# Invocation command line: # /mnt/ramdisk/cpu2017-1.1.8-ic2021.1/bin/harness/runcpu --nobuild --action validate --define default-platform-flags --configfile ic2021.1-lin-core-avx512-speed-20201113_revB.cfg --define cores=48 --tune base,peak --output_format all --define drop_caches --iterations 2 --output_format pdf,html,txt --nopower --runmode speed --tune base:peak --size refspeed fpspeed # output_root was not used for this run ############################################################################ #------------------------------------------------------------------------------ # This is a sample SPEC CPU2017 config file. It is applicable for: # # Compiler name/version: Intel(R) C/C++ and Fortran 2021 Compilers for Linux # Operating system version: Red Hat Enterprise Linux 8.1, GLIBC 2.28 # ld version: GNU ld version 2.30 and above (older version may not work) # Hardware: Intel(R) processors supporting CORE-AVX512 tuning # # If you wish to build your own: # (1) Copy this to a new name # cd %SPEC%/config # copy this.cfg that.cfg # (2) Change items that are marked 'EDIT' (search for it) # # If you have different software or hardware, this config file may not work. # You may find a better config file for your system next to posted results: # http://www.spec.org/cpu2017/results # # Compiler issues: Contact your compiler vendor, not SPEC. # For SPEC help: http://www.spec.org/auto/cpu2017/Docs/techsupport.html #------------------------------------------------------------------------------ #--------- Preprocessor ------------------------------------------------------- # # Optionally edit if you wish: %define build_ncpus 8 # controls number of simultaneous compiles # Used to date the label %define version 20201113_revB # Used for the optimization tuning part of the label (not required) %if defined(%{noopt}) %define opt_label -noopt %elif defined(%{medopt}) %define opt_label -medopt %else %define opt_label %endif # Used for labeling static linked builds (not required) %if defined(%{static}) %define static_label -static %else %define static_label %endif #--------- Label -------------------------------------------------------------- # Arbitrary string, tags your binaries & directories. # Two Suggestions: # (1) Change this label as you try new ideas. label = ic2021.1-lin-core-avx512-speed%{opt_label}%{static_label}-%{version} # (2) Make the label meaningful to YOU. #--------- Global Settings ---------------------------------------------------- # For info, see: # https://www.spec.org/auto/cpu2017/Docs/config.html#fieldname XXX # Example: https://www.spec.org/auto/cpu2017/Docs/config.html#tune ######################################################## # ATTENTION ATTENTION ATTENTION ######################################################## # # NOTE If you change fail_build then PLEASE also # change the line 'define version', because # SPEC review tools use 'label' to track binaries. # ######################################################## # # vvvvvvvvvvvv # do not change unless you read NOTE above fail_build=1 # do not change unless you read NOTE above # ^^^^^^^^^^^^ # do not change unless you read NOTE above # ######################################################## # action = validate command_add_redirect = 1 line_width = 1020 log_line_width = 1020 makeflags = -j%{build_ncpus} output_format = txt,cfg,pdf,csv preenv = 1 tune = base bench_post_setup = sync parallel_test = 1 mean_anyway = 1 reportable = 1 # Set some environment variables preENV_OMP_STACKSIZE = 192M %ifdef %{intspeedaffinity} preENV_KMP_AFFINITY = granularity=fine,scatter %else %if defined(%{smt-on}) preENV_KMP_AFFINITY = granularity=fine,compact,1,0 %else preENV_KMP_AFFINITY = granularity=fine,compact %endif %endif #Reference the flags files flagsurl000=http://www.spec.org/cpu2017/flags/Intel-ic2021-official-linux64_revA.xml %ifdef %{default-platform-flags} flagsurl2=Default-Platform-Flags.xml %endif # Set some environment variables # Retain unused virtual memory for later reuse. This avoids out of memory errors for certain benchmarks. preENV_MALLOC_CONF = retain:true intspeed: preENV_LD_LIBRARY_PATH = $[top]/lib/intel64:$[top]/je5.0.1-64 fpspeed: preENV_LD_LIBRARY_PATH = $[top]/lib/intel64:$[top]/je5.0.1-64 #--------- Compilers ---------------------------------------------------------- intspeed,fpspeed: # How to say "Show me your version, please" CC_VERSION_OPTION = -V CXX_VERSION_OPTION = -V FC_VERSION_OPTION = -V JEMALLOC32_DIR = /usr/local/jemalloc32-5.0.1/lib JEMALLOC64_DIR = /usr/local/jemalloc64-5.0.1/lib INTEL64_DIR = /opt/intel/oneapi/compiler/2021.1.1/linux/compiler/lib/intel64_lin/ %if !defined(%{static}) JEMALLOC32 = jemalloc JEMALLOC64 = jemalloc QKMALLOC = qkmalloc %else JEMALLOC32 = libjemalloc.a JEMALLOC64 = libjemalloc.a %endif OPT_JCC = -mbranches-within-32B-boundaries OPT_JCC_icx = -mbranches-within-32B-boundaries #--------- Portability -------------------------------------------------------- intspeed,fpspeed: PORTABILITY = -DSPEC_LP64 600.perlbench_s: CPORTABILITY = -DSPEC_LINUX_X64 621.wrf_s: CPORTABILITY = -DSPEC_CASE_FLAG FPORTABILITY = -convert big_endian 623.xalancbmk_s: CXXPORTABILITY= -DSPEC_LINUX 627.cam4_s: CPORTABILITY= -DSPEC_CASE_FLAG 628.pop2_s: CPORTABILITY = -DSPEC_CASE_FLAG FPORTABILITY = -convert big_endian -assume byterecl #--------- How Many CPUs? ----------------------------------------------------- # Both SPECrate and SPECspeed can test multiple chips / cores / hw threads # - For SPECspeed, you set the number of threads. # See: https://www.spec.org/cpu2017/Docs/system-requirements.html#MultipleCPUs # # q. How many should I set? # a. Unknown, you will have to try it and see! # # To get you started, some suggestions: # # threads - This config file sets a starting point. You could try raising # it. A higher thread count is much more likely to be useful for # fpspeed than for intspeed. # default: %if !defined(%{cores}) %error please add --define cores=[ncores] to runcpu invocation %endif threads = %{cores} # EDIT to change number of OpenMP threads (see above) %ifdef %{smt-on} %define numpeakthreads %{cores} * 2 %endif intspeed: %define numxzthreads %{cores} * 2 %ifdef %{smt-on} threads = %{numxzthreads} %else threads = %{cores} %endif #-------- Tuning Flags ---------------------------------------------- intrate,fprate: #reconsider using a rate config file instead of a speed config file fail=1 intspeed: CC = icx -m64 -std=c11 -fiopenmp -DSPEC_OPENMP CXX = icpx -m64 -DSPEC_OPENMP FC = ifort -m64 # Compiler tuning toggle, corresponds with isa_ext preprocessor cfg var SSE = -xCORE-AVX512 EXTRA_FOPTIMIZE = -nostandard-realloc-lhs -align array32byte -auto $(OPT_JCC) EXTRA_COPTIMIZE = $(OPT_JCC_icx) EXTRA_CXXOPTIMIZE = $(OPT_JCC_icx) %if defined(%{noopt}) OPT_ROOT = -O0 %elif defined(%{medopt}) OPT_ROOT = -O2 %else OPT_ROOT = -ipo -O3 -no-prec-div %endif FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FORT_FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FAST = $(SSE) $(OPT_ROOT) -static FORT_FAST = $(SSE) $(OPT_ROOT) -static intspeed_any_c: EXTRA_LIBS = -L$(JEMALLOC64_DIR) -l$(JEMALLOC64) EXTRA_LDFLAGS = -Wl,-z,muldefs intspeed_any_cpp: EXTRA_LIBS = -L$(INTEL64_DIR) -l$(QKMALLOC) EXTRA_LDFLAGS = -Wl,-z,muldefs intspeed=base: %if defined(%{noopt}) OPT_ROOT = -O0 %elif defined(%{medopt}) OPT_ROOT = -O2 %else OPT_ROOT = -O3 -ffast-math -flto -mfpmath=sse -funroll-loops OPT_ROOT_F = -O3 -ipo -no-prec-div %endif FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FORT_FAST_NO_STATIC = $(SSE) $(OPT_ROOT_F) FAST = $(SSE) $(OPT_ROOT) -static FORT_FAST = $(SSEF) $(OPT_ROOT_F) -static %if !defined(%{static}) COPTIMIZE = $(FAST_NO_STATIC) -qopt-mem-layout-trans=4 -fiopenmp -DSPEC_OPENMP CXXOPTIMIZE = $(FAST_NO_STATIC) -qopt-mem-layout-trans=4 FOPTIMIZE = $(FORT_FAST_NO_STATIC) -qopt-mem-layout-trans=4 %if defined(%{noopt}) COPTIMIZE = $(OPT_ROOT) -fiopenmp -DSPEC_OPENMP CXXOPTIMIZE = $(OPT_ROOT) FOPTIMIZE = $(OPT_ROOT_F) %endif %else COPTIMIZE = $(FAST) -qopt-mem-layout-trans=4 -fiopenmp -DSPEC_OPENMP CXXOPTIMIZE = $(FAST) -qopt-mem-layout-trans=4 FOPTIMIZE = $(FORT_FAST) -qopt-mem-layout-trans=4 %if defined(%{noopt}) COPTIMIZE = $(OPT_ROOT) -static -fiopenmp -DSPEC_OPENMP CXXOPTIMIZE = $(OPT_ROOT) -static FOPTIMIZE = $(OPT_ROOT_F) -static %endif %endif intspeed=peak: %if defined(%{noopt}) || defined(%{medopt}) #not building or executing peak against less opt fail=1 %endif OPT_ROOT = -flto -O3 -ffast-math OPT_ROOT_ICC = -ipo -O3 -no-prec-div FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FAST_NO_STATIC_ICC = $(SSE) $(OPT_ROOT_ICC) COPTIMIZE = $(FAST_NO_STATIC) -qopt-mem-layout-trans=4 CXXOPTIMIZE = $(FAST_NO_STATIC) -qopt-mem-layout-trans=4 PASS1_CFLAGS = -prof-gen PASS2_CFLAGS = -prof-use PASS1_FFLAGS = -prof-gen PASS2_FFLAGS = -prof-use PASS1_CXXFLAGS = -prof-gen PASS2_CXXFLAGS = -prof-use PASS1_LDFLAGS = -prof-gen PASS2_LDFLAGS = -prof-use 600.perlbench_s=peak=default: #[56]00.perlbench[rs] has non standard signed overflow CC = icc FAST_NO_STATIC_ICC = $(SSE) $(OPT_ROOT_ICC) COPTIMIZE = $(FAST_NO_STATIC_ICC) -qopt-mem-layout-trans=4 EXTRA_OPTIMIZE = -fno-strict-overflow EXTRA_COPTIMIZE = $(OPT_JCC) 625.x264_s=peak: feedback = 0 EXTRA_OPTIMIZE = -fno-alias 602.gcc_s=peak: CC = icx -m64 -std=c11 CXX = icpx -m64 -std=c11 FAST_NO_STATIC = $(SSE) $(OPT_ROOT) COPTIMIZE = $(FAST_NO_STATIC) -qopt-mem-layout-trans=4 CXXOPTIMIZE = $(FAST_NO_STATIC) -qopt-mem-layout-trans=4 EXTRA_LIBS = -L$(JEMALLOC64_DIR) -l$(JEMALLOC64) EXTRA_LDFLAGS = -Wl,-z,muldefs EXTRA_COPTIMIZE = $(OPT_JCC_icx) PASS1_CFLAGS = -fprofile-generate -xCORE-AVX512 -flto -Ofast PASS2_CFLAGS = -fprofile-use=default.profdata PASS1_FFLAGS = -fprofile-generate -xCORE-AVX512 -flto -Ofast PASS2_FFLAGS = -fprofile-use=default.profdata PASS1_CXXFLAGS = -fprofile-generate -xCORE-AVX512 -flto -Ofast PASS2_CXXFLAGS = -fprofile-use=default.profdata PASS1_LDFLAGS = -fprofile-generate -xCORE-AVX512 -flto -Ofast PASS2_LDFLAGS = -fprofile-use=default.profdata fdo_run1 = $command ; llvm-profdata merge -output=default.profdata *.profraw 605.mcf_s,620.omnetpp_s,623.xalancbmk_s,631.deepsjeng_s,648.exchange2_s,641.leela_s,657.xz_s=peak: basepeak=1 fpspeed: CC = icc -m64 -std=c11 CXX = icpc -m64 FC = ifort -m64 # Compiler tuning toggle, corresponds with isa_ext preprocessor cfg var SSE = -xCORE-AVX512 EXTRA_FOPTIMIZE = -nostandard-realloc-lhs $(OPT_JCC) EXTRA_COPTIMIZE = $(OPT_JCC) EXTRA_CXXOPTIMIZE = $(OPT_JCC) fpspeed_any_fortran: EXTRA_LIBS = -L$(JEMALLOC64_DIR) -l$(JEMALLOC64) EXTRA_LDFLAGS = -Wl,-z,muldefs fpspeed=base=default: %if defined(%{noopt}) OPT_ROOT = -O0 %elif defined(%{medopt}) OPT_ROOT = -O2 %else OPT_ROOT = -ipo -O3 -no-prec-div %endif FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FORT_FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FAST = $(SSE) $(OPT_ROOT) -static FORT_FAST = $(SSE) $(OPT_ROOT) -static %if !defined(%{static}) COPTIMIZE = $(FAST_NO_STATIC) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP CXXOPTIMIZE = $(FAST_NO_STATIC) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP FOPTIMIZE = $(FORT_FAST_NO_STATIC) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP %if defined(%{noopt}) COPTIMIZE = $(OPT_ROOT) -qopenmp -DSPEC_OPENMP CXXOPTIMIZE = $(OPT_ROOT) -qopenmp -DSPEC_OPENMP FOPTIMIZE = $(OPT_ROOT) -qopenmp -DSPEC_OPENMP %endif %else COPTIMIZE = $(FAST) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP CXXOPTIMIZE = $(FAST) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP FOPTIMIZE = $(FORT_FAST) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP %if defined(%{noopt}) COPTIMIZE = $(OPT_ROOT) -qopenmp -DSPEC_OPENMP -static CXXOPTIMIZE = $(OPT_ROOT) -qopenmp -DSPEC_OPENMP -static FOPTIMIZE = $(OPT_ROOT) -qopenmp -DSPEC_OPENMP -static %endif %endif fpspeed=peak: %if defined(%{noopt}) || defined(%{medopt}) #not building or executing peak against less opt fail=1 %endif PASS1_CFLAGS = -prof-gen PASS2_CFLAGS = -prof-use PASS1_FFLAGS = -prof-gen PASS2_FFLAGS = -prof-use PASS1_CXXFLAGS = -prof-gen PASS2_CXXFLAGS = -prof-use PASS1_LDFLAGS = -prof-gen PASS2_LDFLAGS = -prof-use OPT_ROOT = -ipo -O3 -no-prec-div FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FORT_FAST_NO_STATIC = $(SSE) $(OPT_ROOT) FAST = $(SSE) $(OPT_ROOT) -static FORT_FAST = $(SSE) $(OPT_ROOT) -static FAST_NO_STATIC_PASS1 = $(OPT_ROOT) FORT_FAST_NO_STATIC_PASS1 = $(OPT_ROOT) FAST_PASS1 = $(OPT_ROOT) -static FORT_FAST_PASS1 = $(OPT_ROOT) -static FAST_NO_STATIC_PASS2 = $(SSE) $(OPT_ROOT) FORT_FAST_NO_STATIC_PASS2 = $(SSE) $(OPT_ROOT) FAST_PASS2 = $(SSE) $(OPT_ROOT) -static FORT_FAST_PASS2 = $(SSE) $(OPT_ROOT) -static %if !defined(%{static}) PASS1_COPTIMIZE = $(FAST_NO_STATIC_PASS1) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -DSPEC_SUPPRESS_OPENMP PASS1_CXXOPTIMIZE = $(FAST_NO_STATIC_PASS1) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -DSPEC_SUPPRESS_OPENMP PASS1_FOPTIMIZE = $(FORT_FAST_NO_STATIC_PASS1) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -DSPEC_SUPPRESS_OPENMP PASS2_COPTIMIZE = $(FAST_NO_STATIC_PASS2) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP PASS2_CXXOPTIMIZE = $(FAST_NO_STATIC_PASS2) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP PASS2_FOPTIMIZE = $(FORT_FAST_NO_STATIC_PASS2) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP %else PASS1_COPTIMIZE = $(FAST_PASS1) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -DSPEC_SUPPRESS_OPENMP PASS1_CXXOPTIMIZE = $(FAST_PASS1) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -DSPEC_SUPPRESS_OPENMP PASS1_FOPTIMIZE = $(FORT_FAST_PASS1) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -DSPEC_SUPPRESS_OPENMP PASS2_COPTIMIZE = $(FAST_PASS2) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP PASS2_CXXOPTIMIZE = $(FAST_PASS2) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP PASS2_FOPTIMIZE = $(FORT_FAST_PASS2) -qopt-prefetch -ffinite-math-only -qopt-mem-layout-trans=4 -qopenmp -DSPEC_OPENMP %endif #some benchmarks do not mind sharing cores %ifdef %{smt-on} 628.pop2_s,644.nab_s=peak: threads = %{numpeakthreads} %endif #fp no FDO 607.cactuBSSN_s,619.lbm_s,627.cam4_s,628.pop2_s,638.imagick_s,654.roms_s=peak: basepeak=1 644.nab_s=peak: CC = icx -m64 CXX = icpx -m64 OPT_ROOT = -Ofast -ffast-math -flto -mfpmath=sse -funroll-loops SSE = -xCORE-AVX512 FAST_NO_STATIC = $(SSE) $(OPT_ROOT) COPTIMIZE = $(FAST_NO_STATIC) -fiopenmp -DSPEC_OPENMP -qopt-mem-layout-trans=4 CXXOPTIMIZE = $(FAST_NO_STATIC) -fiopenmp -DSPEC_OPENMP -qopt-mem-layout-trans=4 feedback = 0 EXTRA_LIBS = -L$(JEMALLOC64_DIR) -l$(JEMALLOC64) EXTRA_LDFLAGS = -Wl,-z,muldefs EXTRA_OPTIMIZE = -fimf-accuracy-bits=14:sqrt $(OPT_JCC_icx) #------------------------------------------------------------------------------- # Tester and System Descriptions - EDIT the sections below #------------------------------------------------------------------------------- # For info about any field, see # https://www.spec.org/auto/cpu2017/Docs/config.html#fieldname # Example: https://www.spec.org/auto/cpu2017/Docs/config.html#hw_memory #------------------------------------------------------------------------------- #--------- If you install new compilers, EDIT this section -------------------- intrate,intspeed,fpspeed,fprate: sw_compiler000 = C/C++: Version 2021.1 of Intel oneAPI DPC++/C++ sw_compiler001 = Compiler Build 20201113 for Linux; sw_compiler002 = Fortran: Version 2021.1 of Intel Fortran Compiler sw_compiler003 = Classic Build 20201112 for Linux; sw_compiler004 = C/C++: Version 2021.1 of Intel C/C++ Compiler sw_compiler005 = Classic Build 20201112 for Linux sw_base_ptrsize = 64-bit sw_other = jemalloc memory allocator V5.0.1 fprate,fpspeed: sw_peak_ptrsize = 64-bit intspeed: sw_peak_ptrsize = 64-bit intrate: sw_peak_ptrsize = 32/64-bit #--------- EDIT Your info --------------------------------------------------------- # To understand the difference between hw_vendor/sponsor/tester, see: # www.spec.org/auto/cpu2017/Docs/config.html#test_sponsor intrate,intspeed,fprate,fpspeed: # Important: keep this line hw_vendor = My Corporation tester = Intel Corporation test_sponsor = Intel Corporation license_num = 13 prepared_by = Intel Corporation #--------- EDIT system availability dates and system information ---------------------------------------------- intrate,intspeed,fprate,fpspeed: # Important: keep this line # Example # Brief info about field hw_avail = # Nov-2099 # Date of LAST hardware component to ship sw_avail = # Nov-2099 # Date of LAST software component to ship hw_cpu_nominal_mhz = # 9999 # Nominal chip frequency, in MHz hw_cpu_max_mhz = # 9999 # Max chip frequency, in MHz hw_ncores = # 9999 # number cores enabled hw_nthreadspercore = # 9 # number threads enabled per core hw_ncpuorder = # 1-9 chips # Ordering options hw_model = # TurboBlaster 3000 # system model name hw_other = # TurboNUMA Router 10 Gb # Other perf-relevant hw, or "None" # sw_other = # TurboHeap Library V8.1 # Other perf-relevant sw, or "None" hw_pcache = # 99 KB I + 99 KB D on chip per core # Primary cache size, type, location hw_scache = # 99 KB I+D on chip per 9 cores # Second cache or "None" hw_tcache = # 9 MB I+D on chip per chip # Third cache or "None" hw_ocache = # 9 GB I+D off chip per system board # Other cache or "None" # hw_memory001 = # 4 TB (256 x 16 GB 2Rx4 PC4-2133P-R, # N GB (M x N GB nRxn # hw_memory002 = # running at 1600 MHz) # PCn-nnnnnR-n[, ECC and other info]) #--------- Sysinfo fields - You may need to adjust this section --------------- # Note: Some commented-out fields above are automatically set to preliminary # values by sysinfo # www.spec.org/auto/cpu2017/Docs/config.html#sysinfo # Uncomment lines for which you already have a better answer than sysinfo # intrate,intspeed,fprate,fpspeed: # Important: keep this line # Example # Brief info about field # hw_cpu_name = # Intel Xeon E9-9999 v9 # chip name # hw_disk = # 9 x 9 TB SATA III 9999 RPM # Size, type, other perf-relevant info # hw_nchips = # 99 # number chips enabled # sw_file = # ext99 # File system # sw_state = # Run level 99 # Software state. # sw_os001 = # Linux Sailboat # Operating system # sw_os002 = # Distribution 7.2 SP1 # and version #--------- EDIT Intel Recommended Fields - You may wish to adjust this section ----- default: notes_000 = Binaries compiled on a system with 1x Intel Core i9-7980XE CPU + 64GB RAM notes_005 = memory using Redhat Enterprise Linux 8.0 notes_os_000 = Stack size set to unlimited using "ulimit -s unlimited" #Ease of tagging results from the runcpu command line with commands run outside of runcpu harneess #Adjust as necessary for your SUT %if defined(%{THP_enabled}) notes_200 = Transparent Huge Pages enabled with: notes_201 = echo always > /sys/kernel/mm/transparent_hugepage/enabled %elif defined(%{THP_disabled}) notes_200 = Transparent Huge Pages disabled with: notes_201 = echo never > /sys/kernel/mm/transparent_hugepage/enabled %else notes_010 = Transparent Huge Pages enabled by default %endif %ifdef %{drop_caches} notes_015 = Prior to runcpu invocation notes_020 = Filesystem page cache synced and cleared with: notes_025 = sync; echo 3> /proc/sys/vm/drop_caches %endif %ifdef %{invoke_with_interleave} notes_205 = runcpu command invoked through numactl i.e.: notes_206 = numactl --interleave=all runcpu %endif intrate,fprate: %if defined(%{no-numa}) notes_submit_000 = The taskset mechanism was used to bind copies to processors. The config file option 'submit' notes_submit_001 = was used to generate taskset commands to bind each copy to a specific processor. notes_submit_002 = For details, please see the config file. %else notes_submit_000 = The numactl mechanism was used to bind copies to processors. The config file option 'submit' notes_submit_001 = was used to generate numactl commands to bind each copy to a specific processor. notes_submit_002 = For details, please see the config file. %endif intrate,fprate,intspeed,fpspeed: notes_jemalloc_000 = jemalloc, a general purpose malloc implementation notes_jemalloc_005 = built with the RedHat Enterprise 7.5, and the system compiler gcc 4.8.5 notes_jemalloc_010 = sources available from jemalloc.net or https://github.com/jemalloc/jemalloc/releases #include: Dell-info-Intel.inc # ----- Begin inclusion of 'Dell-info-Intel.inc' ############################################################################ #------------------------------------------------------- # Dell EMC (Dell Inc.) # # Intel #------------------------------------------------------- default: flagsurl001=http://www.spec.org/cpu2017/flags/Dell-Platform-Flags-PowerEdge-Intel-ICX-rev1.4.xml fprate,fpspeed,intrate,intspeed: # # Date format: Mmm-YYYY (Mmm is first 3 letters of the month - Jun, May, Aug, etc.) # # hw_avail - latter of the availability dates for the server, processor or memory. # sw_avail - latter of the availability dates for the compiler or Operating System # hw_avail = Jul-2021 # HCC Processor stack sw_avail = Dec-2020 #sw_avail = Oct-2020 # RHEL 8.3 base # # No need to edit these if you use a temporary file system (like ramdisk). hw_disk = 1 x 1.6 TB SATA SSD # Size, type, other perf-relevant info sw_file = xfs # File system # # BIOS Settings # - It is rare that these settings would need to be changed. # notes_plat_form_000 = notes_plat_form_005 = BIOS settings: fprate,intrate: notes_plat_form_100 = Sub NUMA Cluster : 2-Way Clustering fpspeed,intspeed: notes_plat_form_010 = Logical Processor : Disabled fprate,fpspeed,intrate,intspeed: notes_plat_form_015 = Virtualization Technology : Disabled notes_plat_form_020 = notes_plat_form_025 = System Profile : Custom notes_plat_form_030 = CPU Power Management : Maximum Performance notes_plat_form_035 = C1E : Disabled notes_plat_form_040 = C States : Autonomous notes_plat_form_045 = Memory Patrol Scrub : Disabled notes_plat_form_050 = Energy Efficiency Policy : Performance notes_plat_form_055 = CPU Interconnect Bus Link notes_plat_form_060 = Power Management : Disabled notes_plat_form_065 = PCI ASPM L1 Link notes_plat_form_070 = Power Management : Disabled power_management000 = BIOS and OS set to prefer performance power_management001 = at the cost of additional power usage. #------------------------------------------------------------------------------- # **** DO NOT EDIT BELOW HERE!!! #------------------------------------------------------------------------------- hw_other = None hw_ocache = None # Company Name, license, etc fprate,fpspeed,intrate,intspeed: hw_vendor = Dell Inc. tester = Dell Inc. test_sponsor = Dell Inc. prepared_by = Dell Inc. license_num = 55 # Cleanup from sysinfo hw_memory001 = %undef% hw_memory002 = %undef% sw_os001 = %undef% sw_os002 = %undef% # Mitigation notes_mitig_000 = notes_mitig_005 = NA: The test sponsor attests, as of date of publication, that CVE-2017-5754 (Meltdown) notes_mitig_010 = is mitigated in the system as tested and documented. notes_mitig_015 = Yes: The test sponsor attests, as of date of publication, that CVE-2017-5753 (Spectre variant 1) notes_mitig_020 = is mitigated in the system as tested and documented. notes_mitig_025 = Yes: The test sponsor attests, as of date of publication, that CVE-2017-5715 (Spectre variant 2) notes_mitig_030 = is mitigated in the system as tested and documented. #include: dell-system-info.inc # ----- Begin inclusion of 'dell-system-info.inc' ############################################################################ fprate,fpspeed,intrate,intspeed: hw_model000 = PowerEdge R650xs (Intel Xeon Gold 6336Y, 2.40 hw_model001 = GHz) hw_cpu_name = Intel Xeon Gold 6336Y hw_cpu_max_mhz = 3600 hw_nchips = 2 hw_ncpuorder = 1,2 chips hw_ncores = 48 hw_nthreadspercore = 1 hw_pcache = 32 KB I + 48 KB D on chip per core hw_scache = 1.25 MB I+D on chip per core hw_tcache = 36 MB I+D on chip per chip fw_bios = Version 1.1.3 released Apr-2021 sw_state = Run level 3 (multi-user) sw_file = tmpfs hw_disk = 225 GB on tmpfs notes_tmpfs_000 = notes_tmpfs_005 = Benchmark run from a 225 GB ramdisk created with the cmd: "mount -t tmpfs -o size=225G tmpfs /mnt/ramdisk" sw_os000 = Red Hat Enterprise Linux 8.3 (Ootpa) sw_os001 = 4.18.0-240.el8.x86_64 hw_cpu_nominal_mhz = 2400 hw_memory000 = 512 GB (16 x 32 GB 2Rx4 PC4-3200AA-R) # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.8-ic2021.1/config/dell-system-info.inc' # ---- End inclusion of '/mnt/ramdisk/cpu2017-1.1.8-ic2021.1/config/Dell-info-Intel.inc' # The following settings were obtained by running the sysinfo_program # 'specperl $[top]/bin/sysinfo' (sysinfo:SHA:679c83684f6f4fc369a093999b6661d0a378911de2a006d3245423ad80d3fb9a) default: notes_plat_sysinfo_000 = notes_plat_sysinfo_005 = Sysinfo program /mnt/ramdisk/cpu2017-1.1.8-ic2021.1/bin/sysinfo notes_plat_sysinfo_010 = Rev: r6622 of 2021-04-07 982a61ec0915b55891ef0e16acafc64d notes_plat_sysinfo_015 = running on r650xs.9yn9cd3.inside.dell.com Mon Aug 23 18:39:16 2021 notes_plat_sysinfo_020 = notes_plat_sysinfo_025 = SUT (System Under Test) info as seen by some common utilities. notes_plat_sysinfo_030 = For more information on this section, see notes_plat_sysinfo_035 = https://www.spec.org/cpu2017/Docs/config.html#sysinfo notes_plat_sysinfo_040 = notes_plat_sysinfo_045 = From /proc/cpuinfo notes_plat_sysinfo_050 = model name : Intel(R) Xeon(R) Gold 6336Y CPU @ 2.40GHz notes_plat_sysinfo_055 = 2 "physical id"s (chips) notes_plat_sysinfo_060 = 48 "processors" notes_plat_sysinfo_065 = cores, siblings (Caution: counting these is hw and system dependent. The following notes_plat_sysinfo_070 = excerpts from /proc/cpuinfo might not be reliable. Use with caution.) notes_plat_sysinfo_075 = cpu cores : 24 notes_plat_sysinfo_080 = siblings : 24 notes_plat_sysinfo_085 = physical 0: cores 0 1 10 11 12 13 14 15 16 17 18 19 20 21 22 23 notes_plat_sysinfo_090 = physical 1: cores 0 1 10 11 12 13 14 15 16 17 18 19 20 21 22 23 notes_plat_sysinfo_095 = notes_plat_sysinfo_100 = From lscpu from util-linux 2.32.1: notes_plat_sysinfo_105 = Architecture: x86_64 notes_plat_sysinfo_110 = CPU op-mode(s): 32-bit, 64-bit notes_plat_sysinfo_115 = Byte Order: Little Endian notes_plat_sysinfo_120 = CPU(s): 48 notes_plat_sysinfo_125 = On-line CPU(s) list: 0-47 notes_plat_sysinfo_130 = Thread(s) per core: 1 notes_plat_sysinfo_135 = Core(s) per socket: 24 notes_plat_sysinfo_140 = Socket(s): 2 notes_plat_sysinfo_145 = NUMA node(s): 2 notes_plat_sysinfo_150 = Vendor ID: GenuineIntel notes_plat_sysinfo_155 = CPU family: 6 notes_plat_sysinfo_160 = Model: 106 notes_plat_sysinfo_165 = Model name: Intel(R) Xeon(R) Gold 6336Y CPU @ 2.40GHz notes_plat_sysinfo_170 = Stepping: 6 notes_plat_sysinfo_175 = CPU MHz: 2602.382 notes_plat_sysinfo_180 = BogoMIPS: 4800.00 notes_plat_sysinfo_185 = Virtualization: VT-x notes_plat_sysinfo_190 = L1d cache: 48K notes_plat_sysinfo_195 = L1i cache: 32K notes_plat_sysinfo_200 = L2 cache: 1280K notes_plat_sysinfo_205 = L3 cache: 36864K notes_plat_sysinfo_210 = NUMA node0 CPU(s): notes_plat_sysinfo_215 = 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46 notes_plat_sysinfo_220 = NUMA node1 CPU(s): notes_plat_sysinfo_225 = 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47 notes_plat_sysinfo_230 = Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov notes_plat_sysinfo_235 = pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp notes_plat_sysinfo_240 = lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid notes_plat_sysinfo_245 = aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 notes_plat_sysinfo_250 = xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave notes_plat_sysinfo_255 = avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single notes_plat_sysinfo_260 = intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 notes_plat_sysinfo_265 = smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma notes_plat_sysinfo_270 = clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 notes_plat_sysinfo_275 = xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd notes_plat_sysinfo_280 = dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq notes_plat_sysinfo_285 = avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid md_clear pconfig flush_l1d notes_plat_sysinfo_290 = arch_capabilities notes_plat_sysinfo_295 = notes_plat_sysinfo_300 = /proc/cpuinfo cache data notes_plat_sysinfo_305 = cache size : 36864 KB notes_plat_sysinfo_310 = notes_plat_sysinfo_315 = From numactl --hardware notes_plat_sysinfo_320 = WARNING: a numactl 'node' might or might not correspond to a physical chip. notes_plat_sysinfo_325 = available: 2 nodes (0-1) notes_plat_sysinfo_330 = node 0 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38 40 42 44 46 notes_plat_sysinfo_335 = node 0 size: 246867 MB notes_plat_sysinfo_340 = node 0 free: 244925 MB notes_plat_sysinfo_345 = node 1 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43 45 47 notes_plat_sysinfo_350 = node 1 size: 247663 MB notes_plat_sysinfo_355 = node 1 free: 253710 MB notes_plat_sysinfo_360 = node distances: notes_plat_sysinfo_365 = node 0 1 notes_plat_sysinfo_370 = 0: 10 20 notes_plat_sysinfo_375 = 1: 20 10 notes_plat_sysinfo_380 = notes_plat_sysinfo_385 = From /proc/meminfo notes_plat_sysinfo_390 = MemTotal: 527547780 kB notes_plat_sysinfo_395 = HugePages_Total: 0 notes_plat_sysinfo_400 = Hugepagesize: 2048 kB notes_plat_sysinfo_405 = notes_plat_sysinfo_410 = /sbin/tuned-adm active notes_plat_sysinfo_415 = Current active profile: throughput-performance notes_plat_sysinfo_420 = notes_plat_sysinfo_425 = From /etc/*release* /etc/*version* notes_plat_sysinfo_430 = os-release: notes_plat_sysinfo_435 = NAME="Red Hat Enterprise Linux" notes_plat_sysinfo_440 = VERSION="8.3 (Ootpa)" notes_plat_sysinfo_445 = ID="rhel" notes_plat_sysinfo_450 = ID_LIKE="fedora" notes_plat_sysinfo_455 = VERSION_ID="8.3" notes_plat_sysinfo_460 = PLATFORM_ID="platform:el8" notes_plat_sysinfo_465 = PRETTY_NAME="Red Hat Enterprise Linux 8.3 (Ootpa)" notes_plat_sysinfo_470 = ANSI_COLOR="0;31" notes_plat_sysinfo_475 = redhat-release: Red Hat Enterprise Linux release 8.3 (Ootpa) notes_plat_sysinfo_480 = system-release: Red Hat Enterprise Linux release 8.3 (Ootpa) notes_plat_sysinfo_485 = system-release-cpe: cpe:/o:redhat:enterprise_linux:8.3:ga notes_plat_sysinfo_490 = notes_plat_sysinfo_495 = uname -a: notes_plat_sysinfo_500 = Linux r650xs.9yn9cd3.inside.dell.com 4.18.0-240.el8.x86_64 #1 SMP Wed Sep 23 05:13:10 notes_plat_sysinfo_505 = EDT 2020 x86_64 x86_64 x86_64 GNU/Linux notes_plat_sysinfo_510 = notes_plat_sysinfo_515 = Kernel self-reported vulnerability status: notes_plat_sysinfo_520 = notes_plat_sysinfo_525 = CVE-2018-12207 (iTLB Multihit): Not affected notes_plat_sysinfo_530 = CVE-2018-3620 (L1 Terminal Fault): Not affected notes_plat_sysinfo_535 = Microarchitectural Data Sampling: Not affected notes_plat_sysinfo_540 = CVE-2017-5754 (Meltdown): Not affected notes_plat_sysinfo_545 = CVE-2018-3639 (Speculative Store Bypass): Mitigation: Speculative Store notes_plat_sysinfo_550 = Bypass disabled via prctl and notes_plat_sysinfo_555 = seccomp notes_plat_sysinfo_560 = CVE-2017-5753 (Spectre variant 1): Mitigation: usercopy/swapgs notes_plat_sysinfo_565 = barriers and __user pointer notes_plat_sysinfo_570 = sanitization notes_plat_sysinfo_575 = CVE-2017-5715 (Spectre variant 2): Mitigation: Enhanced IBRS, IBPB: notes_plat_sysinfo_580 = conditional, RSB filling notes_plat_sysinfo_585 = CVE-2020-0543 (Special Register Buffer Data Sampling): Not affected notes_plat_sysinfo_590 = CVE-2019-11135 (TSX Asynchronous Abort): Not affected notes_plat_sysinfo_595 = notes_plat_sysinfo_600 = run-level 3 Aug 23 16:02 notes_plat_sysinfo_605 = notes_plat_sysinfo_610 = SPEC is set to: /mnt/ramdisk/cpu2017-1.1.8-ic2021.1 notes_plat_sysinfo_615 = Filesystem Type Size Used Avail Use% Mounted on notes_plat_sysinfo_620 = tmpfs tmpfs 225G 11G 215G 5% /mnt/ramdisk notes_plat_sysinfo_625 = notes_plat_sysinfo_630 = From /sys/devices/virtual/dmi/id notes_plat_sysinfo_635 = Vendor: Dell Inc. notes_plat_sysinfo_640 = Product: PowerEdge R650 xs notes_plat_sysinfo_645 = Product Family: PowerEdge notes_plat_sysinfo_650 = Serial: 9YN9CD3 notes_plat_sysinfo_655 = notes_plat_sysinfo_660 = Additional information from dmidecode 3.2 follows. WARNING: Use caution when you notes_plat_sysinfo_665 = interpret this section. The 'dmidecode' program reads system data which is "intended to notes_plat_sysinfo_670 = allow hardware to be accurately determined", but the intent may not be met, as there are notes_plat_sysinfo_675 = frequent changes to hardware, firmware, and the "DMTF SMBIOS" standard. notes_plat_sysinfo_680 = Memory: notes_plat_sysinfo_685 = 16x 00AD063200AD HMA84GR7DJR4N-XN 32 GB 2 rank 3200 notes_plat_sysinfo_690 = notes_plat_sysinfo_695 = BIOS: notes_plat_sysinfo_700 = BIOS Vendor: Dell Inc. notes_plat_sysinfo_705 = BIOS Version: 1.1.3 notes_plat_sysinfo_710 = BIOS Date: 04/27/2021 notes_plat_sysinfo_715 = BIOS Revision: 1.1 notes_plat_sysinfo_720 = notes_plat_sysinfo_725 = (End of data from sysinfo program) hw_cpu_name = Intel Xeon Gold 6336Y hw_disk = 225 GB add more disk info here hw_nchips = 2 prepared_by = root (is never output, only tags rawfile) sw_file = tmpfs sw_os001 = Red Hat Enterprise Linux release 8.3 (Ootpa) sw_state = Run level 3 (add definition here) # End of settings added by sysinfo_program