd_speed_aocc400_znver4_A1.cfg --tune base --reportable --iterations 2 fpspeed notes_plat_sysinfo_400 = runcpu --configfile amd_speed_aocc400_znver4_A1.cfg --tune base --reportable --iterations 2 --nopower notes_plat_sysinfo_405 = --runmode speed --tune base --size test:train:refspeed fpspeed --nopreenv --note-preenv --logfile notes_plat_sysinfo_410 = $SPEC/tmp/CPU2017.001/templogs/preenv.fpspeed.001.0.log --lognum 001.0 --from_runcpu 2 notes_plat_sysinfo_415 = specperl $SPEC/bin/sysinfo notes_plat_sysinfo_420 = $SPEC = /root/speccpu notes_plat_sysinfo_425 = notes_plat_sysinfo_430 = ------------------------------------------------------------ notes_plat_sysinfo_435 = 6. /proc/cpuinfo notes_plat_sysinfo_440 = model name : AMD EPYC 9654 96-Core Processor notes_plat_sysinfo_445 = vendor_id : AuthenticAMD notes_plat_sysinfo_450 = cpu family : 25 notes_plat_sysinfo_455 = model : 17 notes_plat_sysinfo_460 = stepping : 1 notes_plat_sysinfo_465 = microcode : 0xa10113e notes_plat_sysinfo_470 = bugs : sysret_ss_attrs spectre_v1 spectre_v2 spec_store_bypass notes_plat_sysinfo_475 = TLB size : 3584 4K pages notes_plat_sysinfo_480 = cpu cores : 96 notes_plat_sysinfo_485 = siblings : 96 notes_plat_sysinfo_490 = 2 physical ids (chips) notes_plat_sysinfo_495 = 192 processors (hardware threads) notes_plat_sysinfo_500 = physical id 0: core ids 0-7,16-23,32-39,48-55,64-71,80-87,96-103,112-119,128-135,144-151,160-167,176-183 notes_plat_sysinfo_505 = physical id 1: core ids 0-7,16-23,32-39,48-55,64-71,80-87,96-103,112-119,128-135,144-151,160-167,176-183 notes_plat_sysinfo_510 = physical id 0: apicids 0-7,16-23,32-39,48-55,64-71,80-87,96-103,112-119,128-135,144-151,160-167,176-183 notes_plat_sysinfo_515 = physical id 1: apicids notes_plat_sysinfo_520 = 256-263,272-279,288-295,304-311,320-327,336-343,352-359,368-375,384-391,400-407,416-423,432-439 notes_plat_sysinfo_525 = Caution: /proc/cpuinfo data regarding chips, cores, and threads is not necessarily reliable, especially for notes_plat_sysinfo_530 = virtualized systems. Use the above data carefully. notes_plat_sysinfo_535 = notes_plat_sysinfo_540 = ------------------------------------------------------------ notes_plat_sysinfo_545 = 7. lscpu notes_plat_sysinfo_550 = notes_plat_sysinfo_555 = From lscpu from util-linux 2.37.2: notes_plat_sysinfo_560 = Architecture: x86_64 notes_plat_sysinfo_565 = CPU op-mode(s): 32-bit, 64-bit notes_plat_sysinfo_570 = Address sizes: 46 bits physical, 57 bits virtual notes_plat_sysinfo_575 = Byte Order: Little Endian notes_plat_sysinfo_580 = CPU(s): 192 notes_plat_sysinfo_585 = On-line CPU(s) list: 0-191 notes_plat_sysinfo_590 = Vendor ID: AuthenticAMD notes_plat_sysinfo_595 = Model name: AMD EPYC 9654 96-Core Processor notes_plat_sysinfo_600 = CPU family: 25 notes_plat_sysinfo_605 = Model: 17 notes_plat_sysinfo_610 = Thread(s) per core: 1 notes_plat_sysinfo_615 = Core(s) per socket: 96 notes_plat_sysinfo_620 = Socket(s): 2 notes_plat_sysinfo_625 = Stepping: 1 notes_plat_sysinfo_630 = Frequency boost: enabled notes_plat_sysinfo_635 = CPU max MHz: 3707.8120 notes_plat_sysinfo_640 = CPU min MHz: 1500.0000 notes_plat_sysinfo_645 = BogoMIPS: 4792.80 notes_plat_sysinfo_650 = Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 notes_plat_sysinfo_655 = clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm notes_plat_sysinfo_660 = constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl notes_plat_sysinfo_665 = pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe notes_plat_sysinfo_670 = popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy notes_plat_sysinfo_675 = abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext notes_plat_sysinfo_680 = perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 notes_plat_sysinfo_685 = invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 notes_plat_sysinfo_690 = avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap notes_plat_sysinfo_695 = avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt notes_plat_sysinfo_700 = xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local notes_plat_sysinfo_705 = avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv notes_plat_sysinfo_710 = svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists notes_plat_sysinfo_715 = pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl avx512vbmi notes_plat_sysinfo_720 = umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg notes_plat_sysinfo_725 = avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d sme notes_plat_sysinfo_730 = sev sev_es notes_plat_sysinfo_735 = Virtualization: AMD-V notes_plat_sysinfo_740 = L1d cache: 6 MiB (192 instances) notes_plat_sysinfo_745 = L1i cache: 6 MiB (192 instances) notes_plat_sysinfo_750 = L2 cache: 192 MiB (192 instances) notes_plat_sysinfo_755 = L3 cache: 768 MiB (24 instances) notes_plat_sysinfo_760 = NUMA node(s): 2 notes_plat_sysinfo_765 = NUMA node0 CPU(s): 0-95 notes_plat_sysinfo_770 = NUMA node1 CPU(s): 96-191 notes_plat_sysinfo_775 = Vulnerability Itlb multihit: Not affected notes_plat_sysinfo_780 = Vulnerability L1tf: Not affected notes_plat_sysinfo_785 = Vulnerability Mds: Not affected notes_plat_sysinfo_790 = Vulnerability Meltdown: Not affected notes_plat_sysinfo_795 = Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp notes_plat_sysinfo_800 = Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization notes_plat_sysinfo_805 = Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP disabled, RSB notes_plat_sysinfo_810 = filling notes_plat_sysinfo_815 = Vulnerability Srbds: Not affected notes_plat_sysinfo_820 = Vulnerability Tsx async abort: Not affected notes_plat_sysinfo_825 = notes_plat_sysinfo_830 = From lscpu --cache: notes_plat_sysinfo_835 = NAME ONE-SIZE ALL-SIZE WAYS TYPE LEVEL SETS PHY-LINE COHERENCY-SIZE notes_plat_sysinfo_840 = L1d 32K 6M 8 Data 1 64 1 64 notes_plat_sysinfo_845 = L1i 32K 6M 8 Instruction 1 64 1 64 notes_plat_sysinfo_850 = L2 1M 192M 8 Unified 2 2048 1 64 notes_plat_sysinfo_855 = L3 32M 768M 16 Unified 3 32768 1 64 notes_plat_sysinfo_860 = notes_plat_sysinfo_865 = ------------------------------------------------------------ notes_plat_sysinfo_870 = 8. numactl --hardware notes_plat_sysinfo_875 = NOTE: a numactl 'node' might or might not correspond to a physical chip. notes_plat_sysinfo_880 = available: 2 nodes (0-1) notes_plat_sysinfo_885 = node 0 cpus: 0-95 notes_plat_sysinfo_890 = node 0 size: 773614 MB notes_plat_sysinfo_895 = node 0 free: 770846 MB notes_plat_sysinfo_900 = node 1 cpus: 96-191 notes_plat_sysinfo_905 = node 1 size: 773735 MB notes_plat_sysinfo_910 = node 1 free: 772325 MB notes_plat_sysinfo_915 = node distances: notes_plat_sysinfo_920 = node 0 1 notes_plat_sysinfo_925 = 0: 10 32 notes_plat_sysinfo_930 = 1: 32 10 notes_plat_sysinfo_935 = notes_plat_sysinfo_940 = ------------------------------------------------------------ notes_plat_sysinfo_945 = 9. /proc/meminfo notes_plat_sysinfo_950 = MemTotal: 1584486068 kB notes_plat_sysinfo_955 = notes_plat_sysinfo_960 = ------------------------------------------------------------ notes_plat_sysinfo_965 = 10. who -r notes_plat_sysinfo_970 = run-level 3 Oct 12 10:54 notes_plat_sysinfo_975 = notes_plat_sysinfo_980 = ------------------------------------------------------------ notes_plat_sysinfo_985 = 11. Systemd service manager version: systemd 249 (249.11+suse.124.g2bc0b2c447) notes_plat_sysinfo_990 = Default Target Status notes_plat_sysinfo_995 = multi-user running notes_plat_sysinfo_1000= notes_plat_sysinfo_1005= ------------------------------------------------------------ notes_plat_sysinfo_1010= 12. Services, from systemctl list-unit-files notes_plat_sysinfo_1015= STATE UNIT FILES notes_plat_sysinfo_1020= enabled YaST2-Firstboot YaST2-Second-Stage apparmor auditd cron display-manager getty@ haveged notes_plat_sysinfo_1025= irqbalance issue-generator kbdsettings kdump kdump-early klog lvm2-monitor nscd notes_plat_sysinfo_1030= nvmefc-boot-connections postfix purge-kernels rollback rsyslog smartd sshd wicked notes_plat_sysinfo_1035= wickedd-auto4 wickedd-dhcp4 wickedd-dhcp6 wickedd-nanny notes_plat_sysinfo_1040= enabled-runtime systemd-remount-fs notes_plat_sysinfo_1045= disabled autofs autoyast-initscripts blk-availability boot-sysctl ca-certificates chrony-wait notes_plat_sysinfo_1050= chronyd console-getty cups cups-browsed debug-shell ebtables exchange-bmc-os-info notes_plat_sysinfo_1055= firewalld gpm grub2-once haveged-switch-root hwloc-dump-hwdata ipmi ipmievd notes_plat_sysinfo_1060= issue-add-ssh-keys kexec-load lunmask man-db-create multipathd nfs nfs-blkmap notes_plat_sysinfo_1065= nvmf-autoconnect rdisc rpcbind rpmconfigcheck rsyncd serial-getty@ smartd_generate_opts notes_plat_sysinfo_1070= snmpd snmptrapd systemd-boot-check-no-failures systemd-network-generator systemd-sysext notes_plat_sysinfo_1075= systemd-time-wait-sync systemd-timesyncd tuned udisks2 notes_plat_sysinfo_1080= indirect wickedd notes_plat_sysinfo_1085= notes_plat_sysinfo_1090= ------------------------------------------------------------ notes_plat_sysinfo_1095= 13. Linux kernel boot-time arguments, from /proc/cmdline notes_plat_sysinfo_1100= BOOT_IMAGE=/boot/vmlinuz-5.14.21-150400.22-default notes_plat_sysinfo_1105= root=UUID=bf0d00d4-f1bc-4aa3-92ff-ff6ee387ef92 notes_plat_sysinfo_1110= mitigations=auto notes_plat_sysinfo_1115= quiet notes_plat_sysinfo_1120= security=apparmor notes_plat_sysinfo_1125= crashkernel=290M,high notes_plat_sysinfo_1130= crashkernel=72M,low notes_plat_sysinfo_1135= notes_plat_sysinfo_1140= ------------------------------------------------------------ notes_plat_sysinfo_1145= 14. cpupower frequency-info notes_plat_sysinfo_1150= analyzing CPU 0: notes_plat_sysinfo_1155= current policy: frequency should be within 1.50 GHz and 2.40 GHz. notes_plat_sysinfo_1160= The governor "performance" may decide which speed to use notes_plat_sysinfo_1165= within this range. notes_plat_sysinfo_1170= boost state support: notes_plat_sysinfo_1175= Supported: yes notes_plat_sysinfo_1180= Active: yes notes_plat_sysinfo_1185= notes_plat_sysinfo_1190= ------------------------------------------------------------ notes_plat_sysinfo_1195= 15. tuned-adm active notes_plat_sysinfo_1200= It seems that tuned daemon is not running, preset profile is not activated. notes_plat_sysinfo_1205= Preset profile: latency-performance notes_plat_sysinfo_1210= notes_plat_sysinfo_1215= ------------------------------------------------------------ notes_plat_sysinfo_1220= 16. sysctl notes_plat_sysinfo_1225= kernel.numa_balancing 1 notes_plat_sysinfo_1230= kernel.randomize_va_space 0 notes_plat_sysinfo_1235= vm.compaction_proactiveness 20 notes_plat_sysinfo_1240= vm.dirty_background_bytes 0 notes_plat_sysinfo_1245= vm.dirty_background_ratio 10 notes_plat_sysinfo_1250= vm.dirty_bytes 0 notes_plat_sysinfo_1255= vm.dirty_expire_centisecs 3000 notes_plat_sysinfo_1260= vm.dirty_ratio 8 notes_plat_sysinfo_1265= vm.dirty_writeback_centisecs 500 notes_plat_sysinfo_1270= vm.dirtytime_expire_seconds 43200 notes_plat_sysinfo_1275= vm.extfrag_threshold 500 notes_plat_sysinfo_1280= vm.min_unmapped_ratio 1 notes_plat_sysinfo_1285= vm.nr_hugepages 0 notes_plat_sysinfo_1290= vm.nr_hugepages_mempolicy 0 notes_plat_sysinfo_1295= vm.nr_overcommit_hugepages 0 notes_plat_sysinfo_1300= vm.swappiness 1 notes_plat_sysinfo_1305= vm.watermark_boost_factor 15000 notes_plat_sysinfo_1310= vm.watermark_scale_factor 10 notes_plat_sysinfo_1315= vm.zone_reclaim_mode 1 notes_plat_sysinfo_1320= notes_plat_sysinfo_1325= ------------------------------------------------------------ notes_plat_sysinfo_1330= 17. /sys/kernel/mm/transparent_hugepage notes_plat_sysinfo_1335= defrag [always] defer defer+madvise madvise never notes_plat_sysinfo_1340= enabled [always] madvise never notes_plat_sysinfo_1345= hpage_pmd_size 2097152 notes_plat_sysinfo_1350= shmem_enabled always within_size advise [never] deny force notes_plat_sysinfo_1355= notes_plat_sysinfo_1360= ------------------------------------------------------------ notes_plat_sysinfo_1365= 18. /sys/kernel/mm/transparent_hugepage/khugepaged notes_plat_sysinfo_1370= alloc_sleep_millisecs 60000 notes_plat_sysinfo_1375= defrag 1 notes_plat_sysinfo_1380= max_ptes_none 511 notes_plat_sysinfo_1385= max_ptes_shared 256 notes_plat_sysinfo_1390= max_ptes_swap 64 notes_plat_sysinfo_1395= pages_to_scan 4096 notes_plat_sysinfo_1400= scan_sleep_millisecs 10000 notes_plat_sysinfo_1405= notes_plat_sysinfo_1410= ------------------------------------------------------------ notes_plat_sysinfo_1415= 19. OS release notes_plat_sysinfo_1420= From /etc/*-release /etc/*-version notes_plat_sysinfo_1425= os-release SUSE Linux Enterprise High Performance Computing 15 SP4 notes_plat_sysinfo_1430= notes_plat_sysinfo_1435= ------------------------------------------------------------ notes_plat_sysinfo_1440= 20. Disk information notes_plat_sysinfo_1445= SPEC is set to: /root/speccpu notes_plat_sysinfo_1450= Filesystem Type Size Used Avail Use% Mounted on notes_plat_sysinfo_1455= /dev/nvme0n1p3 xfs 2.1T 94G 2.0T 5% / notes_plat_sysinfo_1460= notes_plat_sysinfo_1465= ------------------------------------------------------------ notes_plat_sysinfo_1470= 21. /sys/devices/virtual/dmi/id notes_plat_sysinfo_1475= Vendor: Quanta Cloud Technology Inc. notes_plat_sysinfo_1480= Product: QuantaGrid D44N-1U notes_plat_sysinfo_1485= Product Family: S6N notes_plat_sysinfo_1490= notes_plat_sysinfo_1495= ------------------------------------------------------------ notes_plat_sysinfo_1500= 22. dmidecode notes_plat_sysinfo_1505= Additional information from dmidecode 3.2 follows. WARNING: Use caution when you interpret this section. notes_plat_sysinfo_1510= The 'dmidecode' program reads system data which is "intended to allow hardware to be accurately notes_plat_sysinfo_1515= determined", but the intent may not be met, as there are frequent changes to hardware, firmware, and the notes_plat_sysinfo_1520= "DMTF SMBIOS" standard. notes_plat_sysinfo_1525= Memory: notes_plat_sysinfo_1530= 24x Micron Technology MTC36F2046S1PC48BA1 64 GB 2 rank 4800 notes_plat_sysinfo_1535= notes_plat_sysinfo_1540= notes_plat_sysinfo_1545= ------------------------------------------------------------ notes_plat_sysinfo_1550= 23. BIOS notes_plat_sysinfo_1555= (This section combines info from /sys/devices and dmidecode.) notes_plat_sysinfo_1560= BIOS Vendor: American Megatrends International, LLC. notes_plat_sysinfo_1565= BIOS Version: 3A02 notes_plat_sysinfo_1570= BIOS Date: 09/21/2023 notes_plat_sysinfo_1575= BIOS Revision: 5.27 notes_plat_sysinfo_1580= Firmware Revision: 3.24 hw_cpu_name = AMD EPYC 9654 hw_disk = 2.1 TB add more disk info here hw_memory001 = 1511.084 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 = 192 hw_nthreadspercore = 1 prepared_by = root (is never output, only tags rawfile) sw_file = xfs sw_os001 = SUSE Linux Enterprise High Performance Computing 15 SP4 sw_state = Run level 3 (add definition here) # End of settings added by sysinfo_program # 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 set to prefer performance at the cost of power_management001 = additional power usage notes_plat_000 =BIOS Configuration notes_plat_005 = ACPI CST C2 Latency set to 18 notes_plat_010 = SMT set to disable notes_plat_015 = Determinism Control is Manual notes_plat_020 = Determinism Slider set to Power notes_plat_025 = cTDP Control set to Manual notes_plat_030 = cTDP set to 400 notes_plat_035 = PPT Control set to Manual notes_plat_040 = PPT set to 400