Ryzen 7 1700

AMD Ryzen 7 1700 Eight-Core testing with a MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS) and AMD Radeon RX 470/480/570/570X/580/580X/590 8GB on Ubuntu 21.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2105139-IB-RYZEN717089
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

AV1 4 Tests
Bioinformatics 3 Tests
C++ Boost Tests 3 Tests
Timed Code Compilation 6 Tests
C/C++ Compiler Tests 10 Tests
CPU Massive 14 Tests
Creator Workloads 22 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 3 Tests
Encoding 6 Tests
Game Development 6 Tests
HPC - High Performance Computing 7 Tests
Imaging 6 Tests
Machine Learning 2 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 3 Tests
Multi-Core 17 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 5 Tests
Programmer / Developer System Benchmarks 7 Tests
Python Tests 7 Tests
Scientific Computing 5 Tests
Software Defined Radio 3 Tests
Server CPU Tests 12 Tests
Single-Threaded 3 Tests
Telephony 2 Tests
Texture Compression 4 Tests
Video Encoding 6 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
1
May 11 2021
  17 Hours, 35 Minutes
2
May 12 2021
  6 Hours, 6 Minutes
3
May 12 2021
  6 Hours, 5 Minutes
Invert Hiding All Results Option
  9 Hours, 56 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

1

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001137
Python Notes: Python 3.9.4
Security Notes: 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

2

3

Processor: AMD Ryzen 7 1700 Eight-Core @ 3.00GHz (8 Cores / 16 Threads), Motherboard: MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS), Chipset: AMD 17h, Memory: 16GB, Disk: 120GB Samsung SSD 840, Graphics: AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1266/2000MHz), Audio: AMD Ellesmere HDMI Audio, Monitor: VA2431, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 21.04, Kernel: 5.11.0-17-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.0.1 (LLVM 11.0.1), Vulkan: 1.2.145, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080

Ryzen 7 1700ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen 7 1700 Eight-Core @ 3.00GHz (8 Cores / 16 Threads)MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS)AMD 17h16GB120GB Samsung SSD 840AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1266/2000MHz)AMD Ellesmere HDMI AudioVA2431Realtek RTL8111/8168/8411Ubuntu 21.045.11.0-17-generic (x86_64)GNOME Shell 3.38.4X Server + Wayland4.6 Mesa 21.0.1 (LLVM 11.0.1)1.2.145GCC 10.3.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001137Python Details- Python 3.9.4Security Details- 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite100%106%113%119%126%Timed HMMer SearchTimed MrBayes AnalysisQMCPACKVOSK Speech Recognition ToolkitGoogle DracoQuantLibXcompact3d Incompact3dStockfishSVT-VP9libgav1Timed Linux Kernel CompilationBotanKTX-Software toktxEmbreeCP2K Molecular DynamicsOCRMyPDFDarktableRawTherapeeTimed LLVM CompilationMobile Neural NetworkOpenSCADGNU GMP GMPbenchTimed Wasmer CompilationGIMPASTC EncoderZstd CompressionTimed Erlang/OTP CompilationLiquid-DSPXmrigSVT-AV1Basis UniversalBlenderlibavif avifencGNU RadioLuaRadioPJSIPChia Blockchain VDFTimed Godot Game Engine CompilationHuginHelsingSVT-HEVCAOM AV1libjpeg-turbo tjbenchoneDNNTimed Node.js Compilation

Ryzen 7 1700hmmer: Pfam Database Searchbotan: CAST-256mrbayes: Primate Phylogeny Analysisqmcpack: simple-H2Obotan: CAST-256 - Decryptvosk: gnuradio: FIR Filtergnuradio: Five Back to Back FIR Filtersquantlib: toktx: Zstd Compression 9incompact3d: input.i3d 129 Cells Per Directionsvt-vp9: Visual Quality Optimized - Bosphorus 1080pcompress-zstd: 8, Long Mode - Compression Speedgnuradio: Signal Source (Cosine)draco: Church Facadecompress-zstd: 19, Long Mode - Compression Speeddarktable: Server Rack - CPU-onlystockfish: Total Timegnuradio: FM Deemphasis Filterincompact3d: input.i3d 193 Cells Per Directionlibgav1: Chimera 1080p 10-bitlibgav1: Summer Nature 4Klibgav1: Summer Nature 1080pluaradio: Five Back to Back FIR Filtersgnuradio: Hilbert Transformaom-av1: Speed 6 Two-Pass - Bosphorus 1080pmnn: MobileNetV2_224liquid-dsp: 2 - 256 - 57mnn: mobilenet-v1-1.0gimp: resizeembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer - Crownastcenc: Mediumbuild-linux-kernel: Time To Compilesvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pcompress-zstd: 3 - Compression Speedopenscad: Leonardo Phone Case Slimembree: Pathtracer - Asian Dragongnuradio: IIR Filteraom-av1: Speed 6 Realtime - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 4Kavifenc: 6, Losslesstoktx: Zstd Compression 19svt-vp9: VMAF Optimized - Bosphorus 1080paom-av1: Speed 8 Realtime - Bosphorus 1080pgimp: auto-levelsembree: Pathtracer ISPC - Crownsvt-av1: Preset 8 - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 1080pblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlylibgav1: Chimera 1080pcp2k: Fayalite-FISTbotan: Blowfishdraco: Lionbotan: AES-256mnn: resnet-v2-50openscad: Mini-ITX Casecompress-zstd: 19, Long Mode - Decompression Speedavifenc: 2ocrmypdf: Processing 60 Page PDF Documentcompress-zstd: 19 - Decompression Speedbasis: UASTC Level 0build-llvm: Unix Makefilesbotan: ChaCha20Poly1305onednn: Recurrent Neural Network Inference - f32 - CPUrawtherapee: Total Benchmark Timebotan: ChaCha20Poly1305 - Decrypttoktx: UASTC 3 + Zstd Compression 19openscad: Pistolgimp: unsharp-maskcompress-zstd: 3, Long Mode - Decompression Speedonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUxmrig: Wownero - 1Maom-av1: Speed 4 Two-Pass - Bosphorus 1080ponednn: IP Shapes 3D - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUcompress-zstd: 19 - Compression Speedgmpbench: Total Timeblender: Pabellon Barcelona - CPU-Onlyonednn: Deconvolution Batch shapes_1d - f32 - CPUluaradio: FM Deemphasis Filteronednn: Recurrent Neural Network Training - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUchia-vdf: Square Plain C++build-wasmer: Time To Compilegimp: rotatepjsip: OPTIONS, Statelesssvt-av1: Preset 4 - Bosphorus 1080pcompress-zstd: 8 - Decompression Speedembree: Pathtracer - Asian Dragon Objcompress-zstd: 3, Long Mode - Compression Speedcompress-zstd: 8, Long Mode - Decompression Speedliquid-dsp: 1 - 256 - 57botan: AES-256 - Decryptavifenc: 0botan: Twofish - Decryptdarktable: Masskrug - CPU-onlybotan: Twofishcompress-zstd: 8 - Compression Speedonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUbuild-erlang: Time To Compileaom-av1: Speed 8 Realtime - Bosphorus 4Kopenscad: Retro Caravifenc: 10mnn: SqueezeNetV1.0darktable: Server Room - CPU-onlybotan: KASUMIluaradio: Complex Phaseaom-av1: Speed 6 Two-Pass - Bosphorus 4Kaom-av1: Speed 4 Two-Pass - Bosphorus 4Kbasis: UASTC Level 3onednn: Convolution Batch Shapes Auto - f32 - CPUmnn: inception-v3liquid-dsp: 8 - 256 - 57basis: ETC1Sonednn: IP Shapes 1D - u8s8f32 - CPUavifenc: 10, Losslessaom-av1: Speed 9 Realtime - Bosphorus 4Ktoktx: UASTC 3blender: Barbershop - CPU-Onlyonednn: Recurrent Neural Network Training - u8s8f32 - CPUpjsip: OPTIONS, Statefulbotan: Blowfish - Decryptdarktable: Boat - CPU-onlyluaradio: Hilbert Transformliquid-dsp: 16 - 256 - 57chia-vdf: Square Assembly Optimizedembree: Pathtracer ISPC - Asian Dragon Objblender: Fishy Cat - CPU-Onlypjsip: INVITExmrig: Monero - 1Msvt-hevc: 10 - Bosphorus 1080phelsing: 12 digitonednn: Deconvolution Batch shapes_3d - f32 - CPUbasis: UASTC Level 2liquid-dsp: 4 - 256 - 57onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUaom-av1: Speed 6 Realtime - Bosphorus 4Kopenscad: Projector Mount Swivelonednn: Recurrent Neural Network Inference - u8s8f32 - CPUavifenc: 6botan: KASUMI - Decryptonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUsvt-hevc: 1 - Bosphorus 1080pbuild-godot: Time To Compilebuild-nodejs: Time To Compilebuild-llvm: Ninjahugin: Panorama Photo Assistant + Stitching Timetoktx: UASTC 4 + Zstd Compression 19astcenc: Thoroughsvt-av1: Preset 4 - Bosphorus 4Konednn: IP Shapes 1D - f32 - CPUsvt-hevc: 7 - Bosphorus 1080ptjbench: Decompression Throughputastcenc: Exhaustivehelsing: 14 digitaom-av1: Speed 0 Two-Pass - Bosphorus 1080paom-av1: Speed 0 Two-Pass - Bosphorus 4K123163.481120.146162.68934.929120.13825.081430.4408.71948.63.98444.840105370.87276.72115.61010818.30.26516528903490.6160.89988223.4642.15108.36357.9321.79.096.152889466675.72613.5147.32097.05288.7059126.19490.441755.926.6898.3451463.713.157.70282.13729.27584.5254.7619.0416.306630.01363.08223.96674.0881.461346.058367.21472434731.68654.29866.6202349.158.82633.6592370.910.8751114.204420.1364690.2286.385418.04626.799145.59121.4332696.123.24383089.62.8512.79254718.5420.64331.2762.5411.9630261.68939.305.2426812533396.05117.285405062.5832623.57.4865382.92808.9468756674755.796111.305309.8837.124305.202210.82.766918948.72169.28725.906.8304.53611.6175.00177.600431.13.451.7486.03525.233363.97434291333336.5858.256088.16535.8018.545948.178941.145544368.6767.61179.33072233331131006.3926325.3235781811.6140.329.16917.066845.8961730733336.112838.910638.4513.2094712.7220.17575.32511.80034.72194.528710.8311079.38664.343510.88225.05060.7518.9215766.65144.340109192.8355929.9450.190.06205.474106.59183.63438.808108.73827.587453.2399.71847.83.98645.207588267.97279.62035.61050418.60.27216276123507.1165.90016222.8241.06105.61366.7314.28.946.293892780005.8113.7137.16236.93448.7646128.90688.581766.727.0238.1847457.413.277.65882.91729.03182.9953.919.3786.22429.65264.14222.38682.880.991366.873370.95573444726.20855.01667.4192317.959.52533.7612373.410.9851103.22420.1094712.3985.398417.92326.496146.29921.5082686.523.15363122.72.8712.71714671.5520.84294.1765.6412.004259.28930.235.2564712520096.15317.131408702.572616.27.422380.92833.1472720004737.261111.581311.8947.177307.407210.32.78658976168.18325.916.8114.51311.665.01577.444431.33.471.7486.08625.376963.85634260000036.7718.215488.15835.9618.586945.698903.845541370.1247.59879.23060700001133006.3704324.8935841811.1140.529.14217.016645.931731500006.123428.921978.4413.2054706.7120.21475.48211.80394.72194.874709.6211081.16164.259511.48725.0420.7518.9289366.72144.204431192.7207929.5290.190.06178.739121.333183.69739.389121.59427.563423.8425.51834.84.17346.936069569.95268.72102.41049017.90.27515984772492.2165.54849222.8641.43106.63364.1318.19.156.221909800005.85413.8167.21116.90138.8936127.87889.521791.426.4888.2261466.213.027.55881.37829.57283.5753.819.1346.332230.16463.52226.11685.380.211361.384365.52173464792.56555.0666.5072336.458.75834.0982343.611.011100.607415.0434745.0185.579413.30926.742144.67121.6692715.823.4063093.22.8812.65994707.0320.64289.9769.7512.0754259.38858.045.2906412420095.28917.193406542.5932600.57.4802384.22811.1469760004777.079110.673309.5117.136305.746209.32.770878917.04169.13226.076.7864.54111.6885.03177.903428.83.471.7586.52825.258363.61334437000036.6448.226018.19735.9418.625944.178939.115563369.8947.62779.53071400001135006.3733325.9935721805.9140.759.15317.026746.0271735300006.127678.900658.4613.1784717.6820.22275.3111.77714.73194.553710.2181079.32864.239510.72725.07640.758.9180166.65144.347582192.7518929.5550.190.06OpenBenchmarking.org

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.2Pfam Database Search12350100150200250SE +/- 0.23, N = 3163.48205.47178.741. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.2Pfam Database Search1234080120160200Min: 163.13 / Avg: 163.48 / Max: 163.911. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm -lmpi

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256123306090120150SE +/- 0.25, N = 3120.15106.59121.331. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-25612320406080100Min: 119.75 / Avg: 120.15 / Max: 120.61. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Timed MrBayes Analysis

This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysis1234080120160200SE +/- 0.48, N = 3162.69183.63183.701. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysis123306090120150Min: 162.15 / Avg: 162.69 / Max: 163.641. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm

QMCPACK

QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. QMCPACK is an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids. QMCPACK is supported by the U.S. Department of Energy. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.11Input: simple-H2O123918273645SE +/- 0.34, N = 1534.9338.8139.391. (CXX) g++ options: -fopenmp -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -fomit-frame-pointer -ffast-math -pthread -lm -ldl
OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.11Input: simple-H2O123816243240Min: 33.94 / Avg: 34.93 / Max: 39.241. (CXX) g++ options: -fopenmp -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -fomit-frame-pointer -ffast-math -pthread -lm -ldl

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - Decrypt123306090120150SE +/- 0.42, N = 3120.14108.74121.591. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - Decrypt12320406080100Min: 119.32 / Avg: 120.14 / Max: 120.721. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

VOSK Speech Recognition Toolkit

VOSK is an open-source offline speech recognition API/toolkit. VOSK supports speech recognition in 17 languages and has a variety of models available and interfaces for different programming languages. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterVOSK Speech Recognition Toolkit 0.3.21123612182430SE +/- 0.23, N = 1325.0827.5927.56
OpenBenchmarking.orgSeconds, Fewer Is BetterVOSK Speech Recognition Toolkit 0.3.21123612182430Min: 24.44 / Avg: 25.08 / Max: 27.74

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filter123100200300400500SE +/- 2.21, N = 3430.4453.2423.81. 3.8.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filter12380160240320400Min: 427.9 / Avg: 430.4 / Max: 434.81. 3.8.2.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR Filters12390180270360450SE +/- 4.60, N = 3408.7399.7425.51. 3.8.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR Filters12380160240320400Min: 402.6 / Avg: 408.67 / Max: 417.71. 3.8.2.0

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.21123400800120016002000SE +/- 5.20, N = 31948.61847.81834.81. (CXX) g++ options: -O3 -march=native -rdynamic
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.2112330060090012001500Min: 1941.2 / Avg: 1948.57 / Max: 1958.61. (CXX) g++ options: -O3 -march=native -rdynamic

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 91230.93891.87782.81673.75564.6945SE +/- 0.027, N = 33.9843.9864.173
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9123246810Min: 3.95 / Avg: 3.98 / Max: 4.04

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Direction1231122334455SE +/- 0.42, N = 744.8445.2146.941. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Direction1231020304050Min: 43.25 / Avg: 44.84 / Max: 45.911. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p1231632486480SE +/- 0.36, N = 370.8767.9769.951. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p1231428425670Min: 70.48 / Avg: 70.87 / Max: 71.591. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression Speed12360120180240300SE +/- 2.02, N = 3276.7279.6268.71. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression Speed12350100150200250Min: 272.8 / Avg: 276.73 / Max: 279.51. (CC) gcc options: -O3 -pthread -lz

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)1235001000150020002500SE +/- 6.26, N = 32115.62035.62102.41. 3.8.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)123400800120016002000Min: 2108.9 / Avg: 2115.6 / Max: 2128.11. 3.8.2.0

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.4.1Model: Church Facade1232K4K6K8K10KSE +/- 129.55, N = 31010810504104901. (CXX) g++ options: -O3
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.4.1Model: Church Facade1232K4K6K8K10KMin: 9956 / Avg: 10108.33 / Max: 103661. (CXX) g++ options: -O3

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Compression Speed123510152025SE +/- 0.20, N = 518.318.617.91. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Compression Speed123510152025Min: 17.8 / Avg: 18.32 / Max: 18.81. (CC) gcc options: -O3 -pthread -lz

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Server Rack - Acceleration: CPU-only1230.06190.12380.18570.24760.3095SE +/- 0.002, N = 150.2650.2720.275
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Server Rack - Acceleration: CPU-only12312345Min: 0.26 / Avg: 0.27 / Max: 0.28

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Time1234M8M12M16M20MSE +/- 165498.24, N = 61652890316276123159847721. (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
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Time1233M6M9M12M15MMin: 15920494 / Avg: 16528903.33 / Max: 169732341. (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

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filter123110220330440550SE +/- 2.53, N = 3490.6507.1492.21. 3.8.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filter12390180270360450Min: 487.3 / Avg: 490.63 / Max: 495.61. 3.8.2.0

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction1234080120160200SE +/- 0.24, N = 3160.90165.90165.551. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction123306090120150Min: 160.56 / Avg: 160.9 / Max: 161.351. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080p 10-bit123612182430SE +/- 0.04, N = 323.4622.8222.861. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080p 10-bit123510152025Min: 23.39 / Avg: 23.46 / Max: 23.541. (CXX) g++ options: -O3 -lpthread -lrt

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 4K1231020304050SE +/- 0.26, N = 342.1541.0641.431. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 4K123918273645Min: 41.75 / Avg: 42.15 / Max: 42.641. (CXX) g++ options: -O3 -lpthread -lrt

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 1080p12320406080100SE +/- 0.55, N = 3108.36105.61106.631. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Summer Nature 1080p12320406080100Min: 107.79 / Avg: 108.36 / Max: 109.461. (CXX) g++ options: -O3 -lpthread -lrt

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR Filters12380160240320400SE +/- 2.14, N = 3357.9366.7364.1
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR Filters12370140210280350Min: 355 / Avg: 357.93 / Max: 362.1

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert Transform12370140210280350SE +/- 3.38, N = 3321.7314.2318.11. 3.8.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert Transform12360120180240300Min: 315.2 / Avg: 321.73 / Max: 326.51. 3.8.2.0

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p1233691215SE +/- 0.03, N = 39.098.949.151. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p1233691215Min: 9.04 / Avg: 9.09 / Max: 9.121. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: MobileNetV2_224123246810SE +/- 0.045, N = 36.1526.2936.221MIN: 5.63 / MAX: 8.06MIN: 5.85 / MAX: 7.96MIN: 5.8 / MAX: 6.751. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: MobileNetV2_2241233691215Min: 6.07 / Avg: 6.15 / Max: 6.221. (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

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 5712320M40M60M80M100MSE +/- 191972.51, N = 38894666789278000909800001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 5712316M32M48M64M80MMin: 88567000 / Avg: 88946666.67 / Max: 891860001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: mobilenet-v1-1.01231.31722.63443.95165.26886.586SE +/- 0.048, N = 35.7265.8105.854MIN: 5.24 / MAX: 10.6MIN: 5.41 / MAX: 8.95MIN: 5.44 / MAX: 18.41. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: mobilenet-v1-1.0123246810Min: 5.64 / Avg: 5.73 / Max: 5.81. (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

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: resize12348121620SE +/- 0.07, N = 313.5113.7113.82
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: resize12348121620Min: 13.4 / Avg: 13.51 / Max: 13.63

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon123246810SE +/- 0.0414, N = 37.32097.16237.2111MIN: 7.2 / MAX: 7.47MIN: 7.14 / MAX: 7.25MIN: 7.19 / MAX: 7.27
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon1233691215Min: 7.24 / Avg: 7.32 / Max: 7.37

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Crown123246810SE +/- 0.0473, N = 37.05286.93446.9013MIN: 6.91 / MAX: 7.21MIN: 6.89 / MAX: 7.07MIN: 6.86 / MAX: 7.03
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Crown1233691215Min: 6.96 / Avg: 7.05 / Max: 7.11

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Medium123246810SE +/- 0.0174, N = 38.70598.76468.89361. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Medium1233691215Min: 8.67 / Avg: 8.71 / Max: 8.721. (CXX) g++ options: -O3 -flto -pthread

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To Compile123306090120150SE +/- 0.69, N = 3126.19128.91127.88
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To Compile12320406080100Min: 125.29 / Avg: 126.19 / Max: 127.54

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p12320406080100SE +/- 0.42, N = 390.4488.5889.521. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p12320406080100Min: 89.89 / Avg: 90.44 / Max: 91.261. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3 - Compression Speed123400800120016002000SE +/- 7.85, N = 31755.91766.71791.41. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3 - Compression Speed12330060090012001500Min: 1748 / Avg: 1755.9 / Max: 1771.61. (CC) gcc options: -O3 -pthread -lz

OpenSCAD

OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Leonardo Phone Case Slim123612182430SE +/- 0.07, N = 326.6927.0226.491. OpenSCAD version 2021.01
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Leonardo Phone Case Slim123612182430Min: 26.57 / Avg: 26.69 / Max: 26.81. OpenSCAD version 2021.01

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon123246810SE +/- 0.0922, N = 38.34518.18478.2261MIN: 8.16 / MAX: 8.6MIN: 8.16 / MAX: 8.27MIN: 8.17 / MAX: 8.35
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon1233691215Min: 8.19 / Avg: 8.35 / Max: 8.51

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filter123100200300400500SE +/- 1.40, N = 3463.7457.4466.21. 3.8.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filter12380160240320400Min: 461 / Avg: 463.7 / Max: 465.71. 3.8.2.0

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p1233691215SE +/- 0.11, N = 313.1513.2713.021. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p12348121620Min: 12.99 / Avg: 13.15 / Max: 13.351. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4K123246810SE +/- 0.023, N = 37.7027.6587.5581. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4K1233691215Min: 7.66 / Avg: 7.7 / Max: 7.741. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Lossless12320406080100SE +/- 0.92, N = 482.1482.9281.381. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Lossless1231632486480Min: 79.88 / Avg: 82.14 / Max: 83.91. (CXX) g++ options: -O3 -fPIC -lm

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19123714212835SE +/- 0.04, N = 329.2829.0329.57
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19123714212835Min: 29.22 / Avg: 29.28 / Max: 29.36

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080p12320406080100SE +/- 0.96, N = 484.5282.9983.571. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080p1231632486480Min: 81.78 / Avg: 84.52 / Max: 86.021. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p1231224364860SE +/- 0.12, N = 354.7653.9053.801. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p1231122334455Min: 54.58 / Avg: 54.76 / Max: 54.991. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: auto-levels123510152025SE +/- 0.07, N = 319.0419.3819.13
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: auto-levels123510152025Min: 18.95 / Avg: 19.04 / Max: 19.18

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Crown123246810SE +/- 0.0101, N = 36.30666.22406.3322MIN: 6.25 / MAX: 6.43MIN: 6.19 / MAX: 6.32MIN: 6.27 / MAX: 6.45
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Crown1233691215Min: 6.29 / Avg: 6.31 / Max: 6.33

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 1080p123714212835SE +/- 0.08, N = 330.0129.6530.161. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 1080p123714212835Min: 29.9 / Avg: 30.01 / Max: 30.171. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p1231428425670SE +/- 0.40, N = 363.0864.1463.521. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p1231326395265Min: 62.28 / Avg: 63.08 / Max: 63.591. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-Only12350100150200250SE +/- 1.25, N = 3223.96222.38226.11
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-Only1234080120160200Min: 222.16 / Avg: 223.96 / Max: 226.37

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-Only123150300450600750SE +/- 3.41, N = 3674.08682.80685.30
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-Only123120240360480600Min: 670.21 / Avg: 674.08 / Max: 680.88

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080p12320406080100SE +/- 0.07, N = 381.4680.9980.211. (CXX) g++ options: -O3 -lpthread -lrt
OpenBenchmarking.orgFPS, More Is Betterlibgav1 0.16.3Video Input: Chimera 1080p1231632486480Min: 81.33 / Avg: 81.46 / Max: 81.551. (CXX) g++ options: -O3 -lpthread -lrt

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 8.1Input: Fayalite-FIST123300600900120015001346.061366.871361.38

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish12380160240320400SE +/- 1.32, N = 3367.21370.96365.521. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish12370140210280350Min: 364.57 / Avg: 367.21 / Max: 368.611. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.4.1Model: Lion12316003200480064008000SE +/- 68.00, N = 37243734473461. (CXX) g++ options: -O3
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.4.1Model: Lion12313002600390052006500Min: 7113 / Avg: 7242.67 / Max: 73431. (CXX) g++ options: -O3

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-25612310002000300040005000SE +/- 5.53, N = 34731.694726.214792.571. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-2561238001600240032004000Min: 4723.82 / Avg: 4731.69 / Max: 4742.351. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-501231224364860SE +/- 0.32, N = 354.3055.0255.06MIN: 52.63 / MAX: 80.21MIN: 53.44 / MAX: 71.62MIN: 53.73 / MAX: 66.281. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-501231122334455Min: 53.82 / Avg: 54.3 / Max: 54.911. (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

OpenSCAD

OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Mini-ITX Case1231530456075SE +/- 0.25, N = 366.6267.4266.511. OpenSCAD version 2021.01
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Mini-ITX Case1231326395265Min: 66.24 / Avg: 66.62 / Max: 67.11. OpenSCAD version 2021.01

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression Speed1235001000150020002500SE +/- 8.98, N = 52349.12317.92336.41. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression Speed123400800120016002000Min: 2326.6 / Avg: 2349.08 / Max: 2374.51. (CC) gcc options: -O3 -pthread -lz

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 21231326395265SE +/- 0.20, N = 358.8359.5358.761. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 21231224364860Min: 58.56 / Avg: 58.83 / Max: 59.221. (CXX) g++ options: -O3 -fPIC -lm

OCRMyPDF

OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF Document123816243240SE +/- 0.21, N = 333.6633.7634.10
OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF Document123714212835Min: 33.29 / Avg: 33.66 / Max: 34

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression Speed1235001000150020002500SE +/- 24.46, N = 32370.92373.42343.61. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression Speed123400800120016002000Min: 2326.1 / Avg: 2370.9 / Max: 2410.31. (CC) gcc options: -O3 -pthread -lz

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 01233691215SE +/- 0.05, N = 310.8810.9911.011. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 01233691215Min: 10.77 / Avg: 10.88 / Max: 10.951. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix Makefiles1232004006008001000SE +/- 6.86, N = 31114.201103.221100.61
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Unix Makefiles1232004006008001000Min: 1100.49 / Avg: 1114.2 / Max: 1121.16

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly130512390180270360450SE +/- 1.15, N = 3420.14420.11415.041. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly130512370140210280350Min: 418.12 / Avg: 420.14 / Max: 422.121. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU12310002000300040005000SE +/- 13.79, N = 34690.224712.394745.01MIN: 4641.16MIN: 4693.79MIN: 4725.581. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1238001600240032004000Min: 4664.64 / Avg: 4690.22 / Max: 4711.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Time12320406080100SE +/- 0.12, N = 386.3985.4085.581. RawTherapee, version 5.8, command line.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Time1231632486480Min: 86.17 / Avg: 86.39 / Max: 86.581. RawTherapee, version 5.8, command line.

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - Decrypt12390180270360450SE +/- 1.22, N = 3418.05417.92413.311. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - Decrypt12370140210280350Min: 415.74 / Avg: 418.05 / Max: 419.891. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19123612182430SE +/- 0.03, N = 326.8026.5026.74
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19123612182430Min: 26.74 / Avg: 26.8 / Max: 26.85

OpenSCAD

OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Pistol123306090120150SE +/- 0.64, N = 3145.59146.30144.671. OpenSCAD version 2021.01
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Pistol123306090120150Min: 144.41 / Avg: 145.59 / Max: 146.611. OpenSCAD version 2021.01

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: unsharp-mask123510152025SE +/- 0.05, N = 321.4321.5121.67
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: unsharp-mask123510152025Min: 21.33 / Avg: 21.43 / Max: 21.5

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Decompression Speed1236001200180024003000SE +/- 16.90, N = 32696.12686.52715.81. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Decompression Speed1235001000150020002500Min: 2674.1 / Avg: 2696.07 / Max: 2729.31. (CC) gcc options: -O3 -pthread -lz

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU123612182430SE +/- 0.13, N = 323.2423.1523.41MIN: 22.46MIN: 22.35MIN: 22.591. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU123510152025Min: 23.04 / Avg: 23.24 / Max: 23.51. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1M1237001400210028003500SE +/- 11.13, N = 33089.63122.73093.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1M1235001000150020002500Min: 3069.1 / Avg: 3089.57 / Max: 3107.41. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p1230.6481.2961.9442.5923.24SE +/- 0.01, N = 32.852.872.881. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p123246810Min: 2.83 / Avg: 2.85 / Max: 2.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU1233691215SE +/- 0.03, N = 312.7912.7212.66MIN: 12.34MIN: 12.3MIN: 12.341. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU12348121620Min: 12.74 / Avg: 12.79 / Max: 12.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU12310002000300040005000SE +/- 12.20, N = 34718.544671.554707.03MIN: 4684.36MIN: 4652.51MIN: 4688.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU1238001600240032004000Min: 4703.35 / Avg: 4718.54 / Max: 4742.671. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression Speed123510152025SE +/- 0.19, N = 320.620.820.61. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression Speed123510152025Min: 20.4 / Avg: 20.63 / Max: 211. (CC) gcc options: -O3 -pthread -lz

GNU GMP GMPbench

GMPbench is a test of the GNU Multiple Precision Arithmetic (GMP) Library. GMPbench is a single-threaded integer benchmark that leverages the GMP library to stress the CPU with widening integer multiplication. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total Time12390018002700360045004331.24294.14289.91. (CC) gcc options: -O3 -fomit-frame-pointer -lm

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-Only123170340510680850SE +/- 0.06, N = 3762.54765.64769.75
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-Only123140280420560700Min: 762.44 / Avg: 762.54 / Max: 762.64

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU1233691215SE +/- 0.02, N = 311.9612.0012.08MIN: 11.24MIN: 11.25MIN: 11.341. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU12348121620Min: 11.94 / Avg: 11.96 / Max: 11.991. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filter12360120180240300SE +/- 0.32, N = 3261.6259.2259.3
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filter12350100150200250Min: 261 / Avg: 261.63 / Max: 262

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU1232K4K6K8K10KSE +/- 24.82, N = 38939.308930.238858.04MIN: 8872.14MIN: 8908.34MIN: 8818.061. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU12316003200480064008000Min: 8898.06 / Avg: 8939.3 / Max: 8983.861. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU1231.19042.38083.57124.76165.952SE +/- 0.00501, N = 35.242685.256475.29064MIN: 4.9MIN: 4.9MIN: 4.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU123246810Min: 5.23 / Avg: 5.24 / Max: 5.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Chia Blockchain VDF

Chia is a blockchain and smart transaction platform based on proofs of space and time rather than proofs of work with other cryptocurrencies. This test profile is benchmarking the CPU performance for Chia VDF performance using the Chia VDF benchmark. The Chia VDF is for the Chia Verifiable Delay Function (Proof of Time). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.1Test: Square Plain C++12330K60K90K120K150KSE +/- 622.72, N = 31253331252001242001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.1Test: Square Plain C++12320K40K60K80K100KMin: 124100 / Avg: 125333.33 / Max: 1261001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To Compile12320406080100SE +/- 0.56, N = 396.0596.1595.291. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To Compile12320406080100Min: 94.94 / Avg: 96.05 / Max: 96.721. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: rotate12348121620SE +/- 0.06, N = 317.2917.1317.19
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.22Test: rotate12348121620Min: 17.17 / Avg: 17.29 / Max: 17.35

PJSIP

PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, Stateless1239K18K27K36K45KSE +/- 185.84, N = 34050640870406541. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, Stateless1237K14K21K28K35KMin: 40306 / Avg: 40505.67 / Max: 408771. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 1080p1230.58341.16681.75022.33362.917SE +/- 0.003, N = 32.5832.5702.5931. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 1080p123246810Min: 2.58 / Avg: 2.58 / Max: 2.591. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Decompression Speed1236001200180024003000SE +/- 13.76, N = 32623.52616.22600.51. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Decompression Speed1235001000150020002500Min: 2596.1 / Avg: 2623.5 / Max: 2639.41. (CC) gcc options: -O3 -pthread -lz

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon Obj123246810SE +/- 0.0270, N = 37.48657.42207.4802MIN: 7.4 / MAX: 7.66MIN: 7.38 / MAX: 7.58MIN: 7.43 / MAX: 7.59
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon Obj1233691215Min: 7.45 / Avg: 7.49 / Max: 7.54

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Compression Speed12380160240320400SE +/- 0.61, N = 3382.9380.9384.21. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Compression Speed12370140210280350Min: 381.8 / Avg: 382.87 / Max: 383.91. (CC) gcc options: -O3 -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression Speed1236001200180024003000SE +/- 11.32, N = 32808.92833.12811.11. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression Speed1235001000150020002500Min: 2786.5 / Avg: 2808.9 / Max: 28231. (CC) gcc options: -O3 -pthread -lz

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 5712310M20M30M40M50MSE +/- 326850.80, N = 34687566747272000469760001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 571238M16M24M32M40MMin: 46458000 / Avg: 46875666.67 / Max: 475200001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - Decrypt12310002000300040005000SE +/- 14.29, N = 34755.804737.264777.081. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - Decrypt1238001600240032004000Min: 4727.63 / Avg: 4755.8 / Max: 4774.131. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 012320406080100SE +/- 0.60, N = 3111.31111.58110.671. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 012320406080100Min: 110.28 / Avg: 111.31 / Max: 112.371. (CXX) g++ options: -O3 -fPIC -lm

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - Decrypt12370140210280350SE +/- 1.12, N = 3309.88311.89309.511. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - Decrypt12360120180240300Min: 307.64 / Avg: 309.88 / Max: 311.141. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Masskrug - Acceleration: CPU-only123246810SE +/- 0.055, N = 37.1247.1777.136
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Masskrug - Acceleration: CPU-only1233691215Min: 7.04 / Avg: 7.12 / Max: 7.23

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish12370140210280350SE +/- 0.26, N = 3305.20307.41305.751. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish12360120180240300Min: 304.84 / Avg: 305.2 / Max: 305.71. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression Speed12350100150200250SE +/- 1.12, N = 3210.8210.3209.31. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression Speed1234080120160200Min: 208.7 / Avg: 210.83 / Max: 212.51. (CC) gcc options: -O3 -pthread -lz

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU1230.6271.2541.8812.5083.135SE +/- 0.00600, N = 32.766912.786502.77087MIN: 2.45MIN: 2.48MIN: 2.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU123246810Min: 2.76 / Avg: 2.77 / Max: 2.781. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU1232K4K6K8K10KSE +/- 9.15, N = 38948.728976.008917.04MIN: 8906.46MIN: 8935.14MIN: 8865.481. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU12316003200480064008000Min: 8930.65 / Avg: 8948.72 / Max: 8960.271. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Timed Erlang/OTP Compilation

This test times how long it takes to compile Erlang/OTP. Erlang is a programming language and run-time for massively scalable soft real-time systems with high availability requirements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To Compile1234080120160200SE +/- 0.50, N = 3169.29168.18169.13
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To Compile123306090120150Min: 168.71 / Avg: 169.29 / Max: 170.29

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K123612182430SE +/- 0.05, N = 325.9025.9126.071. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K123612182430Min: 25.81 / Avg: 25.9 / Max: 25.961. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenSCAD

OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Retro Car123246810SE +/- 0.063, N = 36.8306.8116.7861. OpenSCAD version 2021.01
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Retro Car1233691215Min: 6.75 / Avg: 6.83 / Max: 6.951. OpenSCAD version 2021.01

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 101231.02172.04343.06514.08685.1085SE +/- 0.024, N = 34.5364.5134.5411. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10123246810Min: 4.49 / Avg: 4.54 / Max: 4.571. (CXX) g++ options: -O3 -fPIC -lm

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.01233691215SE +/- 0.12, N = 311.6211.6611.69MIN: 10.75 / MAX: 22.91MIN: 11.07 / MAX: 12.69MIN: 11 / MAX: 13.531. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.01233691215Min: 11.41 / Avg: 11.62 / Max: 11.841. (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

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Server Room - Acceleration: CPU-only1231.1322.2643.3964.5285.66SE +/- 0.012, N = 35.0015.0155.031
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Server Room - Acceleration: CPU-only123246810Min: 4.99 / Avg: 5 / Max: 5.02

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI12320406080100SE +/- 0.19, N = 377.6077.4477.901. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI1231530456075Min: 77.32 / Avg: 77.6 / Max: 77.961. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex Phase12390180270360450SE +/- 0.95, N = 3431.1431.3428.8
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex Phase12380160240320400Min: 429.2 / Avg: 431.07 / Max: 432.3

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K1230.78081.56162.34243.12323.904SE +/- 0.01, N = 33.453.473.471. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K123246810Min: 3.43 / Avg: 3.45 / Max: 3.461. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K1230.39380.78761.18141.57521.969SE +/- 0.00, N = 31.741.741.751. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K123246810Min: 1.74 / Avg: 1.74 / Max: 1.751. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 312320406080100SE +/- 0.06, N = 386.0486.0986.531. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 31231632486480Min: 85.93 / Avg: 86.03 / Max: 86.121. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123612182430SE +/- 0.07, N = 325.2325.3825.26MIN: 21.77MIN: 21.79MIN: 22.271. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123612182430Min: 25.15 / Avg: 25.23 / Max: 25.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v31231428425670SE +/- 0.80, N = 363.9763.8663.61MIN: 61.48 / MAX: 77.64MIN: 62.38 / MAX: 74.45MIN: 62.31 / MAX: 75.871. (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
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v31231326395265Min: 63.1 / Avg: 63.97 / Max: 65.571. (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

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 5712370M140M210M280M350MSE +/- 496700.22, N = 33429133333426000003443700001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 5712360M120M180M240M300MMin: 342320000 / Avg: 342913333.33 / Max: 3439000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1S123816243240SE +/- 0.04, N = 336.5936.7736.641. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1S123816243240Min: 36.51 / Avg: 36.59 / Max: 36.631. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU123246810SE +/- 0.02218, N = 38.256088.215488.22601MIN: 7.33MIN: 7.32MIN: 7.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU1233691215Min: 8.22 / Avg: 8.26 / Max: 8.291. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, Lossless123246810SE +/- 0.009, N = 38.1658.1588.1971. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, Lossless1233691215Min: 8.15 / Avg: 8.17 / Max: 8.181. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K123816243240SE +/- 0.04, N = 335.8035.9635.941. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K123816243240Min: 35.73 / Avg: 35.8 / Max: 35.851. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3123510152025SE +/- 0.01, N = 318.5518.5918.63
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3123510152025Min: 18.53 / Avg: 18.55 / Max: 18.56

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-Only1232004006008001000SE +/- 0.71, N = 3948.17945.69944.17
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-Only123170340510680850Min: 947.23 / Avg: 948.17 / Max: 949.56

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU1232K4K6K8K10KSE +/- 14.07, N = 38941.148903.848939.11MIN: 8888.51MIN: 8873.45MIN: 8913.661. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU12316003200480064008000Min: 8913.27 / Avg: 8941.14 / Max: 8958.441. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

PJSIP

PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, Stateful12312002400360048006000SE +/- 2.89, N = 35544554155631. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, Stateful12310002000300040005000Min: 5539 / Avg: 5544 / Max: 55491. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - Decrypt12380160240320400SE +/- 0.81, N = 3368.68370.12369.891. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - Decrypt12370140210280350Min: 367.43 / Avg: 368.68 / Max: 370.21. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Boat - Acceleration: CPU-only123246810SE +/- 0.008, N = 37.6117.5987.627
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.4.1Test: Boat - Acceleration: CPU-only1233691215Min: 7.6 / Avg: 7.61 / Max: 7.63

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transform12320406080100SE +/- 0.12, N = 379.379.279.5
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transform1231530456075Min: 79.1 / Avg: 79.33 / Max: 79.5

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 5712370M140M210M280M350MSE +/- 231828.48, N = 33072233333060700003071400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 5712350M100M150M200M250MMin: 306760000 / Avg: 307223333.33 / Max: 3074700001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Chia Blockchain VDF

Chia is a blockchain and smart transaction platform based on proofs of space and time rather than proofs of work with other cryptocurrencies. This test profile is benchmarking the CPU performance for Chia VDF performance using the Chia VDF benchmark. The Chia VDF is for the Chia Verifiable Delay Function (Proof of Time). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.1Test: Square Assembly Optimized12320K40K60K80K100KSE +/- 321.46, N = 31131001133001135001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
OpenBenchmarking.orgIPS, More Is BetterChia Blockchain VDF 1.0.1Test: Square Assembly Optimized12320K40K60K80K100KMin: 112500 / Avg: 113100 / Max: 1136001. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon Obj123246810SE +/- 0.0118, N = 36.39266.37046.3733MIN: 6.33 / MAX: 6.49MIN: 6.33 / MAX: 6.46MIN: 6.35 / MAX: 6.44
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon Obj1233691215Min: 6.37 / Avg: 6.39 / Max: 6.41

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-Only12370140210280350SE +/- 0.81, N = 3325.32324.89325.99
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-Only12360120180240300Min: 324.19 / Avg: 325.32 / Max: 326.89

PJSIP

PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: INVITE1238001600240032004000SE +/- 3.84, N = 33578358435721. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: INVITE1236001200180024003000Min: 3571 / Avg: 3578.33 / Max: 35841. (CC) gcc options: -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1M123400800120016002000SE +/- 0.44, N = 31811.61811.11805.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1M12330060090012001500Min: 1810.9 / Avg: 1811.6 / Max: 1812.41. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p123306090120150SE +/- 0.22, N = 3140.32140.52140.751. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p123306090120150Min: 140.02 / Avg: 140.32 / Max: 140.751. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 12 digit1233691215SE +/- 0.003, N = 39.1699.1429.1531. (CC) gcc options: -O2 -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 12 digit1233691215Min: 9.16 / Avg: 9.17 / Max: 9.171. (CC) gcc options: -O2 -pthread

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU12348121620SE +/- 0.03, N = 317.0717.0217.03MIN: 16.92MIN: 16.92MIN: 16.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU12348121620Min: 17.02 / Avg: 17.07 / Max: 17.121. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 21231020304050SE +/- 0.04, N = 345.9045.9346.031. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2123918273645Min: 45.84 / Avg: 45.9 / Max: 45.971. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 5712340M80M120M160M200MSE +/- 16666.67, N = 31730733331731500001735300001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 5712330M60M90M120M150MMin: 173040000 / Avg: 173073333.33 / Max: 1730900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU123246810SE +/- 0.00787, N = 36.112836.123426.12767MIN: 5.76MIN: 5.78MIN: 5.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU123246810Min: 6.1 / Avg: 6.11 / Max: 6.131. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU123246810SE +/- 0.01169, N = 38.910638.921978.90065MIN: 8.71MIN: 8.7MIN: 8.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU1233691215Min: 8.89 / Avg: 8.91 / Max: 8.931. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K123246810SE +/- 0.01, N = 38.458.448.461. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K1233691215Min: 8.43 / Avg: 8.45 / Max: 8.471. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenSCAD

OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Projector Mount Swivel1233691215SE +/- 0.08, N = 313.2113.2113.181. OpenSCAD version 2021.01
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenSCADRender: Projector Mount Swivel12348121620Min: 13.09 / Avg: 13.21 / Max: 13.371. OpenSCAD version 2021.01

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU12310002000300040005000SE +/- 18.12, N = 34712.724706.714717.68MIN: 4656.14MIN: 4685.56MIN: 4697.791. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU1238001600240032004000Min: 4676.68 / Avg: 4712.72 / Max: 4734.091. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6123510152025SE +/- 0.03, N = 320.1820.2120.221. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6123510152025Min: 20.14 / Avg: 20.17 / Max: 20.241. (CXX) g++ options: -O3 -fPIC -lm

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - Decrypt12320406080100SE +/- 0.02, N = 375.3375.4875.311. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - Decrypt1231428425670Min: 75.3 / Avg: 75.33 / Max: 75.361. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU1233691215SE +/- 0.01, N = 311.8011.8011.78MIN: 11.7MIN: 11.68MIN: 11.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU1233691215Min: 11.78 / Avg: 11.8 / Max: 11.831. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p1231.06432.12863.19294.25725.3215SE +/- 0.00, N = 34.724.724.731. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p123246810Min: 4.72 / Avg: 4.72 / Max: 4.731. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To Compile1234080120160200SE +/- 0.19, N = 3194.53194.87194.55
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To Compile1234080120160200Min: 194.29 / Avg: 194.53 / Max: 194.91

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To Compile123150300450600750SE +/- 0.30, N = 3710.83709.62710.22
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To Compile123130260390520650Min: 710.25 / Avg: 710.83 / Max: 711.21

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Ninja1232004006008001000SE +/- 0.19, N = 31079.391081.161079.33
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 12.0Build System: Ninja1232004006008001000Min: 1079.03 / Avg: 1079.39 / Max: 1079.65

Hugin

Hugin is an open-source, cross-platform panorama photo stitcher software package. This test profile times how long it takes to run the assistant and panorama photo stitching on a set of images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching Time1231428425670SE +/- 0.27, N = 364.3464.2664.24
OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching Time1231326395265Min: 63.85 / Avg: 64.34 / Max: 64.76

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19123110220330440550SE +/- 0.13, N = 3510.88511.49510.73
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 1912390180270360450Min: 510.73 / Avg: 510.88 / Max: 511.14

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Thorough123612182430SE +/- 0.01, N = 325.0525.0425.081. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Thorough123612182430Min: 25.03 / Avg: 25.05 / Max: 25.061. (CXX) g++ options: -O3 -flto -pthread

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4K1230.1690.3380.5070.6760.845SE +/- 0.002, N = 30.7510.7510.7501. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 4 - Input: Bosphorus 4K123246810Min: 0.75 / Avg: 0.75 / Max: 0.751. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU123246810SE +/- 0.02795, N = 38.921578.928938.91801MIN: 8.53MIN: 8.52MIN: 8.521. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1233691215Min: 8.89 / Avg: 8.92 / Max: 8.981. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p1231530456075SE +/- 0.04, N = 366.6566.7266.651. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p1231326395265Min: 66.6 / Avg: 66.65 / Max: 66.731. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

libjpeg-turbo tjbench

tjbench is a JPEG decompression/compression benchmark that is part of libjpeg-turbo, a JPEG image codec library optimized for SIMD instructions on modern CPU architectures. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression Throughput123306090120150SE +/- 0.16, N = 3144.34144.20144.351. (CC) gcc options: -O3 -rdynamic
OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression Throughput123306090120150Min: 144.13 / Avg: 144.34 / Max: 144.661. (CC) gcc options: -O3 -rdynamic

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustive1234080120160200SE +/- 0.11, N = 3192.84192.72192.751. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustive1234080120160200Min: 192.67 / Avg: 192.84 / Max: 193.041. (CXX) g++ options: -O3 -flto -pthread

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digit1232004006008001000SE +/- 0.14, N = 3929.95929.53929.561. (CC) gcc options: -O2 -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digit123160320480640800Min: 929.69 / Avg: 929.94 / Max: 930.181. (CC) gcc options: -O2 -pthread

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p1230.04280.08560.12840.17120.214SE +/- 0.00, N = 30.190.190.191. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p12312345Min: 0.19 / Avg: 0.19 / Max: 0.191. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K1230.01350.0270.04050.0540.0675SE +/- 0.00, N = 30.060.060.061. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.1Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K12312345Min: 0.06 / Avg: 0.06 / Max: 0.061. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

161 Results Shown

Timed HMMer Search
Botan
Timed MrBayes Analysis
QMCPACK
Botan
VOSK Speech Recognition Toolkit
GNU Radio:
  FIR Filter
  Five Back to Back FIR Filters
QuantLib
KTX-Software toktx
Xcompact3d Incompact3d
SVT-VP9
Zstd Compression
GNU Radio
Google Draco
Zstd Compression
Darktable
Stockfish
GNU Radio
Xcompact3d Incompact3d
libgav1:
  Chimera 1080p 10-bit
  Summer Nature 4K
  Summer Nature 1080p
LuaRadio
GNU Radio
AOM AV1
Mobile Neural Network
Liquid-DSP
Mobile Neural Network
GIMP
Embree:
  Pathtracer ISPC - Asian Dragon
  Pathtracer - Crown
ASTC Encoder
Timed Linux Kernel Compilation
SVT-VP9
Zstd Compression
OpenSCAD
Embree
GNU Radio
AOM AV1
SVT-AV1
libavif avifenc
KTX-Software toktx
SVT-VP9
AOM AV1
GIMP
Embree
SVT-AV1
AOM AV1
Blender:
  BMW27 - CPU-Only
  Classroom - CPU-Only
libgav1
CP2K Molecular Dynamics
Botan
Google Draco
Botan
Mobile Neural Network
OpenSCAD
Zstd Compression
libavif avifenc
OCRMyPDF
Zstd Compression
Basis Universal
Timed LLVM Compilation
Botan
oneDNN
RawTherapee
Botan
KTX-Software toktx
OpenSCAD
GIMP
Zstd Compression
oneDNN
Xmrig
AOM AV1
oneDNN:
  IP Shapes 3D - f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Zstd Compression
GNU GMP GMPbench
Blender
oneDNN
LuaRadio
oneDNN:
  Recurrent Neural Network Training - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
Chia Blockchain VDF
Timed Wasmer Compilation
GIMP
PJSIP
SVT-AV1
Zstd Compression
Embree
Zstd Compression:
  3, Long Mode - Compression Speed
  8, Long Mode - Decompression Speed
Liquid-DSP
Botan
libavif avifenc
Botan
Darktable
Botan
Zstd Compression
oneDNN:
  IP Shapes 3D - u8s8f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
Timed Erlang/OTP Compilation
AOM AV1
OpenSCAD
libavif avifenc
Mobile Neural Network
Darktable
Botan
LuaRadio
AOM AV1:
  Speed 6 Two-Pass - Bosphorus 4K
  Speed 4 Two-Pass - Bosphorus 4K
Basis Universal
oneDNN
Mobile Neural Network
Liquid-DSP
Basis Universal
oneDNN
libavif avifenc
AOM AV1
KTX-Software toktx
Blender
oneDNN
PJSIP
Botan
Darktable
LuaRadio
Liquid-DSP
Chia Blockchain VDF
Embree
Blender
PJSIP
Xmrig
SVT-HEVC
Helsing
oneDNN
Basis Universal
Liquid-DSP
oneDNN:
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
AOM AV1
OpenSCAD
oneDNN
libavif avifenc
Botan
oneDNN
SVT-HEVC
Timed Godot Game Engine Compilation
Timed Node.js Compilation
Timed LLVM Compilation
Hugin
KTX-Software toktx
ASTC Encoder
SVT-AV1
oneDNN
SVT-HEVC
libjpeg-turbo tjbench
ASTC Encoder
Helsing
AOM AV1:
  Speed 0 Two-Pass - Bosphorus 1080p
  Speed 0 Two-Pass - Bosphorus 4K

1

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001137
Python Notes: Python 3.9.4
Security Notes: 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 11 May 2021 20:06 by user phoronix.

2

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001137
Python Notes: Python 3.9.4
Security Notes: 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 12 May 2021 12:54 by user phoronix.

3

Processor: AMD Ryzen 7 1700 Eight-Core @ 3.00GHz (8 Cores / 16 Threads), Motherboard: MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS), Chipset: AMD 17h, Memory: 16GB, Disk: 120GB Samsung SSD 840, Graphics: AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1266/2000MHz), Audio: AMD Ellesmere HDMI Audio, Monitor: VA2431, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 21.04, Kernel: 5.11.0-17-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.0.1 (LLVM 11.0.1), Vulkan: 1.2.145, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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 Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001137
Python Notes: Python 3.9.4
Security Notes: 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 STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 12 May 2021 18:45 by user phoronix.