# Invocation command line: # /cpu2017/bin/harness/runcpu --configfile amd_speed_aocc200_rome_C1.cfg --tune all --reportable --iterations 3 --runmode speed --tune base:peak --size test:train:refspeed fpspeed # output_root was not used for this run ############################################################################ ################################################################################ # AMD AOCC 2.0.0 SPEC CPU2017 V1.1.0 Speed Configuration File for 64-bit Linux # # File name : amd_speed_aocc200_rome_C1.cfg # Creation Date : August 22, 2019 # CPU2017 Version : 1.1.0 # Supported benchmarks : All Speed benchmarks (intspeed, fpspeed) # Compiler name/version : AOCC v2.0.0 # Operating system version : Fedora 26 # Supported OS's : Ubuntu 18.04/19.04, RHEL 8.0, SLES 15 SP1 # Hardware : AMD Rome, Naples (AMD64) # FP Base Pointer Size : 64-bit # FP Peak Pointer Size : 64-bit # INT Base Pointer Size : 64-bit # INT Peak Pointer Size : 32/64-bit # Auto Parallization : No # # Note: DO NOT EDIT THIS FILE, the only edits required to properly run these # binaries are made in the ini Python file. Please consult Readme.amd_speed_aocc200_rome_C1.txt # for a few uncommon exceptions which require edits to this file. # # Description: # # This binary package automates away many of the complexities necessary to set # up and run SPEC CPU2017 under optimized conditions on AMD Rome/Naples-based # server platforms within Linux (AMD64). # # The binary package was built specifically for AMD Rome/Naples microprocessors and # is not intended to run on other products. # # Please install the binary package by following the instructions in # "Readme.amd_speed_aocc200_rome_C1.txt" under the "How To Use the Binaries" section. # # The binary package is designed to work without alteration on two socket AMD # Rome/Naples-based servers with 64 cores per socket, SMT enabled and 1 TiB of DDR4 # memory distributed evenly among all 16 channels using 32 GiB DIMMs. # # To run the binary package on other Rome/Naples configurations, please review # "Readme.amd_speed_aocc200_rome_C1.txt". In general, Rome or Naples CPUs # should be autodetected with no action required by the user. # # In most cases, it should be unnecessary to edit "amd_speed_aocc200_rome_C1.cfg" or any # other file besides "ini_amd_speed_aocc200_rome_C1.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 # 18.04/19.04, RHEL 8.0 and SLES 15 SP1. # # 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. # ################################################################################ # 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 amd_speed_aocc200_rome_C1.inc ################################################################################ # Binary label extension and "allow_build" switch ################################################################################ # Only modify the binary label extension if you plan to rebuild the binaries. %define ext amd_speed_aocc200_rome_C # If you plan to recompile these CPU2017 binaries, please choose a new extension # name (ext above) to avoid confusion with the current binary set on your system # under test, and to avoid confusion for SPEC submission reviewers. You will # also need to set "allow_build" to true below. Finally, you must modify the # Paths section below to point to your library locations if the paths are not # already set up in your build environment. # 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 ################################################################################ # Paths and Environment Variables # ** MODIFY AS NEEDED (modification should not be necessary for runs) ** ################################################################################ # Allow environment variables to be set before runs: preenv = 1 # Necessary to avoid out-of-memory exceptions on certain SUTs: preENV_MALLOC_CONF = retain:true # Define the name of the directory that holds AMD library files: %define lib_dir amd_speed_aocc200_rome_C_lib # Set the shared object library path for runs and builds: preENV_LD_LIBRARY_PATH = $[top]/%{lib_dir}/64;$[top]/%{lib_dir}/32:%{ENV_LD_LIBRARY_PATH} # Define 32-bit library build paths: # Do not use $[top] with the 32-bit libraries because doing so will cause an # options checksum error triggering a xalanc recompile attempt on SUTs having # different file paths: JEMALLOC_LIB32_PATH = /sppo/dev/cpu2017/v110/%{lib_dir}/32 OMP_LIB32_PATH = /sppo/dev/cpu2017/v110/%{lib_dir}/32 %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_aocc200_rome_C1.inc' ############################################################################ ################################################################################ ################################################################################ # File name: amd_speed_aocc200_rome_C1.inc # File generation code date: August 12, 2019 # File generation date/time: May 29, 2019 / 06:13:59 # # 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 ################################################################################ # The following macros define the Speed thread counts for the peak benchmarks. # # 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 # ################################################################################ # 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 ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 1 600.perlbench_s,602.gcc_s,605.mcf_s,620.omnetpp_s,623.xalancbmk_s,625.x264_s,631.deepsjeng_s,641.leela_s,648.exchange2_s=peak: threads = 1 ENV_GOMP_CPU_AFFINITY = 0 bind0 = numactl --physcpubind=0 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 128 603.bwaves_s,607.cactuBSSN_s,621.wrf_s,627.cam4_s,628.pop2_s,638.imagick_s,649.fotonik3d_s,654.roms_s,657.xz_s=peak: threads = 128 ENV_GOMP_CPU_AFFINITY = 0-127 bind0 = numactl --physcpubind=0-127 submit = echo "$command" > run.sh ; $BIND bash run.sh ################################################################################ ################################################################################ # peak thread counts: 128 619.lbm_s,644.nab_s=peak: threads = 128 ENV_GOMP_CPU_AFFINITY = 0 64 1 65 2 66 3 67 4 68 5 69 6 70 7 71 8 72 9 73 10 74 11 75 12 76 13 77 14 78 15 79 16 80 17 81 18 82 19 83 20 84 21 85 22 86 23 87 24 88 25 89 26 90 27 91 28 92 29 93 30 94 31 95 32 96 33 97 34 98 35 99 36 100 37 101 38 102 39 103 40 104 41 105 42 106 43 107 44 108 45 109 46 110 47 111 48 112 49 113 50 114 51 115 52 116 53 117 54 118 55 119 56 120 57 121 58 122 59 123 60 124 61 125 62 126 63 127 bind0 = numactl --physcpubind=0-127 submit = echo "$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 =003 tester =HPE test_sponsor =HPE hw_vendor =Hewlett Packard Enterprise hw_temperature_102161138889_vendor = Digi International Inc. hw_temperature_102161138889_setup = 5 mm in front of SUT main intake hw_temperature_102161138889_serial = V45084325 hw_power_102161138888_vendor = Yokogawa hw_power_102161138888_setup = SUT Power Supply 1 via neoXt NXB 20815 hw_power_102161138888_serial = 91GC21887 hw_power_102161138888_model = YokogawaWT210 hw_power_102161138888_met_inst = NIST hw_power_102161138888_label = 10.216.1.13:8888 hw_power_102161138888_connection = GPIB via NI GIPB-USB-HS hw_power_102161138888_cal_org = TRANSCAT hw_power_102161138888_cal_label = 5-E62NT-80-1 hw_power_102161138888_cal_date = 11-Jun-2019 hw_temperature_102161138889_connection = USB hw_temperature_102161138889_model = DigiWATCHPORT_H hw_temperature_102161138889_label = 10.216.1.13:8889 hw_model000 =ProLiant DL385 Gen10 hw_model001 =(2.00 GHz, AMD EPYC 7702) #--------- If you install new compilers, edit this section -------------------- sw_compiler =C/C++/Fortran: Version 2.0.0 of AOCC ################################################################################ ################################################################################ # Hardware, firmware and software information ################################################################################ hw_avail =Oct-2019 sw_avail =Aug-2019 hw_cpu_name =AMD EPYC 7702 hw_cpu_nominal_mhz =2000 hw_cpu_max_mhz =3350 hw_ncores =128 hw_nthreadspercore =1 hw_ncpuorder =1, 2 chip(s) hw_other =None # Other perf-relevant hw, or "None" fw_bios =HPE BIOS Version A40 07/20/2019 released Aug-2019 sw_base_ptrsize =64-bit hw_pcache =32 KB I + 32 KB D on chip per core hw_scache =512 KB I+D on chip per core hw_tcache000 =256 MB I+D on chip per chip, hw_tcache001 = 16 MB shared / 4 cores hw_ocache =None ################################################################################ # Notes ################################################################################ # Enter notes_000 through notes_100 here. notes_000 =Binaries were compiled on a system with 2x AMD EPYC 7601 CPU + 512GB Memory using Fedora 26 notes_005 = notes_010 =NA: The test sponsor attests, as of date of publication, that CVE-2017-5754 (Meltdown) notes_015 =is mitigated in the system as tested and documented. notes_020 =Yes: The test sponsor attests, as of date of publication, that CVE-2017-5753 (Spectre variant 1) notes_025 =is mitigated in the system as tested and documented. notes_030 =Yes: The test sponsor attests, as of date of publication, that CVE-2017-5715 (Spectre variant 2) notes_035 =is mitigated in the system as tested and documented. notes_040 = notes_submit_000 ='numactl' was used to bind copies to the cores. notes_submit_005 =See the configuration file for details. notes_os_000 ='ulimit -s unlimited' was used to set environment stack size 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 =Set dirty_ratio=8 to limit dirty cache to 8% of memory notes_os_035 =Set swappiness=1 to swap only if necessary notes_os_040 =Set zone_reclaim_mode=1 to free local node memory and avoid remote memory notes_os_045 =sync then drop_caches=3 to reset caches before invoking runcpu notes_os_050 = notes_os_055 =dirty_ratio, swappiness, zone_reclaim_mode and drop_caches were notes_os_060 =all set using privileged echo (e.g. echo 1 > /proc/sys/vm/swappiness). notes_os_065 = notes_os_070 =Transparent huge pages set to 'always' for this run (OS default) notes_os_075 = notes_os_080 =The date was incorrectly set for this system. The test date should be Aug-2019. 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 v9.1.0 in Ubuntu 19.04 with -O3 -znver2 -flto notes_jemalloc_005 =jemalloc 5.1.0 is available here: notes_jemalloc_010 =https://github.com/jemalloc/jemalloc/releases/download/5.1.0/jemalloc-5.1.0.tar.bz2 notes_jemalloc_015 = sw_other =jemalloc: jemalloc memory allocator library v5.1.0 power_management = Disabled test_elevation = 132 hw_line_standard = 208 V / 60 Hz / 1 phase / 2 wires hw_power_provisioning = Line-powered fw_management = Version 1.43 of iLO5 released May 23 2019 hw_memory_mode = Normal hw_psu = 1 x 800 W (non-redundant) hw_backplane = None hw_other_storage = Embedded SATA Controller hw_storage_model = 875488-B21 hw_nics = 1 x HPE Ethernet 4-port 331i Adapter @ 1 Gb hw_nics_enabled = 4 / 4 hw_nics_connected = 2 @ 1 Gb hw_other_model = 6 x High Performance Fans (867810-B21) ################################################################################ # The following note fields describe platorm settings. ################################################################################ # example: (uncomment as necessary) # notes_plat_000 =BIOS settings: # notes_plat_005 = cTDP = 240 # notes_plat_010 = Determinism Slider set to Power # 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 =32/64-bit ################################################################################ # The following fields must be set here for FP benchmarks. ################################################################################ fpspeed: sw_peak_ptrsize =64-bit ################################################################################ # The following fields must be set here or they will be overwritten by sysinfo. ################################################################################ intspeed,fpspeed: hw_disk =1 x HPE 240 GB SATA 6G M.2 SSD hw_memory000 =1 TB (16 x 64 GB 4Rx4 PC4-2933Y-L) hw_memory002 = hw_nchips =2 prepared_by =HPE Performance Engineering sw_file =btrfs sw_os000 =SUSE Linux Enterprise Server 15 (x86_64) SP1 sw_os001 =Kernel 4.12.14-195-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 '/cpu2017/config/amd_speed_aocc200_rome_C1.inc' # Switch back to default block after the include file: default: fail_build = 1 # OpenMP environment variables: preENV_OMP_STACKSIZE = 128M preENV_OMP_SCHEDULE = static preENV_OMP_DYNAMIC = false %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 = $[top]/%{lib_dir}/64;$[top]/%{lib_dir}/32:%{ENV_LIBRARY_PATH} % define build_ncpus 64 # controls the number of simultaneous compile jobs 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/aocc200-flags-C1-HPE.xml flagsurl001 = http://www.spec.org/cpu2017/flags/HPE-Platform-Flags-AMD-V1.2-EPYC-revF.xml #flagsurl02 = $[top]/INVALID_platform_amd_speed_aocc200_rome.xml # 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 power = 1 #Power Details: power_analyzer = 10.216.1.13:8888 temp_meter = 10.216.1.13:8889 voltage_range = 300 current_range = 5 idle_current_range = 1 ################################################################################ # Compilers ################################################################################ default: CC = clang CXX = clang++ FC = flang CLD = clang FLD = flang CC_VERSION_OPTION = --version CXX_VERSION_OPTION = --version FC_VERSION_OPTION = --version default:# data model applies to all benchmarks ################################################################################ # Default Flags ################################################################################ EXTRA_PORTABILITY = -DSPEC_LP64 EXTRA_LIBS = -fopenmp=libomp -lomp -ljemalloc -lamdlibm -lm MATHLIBOPT = ################################################################################ # Portability Flags ################################################################################ default: # *** Benchmark-specific portability *** # Anything other than the data model is only allowed where a need is proven. # (ordered by last 2 digits of benchmark number) 600.perlbench_s: #lang='C' PORTABILITY = -DSPEC_LINUX_X64 621.wrf_s: #lang='F,C' CPORTABILITY = -DSPEC_CASE_FLAG FPORTABILITY = -Mbyteswapio 623.xalancbmk_s: #lang='CXX' PORTABILITY = -DSPEC_LINUX 627.cam4_s: #lang='F,C' PORTABILITY = -DSPEC_CASE_FLAG 628.pop2_s: #lang='F,C' CPORTABILITY = -DSPEC_CASE_FLAG FPORTABILITY = -Mbyteswapio ################################################################################ # Tuning Flags ################################################################################ ##################### # Base tuning flags # ##################### default=base: #optimize flags COPTIMIZE = -O3 -flto -ffast-math -march=znver2 -fstruct-layout=3 \ -mllvm -unroll-threshold=50 -fremap-arrays \ -mllvm -function-specialize -mllvm -enable-gvn-hoist \ -mllvm -reduce-array-computations=3 -mllvm -global-vectorize-slp \ -mllvm -vector-library=LIBMVEC \ -mllvm -inline-threshold=1000 -flv-function-specialization CXXOPTIMIZE = -O3 -flto -ffast-math -march=znver2 \ -mllvm -loop-unswitch-threshold=200000 \ -mllvm -vector-library=LIBMVEC \ -mllvm -unroll-threshold=100 -flv-function-specialization \ -mllvm -enable-partial-unswitch FOPTIMIZE = -O3 -flto -march=znver2 -funroll-loops -Mrecursive \ -mllvm -vector-library=LIBMVEC EXTRA_FFLAGS = -Kieee -fno-finite-math-only #linker flags LDFLAGS = -flto -Wl,-mllvm -Wl,-function-specialize \ -Wl,-mllvm -Wl,-region-vectorize \ -Wl,-mllvm -Wl,-vector-library=LIBMVEC \ -Wl,-mllvm -Wl,-reduce-array-computations=3 LDCXXFLAGS = -Wl,-mllvm -Wl,-suppress-fmas #other libraries # Put OpenMP and math libraries here: EXTRA_LIBS = -fopenmp=libomp -lomp -lpthread -ldl -lmvec -lamdlibm -ljemalloc -lflang -lm # Don't put the AMD and mvec math libraries in MATHLIBOPT because it will trigger a reporting issue # because GCC won't use them. Forcefeed all benchmarks the math libraries in EXTRA_LIBS and clear # out MATHLIBOPT. MATHLIBOPT = # The following is necessary for 502/602 gcc: EXTRA_OPTIMIZE = -DSPEC_OPENMP -fopenmp -Wno-return-type -DUSE_OPENMP # The following is necessary for 502/602 gcc: LDOPTIMIZE = -z muldefs ######################## # intspeed tuning flags # ######################## intspeed: EXTRA_FFLAGS = -ffast-math \ -mllvm -disable-indvar-simplify \ -mllvm -unroll-aggressive \ -mllvm -unroll-threshold=150 LDFFLAGS = -ffast-math \ -Wl,-mllvm -Wl,-inline-recursion=4 \ -Wl,-mllvm -Wl,-lsr-in-nested-loop \ -Wl,-mllvm -Wl,-enable-iv-split 657.xz_s=default: voltage_range = 300 current_range = 5 644.nab_s=default: voltage_range = 300 current_range = 2 ######################## # fpspeed tuning flags # ######################## fpspeed: CXX = clang++ -std=c++98 ##################### # Peak tuning flags # ##################### default=peak: #optimize flags COPTIMIZE = -Ofast -flto -march=znver2 -mno-sse4a -fstruct-layout=5 \ -mllvm -vectorize-memory-aggressively \ -mllvm -function-specialize -mllvm -enable-gvn-hoist \ -mllvm -unroll-threshold=50 -fremap-arrays \ -mllvm -vector-library=LIBMVEC \ -mllvm -reduce-array-computations=3 -mllvm -global-vectorize-slp \ -mllvm -inline-threshold=1000 -flv-function-specialization CXXOPTIMIZE = -Ofast -flto -march=znver2 -flv-function-specialization \ -mllvm -unroll-threshold=100 -mllvm -enable-partial-unswitch \ -mllvm -loop-unswitch-threshold=200000 \ -mllvm -vector-library=LIBMVEC \ -mllvm -inline-threshold=1000 FOPTIMIZE = -O3 -flto -march=znver2 -funroll-loops -Mrecursive \ -mllvm -vector-library=LIBMVEC EXTRA_FFLAGS = -Kieee -fno-finite-math-only #linker flags LDFLAGS = -flto -Wl,-mllvm -Wl,-function-specialize \ -Wl,-mllvm -Wl,-region-vectorize \ -Wl,-mllvm -Wl,-vector-library=LIBMVEC \ -Wl,-mllvm -Wl,-reduce-array-computations=3 #libraries EXTRA_LIBS = -fopenmp=libomp -lomp -lpthread -ldl -lmvec -lamdlibm -ljemalloc -lflang -lm EXTRA_OPTIMIZE = -DSPEC_OPENMP -fopenmp -Wno-return-type -DUSE_OPENMP EXTRA_FLIBS = -lmvec -lamdlibm -lm MATHLIBOPT = -lmvec -lamdlibm -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 = $command ; llvm-profdata merge -output=default.profdata *.profraw ######################################## # Benchmark specific peak tuning flags # ######################################## 600.perlbench_s=peak: #lang='C' feedback = 1 602.gcc_s=peak: #lang='C' EXTRA_COPTIMIZE = -fgnu89-inline LDOPTIMIZE = -z muldefs EXTRA_LIBS = -fopenmp=libomp -lomp -lpthread -ldl -lm -ljemalloc MATHLIBOPT = -lm 623.xalancbmk_s=peak: #lang='CXX` EXTRA_PORTABILITY = -D_FILE_OFFSET_BITS=64 CXX = clang++ -m32 CXXLD = clang++ -m32 EXTRA_LIBS = -L$[OMP_LIB32_PATH] -fopenmp=libomp -L$[OMP_LIB32_PATH] -lomp -lpthread -ldl -L$[JEMALLOC_LIB32_PATH] -ljemalloc MATHLIBOPT = -lm ENV_OMP_STACKSIZE = 128M 625.x264_s=peak: #lang='C' feedback = 1 654.roms_s=peak: LDFFLAGS = -Wl,-mllvm -Wl,-enable-X86-prefetching # The following settings were obtained by running the sysinfo_program # 'specperl $[top]/bin/sysinfo' (sysinfo:SHA:1b187da62efa5d65f0e989c214b6a257d16a31d3cf135973c9043da741052207) default: notes_plat_sysinfo_000 = notes_plat_sysinfo_005 = Sysinfo program /cpu2017/bin/sysinfo notes_plat_sysinfo_010 = Rev: r6365 of 2019-08-21 295195f888a3d7edb1e6e46a485a0011 notes_plat_sysinfo_015 = running on dl385gen10 Wed May 29 06:14:24 2019 notes_plat_sysinfo_020 = notes_plat_sysinfo_025 = SUT (System Under Test) info as seen by some common utilities. notes_plat_sysinfo_030 = For more information on this section, see notes_plat_sysinfo_035 = https://www.spec.org/cpu2017/Docs/config.html#sysinfo notes_plat_sysinfo_040 = notes_plat_sysinfo_045 = From /proc/cpuinfo notes_plat_sysinfo_050 = model name : AMD EPYC 7702 64-Core Processor notes_plat_sysinfo_055 = 2 "physical id"s (chips) notes_plat_sysinfo_060 = 128 "processors" notes_plat_sysinfo_065 = cores, siblings (Caution: counting these is hw and system dependent. The following notes_plat_sysinfo_070 = excerpts from /proc/cpuinfo might not be reliable. Use with caution.) notes_plat_sysinfo_075 = cpu cores : 64 notes_plat_sysinfo_080 = siblings : 64 notes_plat_sysinfo_085 = physical 0: cores 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 notes_plat_sysinfo_090 = 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 notes_plat_sysinfo_095 = 53 54 55 56 57 58 59 60 61 62 63 notes_plat_sysinfo_100 = physical 1: cores 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 notes_plat_sysinfo_105 = 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 notes_plat_sysinfo_110 = 53 54 55 56 57 58 59 60 61 62 63 notes_plat_sysinfo_115 = notes_plat_sysinfo_120 = From lscpu: notes_plat_sysinfo_125 = Architecture: x86_64 notes_plat_sysinfo_130 = CPU op-mode(s): 32-bit, 64-bit notes_plat_sysinfo_135 = Byte Order: Little Endian notes_plat_sysinfo_140 = Address sizes: 48 bits physical, 48 bits virtual notes_plat_sysinfo_145 = CPU(s): 128 notes_plat_sysinfo_150 = On-line CPU(s) list: 0-127 notes_plat_sysinfo_155 = Thread(s) per core: 1 notes_plat_sysinfo_160 = Core(s) per socket: 64 notes_plat_sysinfo_165 = Socket(s): 2 notes_plat_sysinfo_170 = NUMA node(s): 8 notes_plat_sysinfo_175 = Vendor ID: AuthenticAMD notes_plat_sysinfo_180 = CPU family: 23 notes_plat_sysinfo_185 = Model: 49 notes_plat_sysinfo_190 = Model name: AMD EPYC 7702 64-Core Processor notes_plat_sysinfo_195 = Stepping: 0 notes_plat_sysinfo_200 = CPU MHz: 2000.000 notes_plat_sysinfo_205 = CPU max MHz: 2000.0000 notes_plat_sysinfo_210 = CPU min MHz: 1500.0000 notes_plat_sysinfo_215 = BogoMIPS: 3992.51 notes_plat_sysinfo_220 = Virtualization: AMD-V notes_plat_sysinfo_225 = L1d cache: 32K notes_plat_sysinfo_230 = L1i cache: 32K notes_plat_sysinfo_235 = L2 cache: 512K notes_plat_sysinfo_240 = L3 cache: 16384K notes_plat_sysinfo_245 = NUMA node0 CPU(s): 0-15 notes_plat_sysinfo_250 = NUMA node1 CPU(s): 16-31 notes_plat_sysinfo_255 = NUMA node2 CPU(s): 32-47 notes_plat_sysinfo_260 = NUMA node3 CPU(s): 48-63 notes_plat_sysinfo_265 = NUMA node4 CPU(s): 64-79 notes_plat_sysinfo_270 = NUMA node5 CPU(s): 80-95 notes_plat_sysinfo_275 = NUMA node6 CPU(s): 96-111 notes_plat_sysinfo_280 = NUMA node7 CPU(s): 112-127 notes_plat_sysinfo_285 = Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov notes_plat_sysinfo_290 = pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm notes_plat_sysinfo_295 = constant_tsc rep_good nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf pni notes_plat_sysinfo_300 = pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c notes_plat_sysinfo_305 = rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch notes_plat_sysinfo_310 = osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_l2 mwaitx cpb notes_plat_sysinfo_315 = cat_l3 cdp_l3 hw_pstate ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 notes_plat_sysinfo_320 = cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves notes_plat_sysinfo_325 = cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr arat npt notes_plat_sysinfo_330 = lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter notes_plat_sysinfo_335 = pfthreshold avic v_vmsave_vmload vgif umip rdpid overflow_recov succor smca notes_plat_sysinfo_340 = notes_plat_sysinfo_345 = /proc/cpuinfo cache data notes_plat_sysinfo_350 = cache size : 512 KB notes_plat_sysinfo_355 = notes_plat_sysinfo_360 = From numactl --hardware WARNING: a numactl 'node' might or might not correspond to a notes_plat_sysinfo_365 = physical chip. notes_plat_sysinfo_370 = available: 8 nodes (0-7) notes_plat_sysinfo_375 = node 0 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 notes_plat_sysinfo_380 = node 0 size: 128802 MB notes_plat_sysinfo_385 = node 0 free: 128512 MB notes_plat_sysinfo_390 = node 1 cpus: 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 notes_plat_sysinfo_395 = node 1 size: 129019 MB notes_plat_sysinfo_400 = node 1 free: 128726 MB notes_plat_sysinfo_405 = node 2 cpus: 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 notes_plat_sysinfo_410 = node 2 size: 129019 MB notes_plat_sysinfo_415 = node 2 free: 128689 MB notes_plat_sysinfo_420 = node 3 cpus: 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 notes_plat_sysinfo_425 = node 3 size: 129007 MB notes_plat_sysinfo_430 = node 3 free: 128814 MB notes_plat_sysinfo_435 = node 4 cpus: 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 notes_plat_sysinfo_440 = node 4 size: 129019 MB notes_plat_sysinfo_445 = node 4 free: 128873 MB notes_plat_sysinfo_450 = node 5 cpus: 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 notes_plat_sysinfo_455 = node 5 size: 129019 MB notes_plat_sysinfo_460 = node 5 free: 128901 MB notes_plat_sysinfo_465 = node 6 cpus: 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 notes_plat_sysinfo_470 = node 6 size: 128990 MB notes_plat_sysinfo_475 = node 6 free: 128861 MB notes_plat_sysinfo_480 = node 7 cpus: 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 notes_plat_sysinfo_485 = node 7 size: 129018 MB notes_plat_sysinfo_490 = node 7 free: 128895 MB notes_plat_sysinfo_495 = node distances: notes_plat_sysinfo_500 = node 0 1 2 3 4 5 6 7 notes_plat_sysinfo_505 = 0: 10 12 12 12 32 32 32 32 notes_plat_sysinfo_510 = 1: 12 10 12 12 32 32 32 32 notes_plat_sysinfo_515 = 2: 12 12 10 12 32 32 32 32 notes_plat_sysinfo_520 = 3: 12 12 12 10 32 32 32 32 notes_plat_sysinfo_525 = 4: 32 32 32 32 10 12 12 12 notes_plat_sysinfo_530 = 5: 32 32 32 32 12 10 12 12 notes_plat_sysinfo_535 = 6: 32 32 32 32 12 12 10 12 notes_plat_sysinfo_540 = 7: 32 32 32 32 12 12 12 10 notes_plat_sysinfo_545 = notes_plat_sysinfo_550 = From /proc/meminfo notes_plat_sysinfo_555 = MemTotal: 1056663620 kB notes_plat_sysinfo_560 = HugePages_Total: 0 notes_plat_sysinfo_565 = Hugepagesize: 2048 kB notes_plat_sysinfo_570 = notes_plat_sysinfo_575 = From /etc/*release* /etc/*version* notes_plat_sysinfo_580 = os-release: notes_plat_sysinfo_585 = NAME="SLES" notes_plat_sysinfo_590 = VERSION="15-SP1" notes_plat_sysinfo_595 = VERSION_ID="15.1" notes_plat_sysinfo_600 = PRETTY_NAME="SUSE Linux Enterprise Server 15 SP1" notes_plat_sysinfo_605 = ID="sles" notes_plat_sysinfo_610 = ID_LIKE="suse" notes_plat_sysinfo_615 = ANSI_COLOR="0;32" notes_plat_sysinfo_620 = CPE_NAME="cpe:/o:suse:sles:15:sp1" notes_plat_sysinfo_625 = notes_plat_sysinfo_630 = uname -a: notes_plat_sysinfo_635 = Linux dl385gen10 4.12.14-195-default #1 SMP Tue May 7 10:55:11 UTC 2019 (8fba516) notes_plat_sysinfo_640 = x86_64 x86_64 x86_64 GNU/Linux notes_plat_sysinfo_645 = notes_plat_sysinfo_650 = Kernel self-reported vulnerability status: notes_plat_sysinfo_655 = notes_plat_sysinfo_660 = CVE-2018-3620 (L1 Terminal Fault): Not affected notes_plat_sysinfo_665 = Microarchitectural Data Sampling: Not affected notes_plat_sysinfo_670 = CVE-2017-5754 (Meltdown): Not affected notes_plat_sysinfo_675 = CVE-2018-3639 (Speculative Store Bypass): Mitigation: Speculative Store Bypass disabled notes_plat_sysinfo_680 = via prctl and seccomp notes_plat_sysinfo_685 = CVE-2017-5753 (Spectre variant 1): Mitigation: __user pointer sanitization notes_plat_sysinfo_690 = CVE-2017-5715 (Spectre variant 2): Mitigation: Full AMD retpoline, IBPB: notes_plat_sysinfo_695 = conditional, IBRS_FW, STIBP: disabled, RSB notes_plat_sysinfo_700 = filling notes_plat_sysinfo_705 = notes_plat_sysinfo_710 = run-level 3 May 29 06:12 notes_plat_sysinfo_715 = notes_plat_sysinfo_720 = SPEC is set to: /cpu2017 notes_plat_sysinfo_725 = Filesystem Type Size Used Avail Use% Mounted on notes_plat_sysinfo_730 = /dev/sda2 btrfs 222G 43G 178G 20% / notes_plat_sysinfo_735 = notes_plat_sysinfo_740 = From /sys/devices/virtual/dmi/id notes_plat_sysinfo_745 = BIOS: HPE A40 07/20/2019 notes_plat_sysinfo_750 = Vendor: HPE notes_plat_sysinfo_755 = Product: ProLiant DL385 Gen10 notes_plat_sysinfo_760 = Product Family: ProLiant notes_plat_sysinfo_765 = Serial: 7CE724P4SJ notes_plat_sysinfo_770 = notes_plat_sysinfo_775 = Additional information from dmidecode follows. WARNING: Use caution when you interpret notes_plat_sysinfo_780 = this section. The 'dmidecode' program reads system data which is "intended to allow notes_plat_sysinfo_785 = hardware to be accurately determined", but the intent may not be met, as there are notes_plat_sysinfo_790 = frequent changes to hardware, firmware, and the "DMTF SMBIOS" standard. notes_plat_sysinfo_795 = Memory: notes_plat_sysinfo_800 = 16x UNKNOWN NOT AVAILABLE notes_plat_sysinfo_805 = 16x UNKNOWN NOT AVAILABLE 64 GB 4 rank 2933 notes_plat_sysinfo_810 = notes_plat_sysinfo_815 = (End of data from sysinfo program) hw_cpu_name = AMD EPYC 7702 hw_disk = 222 GB add more disk info here hw_memory001 = 1007.713 GB fixme: If using DDR4, the format is: hw_memory002 = 'N GB (N x N GB nRxn PC4-nnnnX-X)' hw_nchips = 2 prepared_by = root (is never output, only tags rawfile) sw_file = btrfs sw_os001 = NAME="SLES" sw_state = Run level 3 (add definition here) # End of settings added by sysinfo_program 654.roms_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 649.fotonik3d_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 644.nab_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 638.imagick_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 627.cam4_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 619.lbm_s: # The following setting was inserted automatically as a result of # post-run basepeak application. basepeak = 1 # The following section was added automatically, and contains settings that # did not appear in the original configuration file, but were added to the # raw file after the run. default: hw_psu_info000 = HPE 800W Flex Slot Titanium Hot Plug Low Halogen hw_psu_info001 = Power Supply Kit (865438-B21) notes_plat_000 =BIOS Configuration: notes_plat_005 = AMD SMT Option set to Disabled notes_plat_010 = Thermal Configuration set to Optimal Cooling notes_plat_015 = Determinism Control set to Manual notes_plat_020 = Performance Determinism set to Power Deterministic notes_plat_025 = Memory Patrol Scrubbing set to Disabled notes_plat_030 = NUMA memory domains per socket set to Four memory domains per socket notes_plat_035 = Last-Level Cache (LLC) as NUMA Node set to Enabled notes_plat_040 = Workload Profile set to General Throughput Compute notes_plat_045 = Minimum Processor Idle Power Core C-State set to C6 State notes_power_000 =PTDaemon to measure power and temperature was run on a ProLiant DL360 Gen9 as a controller notes_power_005 =with 2x Intel Xeon E5-2660 v3 CPU and 128 GB of memory using Windows Server 2012 R2. notes_power_010 =Power management in the OS was disabled by setting Linux CPU governor to performance for all cores: notes_power_015 = cpupower frequency-set -r -g performance notes_power_020 =Power management in the BIOS was default except for any settings mentioned in BIOS Configuration. notes_power_025 =No power management settings were set in the management firmware. notes_power_030 =The Embedded SATA controller was the HPE Smart Array S100i SR Gen10 SW RAID. notes_power_035 =The system was configured with 3 drive cage blanks, 6 High Performance Fans, notes_power_040 =16 DIMM blanks, 2 high performance heatsinks (882098-B21) and baffles that fit over notes_power_045 =the high performance heatsinks in order to produce correct airflow and cooling. notes_power_050 =The run was started and observed through the management firmware. notes_zzzzsubmitinfo_000= notes_zzzzsubmitinfo_005=Submitted_by: "Bucek, James" notes_zzzzsubmitinfo_010=Submitted: Tue Sep 17 00:02:18 EDT 2019 notes_zzzzsubmitinfo_015=Submission: cpu2017-20190903-17795.sub notes_zzzzsubmitinfo_020= notes_zzzzsubmitinfo_025=Submitted_by: "Bucek, James" notes_zzzzsubmitinfo_030=Submitted: Tue Sep 17 09:00:11 EDT 2019 notes_zzzzsubmitinfo_035=Submission: cpu2017-20190903-17795.sub