AMD EPYC 9965 Turin Dense vs. AmpereOne ARM 192-Core CPU Benchmarks

Benchmarks by Michael Larabel for a future article review on Phoronix.

HTML result view exported from: https://openbenchmarking.org/result/2410103-NE-AMPEREONE62&sgm=1&scalar=1&ppd_QW1wZXJlT25lIEExOTItMzJY=5555&ppd_RVBZQyA5OTY1=14813&ppt=D&sor&grr.

AMD EPYC 9965 Turin Dense vs. AmpereOne ARM 192-Core CPU BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelCompilerFile-SystemScreen ResolutionAmpereOne A192-32XEPYC 9965AmpereOne @ 3.20GHz (192 Cores)Supermicro ARS-211M-NR R13SPD v1.02 (T20240726102529 BIOS)Ampere Computing LLC Device e2088 x 64GB DDR5-5200MT/s3841GB SAMSUNG MZQL23T8HCLS-00A07 + 960GB SAMSUNG MZ1L2960HCJR-00A07ASPEEDVGA HDMI2 x Broadcom BCM57414 NetXtreme-E 10Gb/25Gb + 2 x Mellanox MT2892Ubuntu 24.046.8.0-39-generic-64k (aarch64)GCC 13.2.0ext41920x1080AMD EPYC 9965 192-Core @ 2.25GHz (192 Cores / 384 Threads)AMD VOLCANO (RVOT1000D BIOS)AMD Device 153a12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC2 x 1920GB KIOXIA KCD8XPUG1T92Broadcom NetXtreme BCM5720 PCIe6.10.0-phx (x86_64)1920x1200OpenBenchmarking.orgKernel Details- AmpereOne A192-32X: Transparent Huge Pages: always- EPYC 9965: Transparent Huge Pages: madviseCompiler Details- AmpereOne A192-32X: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v - EPYC 9965: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- AmpereOne A192-32X: Scaling Governor: cppc_cpufreq performance (Boost: Disabled)- EPYC 9965: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb101018Python Details- AmpereOne A192-32X: Python 3.12.3- EPYC 9965: Python 3.12.2Security Details- AmpereOne A192-32X: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Not affected + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9965: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected Java Details- EPYC 9965: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)

AMD EPYC 9965 Turin Dense vs. AmpereOne ARM 192-Core CPU Benchmarkswrf: conus 2.5kmhpcg: 144 144 144 - 60stockfish: Chess Benchmarkincompact3d: X3D-benchmarking input.i3daskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddingxmrig: GhostRider - 1Mbuild-gem5: Time To Compilebuild-nodejs: Time To Compilelammps: 20k Atomsbuild-llvm: Ninjaopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeqmcpack: Li2_STO_aelulesh: speedb: Rand Readgraphics-magick: Sharpengraphics-magick: Noise-Gaussianrocksdb: Read While Writinggraphics-magick: Enhancedgraphics-magick: Swirlrocksdb: Rand Readquantlib: Multi-Threadedamg: minife: Smallsrsran: PUSCH Processor Benchmark, Throughput Totalnpb: EP.Dgpaw: Carbon Nanotubepennant: sedovbighelsing: 14 digitcompress-7zip: Decompression Ratingcompress-7zip: Compression Ratinggromacs: MPI CPU - water_GMX50_barenpb: SP.Cjohn-the-ripper: Blowfishjohn-the-ripper: bcryptastcenc: Exhaustivenpb: IS.Dastcenc: Very Thoroughpennant: leblancbigopenfoam: drivaerFastback, Small Mesh Size - Execution Timeprimesieve: 1e13lammps: Rhodopsin Proteincoremark: CoreMark Size 666 - Iterations Per Secondbuild-mesa: Time To Compileastcenc: Thoroughincompact3d: input.i3d 193 Cells Per Directionm-queens: Time To Solveonednn: Deconvolution Batch shapes_3d - CPUcompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionAmpereOne A192-32XEPYC 99659102.31833.3617128602136290.28072118414.720809.217812.6195.568214.15553.859177.104315.65587106.9141890.4077344016354692459803710370953719203371300839.9182826533338349.22824.77557.7241.0604.29058630.4738773057566817.03933612.411763061740484.59302417.047.37483.34943932.35887114.01050.5354561177.33617017.19250.02328.955814845.3572.016291.6444855735.24160.7037362007178196.31866544845.246390.515447.6140.593117.82266.77399.433176.3980694.59134694.14696989073944529618280003495893958354064566481.4297634500065294.58940.917965.5527.5603.80696539.7651001858100715023.142152747.8738608238647411.53127503.0118.77132.37951325.33694515.97655.0194247085.81199315.511128.75626.539376554.7080.6581540.891238OpenBenchmarking.org

WRF

Input: conus 2.5km

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5kmEPYC 9965AmpereOne A192-32X2K4K6K8K10K5735.249102.321. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

High Performance Conjugate Gradient

X Y Z: 144 144 144 - RT: 60

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60EPYC 9965AmpereOne A192-32X1428425670SE +/- 0.02, N = 3SE +/- 0.39, N = 360.7033.361. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

Stockfish

Chess Benchmark

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkEPYC 9965AmpereOne A192-32X80M160M240M320M400MSE +/- 2768351.23, N = 3SE +/- 4643374.23, N = 11362007178128602136-m64 -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi21. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -flto -flto-partition=one -flto=jobserver

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dEPYC 9965AmpereOne A192-32X60120180240300SE +/- 0.30, N = 3SE +/- 0.24, N = 3196.32290.281. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

ASKAP

Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 9965AmpereOne A192-32X10K20K30K40K50KSE +/- 526.44, N = 13SE +/- 93.27, N = 344845.218414.71. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

ASKAP

Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 9965AmpereOne A192-32X10K20K30K40K50KSE +/- 455.47, N = 13SE +/- 159.94, N = 346390.520809.21. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Xmrig

Variant: GhostRider - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MAmpereOne A192-32XEPYC 99654K8K12K16K20KSE +/- 274.17, N = 15SE +/- 53.68, N = 317812.615447.6-maes1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Timed Gem5 Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileEPYC 9965AmpereOne A192-32X4080120160200SE +/- 1.20, N = 3SE +/- 0.58, N = 3140.59195.57

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileEPYC 9965AmpereOne A192-32X50100150200250SE +/- 0.70, N = 3SE +/- 0.34, N = 3117.82214.16

LAMMPS Molecular Dynamics Simulator

Model: 20k Atoms

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 9965AmpereOne A192-32X1530456075SE +/- 0.46, N = 3SE +/- 0.04, N = 366.7753.861. (CXX) g++ options: -O3 -lm -ldl

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaEPYC 9965AmpereOne A192-32X4080120160200SE +/- 0.77, N = 3SE +/- 0.57, N = 399.43177.10

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeEPYC 9965AmpereOne A192-32X70140210280350176.40315.66-m64-mcpu=native1. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

QMCPACK

Input: Li2_STO_ae

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: Li2_STO_aeEPYC 9965AmpereOne A192-32X20406080100SE +/- 0.32, N = 3SE +/- 0.15, N = 394.59106.91-march=native-mcpu=native1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -O3 -lm -ldl

LULESH

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3AmpereOne A192-32XEPYC 99659K18K27K36K45KSE +/- 79.76, N = 3SE +/- 401.87, N = 1541890.4134694.151. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

Speedb

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadEPYC 9965AmpereOne A192-32X200M400M600M800M1000MSE +/- 370648.73, N = 3SE +/- 1533105.14, N = 3969890739734401635-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenAmpereOne A192-32XEPYC 9965100200300400500SE +/- 4.33, N = 3SE +/- 0.88, N = 34694451. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 9965AmpereOne A192-32X60120180240300SE +/- 1.00, N = 3SE +/- 1.20, N = 32962451. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 9965AmpereOne A192-32X4M8M12M16M20MSE +/- 231468.03, N = 3SE +/- 27064.97, N = 3182800039803710-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 9965AmpereOne A192-32X110220330440550SE +/- 1.53, N = 3SE +/- 0.33, N = 34953701. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlAmpereOne A192-32XEPYC 99652004006008001000SE +/- 2.52, N = 3SE +/- 0.33, N = 39538931. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadEPYC 9965AmpereOne A192-32X200M400M600M800M1000MSE +/- 1700402.40, N = 3SE +/- 904748.20, N = 3958354064719203371-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

QuantLib

Configuration: Multi-Threaded

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 9965AmpereOne A192-32X120K240K360K480K600KSE +/- 485.45, N = 3SE +/- 97.87, N = 3566481.4300839.91. (CXX) g++ options: -O3 -march=native -fPIE -pie

Algebraic Multi-Grid Benchmark

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 9965AmpereOne A192-32X600M1200M1800M2400M3000MSE +/- 2247127.13, N = 3SE +/- 1007826.76, N = 3297634500018282653331. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

miniFE

Problem Size: Small

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 9965AmpereOne A192-32X14K28K42K56K70KSE +/- 21.96, N = 6SE +/- 628.57, N = 1565294.538349.21. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

srsRAN Project

Test: PUSCH Processor Benchmark, Throughput Total

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalEPYC 9965AmpereOne A192-32X2K4K6K8K10KSE +/- 0.19, N = 3SE +/- 0.12, N = 38940.92824.7-march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq - MIN: 7191.5 / MAX: 8941.3MIN: 1697.4 / MAX: 2824.91. (CXX) g++ options: -O3 -fno-trapping-math -fno-math-errno -ldl

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 9965AmpereOne A192-32X4K8K12K16K20KSE +/- 908.46, N = 15SE +/- 27.71, N = 317965.557557.721. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

GPAW

Input: Carbon Nanotube

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeEPYC 9965AmpereOne A192-32X918273645SE +/- 0.02, N = 3SE +/- 0.10, N = 327.5641.06-fwrapv -O21. (CC) gcc options: -shared -lxc -lblas -lmpi

Pennant

Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 9965AmpereOne A192-32X0.96541.93082.89623.86164.827SE +/- 0.046313, N = 15SE +/- 0.065187, N = 153.8069654.2905861. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

Helsing

Digit Range: 14 digit

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitAmpereOne A192-32XEPYC 9965918273645SE +/- 0.11, N = 3SE +/- 0.08, N = 330.4739.771. (CC) gcc options: -O2 -pthread

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 9965AmpereOne A192-32X200K400K600K800K1000KSE +/- 150.31, N = 3SE +/- 2055.40, N = 310018588773051. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingEPYC 9965AmpereOne A192-32X200K400K600K800K1000KSE +/- 5680.94, N = 3SE +/- 7822.06, N = 310071507566811. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 9965AmpereOne A192-32X612182430SE +/- 0.050, N = 3SE +/- 0.007, N = 323.1427.0391. (CXX) g++ options: -O3 -lm

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 9965AmpereOne A192-32X30K60K90K120K150KSE +/- 1227.63, N = 4SE +/- 8.41, N = 3152747.8733612.411. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 9965AmpereOne A192-32X80K160K240K320K400KSE +/- 201.40, N = 3SE +/- 564.17, N = 3386082176306-m64 -lgmp1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2

John The Ripper

Test: bcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 9965AmpereOne A192-32X80K160K240K320K400KSE +/- 8.33, N = 3SE +/- 1839.06, N = 3386474174048-m64 -lgmp1. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 9965AmpereOne A192-32X3691215SE +/- 0.0016, N = 4SE +/- 0.0011, N = 311.53124.59301. (CXX) g++ options: -O3 -flto -pthread

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 9965AmpereOne A192-32X16003200480064008000SE +/- 113.41, N = 15SE +/- 10.73, N = 37503.012417.041. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

ASTC Encoder

Preset: Very Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 9965AmpereOne A192-32X510152025SE +/- 0.0042, N = 3SE +/- 0.0004, N = 318.77137.37481. (CXX) g++ options: -O3 -flto -pthread

Pennant

Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 9965AmpereOne A192-32X0.75361.50722.26083.01443.768SE +/- 0.017533, N = 7SE +/- 0.062865, N = 152.3795133.3494391. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Execution Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 9965AmpereOne A192-32X81624324025.3432.36-m64-mcpu=native1. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

Primesieve

Length: 1e13

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13AmpereOne A192-32XEPYC 996548121620SE +/- 0.06, N = 4SE +/- 0.01, N = 414.0115.981. (CXX) g++ options: -O3

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinEPYC 9965AmpereOne A192-32X1224364860SE +/- 0.48, N = 15SE +/- 3.06, N = 1255.0250.541. (CXX) g++ options: -O3 -lm -ldl

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondAmpereOne A192-32XEPYC 99651000K2000K3000K4000K5000KSE +/- 3500.33, N = 3SE +/- 2487.95, N = 34561177.344247085.811. (CC) gcc options: -O2 -lrt" -lrt

Timed Mesa Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 24.0Time To CompileEPYC 9965AmpereOne A192-32X48121620SE +/- 0.07, N = 4SE +/- 0.07, N = 315.5117.19

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 9965AmpereOne A192-32X306090120150SE +/- 0.07, N = 6SE +/- 0.01, N = 4128.7650.021. (CXX) g++ options: -O3 -flto -pthread

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 9965AmpereOne A192-32X3691215SE +/- 0.01223998, N = 5SE +/- 0.04916545, N = 46.539376558.955814841. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveEPYC 9965AmpereOne A192-32X1.20532.41063.61594.82126.0265SE +/- 0.029, N = 8SE +/- 0.010, N = 74.7085.3571. (CXX) g++ options: -fopenmp -O2 -march=native

oneDNN

Harness: Deconvolution Batch shapes_3d - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUEPYC 9965AmpereOne A192-32X0.45370.90741.36111.81482.2685SE +/- 0.001318, N = 9SE +/- 0.012736, N = 90.6581542.016290-msse4.1 - MIN: 0.58-mcpu=generic - MIN: 1.751. (CXX) g++ options: -O3 -march=native -fopenmp -fPIC -pie -ldl -lpthread

Parallel BZIP2 Compression

FreeBSD-13.0-RELEASE-amd64-memstick.img Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionEPYC 9965AmpereOne A192-32X0.370.741.111.481.85SE +/- 0.009424, N = 15SE +/- 0.008273, N = 110.8912381.6444851. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

CPU Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringAmpereOne A192-32XEPYC 996580160240320400Min: 101.66 / Avg: 230.95 / Max: 401.31Min: 19.04 / Avg: 275.17 / Max: 461.59

Primesieve

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 12.1CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.49 / Avg: 301.51 / Max: 386.95Min: 102.19 / Avg: 323.6 / Max: 397.32

Stockfish

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 102.54 / Avg: 294 / Max: 400.19Min: 38.5 / Avg: 388.69 / Max: 420.82

Stockfish

Chess Benchmark

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 16.1Chess BenchmarkEPYC 9965AmpereOne A192-32X200K400K600K800K1000K931347.77437423.93

Helsing

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterHelsing 1.0-betaCPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.62 / Avg: 342.85 / Max: 387.21Min: 105.04 / Avg: 359.98 / Max: 397.64

Xmrig

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996560120180240300Min: 104.15 / Avg: 222.49 / Max: 236.3Min: 38.1 / Avg: 321.57 / Max: 344.6

Xmrig

Variant: GhostRider - Hash Count: 1M

OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MAmpereOne A192-32XEPYC 99652040608010080.0648.04

oneDNN

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X50100150200250Min: 38.46 / Avg: 120.79 / Max: 233.5Min: 104.25 / Avg: 174.99 / Max: 279.82

srsRAN Project

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 104.98 / Avg: 183.4 / Max: 200.5Min: 39.02 / Avg: 312.37 / Max: 368.16

srsRAN Project

Test: PUSCH Processor Benchmark, Throughput Total

OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalEPYC 9965AmpereOne A192-32X71421283528.6215.40

GraphicsMagick

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996550100150200250Min: 106.72 / Avg: 248.15 / Max: 262.76Min: 38.33 / Avg: 255.99 / Max: 276.43

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: SwirlAmpereOne A192-32XEPYC 99650.8641.7282.5923.4564.323.8403.488

GraphicsMagick

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X60120180240300Min: 38.44 / Avg: 289.74 / Max: 312.13Min: 106.92 / Avg: 300.35 / Max: 330.49

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: SharpenAmpereOne A192-32XEPYC 99650.35150.7031.05451.4061.75751.5621.536

GraphicsMagick

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996550100150200250Min: 104.16 / Avg: 238.4 / Max: 254.8Min: 38 / Avg: 265.31 / Max: 285.06

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 9965AmpereOne A192-32X0.41990.83981.25971.67962.09951.8661.552

GraphicsMagick

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X4080120160200Min: 38.31 / Avg: 166.42 / Max: 181.2Min: 105.05 / Avg: 167.57 / Max: 193.59

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 9965AmpereOne A192-32X0.40030.80061.20091.60122.00151.7791.462

ASTC Encoder

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 106.05 / Avg: 231.9 / Max: 270.75Min: 38.46 / Avg: 253 / Max: 377.81

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 9965AmpereOne A192-32X0.01040.02080.03120.04160.0520.0460.020

ASTC Encoder

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105.18 / Avg: 233.56 / Max: 271.06Min: 38.13 / Avg: 249.95 / Max: 374.59

ASTC Encoder

Preset: Very Thorough

OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 9965AmpereOne A192-32X0.01690.03380.05070.06760.08450.0750.032

ASTC Encoder

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.2 / Avg: 159.26 / Max: 364Min: 104.51 / Avg: 189.61 / Max: 266.8

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 9965AmpereOne A192-32X0.18180.36360.54540.72720.9090.8080.264

Parallel BZIP2 Compression

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterParallel BZIP2 Compression 1.1.13CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X50100150200250Min: 38 / Avg: 80.55 / Max: 240.43Min: 103.94 / Avg: 134.98 / Max: 280.44

7-Zip Compression

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105.87 / Avg: 278.72 / Max: 358.51Min: 38.89 / Avg: 311.64 / Max: 408.21

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 9965AmpereOne A192-32X70014002100280035003214.793147.65

OpenFOAM

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 107.53 / Avg: 297.1 / Max: 398.03Min: 38.05 / Avg: 377.53 / Max: 408.64

OpenFOAM

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 104.98 / Avg: 306.31 / Max: 398.09Min: 37.74 / Avg: 322.39 / Max: 406.12

Xcompact3d Incompact3d

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105.69 / Avg: 234.12 / Max: 381.79Min: 38.35 / Avg: 357.77 / Max: 389.51

Xcompact3d Incompact3d

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 107.25 / Avg: 204.21 / Max: 336.02Min: 19.04 / Avg: 239.56 / Max: 402.63

NAS Parallel Benchmarks

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 37.84 / Avg: 183.78 / Max: 364.37Min: 107.67 / Avg: 200.87 / Max: 327.97

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 9965AmpereOne A192-32X91827364540.8312.03

NAS Parallel Benchmarks

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.09 / Avg: 269.5 / Max: 413.08Min: 107.89 / Avg: 305.58 / Max: 338.69

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 9965AmpereOne A192-32X120240360480600566.79110.00

NAS Parallel Benchmarks

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105.52 / Avg: 214.72 / Max: 253.24Min: 37.89 / Avg: 242.18 / Max: 391.39

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 9965AmpereOne A192-32X163248648074.1835.20

Pennant

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105.79 / Avg: 187.28 / Max: 376.9Min: 37.86 / Avg: 197.44 / Max: 381.39

Pennant

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 37.98 / Avg: 172.45 / Max: 384.3Min: 104.62 / Avg: 178.43 / Max: 356.42

High Performance Conjugate Gradient

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 106.77 / Avg: 250.99 / Max: 397.93Min: 38.16 / Avg: 344.96 / Max: 387.51

High Performance Conjugate Gradient

X Y Z: 144 144 144 - RT: 60

OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60EPYC 9965AmpereOne A192-32X0.03960.07920.11880.15840.1980.1760.133

GPAW

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterGPAW 23.6CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 109.1 / Avg: 315.48 / Max: 394.13Min: 38.14 / Avg: 324.56 / Max: 416.87

QMCPACK

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterQMCPACK 3.17.1CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.28 / Avg: 360 / Max: 391.3Min: 106.57 / Avg: 367.85 / Max: 394.45

QuantLib

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 102.86 / Avg: 305.61 / Max: 373.06Min: 37.88 / Avg: 352.68 / Max: 387.81

QuantLib

Configuration: Multi-Threaded

OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 9965AmpereOne A192-32X300600900120015001606.22984.41

GROMACS

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2024CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105 / Avg: 270.4 / Max: 398.48Min: 37.69 / Avg: 288.78 / Max: 417.16

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 9965AmpereOne A192-32X0.0180.0360.0540.0720.090.0800.026

ASKAP

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 104.66 / Avg: 214.12 / Max: 333.71Min: 38.21 / Avg: 310.65 / Max: 396.72

ASKAP

Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMpix/sec Per Watt, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 9965AmpereOne A192-32X306090120150144.3686.00

miniFE

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterminiFE 2.2CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996560120180240300Min: 105.1 / Avg: 154.13 / Max: 234.99Min: 37.77 / Avg: 157.38 / Max: 341.27

miniFE

Problem Size: Small

OpenBenchmarking.orgCG Mflops Per Watt, More Is BetterminiFE 2.2Problem Size: SmallEPYC 9965AmpereOne A192-32X90180270360450414.89248.81

m-queens

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Betterm-queens 1.2CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.1 / Avg: 206.82 / Max: 364.2Min: 108.63 / Avg: 238.77 / Max: 351.4

LAMMPS Molecular Dynamics Simulator

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996580160240320400Min: 104.06 / Avg: 329.3 / Max: 341.95Min: 37.84 / Avg: 396.7 / Max: 422.8

LAMMPS Molecular Dynamics Simulator

Model: 20k Atoms

OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 9965AmpereOne A192-32X0.03780.07560.11340.15120.1890.1680.164

LAMMPS Molecular Dynamics Simulator

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 20.48 / Avg: 130.45 / Max: 330.94Min: 104.89 / Avg: 151.52 / Max: 390.85

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinEPYC 9965AmpereOne A192-32X0.0950.190.2850.380.4750.4220.334

LULESH

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterLULESH 2.0.3CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105.07 / Avg: 191.51 / Max: 305.74Min: 37.91 / Avg: 229.8 / Max: 371.86

LULESH

OpenBenchmarking.orgz/s Per Watt, More Is BetterLULESH 2.0.3AmpereOne A192-32XEPYC 996550100150200250218.74150.98

WRF

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterWRF 4.2.2CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 105.62 / Avg: 265.36 / Max: 401.27Min: 38 / Avg: 377.12 / Max: 411.59

Algebraic Multi-Grid Benchmark

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 106.4 / Avg: 218.6 / Max: 277.51Min: 37.56 / Avg: 297.09 / Max: 369.72

Algebraic Multi-Grid Benchmark

OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 9965AmpereOne A192-32X2M4M6M8M10M10018207.528363571.07

Coremark

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterCoremark 1.0CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996560120180240300Min: 105.11 / Avg: 226.88 / Max: 316.57Min: 37.62 / Avg: 260.98 / Max: 347.04

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec Per Watt, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondAmpereOne A192-32XEPYC 99654K8K12K16K20K20104.1216273.75

Speedb

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.22 / Avg: 357.53 / Max: 383.56Min: 105.06 / Avg: 375.67 / Max: 398.47

Speedb

Test: Random Read

OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random ReadEPYC 9965AmpereOne A192-32X600K1200K1800K2400K3000K2712772.811954905.44

RocksDB

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996580160240320400Min: 107.19 / Avg: 209.34 / Max: 230.87Min: 38.7 / Avg: 355.17 / Max: 422.1

RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 9965AmpereOne A192-32X11K22K33K44K55K51469.0246831.10

RocksDB

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 38.02 / Avg: 354.3 / Max: 379.97Min: 104.34 / Avg: 378.34 / Max: 398.75

RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Random ReadEPYC 9965AmpereOne A192-32X600K1200K1800K2400K3000K2704939.661900947.44

John The Ripper

Test: bcrypt

OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 9965AmpereOne A192-32X20040060080010001127.52669.85

John The Ripper

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 106.28 / Avg: 259.83 / Max: 288.18Min: 38.39 / Avg: 341.67 / Max: 386.74

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 9965AmpereOne A192-32X20040060080010001128.50668.04

Timed Mesa Compilation

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterTimed Mesa Compilation 24.0CPU Power Consumption MonitorEPYC 9965AmpereOne A192-32X70140210280350Min: 37.92 / Avg: 125.14 / Max: 379.26Min: 101.84 / Avg: 135.79 / Max: 362.85

Timed LLVM Compilation

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 101.75 / Avg: 183.19 / Max: 347.18Min: 38.23 / Avg: 254.04 / Max: 404.43

Timed Gem5 Compilation

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 23.0.1CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 101.68 / Avg: 148.16 / Max: 334.89Min: 37.8 / Avg: 163.63 / Max: 402.39

Timed Node.js Compilation

CPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 21.7.2CPU Power Consumption MonitorAmpereOne A192-32XEPYC 996570140210280350Min: 102.28 / Avg: 196.52 / Max: 374.67Min: 37.91 / Avg: 257.75 / Max: 406.9

Geometric Mean Of All Test Results

Result Composite - AMD EPYC 9965 Turin Dense vs. AmpereOne ARM 192-Core CPU Benchmarks

OpenBenchmarking.orgGeometric Mean, More Is BetterGeometric Mean Of All Test ResultsResult Composite - AMD EPYC 9965 Turin Dense vs. AmpereOne ARM 192-Core CPU BenchmarksEPYC 9965AmpereOne A192-32X300600900120015001225.64764.47

WRF

Performance / Cost - Input: conus 2.5km

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterWRF 4.2.2Performance / Cost - Input: conus 2.5kmAmpereOne A192-32XEPYC 996520M40M60M80M100M50563376.4984956124.931. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

High Performance Conjugate Gradient

Performance / Cost - X Y Z: 144 144 144 - RT: 60

OpenBenchmarking.orgGFLOP/s Per Dollar, More Is BetterHigh Performance Conjugate Gradient 3.1Performance / Cost - X Y Z: 144 144 144 - RT: 60AmpereOne A192-32XEPYC 99650.00140.00280.00420.00560.0070.006005710.004098001. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Stockfish

Performance / Cost - Chess Benchmark

OpenBenchmarking.orgNodes Per Second Per Dollar, More Is BetterStockfish 16.1Performance / Cost - Chess BenchmarkEPYC 9965AmpereOne A192-32X5K10K15K20K25K24438.4823150.701. EPYC 9965: $14813 reported cost.2. AmpereOne A192-32X: $5555 reported cost.

Xcompact3d Incompact3d

Performance / Cost - Input: X3D-benchmarking input.i3d

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Performance / Cost - Input: X3D-benchmarking input.i3dAmpereOne A192-32XEPYC 9965600K1200K1800K2400K3000K1612509.412908068.391. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

ASKAP

Performance / Cost - Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMpix/sec Per Dollar, More Is BetterASKAP 1.0Performance / Cost - Test: tConvolve MPI - GriddingAmpereOne A192-32XEPYC 99650.74591.49182.23772.98363.72953.3153.0271. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

ASKAP

Performance / Cost - Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMpix/sec Per Dollar, More Is BetterASKAP 1.0Performance / Cost - Test: tConvolve MPI - DegriddingAmpereOne A192-32XEPYC 99650.84291.68582.52873.37164.21453.7463.1321. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Xmrig

Performance / Cost - Variant: GhostRider - Hash Count: 1M

OpenBenchmarking.orgH/s Per Dollar, More Is BetterXmrig 6.21Performance / Cost - Variant: GhostRider - Hash Count: 1MAmpereOne A192-32XEPYC 99650.72161.44322.16482.88643.6083.2071.0431. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Timed Gem5 Compilation

Performance / Cost - Time To Compile

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterTimed Gem5 Compilation 23.0.1Performance / Cost - Time To CompileAmpereOne A192-32XEPYC 9965400K800K1200K1600K2000K1086380.242082604.111. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Timed Node.js Compilation

Performance / Cost - Time To Compile

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterTimed Node.js Compilation 21.7.2Performance / Cost - Time To CompileAmpereOne A192-32XEPYC 9965400K800K1200K1600K2000K1189631.031745297.291. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

LAMMPS Molecular Dynamics Simulator

Performance / Cost - Model: 20k Atoms

OpenBenchmarking.orgns/day Per Dollar, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Performance / Cost - Model: 20k AtomsAmpereOne A192-32XEPYC 99650.00220.00440.00660.00880.0110.009695590.004507731. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Timed LLVM Compilation

Performance / Cost - Build System: Ninja

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterTimed LLVM Compilation 16.0Performance / Cost - Build System: NinjaAmpereOne A192-32XEPYC 9965300K600K900K1200K1500K983812.721472901.031. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

OpenFOAM

Performance / Cost - Input: drivaerFastback, Medium Mesh Size - Execution Time

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterOpenFOAM 10Performance / Cost - Input: drivaerFastback, Medium Mesh Size - Execution TimeAmpereOne A192-32XEPYC 9965600K1200K1800K2400K3000K1753468.362612984.461. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

QMCPACK

Performance / Cost - Input: Li2_STO_ae

OpenBenchmarking.orgTotal Execution Time - Seconds x Dollar, Fewer Is BetterQMCPACK 3.17.1Performance / Cost - Input: Li2_STO_aeAmpereOne A192-32XEPYC 9965300K600K900K1200K1500K593885.051401176.481. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

LULESH

Performance / Cost

OpenBenchmarking.orgz/s Per Dollar, More Is BetterLULESH 2.0.3Performance / CostAmpereOne A192-32XEPYC 99652468107.5412.3421. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Speedb

Performance / Cost - Test: Random Read

OpenBenchmarking.orgOp/s Per Dollar, More Is BetterSpeedb 2.7Performance / Cost - Test: Random ReadAmpereOne A192-32XEPYC 996530K60K90K120K150K132205.5265475.651. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

GraphicsMagick

Performance / Cost - Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute Per Dollar, More Is BetterGraphicsMagick 1.3.43Performance / Cost - Operation: SharpenAmpereOne A192-32XEPYC 99650.0190.0380.0570.0760.0950.084428440.030041181. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

GraphicsMagick

Performance / Cost - Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute Per Dollar, More Is BetterGraphicsMagick 1.3.43Performance / Cost - Operation: Noise-GaussianAmpereOne A192-32XEPYC 99650.00990.01980.02970.03960.04950.044104410.019982451. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

RocksDB

Performance / Cost - Test: Read While Writing

OpenBenchmarking.orgOp/s Per Dollar, More Is BetterRocksDB 9.0Performance / Cost - Test: Read While WritingAmpereOne A192-32XEPYC 99654008001200160020001764.841234.051. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

GraphicsMagick

Performance / Cost - Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute Per Dollar, More Is BetterGraphicsMagick 1.3.43Performance / Cost - Operation: EnhancedAmpereOne A192-32XEPYC 99650.0150.030.0450.060.0750.066606660.033416591. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

GraphicsMagick

Performance / Cost - Operation: Swirl

OpenBenchmarking.orgIterations Per Minute Per Dollar, More Is BetterGraphicsMagick 1.3.43Performance / Cost - Operation: SwirlAmpereOne A192-32XEPYC 99650.03870.07740.11610.15480.19350.172000000.060284881. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

RocksDB

Performance / Cost - Test: Random Read

OpenBenchmarking.orgOp/s Per Dollar, More Is BetterRocksDB 9.0Performance / Cost - Test: Random ReadAmpereOne A192-32XEPYC 996530K60K90K120K150K129469.5564696.831. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

QuantLib

Performance / Cost - Configuration: Multi-Threaded

OpenBenchmarking.orgMFLOPS Per Dollar, More Is BetterQuantLib 1.32Performance / Cost - Configuration: Multi-ThreadedAmpereOne A192-32XEPYC 9965122436486054.1638.241. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Algebraic Multi-Grid Benchmark

Performance / Cost

OpenBenchmarking.orgFigure Of Merit Per Dollar, More Is BetterAlgebraic Multi-Grid Benchmark 1.2Performance / CostAmpereOne A192-32XEPYC 996570K140K210K280K350K329120.67200927.901. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

miniFE

Performance / Cost - Problem Size: Small

OpenBenchmarking.orgCG Mflops Per Dollar, More Is BetterminiFE 2.2Performance / Cost - Problem Size: SmallAmpereOne A192-32XEPYC 99652468106.9044.4081. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

srsRAN Project

Performance / Cost - Test: PUSCH Processor Benchmark, Throughput Total

OpenBenchmarking.orgMbps Per Dollar, More Is BettersrsRAN Project 23.10.1-20240325Performance / Cost - Test: PUSCH Processor Benchmark, Throughput TotalEPYC 9965AmpereOne A192-32X0.13590.27180.40770.54360.67950.6040.5081. EPYC 9965: $14813 reported cost.2. AmpereOne A192-32X: $5555 reported cost.

NAS Parallel Benchmarks

Performance / Cost - Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s Per Dollar, More Is BetterNAS Parallel Benchmarks 3.4Performance / Cost - Test / Class: EP.DAmpereOne A192-32XEPYC 99650.30620.61240.91861.22481.5311.3611.2131. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

GPAW

Performance / Cost - Input: Carbon Nanotube

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterGPAW 23.6Performance / Cost - Input: Carbon NanotubeAmpereOne A192-32XEPYC 996590K180K270K360K450K228088.30408246.281. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Pennant

Performance / Cost - Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds x Dollar, Fewer Is BetterPennant 1.0.1Performance / Cost - Test: sedovbigAmpereOne A192-32XEPYC 996512K24K36K48K60K23834.2156392.571. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Helsing

Performance / Cost - Digit Range: 14 digit

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterHelsing 1.0-betaPerformance / Cost - Digit Range: 14 digitAmpereOne A192-32XEPYC 9965130K260K390K520K650K169277.52589038.951. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

7-Zip Compression

Performance / Cost - Test: Decompression Rating

OpenBenchmarking.orgMIPS Per Dollar, More Is Better7-Zip Compression 22.01Performance / Cost - Test: Decompression RatingAmpereOne A192-32XEPYC 9965306090120150157.9367.631. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

7-Zip Compression

Performance / Cost - Test: Compression Rating

OpenBenchmarking.orgMIPS Per Dollar, More Is Better7-Zip Compression 22.01Performance / Cost - Test: Compression RatingAmpereOne A192-32XEPYC 9965306090120150136.2267.991. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

GROMACS

Performance / Cost - Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day Per Dollar, More Is BetterGROMACS 2024Performance / Cost - Implementation: MPI CPU - Input: water_GMX50_bareEPYC 9965AmpereOne A192-32X0.00040.00080.00120.00160.0020.001562280.001267151. EPYC 9965: $14813 reported cost.2. AmpereOne A192-32X: $5555 reported cost.

NAS Parallel Benchmarks

Performance / Cost - Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s Per Dollar, More Is BetterNAS Parallel Benchmarks 3.4Performance / Cost - Test / Class: SP.CEPYC 9965AmpereOne A192-32X369121510.3126.0511. EPYC 9965: $14813 reported cost.2. AmpereOne A192-32X: $5555 reported cost.

John The Ripper

Performance / Cost - Test: Blowfish

OpenBenchmarking.orgReal C/S Per Dollar, More Is BetterJohn The Ripper 2023.03.14Performance / Cost - Test: BlowfishAmpereOne A192-32XEPYC 996571421283531.7426.061. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

John The Ripper

Performance / Cost - Test: bcrypt

OpenBenchmarking.orgReal C/S Per Dollar, More Is BetterJohn The Ripper 2023.03.14Performance / Cost - Test: bcryptAmpereOne A192-32XEPYC 996571421283531.3326.091. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

ASTC Encoder

Performance / Cost - Preset: Exhaustive

OpenBenchmarking.orgMT/s Per Dollar, More Is BetterASTC Encoder 4.7Performance / Cost - Preset: ExhaustiveAmpereOne A192-32XEPYC 99650.00020.00040.00060.00080.0010.000826820.000778451. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

NAS Parallel Benchmarks

Performance / Cost - Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s Per Dollar, More Is BetterNAS Parallel Benchmarks 3.4Performance / Cost - Test / Class: IS.DEPYC 9965AmpereOne A192-32X0.11410.22820.34230.45640.57050.5070.4351. EPYC 9965: $14813 reported cost.2. AmpereOne A192-32X: $5555 reported cost.

ASTC Encoder

Performance / Cost - Preset: Very Thorough

OpenBenchmarking.orgMT/s Per Dollar, More Is BetterASTC Encoder 4.7Performance / Cost - Preset: Very ThoroughAmpereOne A192-32XEPYC 99650.00030.00060.00090.00120.00150.001327600.001267221. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Pennant

Performance / Cost - Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds x Dollar, Fewer Is BetterPennant 1.0.1Performance / Cost - Test: leblancbigAmpereOne A192-32XEPYC 99658K16K24K32K40K18606.1335247.731. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

OpenFOAM

Performance / Cost - Input: drivaerFastback, Small Mesh Size - Execution Time

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterOpenFOAM 10Performance / Cost - Input: drivaerFastback, Small Mesh Size - Execution TimeAmpereOne A192-32XEPYC 996580K160K240K320K400K179753.53375316.171. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Primesieve

Performance / Cost - Length: 1e13

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterPrimesieve 12.1Performance / Cost - Length: 1e13AmpereOne A192-32XEPYC 996550K100K150K200K250K77825.55236652.491. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

LAMMPS Molecular Dynamics Simulator

Performance / Cost - Model: Rhodopsin Protein

OpenBenchmarking.orgns/day Per Dollar, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Performance / Cost - Model: Rhodopsin ProteinAmpereOne A192-32XEPYC 99650.0020.0040.0060.0080.010.009097210.003714241. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Coremark

Performance / Cost - CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec Per Dollar, More Is BetterCoremark 1.0Performance / Cost - CoreMark Size 666 - Iterations Per SecondAmpereOne A192-32XEPYC 99652004006008001000821.09286.711. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Timed Mesa Compilation

Performance / Cost - Time To Compile

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterTimed Mesa Compilation 24.0Performance / Cost - Time To CompileAmpereOne A192-32XEPYC 996550K100K150K200K250K95501.56229764.441. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

ASTC Encoder

Performance / Cost - Preset: Thorough

OpenBenchmarking.orgMT/s Per Dollar, More Is BetterASTC Encoder 4.7Performance / Cost - Preset: ThoroughAmpereOne A192-32XEPYC 99650.0020.0040.0060.0080.010.009005080.008692111. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Xcompact3d Incompact3d

Performance / Cost - Input: input.i3d 193 Cells Per Direction

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Performance / Cost - Input: input.i3d 193 Cells Per DirectionAmpereOne A192-32XEPYC 996520K40K60K80K100K49749.5596867.791. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

m-queens

Performance / Cost - Time To Solve

OpenBenchmarking.orgSeconds x Dollar, Fewer Is Betterm-queens 1.2Performance / Cost - Time To SolveAmpereOne A192-32XEPYC 996515K30K45K60K75K29758.1469739.601. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

oneDNN

Performance / Cost - Harness: Deconvolution Batch shapes_3d - Engine: CPU

OpenBenchmarking.orgms x Dollar, Fewer Is BetteroneDNN 3.4Performance / Cost - Harness: Deconvolution Batch shapes_3d - Engine: CPUEPYC 9965AmpereOne A192-32X2K4K6K8K10K9749.2411200.491. EPYC 9965: $14813 reported cost.2. AmpereOne A192-32X: $5555 reported cost.

Parallel BZIP2 Compression

Performance / Cost - FreeBSD-13.0-RELEASE-amd64-memstick.img Compression

OpenBenchmarking.orgSeconds x Dollar, Fewer Is BetterParallel BZIP2 Compression 1.1.13Performance / Cost - FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionAmpereOne A192-32XEPYC 99653K6K9K12K15K9135.1113201.911. AmpereOne A192-32X: $5555 reported cost.2. EPYC 9965: $14813 reported cost.

Phoronix Test Suite v10.8.5