Fedora 32 vs. Fedora 33 Beta Benchmarks

Intel Core i9-10900K testing on Fedora 32 and Fedora 33 Beta by Michael Larabel.

HTML result view exported from: https://openbenchmarking.org/result/2009290-FI-FEDORA85348&grs&sor.

Fedora 32 vs. Fedora 33 Beta BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionDisplay DriverF32 WorkstationF32 Workstation UpdatedF33 Workstation BetaIntel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads)Gigabyte Z490 AORUS MASTER (F3 BIOS)Intel Comet Lake PCH16GBSamsung SSD 970 EVO 250GBGigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1890/875MHz)Realtek ALC1220DELL P2415QIntel Device 15f3 + Intel Wi-Fi 6 AX201Fedora 325.6.6-300.fc32.x86_64 (x86_64)GNOME Shell 3.36.1X Server + Wayland4.6 Mesa 20.0.4 (LLVM 10.0.0)GCC 10.0.1 20200328 + Clang 10.0.1ext43840x2160Intel + Intel-AC 9462/95605.8.11-200.fc32.x86_64 (x86_64)GNOME Shell 3.36.6X Server 1.20.8 + Waylandmodesetting 1.20.84.6 Mesa 20.1.8 (LLVM 10.0.1)GCC 10.2.1 20200723 + Clang 10.0.1Fedora 335.8.11-300.fc33.x86_64 (x86_64)GNOME Shell 3.38.0X Server + Wayland4.6 Mesa 20.2.0-rc4 (LLVM 11.0.0)GCC 10.2.1 20200826 + Clang 11.0.0btrfsOpenBenchmarking.orgCompiler Details- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Disk Details- F32 Workstation: NONE / relatime,rw,seclabel- F32 Workstation Updated: NONE / relatime,rw,seclabel- F33 Workstation Beta: NONE / relatime,rw,seclabel,space_cache,ssd,subvol=/home,subvolid=256Processor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8Java Details- F32 Workstation: OpenJDK Runtime Environment (build 1.8.0_242-b08)- F32 Workstation Updated: OpenJDK Runtime Environment (build 1.8.0_265-b01)- F33 Workstation Beta: OpenJDK Runtime Environment 18.9 (build 11.0.9-ea+6)Python Details- F32 Workstation: Python 3.8.2- F32 Workstation Updated: Python 3.8.5- F33 Workstation Beta: Python 3.9.0rc2Security Details- F32 Workstation: SELinux + itlb_multihit: KVM: Mitigation of Split huge pages + 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 + tsx_async_abort: Not affected - F32 Workstation Updated: SELinux + itlb_multihit: KVM: Mitigation of VMX disabled + 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 - F33 Workstation Beta: SELinux + itlb_multihit: KVM: Mitigation of VMX disabled + 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

Fedora 32 vs. Fedora 33 Beta Benchmarkssqlite: 1realsr-ncnn: 4x - Noleveldb: Seq Fillleveldb: Seq Fillleveldb: Rand Deleteleveldb: Rand Fillleveldb: Rand Fillsystemd-boot-total: Userspaceleveldb: Overwriteleveldb: Overwritegmic: Plotting Isosurface Of A 3D Volume, 1000 Timesrenaissance: Scala Dottysystemd-boot-total: Totalrenaissance: Savina Reactors.IOsqlite-speedtest: Timed Time - Size 1,000libraw: Post-Processing Benchmarkrenaissance: Twitter HTTP Requestsglibc-bench: expsystemd-boot-total: Firmwareglibc-bench: ffsglibc-bench: modfpyperformance: json_loadsglibc-bench: sqrthint: FLOATpyperformance: pathlibdacapobench: Tradebeansbuild-ffmpeg: Time To Compilerenaissance: Apache Spark ALSrenaissance: Rand Forestdacapobench: Jythonbork: File Encryption Timepyperformance: crypto_pyaeslibreoffice: 20 Documents To PDFsystemd-boot-total: Loaderrenaissance: Genetic Algorithm Using Jenetics + Futuresgimp: auto-levelsgimp: unsharp-maskgimp: resizetscp: AI Chess Performanceperl-benchmark: Pod2htmlperl-benchmark: Interpretermnn: SqueezeNetV1.0dolfyn: Computational Fluid Dynamicsgmic: 2D Function Plotting, 1000 Timesphpbench: PHP Benchmark Suitegimp: rotatebuild-linux-kernel: Time To Compilepyperformance: godacapobench: Tradesoapncnn: CPU - blazefacepyperformance: 2to3pyperformance: nbodycrafty: Elapsed Timeavifenc: 8astcenc: Fastrodinia: OpenMP HotSpot3Dbyte: Dhrystone 2ncnn: CPU - mnasnetncnn: CPU - googlenetrenaissance: Akka Unbalanced Cobwebbed Treeai-benchmark: Device Inference Scoreavifenc: 10glibc-bench: sinhmnn: resnet-v2-50ncnn: CPU - alexnetncnn: CPU - vgg16cryptsetup: PBKDF2-sha512build-mplayer: Time To Compilepyperformance: pickle_pure_pythonncnn: CPU - efficientnet-b0ai-benchmark: Device AI Scorepyperformance: floatncnn: CPU - yolov4-tinybasemark: Vulkan - 3840 x 2160 - Mediumcaffe: AlexNet - CPU - 200dav1d: Chimera 1080pluxcorerender: Rainbow Colors and Prismleveldb: Hot Readdav1d: Summer Nature 1080pwebp: Quality 100, Losslessgit: Time To Complete Common Git Commandsmafft: Multiple Sequence Alignment - LSU RNApyperformance: python_startupwebp: Quality 100, Lossless, Highest Compressionpyperformance: django_templateopenvkl: vklBenchmarkai-benchmark: Device Training Scorecompress-zstd: 3stockfish: Total Timepyperformance: chaospybench: Total For Average Test Timeswebp: Quality 100svt-av1: Enc Mode 0 - 1080pwebp: Quality 100, Highest Compressionastcenc: Mediumtnn: CPU - MobileNet v2hugin: Panorama Photo Assistant + Stitching Timedarktable: Server Rack - CPU-onlyglibc-bench: sincosgmic: 3D Elevated Function In Rand Colors, 100 Timesrodinia: OpenMP Leukocytewebp: Defaultncnn: CPU - resnet18tesseract-ocr: Time To OCR 7 Imageshpcg: build-gdb: Time To Compilepyperformance: raytraceleveldb: Seek Randleveldb: Rand Readsvt-av1: Enc Mode 4 - 1080pcaffe: GoogleNet - CPU - 100glibc-bench: ffsllbuild-apache: Time To Compileunigine-super: 1920 x 1080 - Fullscreen - Low - OpenGLdarktable: Server Room - CPU-onlyglibc-bench: asinhcryptsetup: PBKDF2-whirlpoolpyperformance: regex_compilerodinia: OpenMP LavaMDoidn: Memorialmnn: inception-v3caffe: GoogleNet - CPU - 200rodinia: OpenMP CFD Solverncnn: CPU - mobilenetsystemd-boot-total: Kernelrawtherapee: Total Benchmark Timencnn: CPU-v2-v2 - mobilenet-v2mnn: mobilenet-v1-1.0astcenc: Thoroughncnn: CPU - resnet50system-decompress-gzip: namd: ATPase Simulation - 327,506 Atomsdeepspeech: CPUbuild-php: Time To Compileunigine-heaven: 1920 x 1080 - Fullscreen - OpenGLglibc-bench: log2avifenc: 2luxcorerender: DLSCdav1d: Chimera 1080p 10-bitsvt-av1: Enc Mode 8 - 1080punigine-super: 1920 x 1080 - Fullscreen - High - OpenGLtensorflow-lite: NASNet Mobilegromacs: Water Benchmarkavifenc: 0blender: Fishy Cat - CPU-Onlyastcenc: Exhaustivex265: H.265 1080p Video Encodingncnn: CPU - squeezenetlammps: Rhodopsin Proteincompress-zstd: 19rodinia: OpenMP Streamclusterblender: BMW27 - CPU-Onlytensorflow-lite: Mobilenet Quantglibc-bench: pthread_oncencnn: CPU-v3-v3 - mobilenet-v3embree: Pathtracer ISPC - Asian Dragoncaffe: AlexNet - CPU - 100tnn: CPU - SqueezeNet v1.1darktable: Boat - CPU-onlyglibc-bench: cosincompact3d: Cylinderembree: Pathtracer - Asian Dragonbasemark: Vulkan - 3840 x 2160 - Highglibc-bench: sindarktable: Masskrug - CPU-onlytensorflow-lite: Mobilenet Floatdav1d: Summer Nature 4Kglibc-bench: tanhtensorflow-lite: SqueezeNetglibc-bench: atanhtensorflow-lite: Inception V4tensorflow-lite: Inception ResNet V2ncnn: CPU - shufflenet-v2renaissance: Apache Spark PageRankF32 WorkstationF32 Workstation UpdatedF33 Workstation BetaFedora Workstation 32 Updated43.33625.19540.66954.440.69552.841.834801052.542.02216.6741013.0361181114395.21043.67645.921881.0304.9223081351.309881.5170522.31.70406467186547.1196915.9230544.0261647.2891508.21933177.1551006.68818721244.3689.50711.6236.10116275970.099593760.000812104.21415.59492.9238484159.53461.67621529991.31264108103565655.1334.5282.34552011851.23.8713.749211.34714564.9656.7908824.90615.5070.1227.7253715.85261695.925.50221.19217352778.802.508.800726.1614.79140.8118.6146.9430.50744.4192.6111602894.83707314694.88931.9620.1675.9526.67270.61038.6820.17612.408055.39484.7431.26313.8620.0524.3505776.07842310.7208.8744.5542413041.3180017.365131.63.6017.70467880663150173.76711.0329.43248282518.21316.48380155.1855.022.88620.9424.812.4811.2110579.9875246.88689.56565.9871343.6232.17133.7642.03445.11488490.96373.054160.54168.7572.7614.188.45230.317.355114.031180591.319844.0220.3281108663260.72914.16638.7503238.62257417.665145.4538.39474.074114879185.4310.40571679779.40863237865021447073.233732.06843.76325.16442.61851.942.76351.043.297850351.243.16016.4221007.0911228611682.14644.91738.441918.0924.4533781021.304151.7339323.31.50804451902708.2097715.6229444.1561642.1121512.18933137.1211016.57817771284.8969.34111.5895.95716720680.097626250.000794014.39515.83393.1288538659.37862.74121829301.33265108104525675.2094.6384.32951604321.43.8413.439004.04114245.0416.8036025.42515.4870.41207777227.5053785.88256996.425.06219.01217359783.942.488.758736.8814.85840.4458.5617.0130.92744.6191.4211452900.53754456396.08971.9440.1655.8816.75273.81638.3640.17812.275555.78985.3271.25013.7220.2504.3447976.19842710.6878.7964.5412415381.3075017.445132.33.6277.66474880666150173.84611.1029.55148336918.10016.38378355.1805.052.89021.0624.672.4671.2135579.8938346.83790.03435.9571443.5882.17133.1541.84745.21489540.96373.353161.16168.8972.7814.168.42430.217.352114.331177871.316414.0320.3780108780260.93014.14938.8184239.08667517.672745.3738.32844.073114742185.5210.40521679059.40694237794721445703.203559.826144.40615.45261.82335.861.26536.859.9101137937.159.44011.9271364.5001515713907.62852.42542.232229.4054.2291793831.500541.5383420.51.50804497803514.8792914.5249240.8571772.4081622.64435577.60595.86.93217801310.7339.82712.1536.23717009910.101928160.000828464.27816.23489.6998793249.71660.68021130271.35272111106251505.2654.5983.26650797941.33.9313.469163.8175.0746.9385225.20115.1969.03204268227.1983745.9694.725.23222.83213793791.702.468.660737.4115.00740.2268.4916.9130.88945.0193.942863.33708106696.08861.9380.1665.8816.71273.58538.8010.17812.293555.98184.4461.25013.8320.1684.3874075.46542510.6258.8004.5162432551.3083317.503132.63.6287.64781874299149172.71611.0929.36548587518.10016.41377855.5115.022.87321.0324.782.4691.2067979.5426946.63089.68525.9779443.4112.18133.1641.85245.31483090.95973.090161.08169.3973.0314.138.43030.217.301114.041180951.318434.0220.3689108919260.32014.17938.7425238.74986317.696545.4138.32964.067114727185.5810.39801679259.41062237867721451473.203086.4982083292OpenBenchmarking.org

SQLite

Threads / Copies: 1

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 1F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta306090120150SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.21, N = 343.3443.76144.411. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoF33 Workstation BetaF32 Workstation UpdatedF32 Workstation612182430SE +/- 0.04, N = 3SE +/- 0.17, N = 3SE +/- 0.20, N = 315.4525.1625.20

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1428425670SE +/- 0.05, N = 3SE +/- 0.16, N = 3SE +/- 0.86, N = 440.6742.6261.821. (CXX) g++ options: -O2 -lsnappy -lpthread

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1224364860SE +/- 0.09, N = 3SE +/- 0.20, N = 3SE +/- 0.50, N = 454.451.935.81. (CXX) g++ options: -O2 -lsnappy -lpthread

LevelDB

Benchmark: Random Delete

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1428425670SE +/- 0.33, N = 3SE +/- 0.26, N = 3SE +/- 0.40, N = 340.7042.7661.271. (CXX) g++ options: -O2 -lsnappy -lpthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1224364860SE +/- 0.12, N = 3SE +/- 0.39, N = 3SE +/- 0.12, N = 352.851.036.81. (CXX) g++ options: -O2 -lsnappy -lpthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1326395265SE +/- 0.09, N = 3SE +/- 0.33, N = 3SE +/- 0.19, N = 341.8343.3059.911. (CXX) g++ options: -O2 -lsnappy -lpthread

Systemd Total Boot Time

Test: Userspace

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: UserspaceF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta2K4K6K8K10K8010850311379

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1224364860SE +/- 0.52, N = 3SE +/- 0.13, N = 3SE +/- 0.38, N = 352.551.237.11. (CXX) g++ options: -O2 -lsnappy -lpthread

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1326395265SE +/- 0.42, N = 3SE +/- 0.12, N = 3SE +/- 0.61, N = 342.0243.1659.441. (CXX) g++ options: -O2 -lsnappy -lpthread

G'MIC

Test: Plotting Isosurface Of A 3D Volume, 1000 Times

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: Plotting Isosurface Of A 3D Volume, 1000 TimesF33 Workstation BetaF32 Workstation UpdatedF32 Workstation48121620SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 311.9316.4216.671. Version 2.9.0

Renaissance

Test: Scala Dotty

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Scala DottyF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta30060090012001500SE +/- 8.96, N = 5SE +/- 12.25, N = 5SE +/- 7.12, N = 51007.091013.041364.50

Systemd Total Boot Time

Test: Total

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: TotalF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta3K6K9K12K15K118111228615157

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IOF32 Workstation UpdatedF33 Workstation BetaF32 Workstation3K6K9K12K15KSE +/- 62.43, N = 5SE +/- 150.42, N = 20SE +/- 118.55, N = 511682.1513907.6314395.21

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1224364860SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.24, N = 343.6844.9252.431. (CC) gcc options: -O2 -ldl -lz -lpthread

LibRaw

Post-Processing Benchmark

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkF32 WorkstationF33 Workstation BetaF32 Workstation Updated1020304050SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 345.9242.2338.44-llcms21. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

Renaissance

Test: Twitter HTTP Requests

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Twitter HTTP RequestsF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta5001000150020002500SE +/- 3.54, N = 5SE +/- 8.57, N = 5SE +/- 11.76, N = 51881.031918.092229.41

glibc bench

Benchmark: exp

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: expF33 Workstation BetaF32 Workstation UpdatedF32 Workstation1.10752.2153.32254.435.5375SE +/- 0.05192, N = 13SE +/- 0.05716, N = 3SE +/- 0.00966, N = 34.229174.453374.92230

Systemd Total Boot Time

Test: Firmware

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: FirmwareF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta2K4K6K8K10K810281359383

glibc bench

Benchmark: ffs

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta0.33760.67521.01281.35041.688SE +/- 0.00223, N = 3SE +/- 0.00037, N = 3SE +/- 0.00080, N = 31.304151.309881.50054

glibc bench

Benchmark: modf

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: modfF32 WorkstationF33 Workstation BetaF32 Workstation Updated0.39010.78021.17031.56041.9505SE +/- 0.00073, N = 3SE +/- 0.00134, N = 3SE +/- 0.00166, N = 31.517051.538341.73393

PyPerformance

Benchmark: json_loads

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsF33 Workstation BetaF32 WorkstationF32 Workstation Updated612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 320.522.323.3

glibc bench

Benchmark: sqrt

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtF32 Workstation UpdatedF33 Workstation BetaF32 Workstation0.38340.76681.15021.53361.917SE +/- 0.00204, N = 3SE +/- 0.00096, N = 3SE +/- 0.00081, N = 31.508041.508041.70406

Hierarchical INTegration

Test: FLOAT

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATF33 Workstation BetaF32 WorkstationF32 Workstation Updated110M220M330M440M550MSE +/- 518748.60, N = 3SE +/- 662338.05, N = 3SE +/- 65392.17, N = 3497803514.88467186547.12451902708.211. (CC) gcc options: -O3 -march=native -lm

PyPerformance

Benchmark: pathlib

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibF33 Workstation BetaF32 Workstation UpdatedF32 Workstation48121620SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 314.515.615.9

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta5001000150020002500SE +/- 4.70, N = 4SE +/- 25.55, N = 4SE +/- 24.83, N = 4229423052492

Timed FFmpeg Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To CompileF33 Workstation BetaF32 WorkstationF32 Workstation Updated1020304050SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 340.8644.0344.16

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta400800120016002000SE +/- 13.90, N = 5SE +/- 3.97, N = 5SE +/- 9.62, N = 51642.111647.291772.41

Renaissance

Test: Random Forest

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Random ForestF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta30060090012001500SE +/- 15.97, N = 5SE +/- 16.39, N = 5SE +/- 15.99, N = 51508.221512.191622.64

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta8001600240032004000SE +/- 15.35, N = 4SE +/- 12.70, N = 4SE +/- 27.37, N = 4331333173557

Bork File Encrypter

File Encryption Time

OpenBenchmarking.orgSeconds, Fewer Is BetterBork File Encrypter 1.4File Encryption TimeF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta246810SE +/- 0.018, N = 3SE +/- 0.050, N = 3SE +/- 0.019, N = 37.1217.1557.605

PyPerformance

Benchmark: crypto_pyaes

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesF33 Workstation BetaF32 WorkstationF32 Workstation Updated20406080100SE +/- 0.03, N = 395.8100.0101.0

LibreOffice

Test: 20 Documents To PDF

OpenBenchmarking.orgSeconds, Fewer Is BetterLibreOfficeTest: 20 Documents To PDFF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta246810SE +/- 0.034, N = 25SE +/- 0.053, N = 20SE +/- 0.057, N = 56.5786.6886.9321. F32 Workstation Updated: LibreOffice 6.4.6.2 40(Build:2)2. F32 Workstation: LibreOffice 6.4.2.2 40(Build:2)3. F33 Workstation Beta: LibreOffice 7.0.1.2 00(Build:2)

Systemd Total Boot Time

Test: Loader

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: LoaderF32 Workstation UpdatedF33 Workstation BetaF32 Workstation400800120016002000177717801872

Renaissance

Test: Genetic Algorithm Using Jenetics + Futures

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Genetic Algorithm Using Jenetics + FuturesF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta30060090012001500SE +/- 13.46, N = 25SE +/- 9.32, N = 5SE +/- 10.40, N = 251244.371284.901310.73

GIMP

Test: auto-levels

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.20Test: auto-levelsF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta3691215SE +/- 0.023, N = 3SE +/- 0.013, N = 3SE +/- 0.018, N = 39.3419.5079.827

GIMP

Test: unsharp-mask

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.20Test: unsharp-maskF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 311.5911.6212.15

GIMP

Test: resize

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.20Test: resizeF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta246810SE +/- 0.064, N = 3SE +/- 0.082, N = 3SE +/- 0.050, N = 35.9576.1016.237

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceF33 Workstation BetaF32 Workstation UpdatedF32 Workstation400K800K1200K1600K2000KSE +/- 1964.11, N = 5SE +/- 1242.63, N = 5SE +/- 1177.47, N = 51700991167206816275971. (CC) gcc options: -O3 -march=native

Perl Benchmarks

Test: Pod2html

OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: Pod2htmlF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta0.02290.04580.06870.09160.1145SE +/- 0.00021074, N = 3SE +/- 0.00036967, N = 3SE +/- 0.00060182, N = 30.097626250.099593760.10192816

Perl Benchmarks

Test: Interpreter

OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: InterpreterF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta0.00020.00040.00060.00080.001SE +/- 0.00000392, N = 3SE +/- 0.00000261, N = 3SE +/- 0.00001305, N = 30.000794010.000812100.00082846

Mobile Neural Network

Model: SqueezeNetV1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: SqueezeNetV1.0F32 WorkstationF33 Workstation BetaF32 Workstation Updated0.98891.97782.96673.95564.9445SE +/- 0.038, N = 3SE +/- 0.016, N = 3SE +/- 0.027, N = 34.2144.2784.395MIN: 4.06 / MAX: 17.74MIN: 4.16 / MAX: 10.02MIN: 4.28 / MAX: 17.831. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Dolfyn

Computational Fluid Dynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta48121620SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 315.5915.8316.23

G'MIC

Test: 2D Function Plotting, 1000 Times

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 2D Function Plotting, 1000 TimesF33 Workstation BetaF32 WorkstationF32 Workstation Updated20406080100SE +/- 0.48, N = 3SE +/- 0.14, N = 3SE +/- 0.43, N = 389.7092.9293.131. Version 2.9.0

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteF33 Workstation BetaF32 Workstation UpdatedF32 Workstation200K400K600K800K1000KSE +/- 800.41, N = 3SE +/- 4199.16, N = 3SE +/- 2757.69, N = 3879324853865848415

GIMP

Test: rotate

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.20Test: rotateF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta3691215SE +/- 0.011, N = 3SE +/- 0.076, N = 3SE +/- 0.060, N = 39.3789.5349.716

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileF33 Workstation BetaF32 WorkstationF32 Workstation Updated1428425670SE +/- 0.60, N = 3SE +/- 0.33, N = 3SE +/- 1.06, N = 360.6861.6862.74

PyPerformance

Benchmark: go

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goF33 Workstation BetaF32 WorkstationF32 Workstation Updated50100150200250SE +/- 0.33, N = 3SE +/- 1.00, N = 3211215218

DaCapo Benchmark

Java Test: Tradesoap

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta6001200180024003000SE +/- 19.64, N = 19SE +/- 30.37, N = 4SE +/- 18.63, N = 4293029993027

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta0.30380.60760.91141.21521.519SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 31.311.331.35MIN: 1.23 / MAX: 1.36MIN: 1.24 / MAX: 2.53MIN: 1.28 / MAX: 4.891. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

PyPerformance

Benchmark: 2to3

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta60120180240300264265272

PyPerformance

Benchmark: nbody

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta20406080100108108111

Crafty

Elapsed Time

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed TimeF33 Workstation BetaF32 Workstation UpdatedF32 Workstation2M4M6M8M10MSE +/- 21467.07, N = 3SE +/- 13836.18, N = 3SE +/- 5404.30, N = 31062515010452567103565651. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

libavif avifenc

Encoder Speed: 8

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 8F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1.18462.36923.55384.73845.923SE +/- 0.008, N = 3SE +/- 0.020, N = 3SE +/- 0.002, N = 35.1335.2095.2651. (CXX) g++ options: -O3 -fPIC

ASTC Encoder

Preset: Fast

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: FastF32 WorkstationF33 Workstation BetaF32 Workstation Updated1.04182.08363.12544.16725.209SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.524.594.631. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

Rodinia

Test: OpenMP HotSpot3D

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DF32 WorkstationF33 Workstation BetaF32 Workstation Updated20406080100SE +/- 0.05, N = 3SE +/- 0.36, N = 3SE +/- 0.07, N = 382.3583.2784.331. (CXX) g++ options: -O2 -lOpenCL

BYTE Unix Benchmark

Computational Test: Dhrystone 2

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta11M22M33M44M55MSE +/- 727737.47, N = 3SE +/- 135665.15, N = 3SE +/- 8678.89, N = 352011851.251604321.450797941.3

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta0.88431.76862.65293.53724.4215SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 33.843.873.93MIN: 3.65 / MAX: 5.23MIN: 3.77 / MAX: 10.47MIN: 3.65 / MAX: 7.471. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetF32 Workstation UpdatedF33 Workstation BetaF32 Workstation48121620SE +/- 0.01, N = 3SE +/- 0.29, N = 3SE +/- 0.28, N = 313.4313.4613.74MIN: 12.99 / MAX: 26.07MIN: 12.81 / MAX: 18.22MIN: 13.08 / MAX: 32.761. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed TreeF32 Workstation UpdatedF33 Workstation BetaF32 Workstation2K4K6K8K10KSE +/- 75.72, N = 5SE +/- 91.23, N = 9SE +/- 99.99, N = 59004.049163.829211.35

AI Benchmark Alpha

Device Inference Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference ScoreF32 WorkstationF32 Workstation Updated3006009001200150014561424

libavif avifenc

Encoder Speed: 10

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 10F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1.14172.28343.42514.56685.7085SE +/- 0.021, N = 3SE +/- 0.034, N = 3SE +/- 0.008, N = 34.9655.0415.0741. (CXX) g++ options: -O3 -fPIC

glibc bench

Benchmark: sinh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinhF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta246810SE +/- 0.00115, N = 3SE +/- 0.00079, N = 3SE +/- 0.00116, N = 36.790886.803606.93852

Mobile Neural Network

Model: resnet-v2-50

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: resnet-v2-50F32 WorkstationF33 Workstation BetaF32 Workstation Updated612182430SE +/- 0.01, N = 3SE +/- 0.24, N = 3SE +/- 0.26, N = 324.9125.2025.43MIN: 24.66 / MAX: 38.14MIN: 24.79 / MAX: 32.12MIN: 24.69 / MAX: 39.571. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetF33 Workstation BetaF32 Workstation UpdatedF32 Workstation48121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 315.1915.4815.50MIN: 15.01 / MAX: 22.42MIN: 15.29 / MAX: 23.87MIN: 15.3 / MAX: 24.641. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16F33 Workstation BetaF32 WorkstationF32 Workstation Updated1632486480SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 369.0370.1270.41MIN: 68.48 / MAX: 76.07MIN: 69.69 / MAX: 82.73MIN: 69.98 / MAX: 80.651. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Cryptsetup

PBKDF2-sha512

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetup 2.3.4PBKDF2-sha512Fedora Workstation 32 UpdatedF32 Workstation UpdatedF33 Workstation Beta400K800K1200K1600K2000KSE +/- 5504.00, N = 3SE +/- 3634.51, N = 3SE +/- 1331.00, N = 3208329220777722045338

Timed MPlayer Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.4Time To CompileF33 Workstation BetaF32 Workstation UpdatedF32 Workstation714212835SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 327.2027.5127.73

PyPerformance

Benchmark: pickle_pure_python

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonF32 WorkstationF33 Workstation BetaF32 Workstation Updated80160240320400SE +/- 0.33, N = 3SE +/- 0.33, N = 3371374378

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1.3412.6824.0235.3646.705SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 35.855.885.96MIN: 5.63 / MAX: 18.12MIN: 5.68 / MAX: 7.26MIN: 5.76 / MAX: 8.061. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

AI Benchmark Alpha

Device AI Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI ScoreF32 WorkstationF32 Workstation Updated600120018002400300026162569

PyPerformance

Benchmark: float

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatF33 Workstation BetaF32 WorkstationF32 Workstation Updated20406080100SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.22, N = 394.795.996.4

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyF32 Workstation UpdatedF33 Workstation BetaF32 Workstation612182430SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 325.0625.2325.50MIN: 24.6 / MAX: 33.92MIN: 24.69 / MAX: 31.6MIN: 24.82 / MAX: 38.761. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Basemark GPU

Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: Medium

OpenBenchmarking.orgFPS, More Is BetterBasemark GPU 1.2Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: MediumF33 Workstation BetaF32 WorkstationF32 Workstation Updated50100150200250SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.27, N = 3222.83221.19219.01MIN: 141.32 / MAX: 370.49MIN: 140.91 / MAX: 370.01MIN: 140.81 / MAX: 371.24

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 200

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200F33 Workstation BetaF32 WorkstationF32 Workstation Updated50K100K150K200K250KSE +/- 34.91, N = 3SE +/- 96.33, N = 3SE +/- 162.52, N = 32137932173522173591. (CXX) g++ options: -fPIC -O2 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lhdf5_cpp -lhdf5 -lhdf5_hl_cpp -lhdf5_hl -llmdb -lopenblas

dav1d

Video Input: Chimera 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080pF33 Workstation BetaF32 Workstation UpdatedF32 Workstation2004006008001000SE +/- 0.59, N = 3SE +/- 0.79, N = 3SE +/- 1.16, N = 3791.70783.94778.80MIN: 610.59 / MAX: 1080.54MIN: 609.29 / MAX: 1041.56MIN: 607.84 / MAX: 1013.581. (CC) gcc options: -pthread

LuxCoreRender

Scene: Rainbow Colors and Prism

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and PrismF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta0.56251.1251.68752.252.8125SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 32.502.482.46MIN: 2.44 / MAX: 2.53MIN: 2.43 / MAX: 2.51MIN: 2.41 / MAX: 2.51

LevelDB

Benchmark: Hot Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadF33 Workstation BetaF32 Workstation UpdatedF32 Workstation246810SE +/- 0.119, N = 3SE +/- 0.089, N = 8SE +/- 0.098, N = 78.6608.7588.8001. (CXX) g++ options: -O2 -lsnappy -lpthread

dav1d

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pF33 Workstation BetaF32 Workstation UpdatedF32 Workstation160320480640800SE +/- 0.76, N = 3SE +/- 0.93, N = 3SE +/- 7.11, N = 3737.41736.88726.16MIN: 625.08 / MAX: 802.04MIN: 621.65 / MAX: 800.57MIN: 483.53 / MAX: 795.121. (CC) gcc options: -pthread

WebP Image Encode

Encode Settings: Quality 100, Lossless

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta48121620SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 314.7914.8615.011. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16

Git

Time To Complete Common Git Commands

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsF33 Workstation BetaF32 Workstation UpdatedF32 Workstation918273645SE +/- 0.13, N = 3SE +/- 0.22, N = 3SE +/- 0.15, N = 340.2340.4540.811. F33 Workstation Beta: git version 2.28.02. F32 Workstation Updated: git version 2.26.03. F32 Workstation: git version 2.26.0

Timed MAFFT Alignment

Multiple Sequence Alignment - LSU RNA

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAF33 Workstation BetaF32 Workstation UpdatedF32 Workstation246810SE +/- 0.045, N = 3SE +/- 0.050, N = 3SE +/- 0.047, N = 38.4918.5618.6141. (CC) gcc options: -std=c99 -O3 -lm -lpthread

PyPerformance

Benchmark: python_startup

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupF33 Workstation BetaF32 WorkstationF32 Workstation Updated246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 36.916.947.01

WebP Image Encode

Encode Settings: Quality 100, Lossless, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionF32 WorkstationF33 Workstation BetaF32 Workstation Updated714212835SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 330.5130.8930.931. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16

PyPerformance

Benchmark: django_template

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1020304050SE +/- 0.18, N = 3SE +/- 0.13, N = 3SE +/- 0.20, N = 344.444.645.0

OpenVKL

Benchmark: vklBenchmark

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmarkF33 Workstation BetaF32 WorkstationF32 Workstation Updated4080120160200SE +/- 0.25, N = 3SE +/- 0.81, N = 3SE +/- 1.62, N = 3193.94192.61191.42MIN: 1 / MAX: 778MIN: 1 / MAX: 771MIN: 1 / MAX: 781

AI Benchmark Alpha

Device Training Score

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training ScoreF32 WorkstationF32 Workstation Updated200400600800100011601145

Zstd Compression

Compression Level: 3

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3F32 Workstation UpdatedF32 WorkstationF33 Workstation Beta6001200180024003000SE +/- 10.98, N = 3SE +/- 24.28, N = 3SE +/- 16.00, N = 32900.52894.82863.31. (CC) gcc options: -O3 -pthread -lz -llzma

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total TimeF32 Workstation UpdatedF33 Workstation BetaF32 Workstation8M16M24M32M40MSE +/- 201253.35, N = 3SE +/- 265859.79, N = 3SE +/- 180894.45, N = 33754456337081066370731461. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

PyPerformance

Benchmark: chaos

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta20406080100SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 394.896.096.0

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesF33 Workstation BetaF32 WorkstationF32 Workstation Updated2004006008001000SE +/- 9.68, N = 3SE +/- 0.88, N = 3SE +/- 1.73, N = 3886893897

WebP Image Encode

Encode Settings: Quality 100

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100F33 Workstation BetaF32 Workstation UpdatedF32 Workstation0.44150.8831.32451.7662.2075SE +/- 0.002, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 31.9381.9441.9621. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16

SVT-AV1

Encoder Mode: Enc Mode 0 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pF32 WorkstationF33 Workstation BetaF32 Workstation Updated0.03760.07520.11280.15040.188SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.1670.1660.1651. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionF32 Workstation UpdatedF33 Workstation BetaF32 Workstation1.33922.67844.01765.35686.696SE +/- 0.004, N = 3SE +/- 0.010, N = 3SE +/- 0.007, N = 35.8815.8815.9521. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16

ASTC Encoder

Preset: Medium

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: MediumF32 WorkstationF33 Workstation BetaF32 Workstation Updated246810SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.676.716.751. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2F32 WorkstationF33 Workstation BetaF32 Workstation Updated60120180240300SE +/- 1.46, N = 3SE +/- 1.11, N = 3SE +/- 0.64, N = 3270.61273.59273.82MIN: 263.97 / MAX: 283.59MIN: 270.76 / MAX: 280.55MIN: 271.95 / MAX: 283.741. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O2 -rdynamic -ldl

Hugin

Panorama Photo Assistant + Stitching Time

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta918273645SE +/- 0.23, N = 3SE +/- 0.20, N = 3SE +/- 0.17, N = 338.3638.6838.80

Darktable

Test: Server Rack - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.2.1Test: Server Rack - Acceleration: CPU-onlyF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta0.04010.08020.12030.16040.2005SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1760.1780.178

glibc bench

Benchmark: sincos

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sincosF32 Workstation UpdatedF33 Workstation BetaF32 Workstation3691215SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 312.2812.2912.41

G'MIC

Test: 3D Elevated Function In Random Colors, 100 Times

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 3D Elevated Function In Random Colors, 100 TimesF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1326395265SE +/- 0.53, N = 3SE +/- 0.11, N = 3SE +/- 0.29, N = 355.3955.7955.981. Version 2.9.0

Rodinia

Test: OpenMP Leukocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteF33 Workstation BetaF32 WorkstationF32 Workstation Updated20406080100SE +/- 0.56, N = 3SE +/- 1.12, N = 3SE +/- 0.76, N = 384.4584.7485.331. (CXX) g++ options: -O2 -lOpenCL

WebP Image Encode

Encode Settings: Default

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: DefaultF32 Workstation UpdatedF33 Workstation BetaF32 Workstation0.28420.56840.85261.13681.421SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 31.2501.2501.2631. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18F32 Workstation UpdatedF33 Workstation BetaF32 Workstation48121620SE +/- 0.04, N = 3SE +/- 0.28, N = 3SE +/- 0.28, N = 313.7213.8313.86MIN: 13.41 / MAX: 32.26MIN: 13.31 / MAX: 17.98MIN: 13.38 / MAX: 22.351. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Tesseract OCR

Time To OCR 7 Images

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.1Time To OCR 7 ImagesF32 WorkstationF33 Workstation BetaF32 Workstation Updated510152025SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 320.0520.1720.25

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1F33 Workstation BetaF32 WorkstationF32 Workstation Updated0.98721.97442.96163.94884.936SE +/- 0.00255, N = 3SE +/- 0.00174, N = 3SE +/- 0.00338, N = 34.387404.350574.344791. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

Timed GDB GNU Debugger Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileF33 Workstation BetaF32 WorkstationF32 Workstation Updated20406080100SE +/- 0.16, N = 3SE +/- 0.37, N = 3SE +/- 0.35, N = 375.4776.0876.20

PyPerformance

Benchmark: raytrace

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceF32 WorkstationF33 Workstation BetaF32 Workstation Updated90180270360450SE +/- 0.58, N = 3423425427

LevelDB

Benchmark: Seek Random

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomF33 Workstation BetaF32 Workstation UpdatedF32 Workstation3691215SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 310.6310.6910.721. (CXX) g++ options: -O2 -lsnappy -lpthread

LevelDB

Benchmark: Random Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadF32 Workstation UpdatedF33 Workstation BetaF32 Workstation246810SE +/- 0.083, N = 12SE +/- 0.005, N = 3SE +/- 0.061, N = 158.7968.8008.8741. (CXX) g++ options: -O2 -lsnappy -lpthread

SVT-AV1

Encoder Mode: Enc Mode 4 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta1.02472.04943.07414.09885.1235SE +/- 0.017, N = 3SE +/- 0.014, N = 3SE +/- 0.022, N = 34.5544.5414.5161. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 100

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 100F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta50K100K150K200K250KSE +/- 98.00, N = 3SE +/- 67.52, N = 3SE +/- 213.53, N = 32413042415382432551. (CXX) g++ options: -fPIC -O2 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lhdf5_cpp -lhdf5 -lhdf5_hl_cpp -lhdf5_hl -llmdb -lopenblas

glibc bench

Benchmark: ffsll

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsllF32 Workstation UpdatedF33 Workstation BetaF32 Workstation0.29660.59320.88981.18641.483SE +/- 0.00037, N = 3SE +/- 0.00037, N = 3SE +/- 0.00039, N = 31.307501.308331.31800

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To CompileF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta48121620SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.01, N = 317.3717.4517.50

Unigine Superposition

Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Low - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLF33 Workstation BetaF32 Workstation UpdatedF32 Workstation306090120150SE +/- 0.30, N = 3SE +/- 0.22, N = 3SE +/- 0.07, N = 3132.6132.3131.6MAX: 191.4MAX: 190.3MAX: 179.9

Darktable

Test: Server Room - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.2.1Test: Server Room - Acceleration: CPU-onlyF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta0.81631.63262.44893.26524.0815SE +/- 0.004, N = 3SE +/- 0.007, N = 3SE +/- 0.002, N = 33.6013.6273.628

glibc bench

Benchmark: asinh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: asinhF33 Workstation BetaF32 Workstation UpdatedF32 Workstation246810SE +/- 0.01673, N = 3SE +/- 0.00926, N = 3SE +/- 0.01979, N = 37.647817.664747.70467

Cryptsetup

PBKDF2-whirlpool

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-whirlpoolF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta200K400K600K800K1000KSE +/- 1303.47, N = 3SE +/- 493.00, N = 3SE +/- 486.33, N = 3880666880663874299

PyPerformance

Benchmark: regex_compile

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileF33 Workstation BetaF32 WorkstationF32 Workstation Updated306090120150149150150

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDF33 Workstation BetaF32 WorkstationF32 Workstation Updated4080120160200SE +/- 0.00, N = 3SE +/- 0.62, N = 3SE +/- 0.47, N = 3172.72173.77173.851. (CXX) g++ options: -O2 -lOpenCL

Intel Open Image Denoise

Scene: Memorial

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: MemorialF32 Workstation UpdatedF33 Workstation BetaF32 Workstation3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 311.1011.0911.03

Mobile Neural Network

Model: inception-v3

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: inception-v3F33 Workstation BetaF32 WorkstationF32 Workstation Updated714212835SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 329.3729.4329.55MIN: 28.95 / MAX: 35.62MIN: 28.89 / MAX: 54.96MIN: 29 / MAX: 44.231. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 200

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta100K200K300K400K500KSE +/- 123.79, N = 3SE +/- 466.97, N = 3SE +/- 459.90, N = 34828254833694858751. (CXX) g++ options: -fPIC -O2 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lhdf5_cpp -lhdf5 -lhdf5_hl_cpp -lhdf5_hl -llmdb -lopenblas

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverF32 Workstation UpdatedF33 Workstation BetaF32 Workstation48121620SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 318.1018.1018.211. (CXX) g++ options: -O2 -lOpenCL

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetF32 Workstation UpdatedF33 Workstation BetaF32 Workstation48121620SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 316.3816.4116.48MIN: 15.94 / MAX: 30.2MIN: 16.2 / MAX: 22.33MIN: 16.28 / MAX: 27.011. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Systemd Total Boot Time

Test: Kernel

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: KernelF33 Workstation BetaF32 Workstation UpdatedF32 Workstation8001600240032004000377837833801

RawTherapee

Total Benchmark Time

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta1224364860SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 355.1855.1955.511. RawTherapee, version 5.8, command line.

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2F32 WorkstationF33 Workstation BetaF32 Workstation Updated1.13632.27263.40894.54525.6815SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 35.025.025.05MIN: 4.83 / MAX: 11.82MIN: 4.77 / MAX: 7.31MIN: 4.84 / MAX: 6.641. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Mobile Neural Network

Model: mobilenet-v1-1.0

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2020-09-17Model: mobilenet-v1-1.0F33 Workstation BetaF32 WorkstationF32 Workstation Updated0.65031.30061.95092.60123.2515SE +/- 0.003, N = 3SE +/- 0.000, N = 3SE +/- 0.015, N = 32.8732.8862.890MIN: 2.84 / MAX: 10.88MIN: 2.81 / MAX: 12.64MIN: 2.84 / MAX: 15.861. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ThoroughF32 WorkstationF33 Workstation BetaF32 Workstation Updated510152025SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 320.9421.0321.061. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50F32 Workstation UpdatedF33 Workstation BetaF32 Workstation612182430SE +/- 0.08, N = 3SE +/- 0.29, N = 3SE +/- 0.29, N = 324.6724.7824.81MIN: 23.86 / MAX: 39.81MIN: 23.59 / MAX: 29.87MIN: 23.98 / MAX: 33.441. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

System GZIP Decompression

OpenBenchmarking.orgSeconds, Fewer Is BetterSystem GZIP DecompressionF32 Workstation UpdatedF33 Workstation BetaF32 Workstation0.55821.11641.67462.23282.791SE +/- 0.007, N = 3SE +/- 0.011, N = 3SE +/- 0.019, N = 32.4672.4692.481

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsF33 Workstation BetaF32 WorkstationF32 Workstation Updated0.2730.5460.8191.0921.365SE +/- 0.00563, N = 3SE +/- 0.00506, N = 3SE +/- 0.00037, N = 31.206791.211051.21355

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUF33 Workstation BetaF32 Workstation UpdatedF32 Workstation20406080100SE +/- 0.24, N = 3SE +/- 0.74, N = 3SE +/- 0.73, N = 379.5479.8979.99

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To CompileF33 Workstation BetaF32 Workstation UpdatedF32 Workstation1122334455SE +/- 0.22, N = 3SE +/- 0.19, N = 3SE +/- 0.08, N = 346.6346.8446.89

Unigine Heaven

Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGLF32 Workstation UpdatedF33 Workstation BetaF32 Workstation20406080100SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.16, N = 390.0389.6989.57

glibc bench

Benchmark: log2

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: log2F32 Workstation UpdatedF33 Workstation BetaF32 Workstation1.34712.69424.04135.38846.7355SE +/- 0.00325, N = 3SE +/- 0.00132, N = 3SE +/- 0.00206, N = 35.957145.977945.98713

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 2F33 Workstation BetaF32 Workstation UpdatedF32 Workstation1020304050SE +/- 0.08, N = 3SE +/- 0.24, N = 3SE +/- 0.11, N = 343.4143.5943.621. (CXX) g++ options: -O3 -fPIC

LuxCoreRender

Scene: DLSC

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSCF33 Workstation BetaF32 Workstation UpdatedF32 Workstation0.49050.9811.47151.9622.4525SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 32.182.172.17MIN: 2.09 / MAX: 2.25MIN: 2.08 / MAX: 2.25MIN: 2.08 / MAX: 2.25

dav1d

Video Input: Chimera 1080p 10-bit

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitF32 WorkstationF33 Workstation BetaF32 Workstation Updated306090120150SE +/- 0.07, N = 3SE +/- 0.29, N = 3SE +/- 0.15, N = 3133.76133.16133.15MIN: 86.26 / MAX: 301.72MIN: 85.58 / MAX: 304.15MIN: 85.51 / MAX: 306.091. (CC) gcc options: -pthread

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pF32 WorkstationF33 Workstation BetaF32 Workstation Updated1020304050SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 342.0341.8541.851. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Unigine Superposition

Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: High - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: High - Renderer: OpenGLF33 Workstation BetaF32 Workstation UpdatedF32 Workstation1020304050SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 345.345.245.1MAX: 54.1MAX: 54MAX: 53.8

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileF33 Workstation BetaF32 WorkstationF32 Workstation Updated30K60K90K120K150KSE +/- 66.24, N = 3SE +/- 319.30, N = 3SE +/- 84.31, N = 3148309148849148954

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta0.21670.43340.65010.86681.0835SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 30.9630.9630.959-ldl-ldl1. (CXX) g++ options: -O2 -pthread -lrt -lpthread -lm

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 0F32 WorkstationF33 Workstation BetaF32 Workstation Updated1632486480SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.54, N = 373.0573.0973.351. (CXX) g++ options: -O3 -fPIC

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: CPU-OnlyF32 WorkstationF33 Workstation BetaF32 Workstation Updated4080120160200SE +/- 0.40, N = 3SE +/- 0.07, N = 3SE +/- 0.22, N = 3160.54161.08161.16

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveF32 WorkstationF32 Workstation UpdatedF33 Workstation Beta4080120160200SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.36, N = 3168.75168.89169.391. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

x265

H.265 1080p Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video EncodingF33 Workstation BetaF32 Workstation UpdatedF32 Workstation1632486480SE +/- 0.10, N = 3SE +/- 0.53, N = 3SE +/- 0.20, N = 373.0372.7872.761. (CXX) g++ options: -O2 -rdynamic -lpthread -lrt -ldl

NCNN

Target: CPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetF33 Workstation BetaF32 Workstation UpdatedF32 Workstation48121620SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 314.1314.1614.18MIN: 13.69 / MAX: 19.58MIN: 13.79 / MAX: 30.35MIN: 13.9 / MAX: 23.631. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin ProteinF32 WorkstationF33 Workstation BetaF32 Workstation Updated246810SE +/- 0.006, N = 3SE +/- 0.078, N = 3SE +/- 0.032, N = 38.4528.4308.4241. (CXX) g++ options: -O2 -pthread -lm

Zstd Compression

Compression Level: 19

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19F32 WorkstationF33 Workstation BetaF32 Workstation Updated714212835SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 330.330.230.21. (CC) gcc options: -O3 -pthread -lz -llzma

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterF33 Workstation BetaF32 Workstation UpdatedF32 Workstation48121620SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 317.3017.3517.361. (CXX) g++ options: -O2 -lOpenCL

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CPU-OnlyF32 WorkstationF33 Workstation BetaF32 Workstation Updated306090120150SE +/- 0.15, N = 3SE +/- 0.29, N = 3SE +/- 0.18, N = 3114.03114.04114.33

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta30K60K90K120K150KSE +/- 101.41, N = 3SE +/- 16.09, N = 3SE +/- 27.09, N = 3117787118059118095

glibc bench

Benchmark: pthread_once

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceF32 Workstation UpdatedF33 Workstation BetaF32 Workstation0.2970.5940.8911.1881.485SE +/- 0.00312, N = 3SE +/- 0.00071, N = 3SE +/- 0.00022, N = 31.316411.318431.31984

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3F32 WorkstationF33 Workstation BetaF32 Workstation Updated0.90681.81362.72043.62724.534SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 34.024.024.03MIN: 3.82 / MAX: 6.61MIN: 3.75 / MAX: 8.85MIN: 3.8 / MAX: 11.571. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian DragonF32 Workstation UpdatedF33 Workstation BetaF32 Workstation510152025SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 320.3820.3720.33MIN: 20.24 / MAX: 20.85MIN: 20.19 / MAX: 20.81MIN: 20.15 / MAX: 20.73

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 100

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 100F32 WorkstationF32 Workstation UpdatedF33 Workstation Beta20K40K60K80K100KSE +/- 6.96, N = 3SE +/- 38.37, N = 3SE +/- 72.57, N = 31086631087801089191. (CXX) g++ options: -fPIC -O2 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lhdf5_cpp -lhdf5 -lhdf5_hl_cpp -lhdf5_hl -llmdb -lopenblas

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1F33 Workstation BetaF32 WorkstationF32 Workstation Updated60120180240300SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 3260.32260.73260.93MIN: 259.47 / MAX: 266.97MIN: 259.81 / MAX: 265.49MIN: 259.87 / MAX: 265.661. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O2 -rdynamic -ldl

Darktable

Test: Boat - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.2.1Test: Boat - Acceleration: CPU-onlyF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta48121620SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 314.1514.1714.18

glibc bench

Benchmark: cos

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cosF33 Workstation BetaF32 WorkstationF32 Workstation Updated918273645SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 338.7438.7538.82

Incompact3D

Input: Cylinder

OpenBenchmarking.orgSeconds, Fewer Is BetterIncompact3D 2020-09-17Input: CylinderF32 WorkstationF33 Workstation BetaF32 Workstation Updated50100150200250SE +/- 0.07, N = 3SE +/- 0.22, N = 3SE +/- 0.49, N = 3238.62238.75239.091. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Embree

Binary: Pathtracer - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian DragonF33 Workstation BetaF32 Workstation UpdatedF32 Workstation48121620SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 317.7017.6717.67MIN: 17.48 / MAX: 18.12MIN: 17.42 / MAX: 18.09MIN: 17.39 / MAX: 18.1

Basemark GPU

Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: High

OpenBenchmarking.orgFPS, More Is BetterBasemark GPU 1.2Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: HighF32 WorkstationF33 Workstation BetaF32 Workstation Updated1020304050SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 345.4545.4145.37MIN: 38.39 / MAX: 62.12MIN: 37.47 / MAX: 61.91MIN: 38.08 / MAX: 61.86

glibc bench

Benchmark: sin

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinF32 Workstation UpdatedF33 Workstation BetaF32 Workstation918273645SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 338.3338.3338.39

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.2.1Test: Masskrug - Acceleration: CPU-onlyF33 Workstation BetaF32 Workstation UpdatedF32 Workstation0.91671.83342.75013.66684.5835SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 34.0674.0734.074

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatF33 Workstation BetaF32 Workstation UpdatedF32 Workstation20K40K60K80K100KSE +/- 80.77, N = 3SE +/- 29.24, N = 3SE +/- 2.96, N = 3114727114742114879

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KF33 Workstation BetaF32 Workstation UpdatedF32 Workstation4080120160200SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 3185.58185.52185.43MIN: 158.75 / MAX: 192.96MIN: 159.04 / MAX: 193.53MIN: 160.86 / MAX: 193.121. (CC) gcc options: -pthread

glibc bench

Benchmark: tanh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanhF33 Workstation BetaF32 Workstation UpdatedF32 Workstation3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 310.4010.4110.41

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetF32 Workstation UpdatedF33 Workstation BetaF32 Workstation40K80K120K160K200KSE +/- 24.58, N = 3SE +/- 22.10, N = 3SE +/- 22.43, N = 3167905167925167977

glibc bench

Benchmark: atanh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: atanhF32 Workstation UpdatedF32 WorkstationF33 Workstation Beta3691215SE +/- 0.00341, N = 3SE +/- 0.00186, N = 3SE +/- 0.00191, N = 39.406949.408639.41062

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4F32 Workstation UpdatedF32 WorkstationF33 Workstation Beta500K1000K1500K2000K2500KSE +/- 187.47, N = 3SE +/- 101.49, N = 3SE +/- 452.30, N = 3237794723786502378677

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2F32 Workstation UpdatedF32 WorkstationF33 Workstation Beta500K1000K1500K2000K2500KSE +/- 145.03, N = 3SE +/- 138.60, N = 3SE +/- 385.59, N = 3214457021447072145147

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2F32 Workstation UpdatedF33 Workstation BetaF32 Workstation0.72681.45362.18042.90723.634SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 33.203.203.23MIN: 2.97 / MAX: 9.82MIN: 2.88 / MAX: 7.09MIN: 2.95 / MAX: 9.291. (CXX) g++ options: -O2 -rdynamic -lgomp -lpthread

Renaissance

Test: Apache Spark PageRank

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRankF33 Workstation BetaF32 Workstation UpdatedF32 Workstation8001600240032004000SE +/- 38.90, N = 24SE +/- 33.46, N = 25SE +/- 44.56, N = 53086.503559.833732.07


Phoronix Test Suite v10.8.5