Debian 10.10 Benchmarks

2 x AMD EPYC 7763 64-Core testing with a AMD DAYTONA_X (RYM1001D BIOS) and ASPEED on Debian 10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2108166-TJ-DEBIAN10132&sor&grr.

ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionXeon 8380 2PEPYC 7763 2P Debian 10.10 Debian 10.102 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Device 0998504GB7682GB INTEL SSDPF2KX076TZ + 3841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPDebian 104.19.0-17-amd64 (x86_64)GNOME Shell 3.30.2X ServerGCC 8.3.0ext41920x10802 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RYM1001D BIOS)AMD Starship/Matisse7682GB INTEL SSDPF2KX076TZ2 x Mellanox MT27710OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Processor Details- Xeon 8380 2P: Debian 10.10: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270- EPYC 7763 2P: Debian 10.10: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119Java Details- OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1)Python Details- Python 2.7.16 + Python 3.7.3Security Details- Xeon 8380 2P: Debian 10.10: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - EPYC 7763 2P: Debian 10.10: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

incompact3d: input.i3d 193 Cells Per Directionrocksdb: Seq Filllammps: Rhodopsin Proteincassandra: Readsrenaissance: Akka Unbalanced Cobwebbed Treerenaissance: Savina Reactors.IOrenaissance: ALS Movie Lenspgbench: 100 - 250 - Read Only - Average Latencypgbench: 100 - 250 - Read Onlyrenaissance: Genetic Algorithm Using Jenetics + Futuresrenaissance: Apache Spark PageRankrodinia: OpenMP HotSpot3Dyafaray: Total Time For Sample Scenehpcg: pgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writeasmfish: 1024 Hash Memory, 26 Depthnpb: CG.Crocksdb: Read While Writinglammps: 20k Atomsrenaissance: In-Memory Database Shootoutnpb: IS.Dnumpy: incompact3d: X3D-benchmarking input.i3drocksdb: Update Randrocksdb: Rand Fill Syncnpb: EP.Drenaissance: Scala Dottyrodinia: OpenMP Leukocytebuild-llvm: Unix Makefilesrenaissance: Rand Forestvpxenc: Speed 0 - Bosphorus 4Kpyperformance: gogromacs: MPI CPU - water_GMX50_barecassandra: Writesrocksdb: Rand Fillpgbench: 100 - 100 - Read Only - Average Latencypgbench: 100 - 100 - Read Onlypgbench: 100 - 100 - Read Write - Average Latencypgbench: 100 - 100 - Read Writestockfish: Total Timebuild-llvm: Ninjabuild-linux-kernel: Time To Compilestress-ng: Atomicstress-ng: Context Switchingpyperformance: python_startupstress-ng: Forkingrenaissance: Apache Spark ALSstress-ng: Socket Activitystress-ng: System V Message Passingpyperformance: raytraceredis: SETvpxenc: Speed 5 - Bosphorus 4Kpyperformance: 2to3npb: FT.Cbuild-nodejs: Time To Compileredis: GETredis: LPUSHredis: LPOPbuild-gdb: Time To Compilenode-express-loadtest: viennacl: CPU BLAS - dGEMM-TTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sCOPYrocksdb: Read Rand Write Randrocksdb: Rand Readsqlite-speedtest: Timed Time - Size 1,000svt-av1: Preset 4 - Bosphorus 4Krenaissance: Finagle HTTP Requestspyperformance: regex_compilerenaissance: Apache Spark Bayesredis: SADDrodinia: OpenMP LavaMDpyperformance: django_templatepyperformance: pathlibstress-ng: NUMAphpbench: PHP Benchmark Suiterodinia: OpenMP CFD Solverpyperformance: json_loadsnamd: ATPase Simulation - 327,506 Atomsstress-ng: RdRandstress-ng: Memory Copyingstress-ng: CPU Cachestress-ng: CPU Stressstress-ng: Mallocstress-ng: MMAPstress-ng: SENDFILEstress-ng: MEMFDstress-ng: Cryptostress-ng: Glibc Qsort Data Sortingstress-ng: Glibc C String Functionsstress-ng: Matrix Mathpyperformance: chaosstress-ng: Vector Mathstress-ng: Semaphorespyperformance: nbodybuild-apache: Time To Compilepyperformance: floatpyperformance: crypto_pyaespyperformance: pickle_pure_pythonmt-dgemm: Sustained Floating-Point Ratepybench: Total For Average Test Timessvt-av1: Preset 8 - Bosphorus 4Krodinia: OpenMP Streamclusterbuild-ffmpeg: Time To Compilesvt-hevc: 1 - Bosphorus 1080psvt-vp9: Visual Quality Optimized - Bosphorus 1080pincompact3d: input.i3d 129 Cells Per Directionnpb: BT.Csvt-vp9: VMAF Optimized - Bosphorus 1080ptnn: CPU - SqueezeNet v2npb: EP.Csvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080pctx-clock: Context Switch TimeXeon 8380 2PEPYC 7763 2P Debian 10.10 Debian 10.1011.402235610695425.5939156032337.821135.017889.10.3318420816758.75161.7104.973110.68240.29848.8192836417841587740281.43945617735.97818344.43328.81349.31294.80328498999806123586.881300.957.631176.8081464.63.082819.0021622731057090.2005007234.80420823181927486115.95823.466167657.6617508641.0622.749933.183145.349027.356811966.154881621978.775.4050886158.5391.8632078469.421294255.022175922.0583.251648046.463.068.362.2634115653991592.551862749292497331578655458.1412.6666459.5263905.21704483.9644.9738430.09.786965125.54235.20.27214668689.7416234.0710.6528171.811431913434.686575.321175397.414800.5212801.98986.957441922.78317953.14161455954.9412184827.1816832.78615715266348.16164099632.9258.06121.57629.07178.292.95142062196078.72214.2872.8722804.06212.26169.31262.5919710.525304819899028.05136047636698.712875.09304.30.3736735712928.04363.194.001137.3815.7254446929313881646540.981534111237.3538362.25219.74413.562279421867764988.33922.652.273162.052857.65.462609.9592090322043480.09210898582.3554249029317555888.73817.572105358.8676695464.0316.329225.491859.632417.9310330862.265081572054.7011.51342111226.4166.7312086803.031415875.022139255.9559.525700781.889.676.882.478361.86781168897402743463273635460569626460.0473.808184684.91621685.1226.93356.119.18.215833706.83225.20.2271412612.3717.0358839.852869325583.077060.572102730.842214.0027404.941334.6912069712.93450982.95123982834.2524717109.7313021.90710810844845.794024104057.4438.06317.51346.18316.112.69800801259687.67391.6368.777392.19297.04505.94122OpenBenchmarking.org

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionDebian 10.103691215SE +/- 0.03, N = 310.5311.401. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Facebook RocksDB

Test: Sequential Fill

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Sequential FillDebian 10.1040K80K120K160K200KSE +/- 191.32, N = 3SE +/- 38.55, N = 31989901069541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinDebian 10.10714212835SE +/- 0.53, N = 928.0525.591. (CXX) g++ options: -O3 -pthread -lm

Apache Cassandra

Test: Reads

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: ReadsDebian 10.1080K160K240K320K400KSE +/- 32135.40, N = 12SE +/- 2788.94, N = 1236047691560

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Akka Unbalanced Cobwebbed TreeDebian 10.108K16K24K32K40KSE +/- 70.51, N = 3SE +/- 225.38, N = 332337.836698.7

Renaissance

Test: Savina Reactors.IO

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Savina Reactors.IODebian 10.105K10K15K20K25KSE +/- 110.92, N = 12SE +/- 209.23, N = 612875.021135.0

Renaissance

Test: ALS Movie Lens

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: ALS Movie LensDebian 10.104K8K12K16K20KSE +/- 98.38, N = 12SE +/- 122.11, N = 39304.317889.1

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyDebian 10.100.08390.16780.25170.33560.4195SE +/- 0.036, N = 15SE +/- 0.008, N = 130.3310.3731. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Only

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyDebian 10.10200K400K600K800K1000KSE +/- 58323.73, N = 15SE +/- 13117.59, N = 138420816735711. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Renaissance

Test: Genetic Algorithm Using Jenetics + Futures

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Genetic Algorithm Using Jenetics + FuturesDebian 10.1014002800420056007000SE +/- 57.84, N = 12SE +/- 49.06, N = 32928.06758.7

Renaissance

Test: Apache Spark PageRank

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark PageRankDebian 10.1011002200330044005500SE +/- 29.40, N = 3SE +/- 73.30, N = 124363.15161.7

Rodinia

Test: OpenMP HotSpot3D

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DDebian 10.1020406080100SE +/- 1.26, N = 15SE +/- 0.82, N = 1094.00104.971. (CXX) g++ options: -O2 -lOpenCL

YafaRay

Total Time For Sample Scene

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.5.1Total Time For Sample SceneDebian 10.10306090120150SE +/- 11.34, N = 15SE +/- 1.41, N = 3110.68137.381. (CXX) g++ options: -std=c++11 -pthread -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Xeon 8380 2P: Debian 10.10918273645SE +/- 0.15, N = 340.301. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyDebian 10.10246810SE +/- 0.196, N = 15SE +/- 0.013, N = 35.7258.8191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 250 - Mode: Read Write

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteDebian 10.1010K20K30K40K50KSE +/- 1608.03, N = 15SE +/- 40.32, N = 344469283641. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

asmFish

1024 Hash Memory, 26 Depth

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthDebian 10.1060M120M180M240M300MSE +/- 2198775.31, N = 3SE +/- 1630041.23, N = 12293138816178415877

NAS Parallel Benchmarks

Test / Class: CG.C

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CDebian 10.1010K20K30K40K50KSE +/- 37.63, N = 2SE +/- 206.96, N = 346540.9840281.431. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Facebook RocksDB

Test: Read While Writing

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Read While WritingDebian 10.103M6M9M12M15MSE +/- 145400.63, N = 15SE +/- 280022.49, N = 141534111294561771. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

LAMMPS Molecular Dynamics Simulator

Model: 20k Atoms

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsDebian 10.10918273645SE +/- 0.13, N = 3SE +/- 0.01, N = 337.3535.981. (CXX) g++ options: -O3 -pthread -lm

Renaissance

Test: In-Memory Database Shootout

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: In-Memory Database ShootoutDebian 10.104K8K12K16K20KSE +/- 95.08, N = 3SE +/- 113.86, N = 38362.218344.4

NAS Parallel Benchmarks

Test / Class: IS.D

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DDebian 10.1011002200330044005500SE +/- 48.71, N = 2SE +/- 33.43, N = 65219.743328.811. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Numpy Benchmark

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkDebian 10.1090180270360450SE +/- 2.23, N = 3SE +/- 4.21, N = 3413.56349.31

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dXeon 8380 2P: Debian 10.1060120180240300SE +/- 0.73, N = 2294.801. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Facebook RocksDB

Test: Update Random

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Update RandomDebian 10.1050K100K150K200K250KSE +/- 2421.52, N = 15SE +/- 229.83, N = 3227942989991. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Facebook RocksDB

Test: Random Fill Sync

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random Fill SyncDebian 10.1040K80K120K160K200KSE +/- 4837.04, N = 15SE +/- 617.57, N = 3186776806121. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

NAS Parallel Benchmarks

Test / Class: EP.D

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DDebian 10.1011002200330044005500SE +/- 53.96, N = 5SE +/- 3.35, N = 34988.333586.881. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Renaissance

Test: Scala Dotty

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Scala DottyDebian 10.1030060090012001500SE +/- 26.22, N = 12SE +/- 14.18, N = 3922.61300.9

Rodinia

Test: OpenMP Leukocyte

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteDebian 10.101326395265SE +/- 0.71, N = 3SE +/- 1.92, N = 1552.2757.631. (CXX) g++ options: -O2 -lOpenCL

Timed LLVM Compilation

Build System: Unix Makefiles

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix MakefilesDebian 10.104080120160200SE +/- 0.13, N = 3SE +/- 1.22, N = 3162.05176.81

Renaissance

Test: Random Forest

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Random ForestDebian 10.1030060090012001500SE +/- 8.77, N = 15SE +/- 7.60, N = 3857.61464.6

VP9 libvpx Encoding

Speed: Speed 0 - Input: Bosphorus 4K

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 0 - Input: Bosphorus 4KDebian 10.101.22852.4573.68554.9146.1425SE +/- 0.01, N = 3SE +/- 0.03, N = 35.463.081. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

PyPerformance

Benchmark: go

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goDebian 10.1060120180240300SE +/- 0.58, N = 3SE +/- 3.36, N = 14260281

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareDebian 10.103691215SE +/- 0.038, N = 39.9599.0021. (CXX) g++ options: -O3 -pthread

Apache Cassandra

Test: Writes

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesDebian 10.1040K80K120K160K200KSE +/- 775.02, N = 3SE +/- 1239.80, N = 3209032162273

Facebook RocksDB

Test: Random Fill

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random FillDebian 10.1040K80K120K160K200KSE +/- 1692.24, N = 9SE +/- 6.33, N = 32043481057091. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average LatencyDebian 10.100.0450.090.1350.180.225SE +/- 0.001, N = 3SE +/- 0.001, N = 30.0920.2001. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Only

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read OnlyDebian 10.10200K400K600K800K1000KSE +/- 6710.36, N = 3SE +/- 2917.23, N = 310898585007231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average LatencyDebian 10.101.08092.16183.24274.32365.4045SE +/- 0.032, N = 3SE +/- 0.038, N = 32.3554.8041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

PostgreSQL pgbench

Scaling Factor: 100 - Clients: 100 - Mode: Read Write

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read WriteDebian 10.109K18K27K36K45KSE +/- 579.08, N = 3SE +/- 165.20, N = 342490208231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Stockfish

Total Time

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeDebian 10.1060M120M180M240M300MSE +/- 2732137.08, N = 15SE +/- 1879580.86, N = 152931755581819274861. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

Timed LLVM Compilation

Build System: Ninja

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: NinjaDebian 10.10306090120150SE +/- 0.94, N = 3SE +/- 0.46, N = 388.74115.96

Timed Linux Kernel Compilation

Time To Compile

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileDebian 10.10612182430SE +/- 0.21, N = 13SE +/- 0.27, N = 1517.5723.47

Stress-NG

Test: Atomic

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: AtomicDebian 10.1040K80K120K160K200KSE +/- 1931.20, N = 15SE +/- 1233.96, N = 4167657.66105358.861. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Context Switching

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingDebian 10.1016M32M48M64M80MSE +/- 4106805.12, N = 15SE +/- 202037.68, N = 476695464.0317508641.061. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PyPerformance

Benchmark: python_startup

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupDebian 10.10510152025SE +/- 0.03, N = 3SE +/- 0.00, N = 316.322.7

Stress-NG

Test: Forking

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: ForkingDebian 10.1011K22K33K44K55KSE +/- 298.72, N = 3SE +/- 393.50, N = 1549933.1829225.491. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Renaissance

Test: Apache Spark ALS

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark ALSDebian 10.107001400210028003500SE +/- 14.10, N = 3SE +/- 24.14, N = 31859.63145.3

Stress-NG

Test: Socket Activity

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket ActivityDebian 10.1011K22K33K44K55KSE +/- 220.71, N = 3SE +/- 766.70, N = 1549027.3532417.931. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: System V Message Passing

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message PassingDebian 10.102M4M6M8M10MSE +/- 103831.56, N = 15SE +/- 89010.61, N = 310330862.266811966.151. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PyPerformance

Benchmark: raytrace

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceDebian 10.10110220330440550SE +/- 0.88, N = 3488508

Redis

Test: SET

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETDebian 10.10300K600K900K1200K1500KSE +/- 36820.67, N = 15SE +/- 27252.76, N = 151621978.771572054.701. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

VP9 libvpx Encoding

Speed: Speed 5 - Input: Bosphorus 4K

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KDebian 10.103691215SE +/- 0.11, N = 3SE +/- 0.04, N = 311.515.401. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

PyPerformance

Benchmark: 2to3

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Debian 10.10110220330440550342508

NAS Parallel Benchmarks

Test / Class: FT.C

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CDebian 10.1020K40K60K80K100KSE +/- 1030.14, N = 10SE +/- 1673.59, N = 15111226.4186158.531. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Timed Node.js Compilation

Time To Compile

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileDebian 10.1020406080100SE +/- 0.19, N = 3SE +/- 0.97, N = 366.7391.86

Redis

Test: GET

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETDebian 10.10400K800K1200K1600K2000KSE +/- 71868.53, N = 15SE +/- 31165.67, N = 152086803.032078469.421. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPUSH

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSHDebian 10.10300K600K900K1200K1500KSE +/- 34916.81, N = 12SE +/- 24657.83, N = 131415875.021294255.021. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPOP

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPOPDebian 10.10500K1000K1500K2000K2500KSE +/- 35378.74, N = 15SE +/- 57897.76, N = 152175922.052139255.951. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Timed GDB GNU Debugger Compilation

Time To Compile

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 10.2Time To CompileDebian 10.1020406080100SE +/- 0.11, N = 3SE +/- 0.16, N = 359.5383.25

Node.js Express HTTP Load Test

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load TestDebian 10.1015003000450060007500SE +/- 82.82, N = 15SE +/- 383.48, N = 12700764801. Nodejs v10.24.0

ViennaCL

Test: CPU BLAS - dGEMM-TT

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTDebian 10.1020406080100SE +/- 0.43, N = 12SE +/- 3.59, N = 581.846.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMM-TN

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNDebian 10.1020406080100SE +/- 0.59, N = 12SE +/- 4.21, N = 589.663.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMM-NT

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTDebian 10.1020406080100SE +/- 0.42, N = 12SE +/- 3.83, N = 576.868.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMM-NN

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNDebian 10.1020406080100SE +/- 0.48, N = 12SE +/- 2.62, N = 582.462.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMV-T

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TDebian 10.102004006008001000SE +/- 5.85, N = 12SE +/- 1.96, N = 57836341. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dGEMV-N

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NDebian 10.10306090120150SE +/- 0.51, N = 5SE +/- 6.09, N = 12115.061.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dDOT

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTDebian 10.10150300450600750SE +/- 5.95, N = 12SE +/- 2.06, N = 56786531. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dAXPY

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYDebian 10.1030060090012001500SE +/- 11.60, N = 12SE +/- 26.19, N = 511689911. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - dCOPY

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYDebian 10.102004006008001000SE +/- 18.48, N = 12SE +/- 147.13, N = 5897.0592.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - sDOT

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTDebian 10.10110220330440550SE +/- 5.14, N = 5SE +/- 1.84, N = 125184021. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - sAXPY

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYDebian 10.10160320480640800SE +/- 13.64, N = 12SE +/- 2.16, N = 57436271. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - sCOPY

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYDebian 10.10110220330440550SE +/- 5.07, N = 54924631. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Facebook RocksDB

Test: Read Random Write Random

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Read Random Write RandomDebian 10.10600K1200K1800K2400K3000KSE +/- 5393.40, N = 3SE +/- 7187.45, N = 327363549249731. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Facebook RocksDB

Test: Random Read

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random ReadDebian 10.10130M260M390M520M650MSE +/- 1133761.15, N = 3SE +/- 939653.16, N = 36056962643157865541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

SQLite Speedtest

Timed Time - Size 1,000

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Debian 10.101326395265SE +/- 0.13, N = 3SE +/- 0.09, N = 358.1460.051. (CC) gcc options: -O2 -ldl -lz -lpthread

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KDebian 10.100.85681.71362.57043.42724.284SE +/- 0.017, N = 3SE +/- 0.031, N = 33.8082.6661. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Renaissance

Test: Finagle HTTP Requests

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Finagle HTTP RequestsXeon 8380 2P: Debian 10.10140028004200560070006459.5MIN: 5755.44 / MAX: 6516.18

PyPerformance

Benchmark: regex_compile

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileDebian 10.1060120180240300184263

Renaissance

Test: Apache Spark Bayes

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark BayesDebian 10.102004006008001000SE +/- 5.79, N = 3SE +/- 0.82, N = 3684.9905.2

Redis

Test: SADD

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADDDebian 10.10400K800K1200K1600K2000KSE +/- 21924.92, N = 3SE +/- 30995.30, N = 121704483.961621685.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Rodinia

Test: OpenMP LavaMD

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDDebian 10.101020304050SE +/- 0.19, N = 3SE +/- 0.19, N = 326.9344.971. (CXX) g++ options: -O2 -lOpenCL

PyPerformance

Benchmark: django_template

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateDebian 10.1020406080100SE +/- 0.06, N = 356.184.0

PyPerformance

Benchmark: pathlib

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibDebian 10.10714212835SE +/- 0.00, N = 3SE +/- 0.03, N = 319.130.0

Stress-NG

Test: NUMA

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMADebian 10.103691215SE +/- 0.10, N = 3SE +/- 0.04, N = 39.788.211. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PHPBench

PHP Benchmark Suite

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteDebian 10.10150K300K450K600K750KSE +/- 5555.16, N = 3SE +/- 4097.68, N = 3696512583370

Rodinia

Test: OpenMP CFD Solver

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverDebian 10.10246810SE +/- 0.084, N = 15SE +/- 0.103, N = 155.5426.8321. (CXX) g++ options: -O2 -lOpenCL

PyPerformance

Benchmark: json_loads

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsDebian 10.10816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 325.235.2

NAMD

ATPase Simulation - 327,506 Atoms

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsDebian 10.100.06120.12240.18360.24480.306SE +/- 0.00014, N = 3SE +/- 0.00040, N = 30.227140.27214

Stress-NG

Test: RdRand

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: RdRandXeon 8380 2P: Debian 10.10140K280K420K560K700KSE +/- 2334.79, N = 3668689.741. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Memory Copying

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory CopyingDebian 10.103K6K9K12K15KSE +/- 72.26, N = 3SE +/- 50.00, N = 316234.0712612.371. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: CPU Cache

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU CacheDebian 10.1048121620SE +/- 0.00, N = 3SE +/- 0.00, N = 317.0310.651. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: CPU Stress

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressDebian 10.1013K26K39K52K65KSE +/- 661.03, N = 3SE +/- 83.72, N = 358839.8528171.811. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Malloc

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MallocDebian 10.10600M1200M1800M2400M3000MSE +/- 7005388.59, N = 3SE +/- 1935415.45, N = 32869325583.071431913434.681. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: MMAP

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPDebian 10.1015003000450060007500SE +/- 1.61, N = 3SE +/- 50.33, N = 37060.576575.321. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: SENDFILE

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILEDebian 10.10500K1000K1500K2000K2500KSE +/- 23739.75, N = 3SE +/- 2004.92, N = 32102730.841175397.411. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: MEMFD

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFDDebian 10.1010002000300040005000SE +/- 38.39, N = 3SE +/- 4.16, N = 34800.522214.001. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Crypto

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoDebian 10.106K12K18K24K30KSE +/- 156.93, N = 3SE +/- 41.95, N = 327404.9412801.981. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Glibc Qsort Data Sorting

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data SortingDebian 10.1030060090012001500SE +/- 9.70, N = 3SE +/- 3.46, N = 31334.69986.951. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Glibc C String Functions

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsDebian 10.103M6M9M12M15MSE +/- 10977.89, N = 3SE +/- 71343.56, N = 312069712.937441922.781. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Matrix Math

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix MathDebian 10.10100K200K300K400K500KSE +/- 2149.64, N = 3SE +/- 2777.22, N = 3450982.95317953.141. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PyPerformance

Benchmark: chaos

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosDebian 10.104080120160200123161

Stress-NG

Test: Vector Math

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector MathDebian 10.10200K400K600K800K1000KSE +/- 1321.76, N = 3SE +/- 787.69, N = 3982834.25455954.941. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Semaphores

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SemaphoresDebian 10.105M10M15M20M25MSE +/- 15285.56, N = 3SE +/- 15414.63, N = 324717109.7312184827.181. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

PyPerformance

Benchmark: nbody

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyDebian 10.104080120160200130168

Timed Apache Compilation

Time To Compile

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileDebian 10.10816243240SE +/- 0.02, N = 3SE +/- 0.03, N = 321.9132.79

PyPerformance

Benchmark: float

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatDebian 10.10306090120150SE +/- 0.33, N = 3108157

PyPerformance

Benchmark: crypto_pyaes

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesDebian 10.10306090120150108152

PyPerformance

Benchmark: pickle_pure_python

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonDebian 10.10140280420560700SE +/- 0.58, N = 3SE +/- 1.45, N = 3448663

ACES DGEMM

Sustained Floating-Point Rate

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateDebian 10.101122334455SE +/- 0.87, N = 15SE +/- 0.59, N = 1548.1645.791. (CC) gcc options: -O3 -march=native -fopenmp

PyBench

Total For Average Test Times

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesDebian 10.102004006008001000SE +/- 3.38, N = 3SE +/- 14.52, N = 39961040

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KDebian 10.101326395265SE +/- 0.32, N = 3SE +/- 0.13, N = 357.4432.931. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Rodinia

Test: OpenMP Streamcluster

Xeon 8380 2PEPYC 7763 2POpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterDebian 10.10246810SE +/- 0.054, N = 3SE +/- 0.140, N = 128.0618.0631. (CXX) g++ options: -O2 -lOpenCL

Timed FFmpeg Compilation

Time To Compile

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To CompileDebian 10.10510152025SE +/- 0.06, N = 3SE +/- 0.08, N = 317.5121.58

SVT-HEVC

Tuning: 1 - Input: Bosphorus 1080p

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pDebian 10.101020304050SE +/- 0.21, N = 3SE +/- 0.11, N = 346.1829.071. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pDebian 10.1070140210280350SE +/- 3.96, N = 3SE +/- 1.38, N = 15316.11178.291. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionDebian 10.100.66411.32821.99232.65643.3205SE +/- 0.04040236, N = 9SE +/- 0.00306886, N = 32.698008012.951420621. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

Test / Class: BT.C

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CDebian 10.1060K120K180K240K300KSE +/- 197.74, N = 2SE +/- 395.43, N = 3259687.67196078.721. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pDebian 10.1080160240320400SE +/- 2.40, N = 3SE +/- 1.99, N = 7391.63214.281. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

TNN

Target: CPU - Model: SqueezeNet v2

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Debian 10.101632486480SE +/- 0.73, N = 5SE +/- 0.06, N = 368.7872.871. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CXeon 8380 2P: Debian 10.106001200180024003000SE +/- 8.94, N = 32804.061. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pDebian 10.1090180270360450SE +/- 2.19, N = 3SE +/- 1.53, N = 3392.19212.261. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

Tuning: 7 - Input: Bosphorus 1080p

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pDebian 10.1060120180240300SE +/- 0.94, N = 3SE +/- 2.16, N = 3297.04169.311. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-HEVC

Tuning: 10 - Input: Bosphorus 1080p

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pDebian 10.10110220330440550SE +/- 3.22, N = 3SE +/- 2.91, N = 4505.94262.591. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

ctx_clock

Context Switch Time

EPYC 7763 2PXeon 8380 2POpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeDebian 10.104080120160200SE +/- 0.67, N = 3122197

Phoronix Test Suite v10.8.4