Core i7 4960X Intel 2020

Intel Core i7-4960X testing with a MSI X79MA-GD45 (MS-7738) v1.0 (V3.8 BIOS) and AMD FirePro V4800 1GB on Ubuntu 19.10 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 2010198-FI-COREI749648
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 3 Tests
C++ Boost Tests 2 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 16 Tests
Compression Tests 4 Tests
CPU Massive 26 Tests
Creator Workloads 25 Tests
Cryptography 3 Tests
Database Test Suite 4 Tests
Encoding 5 Tests
Fortran Tests 6 Tests
Game Development 3 Tests
HPC - High Performance Computing 22 Tests
Imaging 7 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 3 Tests
Machine Learning 8 Tests
Molecular Dynamics 6 Tests
MPI Benchmarks 5 Tests
Multi-Core 25 Tests
NVIDIA GPU Compute 7 Tests
OCR 2 Tests
Intel oneAPI 4 Tests
OpenCV Tests 2 Tests
OpenMPI Tests 8 Tests
Programmer / Developer System Benchmarks 8 Tests
Python 3 Tests
Renderers 3 Tests
Scientific Computing 11 Tests
Server 4 Tests
Server CPU Tests 15 Tests
Single-Threaded 7 Tests
Speech 2 Tests
Telephony 2 Tests
Video Encoding 5 Tests
Common Workstation Benchmarks 4 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
Linux 5.3
October 16 2020
  23 Hours, 22 Minutes
2
October 17 2020
  23 Hours, 48 Minutes
3
October 18 2020
  23 Hours, 39 Minutes
Invert Hiding All Results Option
  23 Hours, 36 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):

Linux 5.3

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,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-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: intel_pstate powersave - CPU Microcode: 0x42e
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)
Python Notes: Python 2.7.17 + Python 3.7.5
Security Notes: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected

2

3

Processor: Intel Core i7-4960X @ 4.00GHz (6 Cores / 12 Threads), Motherboard: MSI X79MA-GD45 (MS-7738) v1.0 (V3.8 BIOS), Chipset: Intel Xeon E7 v2/Xeon, Memory: 8GB, Disk: VisionTek 240GB, Graphics: AMD FirePro V4800 1GB, Audio: Realtek ALC892, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 19.10, Kernel: 5.3.0-40-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0.0), Compiler: GCC 9.2.1 20191008, File-System: zfs, Screen Resolution: 1920x1080

Core i7 4960X Intel 2020ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionLinux 5.323Intel Core i7-4960X @ 4.00GHz (6 Cores / 12 Threads)MSI X79MA-GD45 (MS-7738) v1.0 (V3.8 BIOS)Intel Xeon E7 v2/Xeon8GBVisionTek 240GBAMD FirePro V4800 1GBRealtek ALC892DELL S2409WRealtek RTL8111/8168/8411Ubuntu 19.105.3.0-40-generic (x86_64)GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.53.3 Mesa 19.2.8 (LLVM 9.0.0)GCC 9.2.1 20191008zfs1920x1080OpenBenchmarking.orgCompiler 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,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-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: intel_pstate powersave - CPU Microcode: 0x42eGraphics Details- GLAMORJava Details- OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Details- Python 2.7.17 + Python 3.7.5Security Details- itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected

Linux 5.323Result OverviewPhoronix Test Suite100%103%106%109%113%G'MICApache CassandraDaCapo BenchmarkMlpack BenchmarkOSBenchBYTE Unix BenchmarkNeatBenchDarmstadt Automotive Parallel Heterogeneous SuiteSockperfIncompact3DEmbreeLULESHTimed LLVM CompilationNumenta Anomaly BenchmarkKeyDBGROMACSoneDNNInfluxDBRNNoiseGLmark2x265Montage Astronomical Image Mosaic EngineOCRMyPDFLAMMPS Molecular Dynamics SimulatorHuginLevelDBSystem GZIP DecompressionNAMDBuild2Chaos Group V-RAYIntel Open Image DenoiseNCNNTimed Linux Kernel CompilationTNNBotanTimed Apache CompilationPyPerformanceMonte Carlo Simulations of Ionised NebulaeGNU Octave BenchmarkHierarchical INTegrationStress-NGNAS Parallel Benchmarkslibavif avifencBRL-CADAlgebraic Multi-Grid BenchmarkRawTherapeeTesseract OCRCrypto++SMHasherFFTE7-Zip CompressionTimed HMMer SearchRodiniaGitDolfynLibRawKvazaarWebP Image EncodeBasis UniversaleSpeak-NG Speech EngineZstd Compressionlzbenchdav1dTensorFlow LiteSVT-AV1CaffeYafaRayOpenVKLLuxCoreRender

Core i7 4960X Intel 2020svt-av1: Enc Mode 0 - 1080pbuild-llvm: Time To Compilekvazaar: Bosphorus 4K - Slowkvazaar: Bosphorus 4K - Mediumbasis: UASTC Level 2 + RDO Post-Processinggmic: 2D Function Plotting, 1000 Timesincompact3d: Cylinderrodinia: OpenMP LavaMDinfluxdb: 4 - 10000 - 2,5000,1 - 10000gromacs: Water Benchmarksvt-av1: Enc Mode 4 - 1080pbyte: Dhrystone 2svt-av1: Enc Mode 8 - 1080pcryptopp: Keyed Algorithmscaffe: GoogleNet - CPU - 200kvazaar: Bosphorus 4K - Very Fastcassandra: Readsmocassin: Dust 2D tau100.0npb: BT.Cyafaray: Total Time For Sample Scenencnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetncnn: CPU - squeezenetnumenta-nab: Earthgecko Skylinecryptopp: Integer + Elliptic Curve Public Key Algorithmsrodinia: OpenMP Leukocytedaphne: OpenMP - Points2Imagebrl-cad: VGR Performance Metricnpb: EP.Davifenc: 0kvazaar: Bosphorus 1080p - Slowkvazaar: Bosphorus 1080p - Mediumbuild2: Time To Compilemlpack: scikit_qdamlpack: scikit_linearridgeregressioncassandra: Writesdav1d: Chimera 1080p 10-bitcaffe: GoogleNet - CPU - 100npb: LU.Cbuild-linux-kernel: Time To Compiletensorflow-lite: Inception V4tensorflow-lite: Inception ResNet V2stress-ng: SENDFILEstress-ng: Atomicnamd: ATPase Simulation - 327,506 Atomscaffe: AlexNet - CPU - 200hmmer: Pfam Database Searchcompress-zstd: 19kvazaar: Bosphorus 4K - Ultra Fastrodinia: OpenMP HotSpot3Dnpb: SP.Bavifenc: 2embree: Pathtracer - Asian Dragon Objstress-ng: CPU Cachepyperformance: raytracebasis: UASTC Level 3hint: FLOATglmark2: 1920 x 1080embree: Pathtracer ISPC - Asian Dragon Objmlpack: scikit_icapyperformance: python_startupmontage: Mosaic of M17, K band, 1.5 deg x 1.5 degembree: Pathtracer - Crowninfluxdb: 64 - 10000 - 2,5000,1 - 10000influxdb: 1024 - 10000 - 2,5000,1 - 10000openvkl: vklBenchmarkonednn: Deconvolution Batch deconv_1d - u8s8f32 - CPUembree: Pathtracer ISPC - Crownx265: Bosphorus 4Krawtherapee: Total Benchmark Timeembree: Pathtracer - Asian Dragonpyperformance: 2to3numenta-nab: Relative Entropyleveldb: Rand Deleteembree: Pathtracer ISPC - Asian Dragonleveldb: Seq Fillleveldb: Seq Filloidn: Memorialhugin: Panorama Photo Assistant + Stitching Timegmic: 3D Elevated Function In Rand Colors, 100 Timeskvazaar: Bosphorus 1080p - Very Fastnumenta-nab: Bayesian Changepointv-ray: CPUbasis: ETC1Scaffe: AlexNet - CPU - 100keydb: cryptopp: Unkeyed Algorithmspyperformance: gogit: Time To Complete Common Git Commandsluxcorerender: DLSCluxcorerender: Rainbow Colors and Prismtensorflow-lite: SqueezeNettensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Quanttensorflow-lite: Mobilenet Floatrodinia: OpenMP CFD Solverbasis: UASTC Level 2onednn: IP Batch All - u8s8f32 - CPUonednn: IP Batch All - f32 - CPUsockperf: Latency Under Loadespeak: Text-To-Speech Synthesisosbench: Create Filespyperformance: pathlibdav1d: Summer Nature 4Kpyperformance: regex_compilestress-ng: System V Message Passingocrmypdf: Processing 60 Page PDF Documentlzbench: XZ 0 - Decompressionlzbench: XZ 0 - Compressionlibraw: Post-Processing Benchmarksockperf: Throughputonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUwebp: Quality 100, Lossless, Highest Compressiondav1d: Chimera 1080pcompress-7zip: Compress Speed Testpyperformance: django_templatedaphne: OpenMP - NDT Mappingonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUrodinia: OpenMP Streamclusternpb: MG.Conednn: IP Batch 1D - u8s8f32 - CPUcompress-zstd: 3dacapobench: H2kvazaar: Bosphorus 1080p - Ultra Fastbotan: AES-256build-apache: Time To Compileamg: pyperformance: chaospyperformance: json_loadsstress-ng: RdRandtesseract-ocr: Time To OCR 7 Imagesstress-ng: NUMAstress-ng: CPU Stressstress-ng: Mallocstress-ng: MMAPstress-ng: Cryptostress-ng: Memory Copyingstress-ng: MEMFDstress-ng: Glibc C String Functionsstress-ng: Glibc Qsort Data Sortingstress-ng: Context Switchingstress-ng: Socket Activitystress-ng: Vector Mathstress-ng: Matrix Mathstress-ng: Semaphoresstress-ng: Forkingpyperformance: nbodypyperformance: floatlzbench: Libdeflate 1 - Decompressionlzbench: Libdeflate 1 - Compressionrnnoise: lzbench: Zstd 8 - Decompressionlzbench: Zstd 8 - Compressionpyperformance: crypto_pyaeslzbench: Brotli 2 - Decompressionlzbench: Brotli 2 - Compressiondaphne: OpenMP - Euclidean Clustergmic: Plotting Isosurface Of A 3D Volume, 1000 Timeslzbench: Brotli 0 - Decompressionlzbench: Brotli 0 - Compressionbotan: Blowfishbotan: Twofishlzbench: Crush 0 - Decompressionlzbench: Crush 0 - Compressionlzbench: Zstd 1 - Decompressionlzbench: Zstd 1 - Compressionx265: Bosphorus 1080pnumenta-nab: Windowed Gaussiandolfyn: Computational Fluid Dynamicstnn: CPU - MobileNet v2botan: CAST-256botan: KASUMIpyperformance: pickle_pure_pythononednn: Deconvolution Batch deconv_1d - f32 - CPUwebp: Quality 100, Losslesstnn: CPU - SqueezeNet v1.1mlpack: scikit_svmoctave-benchmark: leveldb: Rand Fillleveldb: Rand Fillonednn: IP Batch 1D - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUleveldb: Overwriteleveldb: Overwritenpb: EP.Csockperf: Latency Ping Pongsmhasher: Spooky32smhasher: Spooky32dav1d: Summer Nature 1080ponednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUdacapobench: Jythonsmhasher: fasthash32smhasher: fasthash32smhasher: t1ha2_atoncesmhasher: t1ha2_atonceneatbench: CPUbasis: UASTC Level 0leveldb: Hot Readleveldb: Fill Syncleveldb: Fill Syncsmhasher: wyhashsmhasher: wyhashleveldb: Seek Randavifenc: 8webp: Quality 100, Highest Compressionavifenc: 10leveldb: Rand Readonednn: Convolution Batch Shapes Auto - f32 - CPUlammps: Rhodopsin Proteinosbench: Memory Allocationsosbench: Create Processesosbench: Launch Programsosbench: Create Threadssystem-decompress-gzip: ffte: N=256, 3D Complex FFT Routineonednn: Deconvolution Batch deconv_3d - u8s8f32 - CPUonednn: Deconvolution Batch deconv_3d - f32 - CPUwebp: Quality 100webp: Defaultlulesh: Linux 5.3230.011226.8730.650.65868.258200.513621.246725553.587900526.40.3520.16433205805.20.871462.2807643315631.961911329410336.66275.73491.7378.7426.9537.12357.0537.002.02112.4297.585.6951.9812.9743.4941.84259.4133706.428226255.44520806.46456712959769620.57209.6912.912.91204.210120.156.322215672.9116597212432.26165.062548924049616472666.01204460.573.13144143560143.95218.64.41133.9312801.31124.0566.048522.66679113.009333392595.355338476.785467.9113.2107.3395.7470970864.61051454.360.9619.39166.22596.4391.2956.671447350.569165.6817.7138152.4388.72.6076.13675.9707.9674.844591573.08171683257477.28289.76416434464.0460.720.8037480931118526432125799058.72058.721109.722146.75119.24538.973166.99886238.572.762586285917.1049.8131073425.793389767.8742044.229286.732970297.2431.941518.69428.18136.5934757.778.630631743.7403917.34736.31133.57574835.8116333.2185838.8130.186126.282547.1335069017.9686.861236.01708.50328.06546526.1383.531659533.182630.9539289.1723671.83960900.3344899.2215715197220326.096114774135633162863.3825.446541406266.513232.54745485108940125.1823.42823.526325.425106.55777.77068224.784720.671297.13113.7311.280146.6929.113.192062.4837145.7899.1619.398.00257.88711164.27272.368.73283600943.9275993.4644.26111253.127.0610.6605.9842391.0490.634.20013679.908.8248.9288.6428.2685.89738.49143.741100.75696329.06004651.69073716.3801513.25617940.29946956117.197236.72922.7191.766638.730390.011229.7940.650.65867.770243.690613.196289553.598904292.00.3490.16433059413.00.871462.5694843308901.961651229310305.39275.21391.8278.2627.2637.89357.6337.462.03112.9098.215.6751.9712.9043.6041.84260.2763714.477888255.58719476.69227090659665621.05210.0662.912.92204.024120.426.502167273.2616599112376.77165.611548896049631432655.34203089.523.13325143811144.03318.64.41134.3222811.18124.3206.103321.52680113.018334295678.010618396.743878.7813.1107.3745.7201991803.81029071.560.9619.60266.22746.4391.4626.701947352.813167.1337.6892156.0408.52.6075.83875.9377.9774.620593873.46771852256466.80290.38172234464.0400.720.8037492531127926428125793859.00858.734109.829147.33538.988167.42366438.572.732596350040.2749.5191073425.773384298.1373244.169286.062965598.0431.771518.35451.35936.5994804.808.653841741.2393217.41742.84933.58274843.3216433.3185841.6630.130130.142563.7335040588.3586.721236.12699.26328.39543539.7284.081640248.862603.1839291.8523605.41960119.6645129.6815715197220326.208114774135632162862.3025.447540407266.776232.70445485108940125.2923.52223.519324.840106.82377.95968424.744920.657297.25613.7311.312146.1869.113.107463.9741149.0058.9607.037.97657.77211131.32272.488.71663596943.9175994.0444.26211255.987.1010.6365.9942186.9460.634.19413823.388.8208.9738.6718.2745.95638.46203.743102.00627728.86056952.40440416.9658663.25717969.03328025217.242636.87472.7161.758648.441670.011227.1750.650.65867.644284.074626.255493552.818909744.90.3530.16433874925.90.869462.7365193309751.961661729310296.40275.14192.3078.4627.0337.98359.6537.212.04111.1697.615.6251.7012.9843.3642.12260.2493711.730349254.90420582.96133333159791621.99208.8662.912.92204.789120.726.202201873.0316578212440.70165.672550410749669102670.43200592.593.14447143495143.99818.64.41134.0592812.36124.6735.948122.16680113.042333884203.291088406.590467.8313.0108.1585.57641001969.71039980.060.9619.01586.06696.3291.2956.644147451.145166.7627.7073155.8188.52.6176.22375.9907.9775.015592173.32071828254471.41290.54130234464.0940.720.8037499331114926417225798458.86158.799109.795147.03538.963206.63479138.772.792586349001.1049.6031073425.803251607.9648044.281286.132969798.2432.261522.30454.85436.6084796.679.014271741.0402917.41739.70933.48174691.7916533.3185835.0730.170126.982555.2835071564.9986.861233.54709.53330.43545105.2883.551645592.492650.5939269.6223524.54960296.4745082.0115715197220426.359114774136634162862.2725.616541407266.291232.79645485108940125.2824.01623.496325.886106.72577.93868224.764620.658297.42913.7411.303146.5159.113.127964.7582147.5349.0607.337.98657.80211153.05272.688.73149598243.9075995.1644.26211257.886.9410.6345.9172383.0870.634.19413840.268.9498.9578.6548.2635.82838.51673.723100.60826928.92414751.59219116.5994963.27117951.56036901017.333636.98652.7201.756645.47531OpenBenchmarking.org

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080p23Linux 5.30.00230.00460.00690.00920.0115SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.010.010.011. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080p23Linux 5.312345Min: 0.01 / Avg: 0.01 / Max: 0.01Min: 0.01 / Avg: 0.01 / Max: 0.01Min: 0.01 / Avg: 0.01 / Max: 0.011. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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 10.0Time To Compile23Linux 5.330060090012001500SE +/- 1.62, N = 3SE +/- 2.37, N = 3SE +/- 2.17, N = 31229.791227.181226.87
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To Compile23Linux 5.32004006008001000Min: 1227.39 / Avg: 1229.79 / Max: 1232.88Min: 1224.34 / Avg: 1227.18 / Max: 1231.88Min: 1222.81 / Avg: 1226.87 / Max: 1230.22

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Slow23Linux 5.30.14630.29260.43890.58520.7315SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.650.650.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Slow23Linux 5.3246810Min: 0.65 / Avg: 0.65 / Max: 0.65Min: 0.65 / Avg: 0.65 / Max: 0.65Min: 0.65 / Avg: 0.65 / Max: 0.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Medium23Linux 5.30.14630.29260.43890.58520.7315SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.650.650.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Medium23Linux 5.3246810Min: 0.65 / Avg: 0.65 / Max: 0.65Min: 0.65 / Avg: 0.65 / Max: 0.65Min: 0.65 / Avg: 0.65 / Max: 0.651. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Basis Universal

Basis Universal is a GPU texture codoec. 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 1.12Settings: UASTC Level 2 + RDO Post-Processing23Linux 5.32004006008001000SE +/- 0.33, N = 3SE +/- 1.14, N = 3SE +/- 1.46, N = 3867.77867.64868.261. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-Processing23Linux 5.3150300450600750Min: 867.38 / Avg: 867.77 / Max: 868.42Min: 865.98 / Avg: 867.64 / Max: 869.82Min: 865.46 / Avg: 868.26 / Max: 870.361. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 2D Function Plotting, 1000 Times23Linux 5.360120180240300SE +/- 12.80, N = 9SE +/- 19.93, N = 9SE +/- 7.26, N = 9243.69284.07200.511. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 2D Function Plotting, 1000 Times23Linux 5.350100150200250Min: 182.02 / Avg: 243.69 / Max: 285.82Min: 182.33 / Avg: 284.07 / Max: 348.5Min: 168.73 / Avg: 200.51 / Max: 227.111. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

Incompact3D

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 BetterIncompact3D 2020-09-17Input: Cylinder23Linux 5.3140280420560700SE +/- 3.47, N = 3SE +/- 5.55, N = 3SE +/- 9.64, N = 3613.20626.26621.251. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterIncompact3D 2020-09-17Input: Cylinder23Linux 5.3110220330440550Min: 608.59 / Avg: 613.2 / Max: 620Min: 615.26 / Avg: 626.26 / Max: 633.07Min: 610.68 / Avg: 621.25 / Max: 640.51. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMD23Linux 5.3120240360480600SE +/- 0.33, N = 3SE +/- 0.39, N = 3SE +/- 0.21, N = 3553.60552.82553.591. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMD23Linux 5.3100200300400500Min: 553.17 / Avg: 553.6 / Max: 554.24Min: 552.26 / Avg: 552.82 / Max: 553.56Min: 553.23 / Avg: 553.59 / Max: 553.941. (CXX) g++ options: -O2 -lOpenCL

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 1000023Linux 5.3200K400K600K800K1000KSE +/- 11222.25, N = 15SE +/- 10008.11, N = 15SE +/- 16230.18, N = 12904292.0909744.9900526.4
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 1000023Linux 5.3160K320K480K640K800KMin: 838986.7 / Avg: 904291.97 / Max: 997866.2Min: 869508.6 / Avg: 909744.89 / Max: 1002951.3Min: 810066.4 / Avg: 900526.4 / Max: 1005319.1

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water Benchmark23Linux 5.30.07940.15880.23820.31760.397SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.3490.3530.3521. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water Benchmark23Linux 5.312345Min: 0.35 / Avg: 0.35 / Max: 0.35Min: 0.35 / Avg: 0.35 / Max: 0.35Min: 0.35 / Avg: 0.35 / Max: 0.351. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080p23Linux 5.30.03690.07380.11070.14760.1845SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1640.1640.1641. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080p23Linux 5.312345Min: 0.16 / Avg: 0.16 / Max: 0.16Min: 0.16 / Avg: 0.16 / Max: 0.16Min: 0.16 / Avg: 0.16 / Max: 0.161. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

BYTE Unix Benchmark

This is a test of BYTE. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 223Linux 5.37M14M21M28M35MSE +/- 408160.90, N = 12SE +/- 431967.21, N = 5SE +/- 409038.01, N = 1233059413.033874925.933205805.2
OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 223Linux 5.36M12M18M24M30MMin: 30128764.9 / Avg: 33059412.98 / Max: 34318043.8Min: 32147076.2 / Avg: 33874925.9 / Max: 34311645.8Min: 30124755.7 / Avg: 33205805.17 / Max: 34271314.3

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080p23Linux 5.30.1960.3920.5880.7840.98SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.8710.8690.8711. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080p23Linux 5.3246810Min: 0.87 / Avg: 0.87 / Max: 0.87Min: 0.87 / Avg: 0.87 / Max: 0.87Min: 0.87 / Avg: 0.87 / Max: 0.871. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Crypto++

Crypto++ is a C++ class library of cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed Algorithms23Linux 5.3100200300400500SE +/- 0.27, N = 3SE +/- 0.04, N = 3SE +/- 0.17, N = 3462.57462.74462.281. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed Algorithms23Linux 5.380160240320400Min: 462.13 / Avg: 462.57 / Max: 463.06Min: 462.69 / Avg: 462.74 / Max: 462.81Min: 462.03 / Avg: 462.28 / Max: 462.61. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 20023Linux 5.370K140K210K280K350KSE +/- 130.05, N = 3SE +/- 125.43, N = 3SE +/- 342.86, N = 33308903309753315631. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 20023Linux 5.360K120K180K240K300KMin: 330646 / Avg: 330890 / Max: 331090Min: 330832 / Avg: 330975 / Max: 331225Min: 330888 / Avg: 331563.33 / Max: 3320041. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very Fast23Linux 5.30.4410.8821.3231.7642.205SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.961.961.961. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Very Fast23Linux 5.3246810Min: 1.96 / Avg: 1.96 / Max: 1.96Min: 1.96 / Avg: 1.96 / Max: 1.96Min: 1.96 / Avg: 1.96 / Max: 1.961. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Reads23Linux 5.34K8K12K16K20KSE +/- 219.28, N = 3SE +/- 459.84, N = 12SE +/- 259.42, N = 4165121661719113
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Reads23Linux 5.33K6K9K12K15KMin: 16076 / Avg: 16512 / Max: 16771Min: 13457 / Avg: 16616.58 / Max: 18401Min: 18435 / Avg: 19113.25 / Max: 19566

Monte Carlo Simulations of Ionised Nebulae

Mocassin is the Monte Carlo Simulations of Ionised Nebulae. MOCASSIN is a fully 3D or 2D photoionisation and dust radiative transfer code which employs a Monte Carlo approach to the transfer of radiation through media of arbitrary geometry and density distribution. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.023Linux 5.360120180240300SE +/- 0.67, N = 32932932941. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterMonte Carlo Simulations of Ionised Nebulae 2019-03-24Input: Dust 2D tau100.023Linux 5.350100150200250Min: 293 / Avg: 293.67 / Max: 2951. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C23Linux 5.32K4K6K8K10KSE +/- 36.44, N = 3SE +/- 3.67, N = 3SE +/- 3.73, N = 310305.3910296.4010336.661. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C23Linux 5.32K4K6K8K10KMin: 10237.71 / Avg: 10305.39 / Max: 10362.66Min: 10291.95 / Avg: 10296.4 / Max: 10303.69Min: 10332.56 / Avg: 10336.66 / Max: 10344.111. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

YafaRay

YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample Scene23Linux 5.360120180240300SE +/- 0.67, N = 3SE +/- 0.16, N = 3SE +/- 0.52, N = 3275.21275.14275.731. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lboost_system -lboost_filesystem -lboost_locale
OpenBenchmarking.orgSeconds, Fewer Is BetterYafaRay 3.4.1Total Time For Sample Scene23Linux 5.350100150200250Min: 274.26 / Avg: 275.21 / Max: 276.52Min: 274.92 / Avg: 275.14 / Max: 275.45Min: 274.98 / Avg: 275.73 / Max: 276.731. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lboost_system -lboost_filesystem -lboost_locale

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny23Linux 5.320406080100SE +/- 0.88, N = 3SE +/- 0.74, N = 3SE +/- 1.34, N = 391.8292.3091.73MIN: 89.61 / MAX: 112.75MIN: 89.69 / MAX: 111.81MIN: 88.81 / MAX: 111.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tiny23Linux 5.320406080100Min: 90.41 / Avg: 91.82 / Max: 93.44Min: 90.82 / Avg: 92.3 / Max: 93.19Min: 90.28 / Avg: 91.73 / Max: 94.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet5023Linux 5.320406080100SE +/- 1.17, N = 3SE +/- 0.58, N = 3SE +/- 0.65, N = 378.2678.4678.74MIN: 76.45 / MAX: 85.57MIN: 76.5 / MAX: 105.61MIN: 76.4 / MAX: 100.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet5023Linux 5.31530456075Min: 76.95 / Avg: 78.26 / Max: 80.6Min: 77.79 / Avg: 78.46 / Max: 79.62Min: 78.04 / Avg: 78.74 / Max: 80.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet23Linux 5.3612182430SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 327.2627.0326.95MIN: 26.64 / MAX: 46.16MIN: 26.42 / MAX: 31.74MIN: 26.43 / MAX: 31.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnet23Linux 5.3612182430Min: 27.21 / Avg: 27.26 / Max: 27.32Min: 26.81 / Avg: 27.03 / Max: 27.22Min: 26.79 / Avg: 26.95 / Max: 27.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet1823Linux 5.3918273645SE +/- 0.06, N = 3SE +/- 0.38, N = 3SE +/- 0.42, N = 337.8937.9837.12MIN: 37.12 / MAX: 46.05MIN: 35.42 / MAX: 61.12MIN: 35.76 / MAX: 59.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet1823Linux 5.3816243240Min: 37.78 / Avg: 37.89 / Max: 37.96Min: 37.51 / Avg: 37.98 / Max: 38.73Min: 36.38 / Avg: 37.12 / Max: 37.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg1623Linux 5.380160240320400SE +/- 1.82, N = 3SE +/- 0.49, N = 3SE +/- 1.04, N = 3357.63359.65357.05MIN: 347.8 / MAX: 392.36MIN: 347.86 / MAX: 380.9MIN: 341.42 / MAX: 410.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg1623Linux 5.360120180240300Min: 354.99 / Avg: 357.63 / Max: 361.13Min: 358.69 / Avg: 359.65 / Max: 360.26Min: 354.98 / Avg: 357.05 / Max: 358.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet23Linux 5.3918273645SE +/- 0.27, N = 3SE +/- 0.16, N = 3SE +/- 0.20, N = 337.4637.2137.00MIN: 36.97 / MAX: 56.71MIN: 36.8 / MAX: 46.13MIN: 36.18 / MAX: 42.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenet23Linux 5.3816243240Min: 37.14 / Avg: 37.46 / Max: 37.99Min: 36.97 / Avg: 37.21 / Max: 37.5Min: 36.6 / Avg: 37 / Max: 37.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface23Linux 5.30.4590.9181.3771.8362.295SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 32.032.042.02MIN: 1.98 / MAX: 2.12MIN: 1.96 / MAX: 4.34MIN: 1.95 / MAX: 8.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazeface23Linux 5.3246810Min: 1.99 / Avg: 2.03 / Max: 2.06Min: 1.98 / Avg: 2.04 / Max: 2.14Min: 1.99 / Avg: 2.02 / Max: 2.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b023Linux 5.3306090120150SE +/- 0.33, N = 3SE +/- 0.48, N = 3SE +/- 0.08, N = 3112.90111.16112.42MIN: 110.98 / MAX: 194.97MIN: 108.9 / MAX: 194.49MIN: 110.57 / MAX: 135.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b023Linux 5.320406080100Min: 112.29 / Avg: 112.9 / Max: 113.42Min: 110.25 / Avg: 111.16 / Max: 111.86Min: 112.31 / Avg: 112.42 / Max: 112.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnet23Linux 5.320406080100SE +/- 0.08, N = 3SE +/- 0.32, N = 3SE +/- 0.44, N = 398.2197.6197.58MIN: 97.34 / MAX: 122.16MIN: 96.31 / MAX: 103.88MIN: 96.04 / MAX: 120.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnet23Linux 5.320406080100Min: 98.07 / Avg: 98.21 / Max: 98.33Min: 96.99 / Avg: 97.61 / Max: 98.02Min: 96.7 / Avg: 97.58 / Max: 98.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v223Linux 5.31.28032.56063.84095.12126.4015SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 35.675.625.69MIN: 5.62 / MAX: 8.24MIN: 5.35 / MAX: 9.16MIN: 5.55 / MAX: 18.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v223Linux 5.3246810Min: 5.63 / Avg: 5.67 / Max: 5.7Min: 5.51 / Avg: 5.62 / Max: 5.71Min: 5.58 / Avg: 5.69 / Max: 5.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v323Linux 5.31224364860SE +/- 0.27, N = 3SE +/- 0.42, N = 3SE +/- 0.31, N = 351.9751.7051.98MIN: 51.11 / MAX: 76.59MIN: 50.36 / MAX: 78.83MIN: 50.94 / MAX: 61.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v323Linux 5.31020304050Min: 51.69 / Avg: 51.97 / Max: 52.51Min: 50.87 / Avg: 51.7 / Max: 52.15Min: 51.41 / Avg: 51.98 / Max: 52.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v223Linux 5.33691215SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 312.9012.9812.97MIN: 12.35 / MAX: 20.14MIN: 12.48 / MAX: 18.55MIN: 12.45 / MAX: 19.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v223Linux 5.348121620Min: 12.76 / Avg: 12.9 / Max: 13.05Min: 12.94 / Avg: 12.98 / Max: 13.05Min: 12.83 / Avg: 12.97 / Max: 13.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet23Linux 5.31020304050SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 343.6043.3643.49MIN: 42.23 / MAX: 65.82MIN: 42.83 / MAX: 47.31MIN: 42.04 / MAX: 67.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenet23Linux 5.3918273645Min: 43.37 / Avg: 43.6 / Max: 43.75Min: 43.14 / Avg: 43.36 / Max: 43.64Min: 43.45 / Avg: 43.49 / Max: 43.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenet23Linux 5.31020304050SE +/- 0.13, N = 3SE +/- 0.20, N = 3SE +/- 0.14, N = 341.8442.1241.84MIN: 40.68 / MAX: 64.6MIN: 40.78 / MAX: 56.48MIN: 40.49 / MAX: 64.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenet23Linux 5.3918273645Min: 41.62 / Avg: 41.84 / Max: 42.08Min: 41.77 / Avg: 42.12 / Max: 42.47Min: 41.65 / Avg: 41.84 / Max: 42.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skyline23Linux 5.360120180240300SE +/- 2.17, N = 3SE +/- 1.99, N = 3SE +/- 1.85, N = 3260.28260.25259.41
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skyline23Linux 5.350100150200250Min: 256.38 / Avg: 260.28 / Max: 263.88Min: 256.27 / Avg: 260.25 / Max: 262.49Min: 256.57 / Avg: 259.41 / Max: 262.88

Crypto++

Crypto++ is a C++ class library of cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Integer + Elliptic Curve Public Key Algorithms23Linux 5.38001600240032004000SE +/- 4.64, N = 3SE +/- 7.90, N = 3SE +/- 3.48, N = 33714.483711.733706.431. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Integer + Elliptic Curve Public Key Algorithms23Linux 5.36001200180024003000Min: 3705.36 / Avg: 3714.48 / Max: 3720.54Min: 3697.52 / Avg: 3711.73 / Max: 3724.8Min: 3700.18 / Avg: 3706.43 / Max: 3712.231. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Leukocyte23Linux 5.360120180240300SE +/- 0.19, N = 3SE +/- 0.60, N = 3SE +/- 0.89, N = 3255.59254.90255.451. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Leukocyte23Linux 5.350100150200250Min: 255.24 / Avg: 255.59 / Max: 255.89Min: 254.25 / Avg: 254.9 / Max: 256.1Min: 253.75 / Avg: 255.45 / Max: 256.761. (CXX) g++ options: -O2 -lOpenCL

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Points2Image23Linux 5.34K8K12K16K20KSE +/- 76.28, N = 3SE +/- 204.38, N = 8SE +/- 245.75, N = 619476.6920582.9620806.461. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Points2Image23Linux 5.34K8K12K16K20KMin: 19329.65 / Avg: 19476.69 / Max: 19585.44Min: 19172.64 / Avg: 20582.96 / Max: 20931.67Min: 19592.73 / Avg: 20806.46 / Max: 21124.011. (CXX) g++ options: -O3 -std=c++11 -fopenmp

BRL-CAD

BRL-CAD 7.28.0 is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.30.8VGR Performance Metric23Linux 5.313K26K39K52K65K5966559791597691. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D23Linux 5.3130260390520650SE +/- 6.96, N = 3SE +/- 6.88, N = 3SE +/- 6.44, N = 3621.05621.99620.571. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D23Linux 5.3110220330440550Min: 607.14 / Avg: 621.05 / Max: 628.5Min: 608.27 / Avg: 621.99 / Max: 629.66Min: 607.79 / Avg: 620.57 / Max: 628.351. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

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 0.7.3Encoder Speed: 023Linux 5.350100150200250SE +/- 0.10, N = 3SE +/- 0.41, N = 3SE +/- 0.34, N = 3210.07208.87209.691. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 023Linux 5.34080120160200Min: 209.89 / Avg: 210.07 / Max: 210.22Min: 208.13 / Avg: 208.87 / Max: 209.53Min: 209.21 / Avg: 209.69 / Max: 210.351. (CXX) g++ options: -O3 -fPIC

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Slow23Linux 5.30.65481.30961.96442.61923.274SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.912.912.911. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Slow23Linux 5.3246810Min: 2.91 / Avg: 2.91 / Max: 2.91Min: 2.91 / Avg: 2.91 / Max: 2.91Min: 2.91 / Avg: 2.91 / Max: 2.911. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Medium23Linux 5.30.6571.3141.9712.6283.285SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.922.922.911. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Medium23Linux 5.3246810Min: 2.92 / Avg: 2.92 / Max: 2.92Min: 2.92 / Avg: 2.92 / Max: 2.92Min: 2.91 / Avg: 2.91 / Max: 2.921. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To Compile23Linux 5.34080120160200SE +/- 1.60, N = 3SE +/- 0.59, N = 3SE +/- 0.52, N = 3204.02204.79204.21
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To Compile23Linux 5.34080120160200Min: 201.17 / Avg: 204.02 / Max: 206.69Min: 203.92 / Avg: 204.79 / Max: 205.91Min: 203.48 / Avg: 204.21 / Max: 205.21

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qda23Linux 5.3306090120150SE +/- 0.54, N = 3SE +/- 0.35, N = 3SE +/- 0.66, N = 3120.42120.72120.15
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qda23Linux 5.320406080100Min: 119.85 / Avg: 120.42 / Max: 121.5Min: 120.27 / Avg: 120.72 / Max: 121.41Min: 118.96 / Avg: 120.15 / Max: 121.25

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregression23Linux 5.3246810SE +/- 0.07, N = 15SE +/- 0.02, N = 3SE +/- 0.04, N = 36.506.206.32
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregression23Linux 5.33691215Min: 6.18 / Avg: 6.5 / Max: 7.05Min: 6.16 / Avg: 6.2 / Max: 6.23Min: 6.24 / Avg: 6.32 / Max: 6.39

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Writes23Linux 5.35K10K15K20K25KSE +/- 171.94, N = 14SE +/- 202.09, N = 3SE +/- 196.83, N = 3216722201822156
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Writes23Linux 5.34K8K12K16K20KMin: 20380 / Avg: 21671.57 / Max: 22514Min: 21713 / Avg: 22017.67 / Max: 22400Min: 21765 / Avg: 22156 / Max: 22391

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bit23Linux 5.31632486480SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 373.2673.0372.91MIN: 47.54 / MAX: 172.18MIN: 47.48 / MAX: 170.99MIN: 47.42 / MAX: 171.081. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bit23Linux 5.31428425670Min: 73.14 / Avg: 73.26 / Max: 73.33Min: 72.74 / Avg: 73.03 / Max: 73.21Min: 72.7 / Avg: 72.91 / Max: 73.071. (CC) gcc options: -pthread

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 10023Linux 5.340K80K120K160K200KSE +/- 223.63, N = 3SE +/- 121.48, N = 3SE +/- 171.15, N = 31659911657821659721. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 10023Linux 5.330K60K90K120K150KMin: 165690 / Avg: 165991 / Max: 166428Min: 165614 / Avg: 165782 / Max: 166018Min: 165652 / Avg: 165972.33 / Max: 1662371. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C23Linux 5.33K6K9K12K15KSE +/- 5.67, N = 3SE +/- 4.20, N = 3SE +/- 6.67, N = 312376.7712440.7012432.261. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C23Linux 5.32K4K6K8K10KMin: 12365.64 / Avg: 12376.77 / Max: 12384.2Min: 12433.65 / Avg: 12440.7 / Max: 12448.18Min: 12419.87 / Avg: 12432.26 / Max: 12442.751. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compile23Linux 5.34080120160200SE +/- 0.96, N = 3SE +/- 0.82, N = 3SE +/- 1.02, N = 3165.61165.67165.06
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compile23Linux 5.3306090120150Min: 164.58 / Avg: 165.61 / Max: 167.54Min: 164.22 / Avg: 165.67 / Max: 167.07Min: 163.99 / Avg: 165.06 / Max: 167.09

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V423Linux 5.31.2M2.4M3.6M4.8M6MSE +/- 1292.14, N = 3SE +/- 15121.82, N = 3SE +/- 1013.92, N = 3548896055041075489240
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V423Linux 5.31000K2000K3000K4000K5000KMin: 5487440 / Avg: 5488960 / Max: 5491530Min: 5487500 / Avg: 5504106.67 / Max: 5534300Min: 5487240 / Avg: 5489240 / Max: 5490530

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V223Linux 5.31.1M2.2M3.3M4.4M5.5MSE +/- 1215.73, N = 3SE +/- 3953.53, N = 3SE +/- 1228.42, N = 3496314349669104961647
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V223Linux 5.3900K1800K2700K3600K4500KMin: 4960780 / Avg: 4963143.33 / Max: 4964820Min: 4962100 / Avg: 4966910 / Max: 4974750Min: 4959910 / Avg: 4961646.67 / Max: 4964020

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILE23Linux 5.36001200180024003000SE +/- 28.65, N = 15SE +/- 27.95, N = 15SE +/- 29.05, N = 152655.342670.432666.011. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SENDFILE23Linux 5.35001000150020002500Min: 2476.13 / Avg: 2655.34 / Max: 2819.86Min: 2489.2 / Avg: 2670.43 / Max: 2834.05Min: 2489.77 / Avg: 2666.01 / Max: 2830.121. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Atomic23Linux 5.340K80K120K160K200KSE +/- 2446.96, N = 15SE +/- 2384.63, N = 15SE +/- 2400.41, N = 15203089.52200592.59204460.571. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Atomic23Linux 5.340K80K120K160K200KMin: 189248.99 / Avg: 203089.52 / Max: 217662.65Min: 189282.32 / Avg: 200592.59 / Max: 217564.65Min: 189263.07 / Avg: 204460.57 / Max: 217619.341. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms23Linux 5.30.70751.4152.12252.833.5375SE +/- 0.00201, N = 3SE +/- 0.00812, N = 3SE +/- 0.00337, N = 33.133253.144473.13144
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms23Linux 5.3246810Min: 3.13 / Avg: 3.13 / Max: 3.14Min: 3.13 / Avg: 3.14 / Max: 3.16Min: 3.12 / Avg: 3.13 / Max: 3.14

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 20023Linux 5.330K60K90K120K150KSE +/- 180.93, N = 3SE +/- 149.74, N = 3SE +/- 167.91, N = 31438111434951435601. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 20023Linux 5.320K40K60K80K100KMin: 143569 / Avg: 143811 / Max: 144165Min: 143213 / Avg: 143495.33 / Max: 143723Min: 143225 / Avg: 143559.67 / Max: 1437511. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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 3.3.1Pfam Database Search23Linux 5.3306090120150SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3144.03144.00143.951. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database Search23Linux 5.3306090120150Min: 143.84 / Avg: 144.03 / Max: 144.4Min: 143.89 / Avg: 144 / Max: 144.08Min: 143.81 / Avg: 143.95 / Max: 144.21. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu ISO) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 1923Linux 5.3510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 318.618.618.61. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 1923Linux 5.3510152025Min: 18.6 / Avg: 18.6 / Max: 18.6Min: 18.6 / Avg: 18.6 / Max: 18.6Min: 18.5 / Avg: 18.57 / Max: 18.61. (CC) gcc options: -O3 -pthread -lz -llzma

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra Fast23Linux 5.30.99231.98462.97693.96924.9615SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.414.414.411. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 4K - Video Preset: Ultra Fast23Linux 5.3246810Min: 4.41 / Avg: 4.41 / Max: 4.41Min: 4.41 / Avg: 4.41 / Max: 4.41Min: 4.41 / Avg: 4.41 / Max: 4.411. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3D23Linux 5.3306090120150SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 0.31, N = 3134.32134.06133.931. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3D23Linux 5.3306090120150Min: 134.3 / Avg: 134.32 / Max: 134.34Min: 133.77 / Avg: 134.06 / Max: 134.47Min: 133.36 / Avg: 133.93 / Max: 134.411. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B23Linux 5.36001200180024003000SE +/- 2.16, N = 3SE +/- 1.98, N = 3SE +/- 1.75, N = 32811.182812.362801.311. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B23Linux 5.35001000150020002500Min: 2806.94 / Avg: 2811.18 / Max: 2814.01Min: 2808.44 / Avg: 2812.36 / Max: 2814.8Min: 2799.2 / Avg: 2801.31 / Max: 2804.771. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

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 0.7.3Encoder Speed: 223Linux 5.3306090120150SE +/- 0.12, N = 3SE +/- 0.33, N = 3SE +/- 0.36, N = 3124.32124.67124.061. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 223Linux 5.320406080100Min: 124.07 / Avg: 124.32 / Max: 124.47Min: 124.01 / Avg: 124.67 / Max: 125.03Min: 123.46 / Avg: 124.06 / Max: 124.721. (CXX) g++ options: -O3 -fPIC

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon Obj23Linux 5.3246810SE +/- 0.0060, N = 3SE +/- 0.0259, N = 3SE +/- 0.0351, N = 36.10335.94816.0485MIN: 6.04 / MAX: 6.22MIN: 5.88 / MAX: 6.11MIN: 5.93 / MAX: 6.15
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon Obj23Linux 5.3246810Min: 6.1 / Avg: 6.1 / Max: 6.12Min: 5.91 / Avg: 5.95 / Max: 6Min: 5.98 / Avg: 6.05 / Max: 6.09

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Cache23Linux 5.3510152025SE +/- 0.27, N = 15SE +/- 0.30, N = 5SE +/- 0.21, N = 1521.5222.1622.661. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Cache23Linux 5.3510152025Min: 19.37 / Avg: 21.52 / Max: 23.4Min: 21.37 / Avg: 22.16 / Max: 23.07Min: 21.13 / Avg: 22.66 / Max: 241. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytrace23Linux 5.3150300450600750SE +/- 0.88, N = 3SE +/- 0.67, N = 3680680679
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytrace23Linux 5.3120240360480600Min: 678 / Avg: 679.67 / Max: 681Min: 678 / Avg: 678.67 / Max: 680

Basis Universal

Basis Universal is a GPU texture codoec. 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 1.12Settings: UASTC Level 323Linux 5.3306090120150SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3113.02113.04113.011. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 323Linux 5.320406080100Min: 112.96 / Avg: 113.02 / Max: 113.1Min: 113.02 / Avg: 113.04 / Max: 113.07Min: 112.98 / Avg: 113.01 / Max: 113.031. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOAT23Linux 5.370M140M210M280M350MSE +/- 78069.68, N = 3SE +/- 148747.23, N = 3SE +/- 392759.75, N = 3334295678.01333884203.29333392595.361. (CC) gcc options: -O3 -march=native -lm
OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOAT23Linux 5.360M120M180M240M300MMin: 334140488.6 / Avg: 334295678.01 / Max: 334388165.95Min: 333602535.36 / Avg: 333884203.29 / Max: 334107950.45Min: 332997441.52 / Avg: 333392595.36 / Max: 334178109.981. (CC) gcc options: -O3 -march=native -lm

GLmark2

This is a test of Linaro's glmark2 port, currently using the X11 OpenGL 2.0 target. GLmark2 is a basic OpenGL benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterGLmark2 2020.04Resolution: 1920 x 108023Linux 5.32004006008001000839840847

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon Obj23Linux 5.3246810SE +/- 0.0093, N = 3SE +/- 0.0050, N = 3SE +/- 0.0056, N = 36.74386.59046.7854MIN: 6.68 / MAX: 6.88MIN: 6.54 / MAX: 6.72MIN: 6.75 / MAX: 6.9
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon Obj23Linux 5.33691215Min: 6.73 / Avg: 6.74 / Max: 6.76Min: 6.58 / Avg: 6.59 / Max: 6.6Min: 6.78 / Avg: 6.79 / Max: 6.8

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_ica23Linux 5.320406080100SE +/- 1.04, N = 4SE +/- 0.96, N = 4SE +/- 0.91, N = 578.7867.8367.91
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_ica23Linux 5.31530456075Min: 75.71 / Avg: 78.78 / Max: 80.35Min: 66.54 / Avg: 67.83 / Max: 70.67Min: 66.56 / Avg: 67.91 / Max: 71.38

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startup23Linux 5.33691215SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 313.113.013.2
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startup23Linux 5.348121620Min: 12.9 / Avg: 13.07 / Max: 13.3Min: 12.9 / Avg: 13 / Max: 13.1Min: 13 / Avg: 13.2 / Max: 13.5

Montage Astronomical Image Mosaic Engine

Montage is an open-source astronomical image mosaic engine. This BSD-licensed astronomy software is developed by the California Institute of Technology, Pasadena. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMontage Astronomical Image Mosaic Engine 6.0Mosaic of M17, K band, 1.5 deg x 1.5 deg23Linux 5.320406080100SE +/- 1.27, N = 3SE +/- 1.20, N = 3SE +/- 0.53, N = 3107.37108.16107.341. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2
OpenBenchmarking.orgSeconds, Fewer Is BetterMontage Astronomical Image Mosaic Engine 6.0Mosaic of M17, K band, 1.5 deg x 1.5 deg23Linux 5.320406080100Min: 106.05 / Avg: 107.37 / Max: 109.92Min: 106.42 / Avg: 108.16 / Max: 110.46Min: 106.56 / Avg: 107.34 / Max: 108.351. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Crown23Linux 5.31.29312.58623.87935.17246.4655SE +/- 0.0132, N = 3SE +/- 0.0204, N = 3SE +/- 0.0117, N = 35.72015.57645.7470MIN: 5.67 / MAX: 5.82MIN: 5.5 / MAX: 5.69MIN: 5.69 / MAX: 5.85
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Crown23Linux 5.3246810Min: 5.7 / Avg: 5.72 / Max: 5.74Min: 5.54 / Avg: 5.58 / Max: 5.6Min: 5.72 / Avg: 5.75 / Max: 5.76

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 1000023Linux 5.3200K400K600K800K1000KSE +/- 2803.79, N = 3SE +/- 7515.99, N = 3SE +/- 10965.48, N = 3991803.81001969.7970864.6
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 1000023Linux 5.3200K400K600K800K1000KMin: 986749.7 / Avg: 991803.83 / Max: 996434.6Min: 987074.9 / Avg: 1001969.7 / Max: 1011171.8Min: 949476.7 / Avg: 970864.63 / Max: 985758.9

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 1000023Linux 5.3200K400K600K800K1000KSE +/- 6863.89, N = 3SE +/- 15644.14, N = 3SE +/- 8454.54, N = 31029071.51039980.01051454.3
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 1000023Linux 5.3200K400K600K800K1000KMin: 1019962.4 / Avg: 1029071.53 / Max: 1042520.3Min: 1016505.1 / Avg: 1039979.97 / Max: 1069631.5Min: 1034548.9 / Avg: 1051454.33 / Max: 1060211.4

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmark23Linux 5.31428425670SE +/- 0.04, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 360.9660.9660.96MIN: 1 / MAX: 210MIN: 1 / MAX: 211MIN: 1 / MAX: 210
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 0.9Benchmark: vklBenchmark23Linux 5.31224364860Min: 60.89 / Avg: 60.96 / Max: 61Min: 60.67 / Avg: 60.96 / Max: 61.33Min: 60.89 / Avg: 60.96 / Max: 61.11

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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU23Linux 5.3510152025SE +/- 0.90, N = 12SE +/- 0.78, N = 15SE +/- 0.84, N = 1519.6019.0219.39MIN: 16.5MIN: 16.48MIN: 16.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU23Linux 5.3510152025Min: 16.6 / Avg: 19.6 / Max: 24.61Min: 16.61 / Avg: 19.02 / Max: 24.51Min: 16.62 / Avg: 19.39 / Max: 24.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Crown23Linux 5.3246810SE +/- 0.0150, N = 3SE +/- 0.0047, N = 3SE +/- 0.0180, N = 36.22746.06696.2259MIN: 6.17 / MAX: 6.35MIN: 5.99 / MAX: 6.2MIN: 6.17 / MAX: 6.35
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Crown23Linux 5.3246810Min: 6.21 / Avg: 6.23 / Max: 6.26Min: 6.06 / Avg: 6.07 / Max: 6.07Min: 6.21 / Avg: 6.23 / Max: 6.26

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4K23Linux 5.3246810SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 36.436.326.431. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4K23Linux 5.33691215Min: 6.35 / Avg: 6.43 / Max: 6.5Min: 6.26 / Avg: 6.32 / Max: 6.41Min: 6.36 / Avg: 6.43 / Max: 6.521. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 Time23Linux 5.320406080100SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 391.4691.3091.301. RawTherapee, version 5.6, command line.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Time23Linux 5.320406080100Min: 91.3 / Avg: 91.46 / Max: 91.68Min: 91.22 / Avg: 91.3 / Max: 91.42Min: 91.23 / Avg: 91.29 / Max: 91.361. RawTherapee, version 5.6, command line.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon23Linux 5.3246810SE +/- 0.0354, N = 3SE +/- 0.0202, N = 3SE +/- 0.0263, N = 36.70196.64416.6714MIN: 6.6 / MAX: 6.81MIN: 6.56 / MAX: 6.76MIN: 6.6 / MAX: 6.79
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon23Linux 5.33691215Min: 6.63 / Avg: 6.7 / Max: 6.74Min: 6.61 / Avg: 6.64 / Max: 6.68Min: 6.64 / Avg: 6.67 / Max: 6.72

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to323Linux 5.3100200300400500473474473

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropy23Linux 5.31224364860SE +/- 0.35, N = 3SE +/- 0.48, N = 9SE +/- 0.17, N = 352.8151.1550.57
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropy23Linux 5.31122334455Min: 52.13 / Avg: 52.81 / Max: 53.28Min: 48.92 / Avg: 51.15 / Max: 53.62Min: 50.22 / Avg: 50.57 / Max: 50.76

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Delete23Linux 5.34080120160200SE +/- 0.20, N = 3SE +/- 0.32, N = 3SE +/- 0.07, N = 3167.13166.76165.681. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Delete23Linux 5.3306090120150Min: 166.73 / Avg: 167.13 / Max: 167.37Min: 166.19 / Avg: 166.76 / Max: 167.31Min: 165.55 / Avg: 165.68 / Max: 165.771. (CXX) g++ options: -O3 -lsnappy -lpthread

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon23Linux 5.3246810SE +/- 0.0351, N = 3SE +/- 0.0041, N = 3SE +/- 0.0421, N = 37.68927.70737.7138MIN: 7.59 / MAX: 7.84MIN: 7.65 / MAX: 7.81MIN: 7.62 / MAX: 7.91
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon23Linux 5.33691215Min: 7.62 / Avg: 7.69 / Max: 7.73Min: 7.7 / Avg: 7.71 / Max: 7.71Min: 7.67 / Avg: 7.71 / Max: 7.8

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential Fill23Linux 5.3306090120150SE +/- 1.28, N = 3SE +/- 0.61, N = 3SE +/- 0.21, N = 3156.04155.82152.441. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential Fill23Linux 5.3306090120150Min: 153.79 / Avg: 156.04 / Max: 158.21Min: 154.85 / Avg: 155.82 / Max: 156.94Min: 152.1 / Avg: 152.44 / Max: 152.811. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential Fill23Linux 5.3246810SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 38.58.58.71. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential Fill23Linux 5.33691215Min: 8.4 / Avg: 8.5 / Max: 8.6Min: 8.5 / Avg: 8.53 / Max: 8.6Min: 8.7 / Avg: 8.7 / Max: 8.71. (CXX) g++ options: -O3 -lsnappy -lpthread

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: Memorial23Linux 5.30.58731.17461.76192.34922.9365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.602.612.60
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.2.0Scene: Memorial23Linux 5.3246810Min: 2.6 / Avg: 2.6 / Max: 2.61Min: 2.6 / Avg: 2.61 / Max: 2.61Min: 2.6 / Avg: 2.6 / Max: 2.6

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 Time23Linux 5.320406080100SE +/- 0.61, N = 3SE +/- 0.52, N = 3SE +/- 0.53, N = 375.8476.2276.14
OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching Time23Linux 5.31530456075Min: 74.72 / Avg: 75.84 / Max: 76.83Min: 75.53 / Avg: 76.22 / Max: 77.24Min: 75.11 / Avg: 76.14 / Max: 76.88

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 3D Elevated Function In Random Colors, 100 Times23Linux 5.320406080100SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 375.9475.9975.971. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: 3D Elevated Function In Random Colors, 100 Times23Linux 5.31530456075Min: 75.89 / Avg: 75.94 / Max: 75.99Min: 75.99 / Avg: 75.99 / Max: 75.99Min: 75.92 / Avg: 75.97 / Max: 76.011. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very Fast23Linux 5.3246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.977.977.961. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Very Fast23Linux 5.33691215Min: 7.97 / Avg: 7.97 / Max: 7.98Min: 7.97 / Avg: 7.97 / Max: 7.98Min: 7.96 / Avg: 7.96 / Max: 7.971. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepoint23Linux 5.320406080100SE +/- 0.42, N = 3SE +/- 0.47, N = 3SE +/- 0.18, N = 374.6275.0274.84
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepoint23Linux 5.31428425670Min: 73.79 / Avg: 74.62 / Max: 75.08Min: 74.1 / Avg: 75.02 / Max: 75.67Min: 74.48 / Avg: 74.84 / Max: 75.08

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPU23Linux 5.313002600390052006500SE +/- 43.59, N = 3SE +/- 14.43, N = 3SE +/- 50.98, N = 3593859215915
OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPU23Linux 5.310002000300040005000Min: 5862 / Avg: 5937.67 / Max: 6013Min: 5896 / Avg: 5921 / Max: 5946Min: 5821 / Avg: 5915.33 / Max: 5996

Basis Universal

Basis Universal is a GPU texture codoec. 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 1.12Settings: ETC1S23Linux 5.31632486480SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 373.4773.3273.081. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1S23Linux 5.31428425670Min: 73.37 / Avg: 73.47 / Max: 73.63Min: 73.11 / Avg: 73.32 / Max: 73.55Min: 73 / Avg: 73.08 / Max: 73.141. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 10023Linux 5.315K30K45K60K75KSE +/- 53.44, N = 3SE +/- 119.13, N = 3SE +/- 124.24, N = 37185271828716831. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 10023Linux 5.312K24K36K48K60KMin: 71748 / Avg: 71851.67 / Max: 71926Min: 71604 / Avg: 71828.33 / Max: 72010Min: 71551 / Avg: 71682.67 / Max: 719311. (CXX) g++ options: -fPIC -O3 -rdynamic -lboost_system -lboost_thread -lboost_filesystem -lboost_chrono -lboost_date_time -lboost_atomic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

KeyDB

A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.1623Linux 5.360K120K180K240K300KSE +/- 461.96, N = 3SE +/- 3662.06, N = 3SE +/- 2596.47, N = 3256466.80254471.41257477.281. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.1623Linux 5.340K80K120K160K200KMin: 255551.82 / Avg: 256466.8 / Max: 257035.3Min: 247426.76 / Avg: 254471.41 / Max: 259729.16Min: 253184.52 / Avg: 257477.28 / Max: 262154.31. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Crypto++

Crypto++ is a C++ class library of cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed Algorithms23Linux 5.360120180240300SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.29, N = 3290.38290.54289.761. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed Algorithms23Linux 5.350100150200250Min: 290.25 / Avg: 290.38 / Max: 290.52Min: 290.4 / Avg: 290.54 / Max: 290.62Min: 289.33 / Avg: 289.76 / Max: 290.321. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: go23Linux 5.370140210280350344344344

Git

This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git Commands23Linux 5.31428425670SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 364.0464.0964.051. git version 2.20.1
OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git Commands23Linux 5.31326395265Min: 63.86 / Avg: 64.04 / Max: 64.17Min: 63.86 / Avg: 64.09 / Max: 64.32Min: 63.82 / Avg: 64.05 / Max: 64.221. git version 2.20.1

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSC23Linux 5.30.1620.3240.4860.6480.81SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.720.720.72MIN: 0.7 / MAX: 0.73MIN: 0.7MIN: 0.71
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSC23Linux 5.3246810Min: 0.72 / Avg: 0.72 / Max: 0.72Min: 0.71 / Avg: 0.72 / Max: 0.72Min: 0.72 / Avg: 0.72 / Max: 0.72

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and Prism23Linux 5.30.180.360.540.720.9SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.800.800.80MIN: 0.78 / MAX: 0.85MIN: 0.77 / MAX: 0.85MIN: 0.78 / MAX: 0.85
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and Prism23Linux 5.3246810Min: 0.8 / Avg: 0.8 / Max: 0.8Min: 0.79 / Avg: 0.8 / Max: 0.8Min: 0.8 / Avg: 0.8 / Max: 0.8

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNet23Linux 5.380K160K240K320K400KSE +/- 26.31, N = 3SE +/- 113.77, N = 3SE +/- 62.52, N = 3374925374993374809
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNet23Linux 5.370K140K210K280K350KMin: 374873 / Avg: 374925 / Max: 374958Min: 374778 / Avg: 374993 / Max: 375165Min: 374709 / Avg: 374809 / Max: 374924

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobile23Linux 5.370K140K210K280K350KSE +/- 320.08, N = 3SE +/- 273.31, N = 3SE +/- 78.69, N = 3311279311149311185
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobile23Linux 5.350K100K150K200K250KMin: 310691 / Avg: 311279.33 / Max: 311792Min: 310802 / Avg: 311148.67 / Max: 311688Min: 311089 / Avg: 311185 / Max: 311341

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quant23Linux 5.360K120K180K240K300KSE +/- 64.63, N = 3SE +/- 100.66, N = 3SE +/- 87.08, N = 3264281264172264321
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quant23Linux 5.350K100K150K200K250KMin: 264183 / Avg: 264281 / Max: 264403Min: 263971 / Avg: 264171.67 / Max: 264286Min: 264160 / Avg: 264321 / Max: 264459

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Float23Linux 5.360K120K180K240K300KSE +/- 43.21, N = 3SE +/- 16.26, N = 3SE +/- 35.46, N = 3257938257984257990
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Float23Linux 5.340K80K120K160K200KMin: 257852 / Avg: 257938.33 / Max: 257985Min: 257953 / Avg: 257984 / Max: 258008Min: 257944 / Avg: 257990.33 / Max: 258060

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solver23Linux 5.31326395265SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 359.0158.8658.721. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solver23Linux 5.31224364860Min: 58.74 / Avg: 59.01 / Max: 59.16Min: 58.83 / Avg: 58.86 / Max: 58.91Min: 58.55 / Avg: 58.72 / Max: 58.821. (CXX) g++ options: -O2 -lOpenCL

Basis Universal

Basis Universal is a GPU texture codoec. 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 1.12Settings: UASTC Level 223Linux 5.31326395265SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 358.7358.8058.721. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 223Linux 5.31224364860Min: 58.72 / Avg: 58.73 / Max: 58.75Min: 58.75 / Avg: 58.8 / Max: 58.86Min: 58.69 / Avg: 58.72 / Max: 58.741. (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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU23Linux 5.320406080100SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3109.83109.80109.72MIN: 109.35MIN: 109.42MIN: 109.351. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU23Linux 5.320406080100Min: 109.77 / Avg: 109.83 / Max: 109.91Min: 109.77 / Avg: 109.79 / Max: 109.82Min: 109.68 / Avg: 109.72 / Max: 109.791. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: f32 - Engine: CPU23Linux 5.3306090120150SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3147.34147.04146.75MIN: 145.82MIN: 145.7MIN: 145.371. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: f32 - Engine: CPU23Linux 5.3306090120150Min: 147.15 / Avg: 147.34 / Max: 147.57Min: 146.85 / Avg: 147.04 / Max: 147.14Min: 146.58 / Avg: 146.75 / Max: 146.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Sockperf

This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under LoadLinux 5.3510152025SE +/- 13914.73, N = 2019.251. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

eSpeak-NG Speech Engine

This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. This test profile is now tracking the eSpeak-NG version of eSpeak. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech Synthesis23Linux 5.3918273645SE +/- 0.03, N = 4SE +/- 0.02, N = 4SE +/- 0.03, N = 438.9938.9638.971. (CC) gcc options: -O2 -std=c99
OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech Synthesis23Linux 5.3816243240Min: 38.93 / Avg: 38.99 / Max: 39.06Min: 38.92 / Avg: 38.96 / Max: 39.03Min: 38.93 / Avg: 38.97 / Max: 39.071. (CC) gcc options: -O2 -std=c99

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Files23Linux 5.350100150200250SE +/- 7.28, N = 15SE +/- 22.33, N = 12SE +/- 14.12, N = 12167.42206.63167.001. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Files23Linux 5.34080120160200Min: 118.34 / Avg: 167.42 / Max: 216.37Min: 117.03 / Avg: 206.63 / Max: 361.14Min: 114.39 / Avg: 167 / Max: 255.611. (CC) gcc options: -lm

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlib23Linux 5.3918273645SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 338.538.738.5
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlib23Linux 5.3816243240Min: 38.4 / Avg: 38.5 / Max: 38.6Min: 38.7 / Avg: 38.73 / Max: 38.8Min: 38.5 / Avg: 38.53 / Max: 38.6

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4K23Linux 5.31632486480SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 372.7372.7972.76MIN: 65.52 / MAX: 77.31MIN: 65.93 / MAX: 77.49MIN: 65.87 / MAX: 77.41. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4K23Linux 5.31428425670Min: 72.64 / Avg: 72.73 / Max: 72.82Min: 72.69 / Avg: 72.79 / Max: 72.85Min: 72.7 / Avg: 72.76 / Max: 72.791. (CC) gcc options: -pthread

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compile23Linux 5.360120180240300SE +/- 0.33, N = 3259258258
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compile23Linux 5.350100150200250Min: 258 / Avg: 258.67 / Max: 259

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message Passing23Linux 5.31.4M2.8M4.2M5.6M7MSE +/- 61448.17, N = 9SE +/- 60575.70, N = 3SE +/- 53048.21, N = 36350040.276349001.106285917.101. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message Passing23Linux 5.31.1M2.2M3.3M4.4M5.5MMin: 6026626.45 / Avg: 6350040.27 / Max: 6554256.04Min: 6233615.51 / Avg: 6349001.1 / Max: 6438676.27Min: 6218127.47 / Avg: 6285917.1 / Max: 6390492.621. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

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 9.0.3+dfsgProcessing 60 Page PDF Document23Linux 5.31122334455SE +/- 0.33, N = 3SE +/- 0.32, N = 3SE +/- 0.22, N = 349.5249.6049.81
OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 9.0.3+dfsgProcessing 60 Page PDF Document23Linux 5.31020304050Min: 49.02 / Avg: 49.52 / Max: 50.14Min: 49.25 / Avg: 49.6 / Max: 50.25Min: 49.53 / Avg: 49.81 / Max: 50.26

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: XZ 0 - Process: Decompression23Linux 5.3204060801001071071071. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: XZ 0 - Process: Compression23Linux 5.3816243240SE +/- 0.33, N = 33434341. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: XZ 0 - Process: Compression23Linux 5.3714212835Min: 33 / Avg: 33.67 / Max: 341. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

LibRaw

LibRaw is a RAW image decoder for digital camera photos. This test profile runs LibRaw's post-processing benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing Benchmark23Linux 5.3612182430SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 325.7725.8025.791. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing Benchmark23Linux 5.3612182430Min: 25.71 / Avg: 25.77 / Max: 25.87Min: 25.75 / Avg: 25.8 / Max: 25.89Min: 25.76 / Avg: 25.79 / Max: 25.821. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

Sockperf

This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: Throughput23Linux 5.370K140K210K280K350KSE +/- 3294.17, N = 25SE +/- 2917.43, N = 5SE +/- 9499.69, N = 203384293251603389761. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: Throughput23Linux 5.360K120K180K240K300KMin: 310120 / Avg: 338428.96 / Max: 359596Min: 320199 / Avg: 325159.8 / Max: 335475Min: 311031 / Avg: 338975.5 / Max: 5117851. (CXX) g++ options: --param -O3 -rdynamic -ldl -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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU23Linux 5.3246810SE +/- 0.02645, N = 3SE +/- 0.09334, N = 15SE +/- 0.08661, N = 158.137327.964807.87420MIN: 7.83MIN: 6.78MIN: 7.061. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU23Linux 5.33691215Min: 8.11 / Avg: 8.14 / Max: 8.19Min: 7.1 / Avg: 7.96 / Max: 8.29Min: 7.36 / Avg: 7.87 / Max: 8.131. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest Compression23Linux 5.31020304050SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 344.1744.2844.231. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest Compression23Linux 5.3918273645Min: 44.05 / Avg: 44.17 / Max: 44.26Min: 44.2 / Avg: 44.28 / Max: 44.37Min: 44.16 / Avg: 44.23 / Max: 44.271. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p23Linux 5.360120180240300SE +/- 0.08, N = 3SE +/- 0.45, N = 3SE +/- 0.09, N = 3286.06286.13286.73MIN: 209.37 / MAX: 474.93MIN: 209.24 / MAX: 478.75MIN: 209.66 / MAX: 489.661. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p23Linux 5.350100150200250Min: 285.9 / Avg: 286.06 / Max: 286.18Min: 285.67 / Avg: 286.13 / Max: 287.02Min: 286.58 / Avg: 286.73 / Max: 286.891. (CC) gcc options: -pthread

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test23Linux 5.36K12K18K24K30KSE +/- 133.98, N = 3SE +/- 116.95, N = 3SE +/- 195.91, N = 32965529697297021. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test23Linux 5.35K10K15K20K25KMin: 29466 / Avg: 29655 / Max: 29914Min: 29492 / Avg: 29697.33 / Max: 29897Min: 29321 / Avg: 29702.33 / Max: 299711. (CXX) g++ options: -pipe -lpthread

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_template23Linux 5.320406080100SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 398.098.297.2
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_template23Linux 5.320406080100Min: 97.8 / Avg: 98.03 / Max: 98.2Min: 98 / Avg: 98.2 / Max: 98.4Min: 97 / Avg: 97.17 / Max: 97.3

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT Mapping23Linux 5.390180270360450SE +/- 0.10, N = 3SE +/- 0.22, N = 3SE +/- 0.33, N = 3431.77432.26431.941. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT Mapping23Linux 5.380160240320400Min: 431.6 / Avg: 431.77 / Max: 431.95Min: 431.92 / Avg: 432.26 / Max: 432.67Min: 431.29 / Avg: 431.94 / Max: 432.351. (CXX) g++ options: -O3 -std=c++11 -fopenmp

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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU23Linux 5.330060090012001500SE +/- 6.69, N = 3SE +/- 2.30, N = 3SE +/- 0.30, N = 31518.351522.301518.69MIN: 1504.65MIN: 1515.62MIN: 1509.851. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU23Linux 5.330060090012001500Min: 1508.3 / Avg: 1518.35 / Max: 1531.01Min: 1518.12 / Avg: 1522.3 / Max: 1526.04Min: 1518.29 / Avg: 1518.69 / Max: 1519.281. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU23Linux 5.3100200300400500SE +/- 1.71, N = 3SE +/- 0.09, N = 3SE +/- 1.36, N = 3451.36454.85428.18MIN: 446.84MIN: 452.76MIN: 423.121. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU23Linux 5.380160240320400Min: 447.96 / Avg: 451.36 / Max: 453.38Min: 454.68 / Avg: 454.85 / Max: 454.95Min: 426.07 / Avg: 428.18 / Max: 430.731. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamcluster23Linux 5.3816243240SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 336.6036.6136.591. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamcluster23Linux 5.3816243240Min: 36.56 / Avg: 36.6 / Max: 36.63Min: 36.58 / Avg: 36.61 / Max: 36.65Min: 36.58 / Avg: 36.59 / Max: 36.611. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C23Linux 5.310002000300040005000SE +/- 5.63, N = 3SE +/- 5.98, N = 3SE +/- 4.85, N = 34804.804796.674757.771. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C23Linux 5.38001600240032004000Min: 4797.4 / Avg: 4804.8 / Max: 4815.85Min: 4786.55 / Avg: 4796.67 / Max: 4807.25Min: 4748.09 / Avg: 4757.77 / Max: 4763.091. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU23Linux 5.33691215SE +/- 0.00712, N = 3SE +/- 0.34521, N = 15SE +/- 0.00132, N = 38.653849.014278.63063MIN: 8.57MIN: 8.26MIN: 8.541. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU23Linux 5.33691215Min: 8.64 / Avg: 8.65 / Max: 8.66Min: 8.54 / Avg: 9.01 / Max: 13.84Min: 8.63 / Avg: 8.63 / Max: 8.631. (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 a sample file (an Ubuntu ISO) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 323Linux 5.3400800120016002000SE +/- 0.88, N = 3SE +/- 3.24, N = 3SE +/- 2.84, N = 31741.21741.01743.71. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 323Linux 5.330060090012001500Min: 1740 / Avg: 1741.17 / Max: 1742.9Min: 1735.5 / Avg: 1740.97 / Max: 1746.7Min: 1739.1 / Avg: 1743.7 / Max: 1748.91. (CC) gcc options: -O3 -pthread -lz -llzma

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H223Linux 5.39001800270036004500SE +/- 53.08, N = 4SE +/- 43.29, N = 4SE +/- 36.67, N = 20393240294039
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H223Linux 5.37001400210028003500Min: 3785 / Avg: 3932 / Max: 4031Min: 3939 / Avg: 4028.5 / Max: 4147Min: 3734 / Avg: 4039.05 / Max: 4407

Kvazaar

This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra Fast23Linux 5.348121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 317.4117.4117.341. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.0Video Input: Bosphorus 1080p - Video Preset: Ultra Fast23Linux 5.348121620Min: 17.4 / Avg: 17.41 / Max: 17.42Min: 17.4 / Avg: 17.41 / Max: 17.42Min: 17.33 / Avg: 17.34 / Max: 17.371. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: AES-25623Linux 5.3160320480640800SE +/- 1.92, N = 3SE +/- 0.34, N = 3SE +/- 2.14, N = 3742.85739.71736.311. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: AES-25623Linux 5.3130260390520650Min: 739.31 / Avg: 742.85 / Max: 745.91Min: 739.14 / Avg: 739.71 / Max: 740.3Min: 732.33 / Avg: 736.31 / Max: 739.651. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Timed Apache Compilation

This test times how long it takes to build the Apache HTTPD web server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compile23Linux 5.3816243240SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 333.5833.4833.58
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compile23Linux 5.3714212835Min: 33.4 / Avg: 33.58 / Max: 33.79Min: 33.25 / Avg: 33.48 / Max: 33.6Min: 33.45 / Avg: 33.58 / Max: 33.82

Algebraic Multi-Grid Benchmark

AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark23Linux 5.316K32K48K64K80KSE +/- 9.92, N = 3SE +/- 86.27, N = 3SE +/- 87.89, N = 374843.3274691.7974835.811. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi
OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark23Linux 5.313K26K39K52K65KMin: 74825.54 / Avg: 74843.32 / Max: 74859.84Min: 74564.7 / Avg: 74691.79 / Max: 74856.4Min: 74700.37 / Avg: 74835.81 / Max: 75000.561. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaos23Linux 5.34080120160200164165163

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loads23Linux 5.3816243240SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 333.333.333.2
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loads23Linux 5.3714212835Min: 33.3 / Avg: 33.33 / Max: 33.4Min: 33.2 / Avg: 33.33 / Max: 33.4Min: 33.1 / Avg: 33.17 / Max: 33.2

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: RdRand23Linux 5.340K80K120K160K200KSE +/- 11.03, N = 3SE +/- 2.98, N = 3SE +/- 5.50, N = 3185841.66185835.07185838.811. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: RdRand23Linux 5.330K60K90K120K150KMin: 185827.61 / Avg: 185841.66 / Max: 185863.41Min: 185829.2 / Avg: 185835.07 / Max: 185838.89Min: 185827.89 / Avg: 185838.81 / Max: 185845.391. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Tesseract OCR

Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.0Time To OCR 7 Images23Linux 5.3714212835SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 330.1330.1730.19
OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.0Time To OCR 7 Images23Linux 5.3714212835Min: 29.99 / Avg: 30.13 / Max: 30.39Min: 30 / Avg: 30.17 / Max: 30.47Min: 30.02 / Avg: 30.19 / Max: 30.45

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMA23Linux 5.3306090120150SE +/- 0.84, N = 3SE +/- 0.81, N = 3SE +/- 0.78, N = 3130.14126.98126.281. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: NUMA23Linux 5.320406080100Min: 128.47 / Avg: 130.14 / Max: 130.98Min: 126.01 / Avg: 126.98 / Max: 128.58Min: 124.73 / Avg: 126.28 / Max: 127.181. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Stress23Linux 5.36001200180024003000SE +/- 7.75, N = 3SE +/- 6.95, N = 3SE +/- 1.41, N = 32563.732555.282547.131. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Stress23Linux 5.3400800120016002000Min: 2548.4 / Avg: 2563.73 / Max: 2573.39Min: 2546.52 / Avg: 2555.28 / Max: 2569Min: 2545.55 / Avg: 2547.13 / Max: 2549.951. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Malloc23Linux 5.38M16M24M32M40MSE +/- 23175.94, N = 3SE +/- 21862.11, N = 3SE +/- 11923.26, N = 335040588.3535071564.9935069017.961. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Malloc23Linux 5.36M12M18M24M30MMin: 35002064.93 / Avg: 35040588.35 / Max: 35082173.42Min: 35042220.74 / Avg: 35071564.99 / Max: 35114309.19Min: 35050019.78 / Avg: 35069017.96 / Max: 35090998.811. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAP23Linux 5.320406080100SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 386.7286.8686.861. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAP23Linux 5.31632486480Min: 86.63 / Avg: 86.72 / Max: 86.79Min: 86.83 / Avg: 86.86 / Max: 86.9Min: 86.83 / Avg: 86.86 / Max: 86.891. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Crypto23Linux 5.330060090012001500SE +/- 0.45, N = 3SE +/- 1.79, N = 3SE +/- 0.52, N = 31236.121233.541236.011. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Crypto23Linux 5.32004006008001000Min: 1235.23 / Avg: 1236.12 / Max: 1236.71Min: 1230 / Avg: 1233.54 / Max: 1235.74Min: 1235.06 / Avg: 1236.01 / Max: 1236.841. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory Copying23Linux 5.3150300450600750SE +/- 1.75, N = 3SE +/- 1.86, N = 3SE +/- 0.58, N = 3699.26709.53708.501. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory Copying23Linux 5.3120240360480600Min: 695.99 / Avg: 699.26 / Max: 701.96Min: 706.16 / Avg: 709.53 / Max: 712.58Min: 707.43 / Avg: 708.5 / Max: 709.441. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFD23Linux 5.370140210280350SE +/- 3.04, N = 3SE +/- 0.45, N = 3SE +/- 3.85, N = 3328.39330.43328.061. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MEMFD23Linux 5.360120180240300Min: 322.35 / Avg: 328.39 / Max: 332.06Min: 329.57 / Avg: 330.43 / Max: 331.1Min: 320.37 / Avg: 328.06 / Max: 332.291. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String Functions23Linux 5.3120K240K360K480K600KSE +/- 3212.34, N = 3SE +/- 1986.37, N = 3SE +/- 2748.16, N = 3543539.72545105.28546526.131. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String Functions23Linux 5.390K180K270K360K450KMin: 537518.25 / Avg: 543539.72 / Max: 548490.52Min: 542113.43 / Avg: 545105.28 / Max: 548864.74Min: 541072.51 / Avg: 546526.13 / Max: 549845.151. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data Sorting23Linux 5.320406080100SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.60, N = 384.0883.5583.531. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data Sorting23Linux 5.31632486480Min: 83.83 / Avg: 84.08 / Max: 84.27Min: 83.4 / Avg: 83.55 / Max: 83.67Min: 82.4 / Avg: 83.53 / Max: 84.431. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context Switching23Linux 5.3400K800K1200K1600K2000KSE +/- 13890.18, N = 3SE +/- 12187.34, N = 3SE +/- 12658.86, N = 31640248.861645592.491659533.181. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context Switching23Linux 5.3300K600K900K1200K1500KMin: 1614092.58 / Avg: 1640248.86 / Max: 1661432.42Min: 1621294.57 / Avg: 1645592.49 / Max: 1659415.34Min: 1638932.64 / Avg: 1659533.18 / Max: 1682579.181. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket Activity23Linux 5.36001200180024003000SE +/- 21.52, N = 3SE +/- 24.29, N = 3SE +/- 22.16, N = 32603.182650.592630.951. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Socket Activity23Linux 5.35001000150020002500Min: 2560.96 / Avg: 2603.18 / Max: 2631.5Min: 2603.22 / Avg: 2650.59 / Max: 2683.62Min: 2586.82 / Avg: 2630.95 / Max: 2656.491. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector Math23Linux 5.38K16K24K32K40KSE +/- 6.31, N = 3SE +/- 22.72, N = 3SE +/- 3.56, N = 339291.8539269.6239289.171. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector Math23Linux 5.37K14K21K28K35KMin: 39281.52 / Avg: 39291.85 / Max: 39303.3Min: 39226.77 / Avg: 39269.62 / Max: 39304.14Min: 39282.16 / Avg: 39289.17 / Max: 39293.751. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix Math23Linux 5.35K10K15K20K25KSE +/- 45.57, N = 3SE +/- 98.55, N = 3SE +/- 24.40, N = 323605.4123524.5423671.831. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix Math23Linux 5.34K8K12K16K20KMin: 23557.94 / Avg: 23605.41 / Max: 23696.52Min: 23348.74 / Avg: 23524.54 / Max: 23689.62Min: 23645.7 / Avg: 23671.83 / Max: 23720.591. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Semaphores23Linux 5.3200K400K600K800K1000KSE +/- 287.20, N = 3SE +/- 627.25, N = 3SE +/- 179.56, N = 3960119.66960296.47960900.331. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Semaphores23Linux 5.3170K340K510K680K850KMin: 959569.68 / Avg: 960119.66 / Max: 960538.13Min: 959154.29 / Avg: 960296.47 / Max: 961316.88Min: 960554.57 / Avg: 960900.33 / Max: 961157.271. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Forking23Linux 5.310K20K30K40K50KSE +/- 125.92, N = 3SE +/- 120.51, N = 3SE +/- 202.61, N = 345129.6845082.0144899.221. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Forking23Linux 5.38K16K24K32K40KMin: 44933.21 / Avg: 45129.68 / Max: 45364.36Min: 44841.82 / Avg: 45082.01 / Max: 45219.29Min: 44572.52 / Avg: 44899.22 / Max: 45270.171. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbody23Linux 5.3306090120150SE +/- 0.58, N = 3157157157
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbody23Linux 5.3306090120150Min: 156 / Avg: 157 / Max: 158

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: float23Linux 5.3306090120150SE +/- 0.33, N = 3151151151
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: float23Linux 5.3306090120150Min: 150 / Avg: 150.67 / Max: 151

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Libdeflate 1 - Process: Decompression23Linux 5.320040060080010009729729721. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Libdeflate 1 - Process: Compression23Linux 5.34080120160200SE +/- 0.33, N = 32032042031. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Libdeflate 1 - Process: Compression23Linux 5.34080120160200Min: 202 / Avg: 202.67 / Max: 2031. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-2823Linux 5.3612182430SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 326.2126.3626.101. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-2823Linux 5.3612182430Min: 26.05 / Avg: 26.21 / Max: 26.52Min: 26.09 / Avg: 26.36 / Max: 26.53Min: 26.03 / Avg: 26.1 / Max: 26.171. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 8 - Process: Decompression23Linux 5.32004006008001000SE +/- 0.33, N = 31147114711471. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 8 - Process: Decompression23Linux 5.32004006008001000Min: 1146 / Avg: 1146.67 / Max: 11471. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 8 - Process: Compression23Linux 5.316324864807474741. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaes23Linux 5.3306090120150135136135

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 2 - Process: Decompression23Linux 5.3140280420560700SE +/- 0.33, N = 3SE +/- 0.88, N = 36326346331. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 2 - Process: Decompression23Linux 5.3110220330440550Min: 632 / Avg: 632.33 / Max: 633Min: 631 / Avg: 632.67 / Max: 6341. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 2 - Process: Compression23Linux 5.340801201602001621621621. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Euclidean Cluster23Linux 5.32004006008001000SE +/- 0.19, N = 3SE +/- 0.35, N = 3SE +/- 0.12, N = 3862.30862.27863.381. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Euclidean Cluster23Linux 5.3150300450600750Min: 861.94 / Avg: 862.3 / Max: 862.57Min: 861.58 / Avg: 862.27 / Max: 862.64Min: 863.14 / Avg: 863.38 / Max: 863.541. (CXX) g++ options: -O3 -std=c++11 -fopenmp

G'MIC

G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: Plotting Isosurface Of A 3D Volume, 1000 Times23Linux 5.3612182430SE +/- 0.32, N = 3SE +/- 0.32, N = 3SE +/- 0.18, N = 325.4525.6225.451. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
OpenBenchmarking.orgSeconds, Fewer Is BetterG'MICTest: Plotting Isosurface Of A 3D Volume, 1000 Times23Linux 5.3612182430Min: 25.12 / Avg: 25.45 / Max: 26.09Min: 25.16 / Avg: 25.62 / Max: 26.24Min: 25.15 / Avg: 25.45 / Max: 25.771. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 0 - Process: Decompression23Linux 5.3120240360480600SE +/- 1.15, N = 35405415411. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 0 - Process: Decompression23Linux 5.3100200300400500Min: 538 / Avg: 540 / Max: 5421. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 0 - Process: Compression23Linux 5.390180270360450SE +/- 0.33, N = 3SE +/- 0.33, N = 34074074061. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 0 - Process: Compression23Linux 5.370140210280350Min: 406 / Avg: 406.67 / Max: 407Min: 406 / Avg: 406.33 / Max: 4071. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: Blowfish23Linux 5.360120180240300SE +/- 0.06, N = 3SE +/- 0.42, N = 3SE +/- 0.11, N = 3266.78266.29266.511. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: Blowfish23Linux 5.350100150200250Min: 266.69 / Avg: 266.78 / Max: 266.9Min: 265.46 / Avg: 266.29 / Max: 266.79Min: 266.34 / Avg: 266.51 / Max: 266.711. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: Twofish23Linux 5.350100150200250SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3232.70232.80232.551. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: Twofish23Linux 5.34080120160200Min: 232.6 / Avg: 232.7 / Max: 232.85Min: 232.69 / Avg: 232.8 / Max: 232.95Min: 232.4 / Avg: 232.55 / Max: 232.641. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Decompression23Linux 5.3100200300400500SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 34544544541. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Decompression23Linux 5.380160240320400Min: 454 / Avg: 454.33 / Max: 455Min: 454 / Avg: 454.33 / Max: 455Min: 454 / Avg: 454.33 / Max: 4551. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Compression23Linux 5.320406080100SE +/- 0.58, N = 3SE +/- 0.67, N = 38585851. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Compression23Linux 5.31632486480Min: 84 / Avg: 85 / Max: 86Min: 84 / Avg: 84.67 / Max: 861. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Decompression23Linux 5.32004006008001000SE +/- 0.33, N = 31089108910891. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Decompression23Linux 5.32004006008001000Min: 1088 / Avg: 1088.67 / Max: 10891. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Compression23Linux 5.390180270360450SE +/- 0.33, N = 34014014011. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Compression23Linux 5.370140210280350Min: 400 / Avg: 400.67 / Max: 4011. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080p23Linux 5.3612182430SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 325.2925.2825.181. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080p23Linux 5.3612182430Min: 25.02 / Avg: 25.29 / Max: 25.46Min: 25.15 / Avg: 25.28 / Max: 25.37Min: 25.13 / Avg: 25.18 / Max: 25.231. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussian23Linux 5.3612182430SE +/- 0.20, N = 3SE +/- 0.35, N = 3SE +/- 0.06, N = 323.5224.0223.43
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussian23Linux 5.3612182430Min: 23.32 / Avg: 23.52 / Max: 23.92Min: 23.53 / Avg: 24.02 / Max: 24.7Min: 23.32 / Avg: 23.43 / Max: 23.54

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid Dynamics23Linux 5.3612182430SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 323.5223.5023.53
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid Dynamics23Linux 5.3510152025Min: 23.47 / Avg: 23.52 / Max: 23.56Min: 23.44 / Avg: 23.5 / Max: 23.56Min: 23.47 / Avg: 23.53 / Max: 23.62

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v223Linux 5.370140210280350SE +/- 0.63, N = 3SE +/- 0.38, N = 3SE +/- 0.72, N = 3324.84325.89325.43MIN: 321.69 / MAX: 331.12MIN: 322.8 / MAX: 335.24MIN: 321.79 / MAX: 331.331. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v223Linux 5.360120180240300Min: 323.63 / Avg: 324.84 / Max: 325.76Min: 325.31 / Avg: 325.89 / Max: 326.62Min: 324 / Avg: 325.43 / Max: 326.381. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: CAST-25623Linux 5.320406080100SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3106.82106.73106.561. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: CAST-25623Linux 5.320406080100Min: 106.73 / Avg: 106.82 / Max: 106.93Min: 106.62 / Avg: 106.72 / Max: 106.93Min: 106.49 / Avg: 106.56 / Max: 106.661. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: KASUMI23Linux 5.320406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 377.9677.9477.771. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: KASUMI23Linux 5.31530456075Min: 77.93 / Avg: 77.96 / Max: 78.02Min: 77.9 / Avg: 77.94 / Max: 78Min: 77.72 / Avg: 77.77 / Max: 77.81. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_python23Linux 5.3150300450600750SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3684682682
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_python23Linux 5.3120240360480600Min: 682 / Avg: 683.67 / Max: 686Min: 681 / Avg: 682.33 / Max: 684Min: 682 / Avg: 682.33 / Max: 683

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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU23Linux 5.3612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 324.7424.7624.78MIN: 24.52MIN: 24.49MIN: 24.531. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU23Linux 5.3612182430Min: 24.72 / Avg: 24.74 / Max: 24.78Min: 24.72 / Avg: 24.76 / Max: 24.83Min: 24.74 / Avg: 24.78 / Max: 24.821. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless23Linux 5.3510152025SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 320.6620.6620.671. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless23Linux 5.3510152025Min: 20.65 / Avg: 20.66 / Max: 20.67Min: 20.63 / Avg: 20.66 / Max: 20.68Min: 20.63 / Avg: 20.67 / Max: 20.731. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.123Linux 5.360120180240300SE +/- 0.45, N = 3SE +/- 0.21, N = 3SE +/- 0.43, N = 3297.26297.43297.13MIN: 296.07 / MAX: 300.34MIN: 296.68 / MAX: 299.76MIN: 295.81 / MAX: 299.461. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.123Linux 5.350100150200250Min: 296.47 / Avg: 297.26 / Max: 298.04Min: 297.03 / Avg: 297.43 / Max: 297.73Min: 296.35 / Avg: 297.13 / Max: 297.821. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svm23Linux 5.348121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 313.7313.7413.73
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svm23Linux 5.348121620Min: 13.72 / Avg: 13.73 / Max: 13.75Min: 13.7 / Avg: 13.74 / Max: 13.77Min: 13.68 / Avg: 13.73 / Max: 13.75

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 4.4.123Linux 5.33691215SE +/- 0.07, N = 5SE +/- 0.08, N = 5SE +/- 0.10, N = 511.3111.3011.28
OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 4.4.123Linux 5.33691215Min: 11.23 / Avg: 11.31 / Max: 11.59Min: 11.21 / Avg: 11.3 / Max: 11.6Min: 11.01 / Avg: 11.28 / Max: 11.61

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Fill23Linux 5.3306090120150SE +/- 1.87, N = 5SE +/- 1.18, N = 3SE +/- 1.43, N = 3146.19146.52146.691. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Fill23Linux 5.3306090120150Min: 142.78 / Avg: 146.19 / Max: 152.54Min: 144.21 / Avg: 146.51 / Max: 148.15Min: 144.7 / Avg: 146.69 / Max: 149.461. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random Fill23Linux 5.33691215SE +/- 0.11, N = 5SE +/- 0.07, N = 3SE +/- 0.09, N = 39.19.19.11. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random Fill23Linux 5.33691215Min: 8.7 / Avg: 9.1 / Max: 9.3Min: 9 / Avg: 9.07 / Max: 9.2Min: 8.9 / Avg: 9.07 / Max: 9.21. (CXX) g++ options: -O3 -lsnappy -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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPU23Linux 5.33691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 313.1113.1313.19MIN: 13.01MIN: 13.01MIN: 13.051. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPU23Linux 5.348121620Min: 13.1 / Avg: 13.11 / Max: 13.12Min: 13.12 / Avg: 13.13 / Max: 13.14Min: 13.14 / Avg: 13.19 / Max: 13.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU23Linux 5.31428425670SE +/- 0.01, N = 3SE +/- 0.81, N = 3SE +/- 0.69, N = 1563.9764.7662.48MIN: 63.19MIN: 63.53MIN: 57.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU23Linux 5.31326395265Min: 63.95 / Avg: 63.97 / Max: 63.99Min: 63.93 / Avg: 64.76 / Max: 66.38Min: 57.91 / Avg: 62.48 / Max: 64.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Overwrite23Linux 5.3306090120150SE +/- 1.36, N = 3SE +/- 1.03, N = 3SE +/- 0.27, N = 3149.01147.53145.791. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Overwrite23Linux 5.3306090120150Min: 146.34 / Avg: 149 / Max: 150.81Min: 146.01 / Avg: 147.53 / Max: 149.49Min: 145.45 / Avg: 145.79 / Max: 146.331. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Overwrite23Linux 5.33691215SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 38.99.09.11. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Overwrite23Linux 5.33691215Min: 8.8 / Avg: 8.93 / Max: 9.1Min: 8.9 / Avg: 9 / Max: 9.1Min: 9.1 / Avg: 9.1 / Max: 9.11. (CXX) g++ options: -O3 -lsnappy -lpthread

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C23Linux 5.3130260390520650SE +/- 9.90, N = 3SE +/- 0.32, N = 3SE +/- 6.77, N = 3607.03607.33619.391. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C23Linux 5.3110220330440550Min: 589.04 / Avg: 607.03 / Max: 623.17Min: 606.82 / Avg: 607.33 / Max: 607.91Min: 605.92 / Avg: 619.39 / Max: 627.241. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Sockperf

This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping Pong23Linux 5.3246810SE +/- 0.024, N = 5SE +/- 0.052, N = 5SE +/- 0.017, N = 57.9767.9868.0021. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping Pong23Linux 5.33691215Min: 7.89 / Avg: 7.98 / Max: 8.03Min: 7.91 / Avg: 7.99 / Max: 8.19Min: 7.94 / Avg: 8 / Max: 8.041. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: Spooky3223Linux 5.31326395265SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 357.7757.8057.891. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: Spooky3223Linux 5.31122334455Min: 57.75 / Avg: 57.77 / Max: 57.81Min: 57.74 / Avg: 57.8 / Max: 57.86Min: 57.74 / Avg: 57.89 / Max: 58.091. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: Spooky3223Linux 5.32K4K6K8K10KSE +/- 3.30, N = 3SE +/- 7.20, N = 3SE +/- 9.06, N = 311131.3211153.0511164.271. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: Spooky3223Linux 5.32K4K6K8K10KMin: 11125.17 / Avg: 11131.32 / Max: 11136.45Min: 11139.1 / Avg: 11153.05 / Max: 11163.11Min: 11147.79 / Avg: 11164.27 / Max: 11179.041. (CXX) g++ options: -march=native -O3 -lpthread

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080p23Linux 5.360120180240300SE +/- 0.46, N = 3SE +/- 0.35, N = 3SE +/- 0.72, N = 3272.48272.68272.36MIN: 235.92 / MAX: 296.72MIN: 236.29 / MAX: 296.67MIN: 227.28 / MAX: 296.881. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080p23Linux 5.350100150200250Min: 271.64 / Avg: 272.48 / Max: 273.24Min: 271.99 / Avg: 272.68 / Max: 273.07Min: 271.31 / Avg: 272.36 / Max: 273.721. (CC) gcc options: -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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU23Linux 5.3246810SE +/- 0.01107, N = 3SE +/- 0.00380, N = 3SE +/- 0.00552, N = 38.716638.731498.73283MIN: 8.56MIN: 8.56MIN: 8.541. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU23Linux 5.33691215Min: 8.7 / Avg: 8.72 / Max: 8.74Min: 8.72 / Avg: 8.73 / Max: 8.74Min: 8.72 / Avg: 8.73 / Max: 8.741. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython23Linux 5.313002600390052006500SE +/- 53.57, N = 4SE +/- 30.91, N = 4SE +/- 52.85, N = 4596959826009
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython23Linux 5.310002000300040005000Min: 5816 / Avg: 5968.5 / Max: 6057Min: 5904 / Avg: 5982 / Max: 6036Min: 5918 / Avg: 6008.75 / Max: 6124

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: fasthash3223Linux 5.31020304050SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 343.9243.9143.931. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: fasthash3223Linux 5.3918273645Min: 43.91 / Avg: 43.92 / Max: 43.93Min: 43.9 / Avg: 43.91 / Max: 43.91Min: 43.92 / Avg: 43.93 / Max: 43.931. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: fasthash3223Linux 5.313002600390052006500SE +/- 0.89, N = 3SE +/- 0.51, N = 3SE +/- 2.16, N = 35994.045995.165993.461. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: fasthash3223Linux 5.310002000300040005000Min: 5992.34 / Avg: 5994.04 / Max: 5995.37Min: 5994.15 / Avg: 5995.16 / Max: 5995.77Min: 5989.17 / Avg: 5993.46 / Max: 5996.051. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: t1ha2_atonce23Linux 5.31020304050SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 344.2644.2644.261. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: t1ha2_atonce23Linux 5.3918273645Min: 44.26 / Avg: 44.26 / Max: 44.26Min: 44.26 / Avg: 44.26 / Max: 44.26Min: 44.26 / Avg: 44.26 / Max: 44.261. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: t1ha2_atonce23Linux 5.32K4K6K8K10KSE +/- 14.43, N = 3SE +/- 7.04, N = 3SE +/- 4.12, N = 311255.9811257.8811253.121. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: t1ha2_atonce23Linux 5.32K4K6K8K10KMin: 11240.86 / Avg: 11255.98 / Max: 11284.83Min: 11244.19 / Avg: 11257.88 / Max: 11267.54Min: 11248.7 / Avg: 11253.12 / Max: 11261.351. (CXX) g++ options: -march=native -O3 -lpthread

NeatBench

NeatBench is a benchmark of the cross-platform Neat Video software on the CPU and optional GPU (OpenCL / CUDA) support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPU23Linux 5.3246810SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 37.106.947.06
OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPU23Linux 5.33691215Min: 7.05 / Avg: 7.1 / Max: 7.14Min: 6.82 / Avg: 6.94 / Max: 7.03Min: 6.98 / Avg: 7.06 / Max: 7.19

Basis Universal

Basis Universal is a GPU texture codoec. 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 1.12Settings: UASTC Level 023Linux 5.33691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 310.6410.6310.661. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 023Linux 5.33691215Min: 10.63 / Avg: 10.64 / Max: 10.64Min: 10.63 / Avg: 10.63 / Max: 10.64Min: 10.64 / Avg: 10.66 / Max: 10.691. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot Read23Linux 5.31.34872.69744.04615.39486.7435SE +/- 0.059, N = 3SE +/- 0.012, N = 3SE +/- 0.058, N = 95.9945.9175.9841. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot Read23Linux 5.3246810Min: 5.92 / Avg: 5.99 / Max: 6.11Min: 5.89 / Avg: 5.92 / Max: 5.94Min: 5.81 / Avg: 5.98 / Max: 6.391. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill Sync23Linux 5.35001000150020002500SE +/- 14.16, N = 3SE +/- 86.67, N = 15SE +/- 142.02, N = 122186.952383.092391.051. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill Sync23Linux 5.3400800120016002000Min: 2158.69 / Avg: 2186.95 / Max: 2202.81Min: 2169.02 / Avg: 2383.09 / Max: 3467.05Min: 2195.72 / Avg: 2391.05 / Max: 3940.371. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill Sync23Linux 5.30.1350.270.4050.540.675SE +/- 0.00, N = 3SE +/- 0.02, N = 15SE +/- 0.03, N = 120.60.60.61. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill Sync23Linux 5.3246810Min: 0.6 / Avg: 0.6 / Max: 0.6Min: 0.4 / Avg: 0.57 / Max: 0.6Min: 0.3 / Avg: 0.57 / Max: 0.61. (CXX) g++ options: -O3 -lsnappy -lpthread

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: wyhash23Linux 5.3816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 334.1934.1934.201. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: wyhash23Linux 5.3714212835Min: 34.19 / Avg: 34.19 / Max: 34.19Min: 34.19 / Avg: 34.19 / Max: 34.19Min: 34.2 / Avg: 34.2 / Max: 34.21. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: wyhash23Linux 5.33K6K9K12K15KSE +/- 121.84, N = 3SE +/- 45.88, N = 3SE +/- 23.76, N = 313823.3813840.2613679.901. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: wyhash23Linux 5.32K4K6K8K10KMin: 13646.91 / Avg: 13823.38 / Max: 14057.14Min: 13764.25 / Avg: 13840.26 / Max: 13922.79Min: 13635.83 / Avg: 13679.9 / Max: 13717.321. (CXX) g++ options: -march=native -O3 -lpthread

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek Random23Linux 5.3246810SE +/- 0.145, N = 3SE +/- 0.133, N = 3SE +/- 0.130, N = 38.8208.9498.8241. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek Random23Linux 5.33691215Min: 8.6 / Avg: 8.82 / Max: 9.09Min: 8.76 / Avg: 8.95 / Max: 9.2Min: 8.58 / Avg: 8.82 / Max: 9.021. (CXX) g++ options: -O3 -lsnappy -lpthread

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 0.7.3Encoder Speed: 823Linux 5.33691215SE +/- 0.016, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 38.9738.9578.9281. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 823Linux 5.33691215Min: 8.94 / Avg: 8.97 / Max: 9Min: 8.95 / Avg: 8.96 / Max: 8.96Min: 8.93 / Avg: 8.93 / Max: 8.931. (CXX) g++ options: -O3 -fPIC

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest Compression23Linux 5.3246810SE +/- 0.030, N = 3SE +/- 0.006, N = 3SE +/- 0.007, N = 38.6718.6548.6421. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest Compression23Linux 5.33691215Min: 8.63 / Avg: 8.67 / Max: 8.73Min: 8.65 / Avg: 8.65 / Max: 8.67Min: 8.64 / Avg: 8.64 / Max: 8.661. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 0.7.3Encoder Speed: 1023Linux 5.3246810SE +/- 0.016, N = 3SE +/- 0.016, N = 3SE +/- 0.016, N = 38.2748.2638.2681. (CXX) g++ options: -O3 -fPIC
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.7.3Encoder Speed: 1023Linux 5.33691215Min: 8.25 / Avg: 8.27 / Max: 8.31Min: 8.24 / Avg: 8.26 / Max: 8.3Min: 8.24 / Avg: 8.27 / Max: 8.291. (CXX) g++ options: -O3 -fPIC

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Read23Linux 5.31.34012.68024.02035.36046.7005SE +/- 0.077, N = 5SE +/- 0.067, N = 3SE +/- 0.058, N = 35.9565.8285.8971. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Read23Linux 5.3246810Min: 5.74 / Avg: 5.96 / Max: 6.16Min: 5.7 / Avg: 5.83 / Max: 5.9Min: 5.78 / Avg: 5.9 / Max: 5.971. (CXX) g++ options: -O3 -lsnappy -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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU23Linux 5.3918273645SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 338.4638.5238.49MIN: 37.9MIN: 37.87MIN: 37.781. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU23Linux 5.3816243240Min: 38.37 / Avg: 38.46 / Max: 38.61Min: 38.42 / Avg: 38.52 / Max: 38.7Min: 38.31 / Avg: 38.49 / Max: 38.631. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin Protein23Linux 5.30.84221.68442.52663.36884.211SE +/- 0.006, N = 3SE +/- 0.022, N = 3SE +/- 0.008, N = 33.7433.7233.7411. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 24Aug2020Model: Rhodopsin Protein23Linux 5.3246810Min: 3.74 / Avg: 3.74 / Max: 3.76Min: 3.68 / Avg: 3.72 / Max: 3.75Min: 3.73 / Avg: 3.74 / Max: 3.761. (CXX) g++ options: -O3 -pthread -lm

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations23Linux 5.320406080100SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3102.01100.61100.761. (CC) gcc options: -lm
OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations23Linux 5.320406080100Min: 101.54 / Avg: 102.01 / Max: 102.52Min: 100.4 / Avg: 100.61 / Max: 100.82Min: 100.58 / Avg: 100.76 / Max: 100.871. (CC) gcc options: -lm

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processes23Linux 5.3714212835SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.28, N = 328.8628.9229.061. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processes23Linux 5.3612182430Min: 28.66 / Avg: 28.86 / Max: 28.97Min: 28.85 / Avg: 28.92 / Max: 29.02Min: 28.53 / Avg: 29.06 / Max: 29.481. (CC) gcc options: -lm

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programs23Linux 5.31224364860SE +/- 0.25, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 352.4051.5951.691. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programs23Linux 5.31020304050Min: 51.99 / Avg: 52.4 / Max: 52.87Min: 51.54 / Avg: 51.59 / Max: 51.68Min: 51.54 / Avg: 51.69 / Max: 51.941. (CC) gcc options: -lm

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threads23Linux 5.348121620SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 316.9716.6016.381. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threads23Linux 5.348121620Min: 16.65 / Avg: 16.97 / Max: 17.18Min: 16.44 / Avg: 16.6 / Max: 16.83Min: 16.24 / Avg: 16.38 / Max: 16.621. (CC) gcc options: -lm

System GZIP Decompression

This simple test measures the time to decompress a gzipped tarball (the Qt5 toolkit source package). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSystem GZIP Decompression23Linux 5.30.7361.4722.2082.9443.68SE +/- 0.029, N = 3SE +/- 0.043, N = 5SE +/- 0.030, N = 33.2573.2713.256
OpenBenchmarking.orgSeconds, Fewer Is BetterSystem GZIP Decompression23Linux 5.3246810Min: 3.23 / Avg: 3.26 / Max: 3.32Min: 3.23 / Avg: 3.27 / Max: 3.44Min: 3.23 / Avg: 3.26 / Max: 3.32

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT Routine23Linux 5.34K8K12K16K20KSE +/- 35.72, N = 3SE +/- 23.55, N = 3SE +/- 23.44, N = 317969.0317951.5617940.301. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT Routine23Linux 5.33K6K9K12K15KMin: 17902.92 / Avg: 17969.03 / Max: 18025.55Min: 17914.04 / Avg: 17951.56 / Max: 17994.99Min: 17913.87 / Avg: 17940.3 / Max: 17987.051. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

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 oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU23Linux 5.348121620SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 317.2417.3317.20MIN: 16.58MIN: 16.58MIN: 16.541. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU23Linux 5.348121620Min: 17.07 / Avg: 17.24 / Max: 17.34Min: 17.27 / Avg: 17.33 / Max: 17.37Min: 17.08 / Avg: 17.2 / Max: 17.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU23Linux 5.3918273645SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 336.8736.9936.73MIN: 36.62MIN: 36.72MIN: 36.591. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU23Linux 5.3816243240Min: 36.75 / Avg: 36.87 / Max: 37.11Min: 36.8 / Avg: 36.99 / Max: 37.23Min: 36.68 / Avg: 36.73 / Max: 36.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 10023Linux 5.30.6121.2241.8362.4483.06SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 32.7162.7202.7191. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 10023Linux 5.3246810Min: 2.71 / Avg: 2.72 / Max: 2.72Min: 2.72 / Avg: 2.72 / Max: 2.72Min: 2.71 / Avg: 2.72 / Max: 2.731. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Default23Linux 5.30.39740.79481.19221.58961.987SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.011, N = 31.7581.7561.7661. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Default23Linux 5.3246810Min: 1.76 / Avg: 1.76 / Max: 1.76Min: 1.75 / Avg: 1.76 / Max: 1.76Min: 1.75 / Avg: 1.77 / Max: 1.791. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

LULESH

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.323Linux 5.3140280420560700SE +/- 7.22, N = 3SE +/- 2.81, N = 3SE +/- 7.56, N = 3648.44645.48638.731. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.323Linux 5.3110220330440550Min: 634.42 / Avg: 648.44 / Max: 658.46Min: 641.31 / Avg: 645.48 / Max: 650.83Min: 629.53 / Avg: 638.73 / Max: 653.731. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi

232 Results Shown

SVT-AV1
Timed LLVM Compilation
Kvazaar:
  Bosphorus 4K - Slow
  Bosphorus 4K - Medium
Basis Universal
G'MIC
Incompact3D
Rodinia
InfluxDB
GROMACS
SVT-AV1
BYTE Unix Benchmark
SVT-AV1
Crypto++
Caffe
Kvazaar
Apache Cassandra
Monte Carlo Simulations of Ionised Nebulae
NAS Parallel Benchmarks
YafaRay
NCNN:
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
  CPU - squeezenet
Numenta Anomaly Benchmark
Crypto++
Rodinia
Darmstadt Automotive Parallel Heterogeneous Suite
BRL-CAD
NAS Parallel Benchmarks
libavif avifenc
Kvazaar:
  Bosphorus 1080p - Slow
  Bosphorus 1080p - Medium
Build2
Mlpack Benchmark:
  scikit_qda
  scikit_linearridgeregression
Apache Cassandra
dav1d
Caffe
NAS Parallel Benchmarks
Timed Linux Kernel Compilation
TensorFlow Lite:
  Inception V4
  Inception ResNet V2
Stress-NG:
  SENDFILE
  Atomic
NAMD
Caffe
Timed HMMer Search
Zstd Compression
Kvazaar
Rodinia
NAS Parallel Benchmarks
libavif avifenc
Embree
Stress-NG
PyPerformance
Basis Universal
Hierarchical INTegration
GLmark2
Embree
Mlpack Benchmark
PyPerformance
Montage Astronomical Image Mosaic Engine
Embree
InfluxDB:
  64 - 10000 - 2,5000,1 - 10000
  1024 - 10000 - 2,5000,1 - 10000
OpenVKL
oneDNN
Embree
x265
RawTherapee
Embree
PyPerformance
Numenta Anomaly Benchmark
LevelDB
Embree
LevelDB:
  Seq Fill:
    Microseconds Per Op
    MB/s
Intel Open Image Denoise
Hugin
G'MIC
Kvazaar
Numenta Anomaly Benchmark
Chaos Group V-RAY
Basis Universal
Caffe
KeyDB
Crypto++
PyPerformance
Git
LuxCoreRender:
  DLSC
  Rainbow Colors and Prism
TensorFlow Lite:
  SqueezeNet
  NASNet Mobile
  Mobilenet Quant
  Mobilenet Float
Rodinia
Basis Universal
oneDNN:
  IP Batch All - u8s8f32 - CPU
  IP Batch All - f32 - CPU
Sockperf
eSpeak-NG Speech Engine
OSBench
PyPerformance
dav1d
PyPerformance
Stress-NG
OCRMyPDF
lzbench:
  XZ 0 - Decompression
  XZ 0 - Compression
LibRaw
Sockperf
oneDNN
WebP Image Encode
dav1d
7-Zip Compression
PyPerformance
Darmstadt Automotive Parallel Heterogeneous Suite
oneDNN:
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
Rodinia
NAS Parallel Benchmarks
oneDNN
Zstd Compression
DaCapo Benchmark
Kvazaar
Botan
Timed Apache Compilation
Algebraic Multi-Grid Benchmark
PyPerformance:
  chaos
  json_loads
Stress-NG
Tesseract OCR
Stress-NG:
  NUMA
  CPU Stress
  Malloc
  MMAP
  Crypto
  Memory Copying
  MEMFD
  Glibc C String Functions
  Glibc Qsort Data Sorting
  Context Switching
  Socket Activity
  Vector Math
  Matrix Math
  Semaphores
  Forking
PyPerformance:
  nbody
  float
lzbench:
  Libdeflate 1 - Decompression
  Libdeflate 1 - Compression
RNNoise
lzbench:
  Zstd 8 - Decompression
  Zstd 8 - Compression
PyPerformance
lzbench:
  Brotli 2 - Decompression
  Brotli 2 - Compression
Darmstadt Automotive Parallel Heterogeneous Suite
G'MIC
lzbench:
  Brotli 0 - Decompression
  Brotli 0 - Compression
Botan:
  Blowfish
  Twofish
lzbench:
  Crush 0 - Decompression
  Crush 0 - Compression
  Zstd 1 - Decompression
  Zstd 1 - Compression
x265
Numenta Anomaly Benchmark
Dolfyn
TNN
Botan:
  CAST-256
  KASUMI
PyPerformance
oneDNN
WebP Image Encode
TNN
Mlpack Benchmark
GNU Octave Benchmark
LevelDB:
  Rand Fill:
    Microseconds Per Op
    MB/s
oneDNN:
  IP Batch 1D - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
LevelDB:
  Overwrite:
    Microseconds Per Op
    MB/s
NAS Parallel Benchmarks
Sockperf
SMHasher:
  Spooky32:
    cycles/hash
    MiB/sec
dav1d
oneDNN
DaCapo Benchmark
SMHasher:
  fasthash32:
    cycles/hash
    MiB/sec
  t1ha2_atonce:
    cycles/hash
    MiB/sec
NeatBench
Basis Universal
LevelDB:
  Hot Read
  Fill Sync
  Fill Sync
SMHasher:
  wyhash:
    cycles/hash
    MiB/sec
LevelDB
libavif avifenc
WebP Image Encode
libavif avifenc
LevelDB
oneDNN
LAMMPS Molecular Dynamics Simulator
OSBench:
  Memory Allocations
  Create Processes
  Launch Programs
  Create Threads
System GZIP Decompression
FFTE
oneDNN:
  Deconvolution Batch deconv_3d - u8s8f32 - CPU
  Deconvolution Batch deconv_3d - f32 - CPU
WebP Image Encode:
  Quality 100
  Default
LULESH

Linux 5.3

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,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-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: intel_pstate powersave - CPU Microcode: 0x42e
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)
Python Notes: Python 2.7.17 + Python 3.7.5
Security Notes: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected

Testing initiated at 16 October 2020 15:53 by user phoronix.

2

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,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-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: intel_pstate powersave - CPU Microcode: 0x42e
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)
Python Notes: Python 2.7.17 + Python 3.7.5
Security Notes: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected

Testing initiated at 17 October 2020 18:04 by user phoronix.

3

Processor: Intel Core i7-4960X @ 4.00GHz (6 Cores / 12 Threads), Motherboard: MSI X79MA-GD45 (MS-7738) v1.0 (V3.8 BIOS), Chipset: Intel Xeon E7 v2/Xeon, Memory: 8GB, Disk: VisionTek 240GB, Graphics: AMD FirePro V4800 1GB, Audio: Realtek ALC892, Monitor: DELL S2409W, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 19.10, Kernel: 5.3.0-40-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0.0), Compiler: GCC 9.2.1 20191008, File-System: zfs, Screen Resolution: 1920x1080

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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,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-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: intel_pstate powersave - CPU Microcode: 0x42e
Graphics Notes: GLAMOR
Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)
Python Notes: Python 2.7.17 + Python 3.7.5
Security Notes: itlb_multihit: KVM: Vulnerable + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected

Testing initiated at 18 October 2020 17:42 by user phoronix.