Debian 11 Benchmarks

Debian 11 server benchmarks by Michael Larabel for a future article with Intel and AMD hardware.

HTML result view exported from: https://openbenchmarking.org/result/2108187-TJ-DEBIAN88508&sgm=1&imw=1&sro&grr.

ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionVulkanXeon 8380 2PEPYC 7763 2P Debian 10.10 Debian 11.0 Debian 10.10 Debian 11.02 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Device 0998504GB7682GB INTEL SSDPF2KX076TZASPEEDVE2282 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 8.3.0ext41920x1080Debian 115.10.0-8-amd64 (x86_64)GNOME Shell 3.38.4X Server 1.20.111.0.2GCC 10.2.1 202101101024x7682 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RYM1001D BIOS)AMD Starship/MatisseVE2282 x Mellanox MT27710Debian 104.19.0-17-amd64 (x86_64)GNOME Shell 3.30.2X ServerGCC 8.3.01920x1080Debian 115.10.0-8-amd64 (x86_64)GNOME Shell 3.38.4GCC 10.2.1 20210110OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- Xeon 8380 2P: Debian 10.10: --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 - Xeon 8380 2P: Debian 11.0: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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-build-config=bootstrap-lto-lean --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 - EPYC 7763 2P: Debian 10.10: --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 - EPYC 7763 2P: Debian 11.0: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --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-build-config=bootstrap-lto-lean --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- Xeon 8380 2P: Debian 10.10: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270- Xeon 8380 2P: Debian 11.0: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270- EPYC 7763 2P: Debian 10.10: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119- EPYC 7763 2P: Debian 11.0: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Java Details- Xeon 8380 2P: Debian 10.10: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1)- Xeon 8380 2P: Debian 11.0: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)- EPYC 7763 2P: Debian 10.10: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1)- EPYC 7763 2P: Debian 11.0: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)Python Details- Xeon 8380 2P: Debian 10.10: Python 2.7.16 + Python 3.7.3- Xeon 8380 2P: Debian 11.0: Python 3.9.2- EPYC 7763 2P: Debian 10.10: Python 2.7.16 + Python 3.7.3- EPYC 7763 2P: Debian 11.0: Python 3.9.2Security 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 - Xeon 8380 2P: Debian 11.0: 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 - EPYC 7763 2P: Debian 11.0: 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

rocksdb: Seq Fillrenaissance: Akka Unbalanced Cobwebbed Treerenaissance: Genetic Algorithm Using Jenetics + Futureslammps: Rhodopsin Proteinrenaissance: Savina Reactors.IOrodinia: OpenMP HotSpot3Dpgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writerenaissance: Apache Spark PageRankyafaray: Total Time For Sample Scenerenaissance: In-Memory Database Shootoutcassandra: Writesrocksdb: Read While Writingasmfish: 1024 Hash Memory, 26 Depthnumpy: pgbench: 100 - 100 - Read Write - Average Latencypgbench: 100 - 100 - Read Writerenaissance: Scala Dottybuild-llvm: Unix Makefilesnpb: CG.Cpyperformance: gopgbench: 100 - 100 - Read Only - Average Latencypgbench: 100 - 100 - Read Onlyrocksdb: Update Randrocksdb: Rand Readnpb: EP.Dbuild-llvm: Ninjabuild-linux-kernel: Time To Compilerocksdb: Rand Fillstress-ng: System V Message Passinggromacs: MPI CPU - water_GMX50_barepyperformance: raytracestockfish: Total Timepyperformance: 2to3build-nodejs: Time To Compileviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - sAXPYpyperformance: django_templateredis: SETredis: LPUSHrocksdb: Read Rand Write Randpyperformance: chaosredis: LPOPpyperformance: nbodysvt-av1: Preset 4 - Bosphorus 4Kpyperformance: crypto_pyaespyperformance: pathlibredis: SADDpyperformance: pickle_pure_pythonnpb: FT.Cpyperformance: regex_compilerodinia: OpenMP LavaMDpyperformance: json_loadsnamd: ATPase Simulation - 327,506 Atomsphpbench: PHP Benchmark Suitestress-ng: Mallocstress-ng: Cryptostress-ng: Glibc C String Functionsrodinia: OpenMP Streamclusterbuild-apache: Time To Compilepybench: Total For Average Test Timessvt-av1: Preset 8 - Bosphorus 4Ksvt-hevc: 1 - Bosphorus 1080pbuild-ffmpeg: Time To Compilenpb: BT.Csvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080ptnn: CPU - SqueezeNet v2svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080pctx-clock: Context Switch TimeXeon 8380 2PEPYC 7763 2P Debian 10.10 Debian 11.0 Debian 10.10 Debian 11.010695432337.86758.725.59321135.0104.9738.819283645161.7110.68218344.41622739456177178415877349.314.804208231300.9176.80840281.432810.200500723989993157865543586.88115.95823.4661057096811966.159.00248818192748650891.863634518627841621978.771294255.029249731612175922.051682.66615230.01704483.9666386158.5326344.97335.20.272146965121431913434.6812801.987441922.788.06132.78699632.92529.0721.576196078.72178.29262.59214.2872.872212.26169.311979877032700.57003.224.35121000.4104.0028.823283565929.377.59418748.41655779863087175018835383.233.186314081245.1199.60039507.123010.0901106588898543673602768858.02127.81124.561938628987819.529.06946218253650950598.839642526224358.41751650.191492781.428426541362482298.751432.56012525.32033925.8260788493.5119937.77729.90.272477224041439057052.0813490.327917452.977.93534.20998032.55427.9616.207189492.52183.67267.46216.7672.841207.43171.3821019899036698.72928.028.05112875.094.0015.725444694363.1137.3818362.220903215341112293138816413.562.35542490922.6162.05246540.982600.09210898582279426056962644988.3388.73817.57220434810330862.269.95950829317555834266.73178340274356.11572054.701415875.0227363541232139255.951303.80810819.11621685.12448111226.4118426.93325.20.227145833702869325583.0727404.9412069712.938.06321.907104057.44346.1817.513259687.67316.11505.94391.6368.777392.19297.0412219036236821.13351.332.77313591.692.5904.141606084550.554.2509020.619372916290934297587716426.631.76557604899.7179.78149354.992580.09011093901880286475403449945.1896.64219.33418162915918301.2210.14747529702125835371.573930470106148.41743277.501532789.8222961521082204683.331254.08910617.72004012.64440123519.4516822.02524.90.226886076062837926434.8728094.7214357589.217.72922.31998265.21446.5714.229257121.36337.18572.17438.7768.257438.74325.76147OpenBenchmarking.org

Facebook RocksDB

Test: Sequential Fill

Debian 10.10Debian 11.0OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Sequential FillEPYC 7763 2PXeon 8380 2P40K80K120K160K200KSE +/- 191.32, N = 3SE +/- 38.55, N = 3SE +/- 141.18, N = 3SE +/- 203.10, N = 3198990106954190362987701. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Akka Unbalanced Cobwebbed TreeEPYC 7763 2PXeon 8380 2P8K16K24K32K40KSE +/- 225.38, N = 3SE +/- 70.51, N = 3SE +/- 328.50, N = 3SE +/- 388.94, N = 436698.732337.836821.132700.5

Renaissance

Test: Genetic Algorithm Using Jenetics + Futures

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Genetic Algorithm Using Jenetics + FuturesEPYC 7763 2PXeon 8380 2P15003000450060007500SE +/- 57.84, N = 12SE +/- 49.06, N = 3SE +/- 54.92, N = 12SE +/- 33.01, N = 32928.06758.73351.37003.2

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

Debian 10.10Debian 11.0OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinEPYC 7763 2PXeon 8380 2P816243240SE +/- 0.53, N = 9SE +/- 0.40, N = 3SE +/- 0.46, N = 1528.0525.5932.7724.351. (CXX) g++ options: -O3 -pthread -lm

Renaissance

Test: Savina Reactors.IO

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Savina Reactors.IOEPYC 7763 2PXeon 8380 2P5K10K15K20K25KSE +/- 110.92, N = 12SE +/- 209.23, N = 6SE +/- 65.28, N = 3SE +/- 135.17, N = 312875.021135.013591.621000.4

Rodinia

Test: OpenMP HotSpot3D

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DEPYC 7763 2PXeon 8380 2P20406080100SE +/- 1.26, N = 15SE +/- 0.82, N = 10SE +/- 1.30, N = 13SE +/- 0.21, N = 394.00104.9792.59104.001. (CXX) g++ options: -O2 -lOpenCL

PostgreSQL pgbench

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

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyEPYC 7763 2PXeon 8380 2P246810SE +/- 0.196, N = 15SE +/- 0.013, N = 3SE +/- 0.063, N = 15SE +/- 0.019, N = 35.7258.8194.1418.8231. (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

Debian 10.10Debian 11.0OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteEPYC 7763 2PXeon 8380 2P13K26K39K52K65KSE +/- 1608.03, N = 15SE +/- 40.32, N = 3SE +/- 898.39, N = 15SE +/- 62.46, N = 3444692836460608283561. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Renaissance

Test: Apache Spark PageRank

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Apache Spark PageRankEPYC 7763 2PXeon 8380 2P13002600390052006500SE +/- 29.40, N = 3SE +/- 73.30, N = 12SE +/- 51.18, N = 3SE +/- 62.80, N = 34363.15161.74550.55929.3

YafaRay

Total Time For Sample Scene

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.5.1Total Time For Sample SceneEPYC 7763 2PXeon 8380 2P306090120150SE +/- 1.41, N = 3SE +/- 11.34, N = 15SE +/- 0.34, N = 3SE +/- 1.78, N = 15137.38110.6854.2577.591. (CXX) g++ options: -std=c++11 -pthread -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype

Renaissance

Test: In-Memory Database Shootout

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: In-Memory Database ShootoutEPYC 7763 2PXeon 8380 2P4K8K12K16K20KSE +/- 95.08, N = 3SE +/- 113.86, N = 3SE +/- 75.93, N = 3SE +/- 180.05, N = 38362.218344.49020.618748.4

Apache Cassandra

Test: Writes

Debian 10.10Debian 11.0OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesEPYC 7763 2PXeon 8380 2P40K80K120K160K200KSE +/- 775.02, N = 3SE +/- 1239.80, N = 3SE +/- 1683.25, N = 3SE +/- 1583.88, N = 12209032162273193729165577

Facebook RocksDB

Test: Read While Writing

Debian 10.10Debian 11.0OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Read While WritingEPYC 7763 2PXeon 8380 2P3M6M9M12M15MSE +/- 145400.63, N = 15SE +/- 280022.49, N = 14SE +/- 342025.49, N = 12SE +/- 120135.63, N = 41534111294561771629093498630871. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

asmFish

1024 Hash Memory, 26 Depth

Debian 10.10Debian 11.0OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthEPYC 7763 2PXeon 8380 2P60M120M180M240M300MSE +/- 2198775.31, N = 3SE +/- 1630041.23, N = 12SE +/- 2315275.72, N = 3SE +/- 829521.76, N = 3293138816178415877297587716175018835

Numpy Benchmark

Debian 10.10Debian 11.0OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkEPYC 7763 2PXeon 8380 2P90180270360450SE +/- 2.23, N = 3SE +/- 4.21, N = 3SE +/- 2.50, N = 3SE +/- 1.83, N = 3413.56349.31426.63383.23

PostgreSQL pgbench

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

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average LatencyEPYC 7763 2PXeon 8380 2P1.08092.16183.24274.32365.4045SE +/- 0.032, N = 3SE +/- 0.038, N = 3SE +/- 0.062, N = 15SE +/- 0.034, N = 32.3554.8041.7653.1861. (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

Debian 10.10Debian 11.0OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read WriteEPYC 7763 2PXeon 8380 2P12K24K36K48K60KSE +/- 579.08, N = 3SE +/- 165.20, N = 3SE +/- 1886.93, N = 15SE +/- 337.26, N = 3424902082357604314081. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Renaissance

Test: Scala Dotty

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.12Test: Scala DottyEPYC 7763 2PXeon 8380 2P30060090012001500SE +/- 26.22, N = 12SE +/- 14.18, N = 3SE +/- 8.31, N = 3SE +/- 39.86, N = 12922.61300.9899.71245.1

Timed LLVM Compilation

Build System: Unix Makefiles

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix MakefilesEPYC 7763 2PXeon 8380 2P4080120160200SE +/- 0.13, N = 3SE +/- 1.22, N = 3SE +/- 0.49, N = 3SE +/- 0.49, N = 3162.05176.81179.78199.60

NAS Parallel Benchmarks

Test / Class: CG.C

Debian 10.10Debian 11.0OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 7763 2PXeon 8380 2P11K22K33K44K55KSE +/- 37.63, N = 2SE +/- 206.96, N = 3SE +/- 696.79, N = 15SE +/- 240.20, N = 346540.9840281.4349354.9939507.121. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

PyPerformance

Benchmark: go

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goEPYC 7763 2PXeon 8380 2P70140210280350SE +/- 0.58, N = 3SE +/- 3.36, N = 14SE +/- 6.06, N = 15260281258301

PostgreSQL pgbench

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

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average LatencyEPYC 7763 2PXeon 8380 2P0.0450.090.1350.180.225SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 5SE +/- 0.000, N = 30.0920.2000.0900.0901. (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

Debian 10.10Debian 11.0OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 100 - Clients: 100 - Mode: Read OnlyEPYC 7763 2PXeon 8380 2P200K400K600K800K1000KSE +/- 6710.36, N = 3SE +/- 2917.23, N = 3SE +/- 12260.17, N = 5SE +/- 4824.14, N = 31089858500723110939011065881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

Facebook RocksDB

Test: Update Random

Debian 10.10Debian 11.0OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Update RandomEPYC 7763 2PXeon 8380 2P50K100K150K200K250KSE +/- 2421.52, N = 15SE +/- 229.83, N = 3SE +/- 2364.67, N = 3SE +/- 231.53, N = 322794298999188028898541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Facebook RocksDB

Test: Random Read

Debian 10.10Debian 11.0OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random ReadEPYC 7763 2PXeon 8380 2P140M280M420M560M700MSE +/- 1133761.15, N = 3SE +/- 939653.16, N = 3SE +/- 3465595.70, N = 3SE +/- 3332857.15, N = 156056962643157865546475403443673602761. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

NAS Parallel Benchmarks

Test / Class: EP.D

Debian 10.10Debian 11.0OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7763 2PXeon 8380 2P2K4K6K8K10KSE +/- 53.96, N = 5SE +/- 3.35, N = 3SE +/- 211.44, N = 15SE +/- 102.35, N = 44988.333586.889945.188858.021. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

Timed LLVM Compilation

Build System: Ninja

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: NinjaEPYC 7763 2PXeon 8380 2P306090120150SE +/- 0.94, N = 3SE +/- 0.46, N = 3SE +/- 0.26, N = 3SE +/- 0.33, N = 388.74115.9696.64127.81

Timed Linux Kernel Compilation

Time To Compile

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileEPYC 7763 2PXeon 8380 2P612182430SE +/- 0.21, N = 13SE +/- 0.27, N = 15SE +/- 0.18, N = 15SE +/- 0.32, N = 1417.5723.4719.3324.56

Facebook RocksDB

Test: Random Fill

Debian 10.10Debian 11.0OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Random FillEPYC 7763 2PXeon 8380 2P40K80K120K160K200KSE +/- 1692.24, N = 9SE +/- 6.33, N = 3SE +/- 169.49, N = 3SE +/- 336.83, N = 3204348105709181629938621. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Stress-NG

Test: System V Message Passing

Debian 10.10Debian 11.0OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message PassingEPYC 7763 2PXeon 8380 2P3M6M9M12M15MSE +/- 103831.56, N = 15SE +/- 89010.61, N = 3SE +/- 124919.37, N = 15SE +/- 82511.89, N = 310330862.266811966.1515918301.228987819.521. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

Debian 10.10Debian 11.0OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareEPYC 7763 2PXeon 8380 2P3691215SE +/- 0.038, N = 3SE +/- 0.034, N = 3SE +/- 0.030, N = 39.9599.00210.1479.0691. (CXX) g++ options: -O3 -pthread

PyPerformance

Benchmark: raytrace

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceEPYC 7763 2PXeon 8380 2P110220330440550SE +/- 0.88, N = 3SE +/- 2.65, N = 3508488475462

Stockfish

Total Time

Debian 10.10Debian 11.0OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total TimeEPYC 7763 2PXeon 8380 2P60M120M180M240M300MSE +/- 2732137.08, N = 15SE +/- 1879580.86, N = 15SE +/- 1249676.02, N = 3SE +/- 1241246.00, N = 132931755581819274862970212581825365091. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -flto -flto=jobserver

PyPerformance

Benchmark: 2to3

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3EPYC 7763 2PXeon 8380 2P110220330440550SE +/- 0.33, N = 3SE +/- 0.67, N = 3342508353505

Timed Node.js Compilation

Time To Compile

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileEPYC 7763 2PXeon 8380 2P20406080100SE +/- 0.19, N = 3SE +/- 0.97, N = 3SE +/- 0.60, N = 3SE +/- 0.26, N = 366.7391.8671.5798.84

ViennaCL

Test: CPU BLAS - dGEMV-T

Debian 10.10Debian 11.0OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TEPYC 7763 2PXeon 8380 2P2004006008001000SE +/- 5.85, N = 12SE +/- 1.96, N = 5SE +/- 7.43, N = 15SE +/- 2.51, N = 127836349306421. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - sDOT

Debian 10.10Debian 11.0OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTEPYC 7763 2PXeon 8380 2P110220330440550SE +/- 1.84, N = 12SE +/- 5.14, N = 5SE +/- 5.74, N = 15SE +/- 2.72, N = 124025184705261. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

ViennaCL

Test: CPU BLAS - sAXPY

Debian 10.10Debian 11.0OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYEPYC 7763 2PXeon 8380 2P5001000150020002500SE +/- 13.64, N = 12SE +/- 2.16, N = 5SE +/- 13.01, N = 15SE +/- 27.77, N = 12743627106122431. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

PyPerformance

Benchmark: django_template

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateEPYC 7763 2PXeon 8380 2P20406080100SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.59, N = 1556.184.048.458.4

Redis

Test: SET

Debian 10.10Debian 11.0OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETEPYC 7763 2PXeon 8380 2P400K800K1200K1600K2000KSE +/- 27252.76, N = 15SE +/- 36820.67, N = 15SE +/- 51019.41, N = 15SE +/- 21341.26, N = 41572054.701621978.771743277.501751650.191. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPUSH

Debian 10.10Debian 11.0OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSHEPYC 7763 2PXeon 8380 2P300K600K900K1200K1500KSE +/- 34916.81, N = 12SE +/- 24657.83, N = 13SE +/- 37826.18, N = 15SE +/- 10237.69, N = 31415875.021294255.021532789.821492781.421. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Facebook RocksDB

Test: Read Random Write Random

Debian 10.10Debian 11.0OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.22.1Test: Read Random Write RandomEPYC 7763 2PXeon 8380 2P600K1200K1800K2400K3000KSE +/- 5393.40, N = 3SE +/- 7187.45, N = 3SE +/- 3677.40, N = 3SE +/- 1551.48, N = 3273635492497322961528426541. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

PyPerformance

Benchmark: chaos

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosEPYC 7763 2PXeon 8380 2P4080120160200SE +/- 1.89, N = 15123161108136

Redis

Test: LPOP

Debian 10.10Debian 11.0OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPOPEPYC 7763 2PXeon 8380 2P500K1000K1500K2000K2500KSE +/- 57897.76, N = 15SE +/- 35378.74, N = 15SE +/- 31946.73, N = 15SE +/- 18880.19, N = 32139255.952175922.052204683.332482298.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

PyPerformance

Benchmark: nbody

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyEPYC 7763 2PXeon 8380 2P4080120160200SE +/- 2.57, N = 15130168125143

SVT-AV1

Encoder Mode: Preset 4 - Input: Bosphorus 4K

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 7763 2PXeon 8380 2P0.921.842.763.684.6SE +/- 0.017, N = 3SE +/- 0.031, N = 3SE +/- 0.009, N = 3SE +/- 0.016, N = 33.8082.6664.0892.5601. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

PyPerformance

Benchmark: crypto_pyaes

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesEPYC 7763 2PXeon 8380 2P306090120150SE +/- 2.05, N = 15108152106125

PyPerformance

Benchmark: pathlib

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibEPYC 7763 2PXeon 8380 2P714212835SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.46, N = 1219.130.017.725.3

Redis

Test: SADD

Debian 10.10Debian 11.0OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SADDEPYC 7763 2PXeon 8380 2P400K800K1200K1600K2000KSE +/- 30995.30, N = 12SE +/- 21924.92, N = 3SE +/- 75850.49, N = 12SE +/- 37455.60, N = 121621685.121704483.962004012.642033925.821. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

PyPerformance

Benchmark: pickle_pure_python

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonEPYC 7763 2PXeon 8380 2P140280420560700SE +/- 0.58, N = 3SE +/- 1.45, N = 3SE +/- 8.91, N = 15448663440607

NAS Parallel Benchmarks

Test / Class: FT.C

Debian 10.10Debian 11.0OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CEPYC 7763 2PXeon 8380 2P30K60K90K120K150KSE +/- 1030.14, N = 10SE +/- 1673.59, N = 15SE +/- 634.26, N = 3SE +/- 1611.88, N = 15111226.4186158.53123519.4588493.511. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

PyPerformance

Benchmark: regex_compile

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileEPYC 7763 2PXeon 8380 2P60120180240300SE +/- 2.00, N = 3184263168199

Rodinia

Test: OpenMP LavaMD

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDEPYC 7763 2PXeon 8380 2P1020304050SE +/- 0.19, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 326.9344.9722.0337.781. (CXX) g++ options: -O2 -lOpenCL

PyPerformance

Benchmark: json_loads

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsEPYC 7763 2PXeon 8380 2P816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.37, N = 425.235.224.929.9

NAMD

ATPase Simulation - 327,506 Atoms

Debian 10.10Debian 11.0OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEPYC 7763 2PXeon 8380 2P0.06130.12260.18390.24520.3065SE +/- 0.00014, N = 3SE +/- 0.00040, N = 3SE +/- 0.00152, N = 3SE +/- 0.00028, N = 30.227140.272140.226880.27247

PHPBench

PHP Benchmark Suite

Debian 10.10Debian 11.0OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteEPYC 7763 2PXeon 8380 2P150K300K450K600K750KSE +/- 4097.68, N = 3SE +/- 5555.16, N = 3SE +/- 2571.82, N = 3SE +/- 4567.18, N = 3583370696512607606722404

Stress-NG

Test: Malloc

Debian 10.10Debian 11.0OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MallocEPYC 7763 2PXeon 8380 2P600M1200M1800M2400M3000MSE +/- 7005388.59, N = 3SE +/- 1935415.45, N = 3SE +/- 2079960.32, N = 3SE +/- 1322257.28, N = 32869325583.071431913434.682837926434.871439057052.081. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Crypto

Debian 10.10Debian 11.0OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoEPYC 7763 2PXeon 8380 2P6K12K18K24K30KSE +/- 156.93, N = 3SE +/- 41.95, N = 3SE +/- 33.31, N = 3SE +/- 56.52, N = 327404.9412801.9828094.7213490.321. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Glibc C String Functions

Debian 10.10Debian 11.0OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsEPYC 7763 2PXeon 8380 2P3M6M9M12M15MSE +/- 10977.89, N = 3SE +/- 71343.56, N = 3SE +/- 29361.60, N = 3SE +/- 83997.23, N = 312069712.937441922.7814357589.217917452.971. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Rodinia

Test: OpenMP Streamcluster

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterEPYC 7763 2PXeon 8380 2P246810SE +/- 0.140, N = 12SE +/- 0.054, N = 3SE +/- 0.070, N = 15SE +/- 0.101, N = 158.0638.0617.7297.9351. (CXX) g++ options: -O2 -lOpenCL

Timed Apache Compilation

Time To Compile

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileEPYC 7763 2PXeon 8380 2P816243240SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 321.9132.7922.3234.21

PyBench

Total For Average Test Times

Debian 10.10Debian 11.0OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesEPYC 7763 2PXeon 8380 2P2004006008001000SE +/- 14.52, N = 3SE +/- 3.38, N = 3SE +/- 1.53, N = 3SE +/- 1.76, N = 31040996982980

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 7763 2PXeon 8380 2P1530456075SE +/- 0.32, N = 3SE +/- 0.13, N = 3SE +/- 0.29, N = 3SE +/- 0.22, N = 357.4432.9365.2132.551. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

SVT-HEVC

Tuning: 1 - Input: Bosphorus 1080p

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pEPYC 7763 2PXeon 8380 2P1122334455SE +/- 0.21, N = 3SE +/- 0.11, N = 3SE +/- 0.28, N = 3SE +/- 0.29, N = 346.1829.0746.5727.961. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Timed FFmpeg Compilation

Time To Compile

Debian 10.10Debian 11.0OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.4Time To CompileEPYC 7763 2PXeon 8380 2P510152025SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 317.5121.5814.2316.21

NAS Parallel Benchmarks

Test / Class: BT.C

Debian 10.10Debian 11.0OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7763 2PXeon 8380 2P60K120K180K240K300KSE +/- 197.74, N = 2SE +/- 395.43, N = 3SE +/- 283.81, N = 3SE +/- 2528.51, N = 3259687.67196078.72257121.36189492.521. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pEPYC 7763 2PXeon 8380 2P70140210280350SE +/- 3.96, N = 3SE +/- 1.38, N = 15SE +/- 2.26, N = 3SE +/- 0.36, N = 3316.11178.29337.18183.671. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

Tuning: 10 - Input: Bosphorus 1080p

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pEPYC 7763 2PXeon 8380 2P120240360480600SE +/- 3.22, N = 3SE +/- 2.91, N = 4SE +/- 2.37, N = 3SE +/- 1.92, N = 15505.94262.59572.17267.461. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080pEPYC 7763 2PXeon 8380 2P100200300400500SE +/- 2.40, N = 3SE +/- 1.99, N = 7SE +/- 3.54, N = 3SE +/- 2.06, N = 3391.63214.28438.77216.761. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

TNN

Target: CPU - Model: SqueezeNet v2

Debian 10.10Debian 11.0OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2EPYC 7763 2PXeon 8380 2P1632486480SE +/- 0.73, N = 5SE +/- 0.06, N = 3SE +/- 0.63, N = 3SE +/- 0.11, N = 368.7872.8768.2672.841. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

SVT-VP9

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

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pEPYC 7763 2PXeon 8380 2P100200300400500SE +/- 2.19, N = 3SE +/- 1.53, N = 3SE +/- 3.16, N = 3SE +/- 2.65, N = 3392.19212.26438.74207.431. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

Tuning: 7 - Input: Bosphorus 1080p

Debian 10.10Debian 11.0OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pEPYC 7763 2PXeon 8380 2P70140210280350SE +/- 0.94, N = 3SE +/- 2.16, N = 3SE +/- 2.23, N = 3SE +/- 1.85, N = 4297.04169.31325.76171.381. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

ctx_clock

Context Switch Time

Debian 10.10Debian 11.0OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeEPYC 7763 2PXeon 8380 2P50100150200250SE +/- 0.67, N = 3SE +/- 5.85, N = 12122197147210

Geometric Mean Of All Test Results

Result Composite - Debian 11 Benchmarks

Debian 10.10Debian 11.0OpenBenchmarking.orgGeometric Mean, More Is BetterGeometric Mean Of All Test ResultsResult Composite - Debian 11 BenchmarksEPYC 7763 2PXeon 8380 2P80160240320400322.82226.48348.26249.98

Phoronix Test Suite v10.8.5