Xeon E3-1235L

Intel Xeon E3-1235L v5 testing with a ASRockRack C236M WS (P2.60 BIOS) and Intel HD 530 3GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2012156-HA-XEONE312363
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 2 Tests
Bioinformatics 2 Tests
Chess Test Suite 4 Tests
Timed Code Compilation 2 Tests
C/C++ Compiler Tests 15 Tests
Compression Tests 3 Tests
CPU Massive 17 Tests
Creator Workloads 15 Tests
Database Test Suite 3 Tests
Disk Test Suite 2 Tests
Encoding 4 Tests
Fortran Tests 5 Tests
Game Development 3 Tests
HPC - High Performance Computing 15 Tests
Imaging 4 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 4 Tests
Multi-Core 17 Tests
NVIDIA GPU Compute 7 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 5 Tests
Programmer / Developer System Benchmarks 3 Tests
Python Tests 4 Tests
Scientific Computing 9 Tests
Server 3 Tests
Server CPU Tests 9 Tests
Single-Threaded 3 Tests
Speech 2 Tests
Telephony 2 Tests
Texture Compression 3 Tests
Video Encoding 4 Tests
Vulkan Compute 4 Tests
Common Workstation Benchmarks 2 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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

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
Performance Per
Dollar
Date
Run
  Test
  Duration
1
December 12 2020
  21 Hours, 38 Minutes
2
December 13 2020
  17 Hours, 17 Minutes
3
December 14 2020
  17 Hours, 17 Minutes
Invert Hiding All Results Option
  18 Hours, 44 Minutes

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

1

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xdc - Thermald 1.9.1
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + 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: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

2

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + 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: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

3

Processor: Intel Xeon E3-1235L v5 @ 3.00GHz (4 Cores), Motherboard: ASRockRack C236M WS (P2.60 BIOS), Chipset: Intel Xeon E3-1200 v5/E3-1500, Memory: 8GB, Disk: Samsung SSD 960 EVO 500GB + 123GB Ultra Luxe, Graphics: Intel HD 530 3GB (1000MHz), Audio: Realtek ALC1150, Monitor: DELL S2409W, Network: Intel I219-LM + Intel I210

OS: Ubuntu 20.04, Kernel: 5.8.0-050800-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.4, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Xeon E3-1235LProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution123Intel Xeon E3-1235L v5 @ 3.00GHz (4 Cores)ASRockRack C236M WS (P2.60 BIOS)Intel Xeon E3-1200 v5/E3-15008GBSamsung SSD 960 EVO 500GB + 123GB Ultra LuxeIntel HD 530 3GB (1000MHz)Realtek ALC1150DELL S2409WIntel I219-LM + Intel I210Ubuntu 20.045.8.0-050800-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.0.4GCC 9.3.0ext41920x1080OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 Disk Details- NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Details- 1: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xdc - Thermald 1.9.1 - 2: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1 - 3: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1 Java Details- 1: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04) Python Details- Python 3.8.5Security Details- itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + 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: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

123Result OverviewPhoronix Test Suite100%104%107%111%115%Betsy GPU CompressorCompile BenchFlexible IO TesterGLmark2Apache CouchDByquake2StockfishCoremarkTimed LLVM CompilationLevelDBLeelaChessZeroTimed FFmpeg CompilationasmFishKeyDBWebP Image EncodeGROMACSFFTEeSpeak-NG Speech EngineNumpy BenchmarkDDraceNetworkTimed Clash CompilationASTC EncoderGraphicsMagickCraftyOSBenchRNNoiseMontage Astronomical Image Mosaic Enginex265NAMDBYTE Unix BenchmarkLAMMPS Molecular Dynamics SimulatoroneDNNTimed MAFFT AlignmentSystem GZIP DecompressionKvazaarVkFFTDolfynEmbreeWaifu2x-NCNN VulkanRodiniarav1eLZ4 CompressionLibRawBasis UniversalAOM AV1TensorFlow LiteZstd CompressionRealSR-NCNNIncompact3DMonte Carlo Simulations of Ionised NebulaeTimed HMMer Search

Xeon E3-1235Lbuild-llvm: Time To Compilerealsr-ncnn: 4x - Yesrodinia: OpenMP LavaMDincompact3d: Cylinderastcenc: Exhaustivegromacs: Water Benchmarkkvazaar: Bosphorus 4K - Mediumvkfft: mocassin: Dust 2D tau100.0rodinia: OpenMP Leukocytelczero: Eigenlczero: BLASbuild-clash: Time To Compilerealsr-ncnn: 4x - Nonumpy: couchdb: 100 - 1000 - 24namd: ATPase Simulation - 327,506 Atomscompress-zstd: 19embree: Pathtracer - Crownembree: Pathtracer - Asian Dragon Objasmfish: 1024 Hash Memory, 26 Depthbasis: UASTC Level 3embree: Pathtracer ISPC - Crownembree: Pathtracer ISPC - Asian Dragon Objembree: Pathtracer - Asian Dragonbuild-ffmpeg: Time To Compileembree: Pathtracer ISPC - Asian Dragontensorflow-lite: Inception ResNet V2tensorflow-lite: Inception V4kvazaar: Bosphorus 4K - Very Fasthmmer: Pfam Database Searchrodinia: OpenMP HotSpot3Dfio: Seq Read - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 2MB - Default Test Directoryastcenc: Thoroughwaifu2x-ncnn: 2x - 3 - Yesbyte: Dhrystone 2x265: Bosphorus 4Kmontage: Mosaic of M17, K band, 1.5 deg x 1.5 degonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUbasis: ETC1Sbasis: UASTC Level 2glmark2: 1920 x 1080kvazaar: Bosphorus 1080p - Mediumcompress-lz4: 9 - Decompression Speedcompress-lz4: 9 - Compression Speedstockfish: Total Timecompress-lz4: 3 - Decompression Speedcompress-lz4: 3 - Compression Speedonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUkvazaar: Bosphorus 4K - Ultra Fastrav1e: 5coremark: CoreMark Size 666 - Iterations Per Secondkeydb: rodinia: OpenMP CFD Solverlibraw: Post-Processing Benchmarkaom-av1: Speed 0 Two-Passwebp: Quality 100, Lossless, Highest Compressiontensorflow-lite: SqueezeNetddnet: 1920 x 1080 - Fullscreen - OpenGL 3.3 - Default - Multeasymaptensorflow-lite: Mobilenet Quantddnet: 1920 x 1080 - Fullscreen - OpenGL 3.0 - Default - Multeasymapddnet: 1920 x 1080 - Fullscreen - OpenGL 3.0 - Default - RaiNyMore2tensorflow-lite: Mobilenet Floatddnet: 1920 x 1080 - Fullscreen - OpenGL 3.3 - Default - RaiNyMore2graphics-magick: Sharpentensorflow-lite: NASNet Mobilegraphics-magick: Swirlgraphics-magick: Noise-Gaussiangraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Rotategraphics-magick: Enhancedrav1e: 6aom-av1: Speed 6 Realtimeespeak: Text-To-Speech Synthesisrodinia: OpenMP Streamclusteraom-av1: Speed 6 Two-Passrav1e: 10kvazaar: Bosphorus 1080p - Very Fastbetsy: ETC1 - Highestrnnoise: compilebench: Compilecompress-lz4: 1 - Decompression Speedcompress-lz4: 1 - Compression Speedaom-av1: Speed 4 Two-Passcrafty: Elapsed Timefio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 2MB - Default Test Directorycompress-zstd: 3fio: Rand Write - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 2MB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directorydolfyn: Computational Fluid Dynamicsx265: Bosphorus 1080pwebp: Quality 100, Losslessastcenc: Mediumaom-av1: Speed 8 Realtimekvazaar: Bosphorus 1080p - Ultra Fastonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUwaifu2x-ncnn: 2x - 3 - Noonednn: IP Shapes 1D - f32 - CPUbasis: UASTC Level 0onednn: IP Shapes 1D - u8s8f32 - CPUmafft: Multiple Sequence Alignment - LSU RNAastcenc: Fastonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUleveldb: Seq Fillleveldb: Seq Fillleveldb: Rand Deletewebp: Quality 100, Highest Compressiononednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUosbench: Create Threadsyquake2: Software CPU - 1920 x 1080lammps: Rhodopsin Proteinonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUleveldb: Fill Syncleveldb: Fill Syncbetsy: ETC2 RGB - Highestosbench: Create Filesosbench: Memory Allocationsosbench: Launch Programsosbench: Create Processessystem-decompress-gzip: webp: Quality 100yquake2: OpenGL 3.x - 1920 x 1080onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUyquake2: OpenGL 1.x - 1920 x 1080webp: Defaultleveldb: Seek Randleveldb: Rand Fillleveldb: Rand Fillleveldb: Overwriteleveldb: Overwriteleveldb: Hot Readffte: N=256, 3D Complex FFT Routineleveldb: Rand Readcompilebench: Read Compiled Treecompilebench: Initial Create1232359.4832526.6881030.420986.674032969.610.3991.41009394372.765679711335.587319.578252.51243.2506.0659612.32.41882.73666915903226.2652.76413.21352.9529190.9973.5908865095095529833.83156.759153.37210462098122.64127.09929465235.65.13116.6539559.909555.339555.13111.772110.7324696.187377.733.3348760637400.534.285275.375261.535266.776.900.76975749.248638196823.7567.59618.940.1660.793663351168.86462175148.0089.8145138973.343048062410161291440572571.02510.8840.17447.8902.262.31015.7011.40836.066873.137600.86133.001.415795852252000985281333109859011862271.6792159288317733640001422368000143727.74822.1125.03818.8127.6127.7619.400114.965017.14310.865715.0907.3677814.7647.525.514779.9038922.73319.422.51310.6014.7321412.513118.26551272.52.14220.883821.29565987.1390.12.54420.554782104.391734112.87371331.4871474.2853.547261.314.765818.2058285.42.2622.42523.29518.923.64218.71.89715355.2863948671.9011037.77342.412334.3592527.1611028.739988.300374977.840.3961.391006394372.960687695336.790319.797251.87251.3186.0902412.32.41442.72996982908226.6712.75693.21412.9833193.2783.5584864853795576473.83156.810153.37212312469123.14127.35629461805.65.13116.1889612.969603.439603.24112.033110.8294906.167384.533.4549156267374.434.105284.395297.195294.836.890.76677004.522143198980.7667.64518.940.1661.119663491169.32462425148.2689.5045145273.913048067110161290441559571.02510.9240.48748.0512.252.30815.6510.66436.230898.327579.56154.741.405824840252000984280667109758411762271.6774155588217733640001422371333145127.67021.9125.17418.8727.6827.7619.408015.040717.12310.902115.0927.3655014.7467.575.534009.9772221.96320.121.71410.6104.7771412.700818.06100273.82.14521.043821.42136005.5790.12.06520.430840102.514346113.13358931.7335134.2983.554270.414.743918.2538297.82.3522.43423.11419.123.03119.11.93815246.0904365071.8981141.92347.092325.5482536.6411033.207987.472656984.980.3951.391007394372.655687716337.767320.660253.80245.8146.0628612.32.41792.72547008564226.5962.75533.20742.9732191.4273.5541865307795531403.82156.779153.4728861780123.28127.55129340852.05.12116.3709589.849548.819557.40112.105110.7674826.167389.033.3347902067415.034.285245.245250.855267.026.880.76775150.850584198990.6967.65718.920.1660.963663532167.37462594147.4288.9445180173.583048082810161290434557571.02610.8940.49848.0162.252.30115.6611.15036.095917.727613.56138.651.415830763252000985279667109357611592270.0783157485317133626671417373333145927.74921.9925.00418.8727.6027.7519.379415.030217.16710.894515.0977.3670414.7947.555.575009.9670221.99720.021.93910.6724.7685712.832718.08118873.62.15121.041521.35275991.5680.12.08920.453449104.718606113.23293131.1422354.2993.552267.714.746618.1241294.62.2602.41522.72819.423.01119.21.89815203.7193568691.9071046.37341.68OpenBenchmarking.org

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 Compile3215001000150020002500SE +/- 0.38, N = 3SE +/- 6.63, N = 3SE +/- 38.26, N = 92325.552334.362359.48
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To Compile321400800120016002000Min: 2324.94 / Avg: 2325.55 / Max: 2326.25Min: 2326.72 / Avg: 2334.36 / Max: 2347.57Min: 2317.84 / Avg: 2359.48 / Max: 2665.53

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes1235001000150020002500SE +/- 0.41, N = 3SE +/- 0.06, N = 3SE +/- 0.25, N = 32526.692527.162536.64
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes123400800120016002000Min: 2525.9 / Avg: 2526.69 / Max: 2527.27Min: 2527.08 / Avg: 2527.16 / Max: 2527.27Min: 2536.26 / Avg: 2536.64 / Max: 2537.12

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 LavaMD2132004006008001000SE +/- 0.29, N = 3SE +/- 1.51, N = 3SE +/- 0.47, N = 31028.741030.421033.211. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMD2132004006008001000Min: 1028.29 / Avg: 1028.74 / Max: 1029.27Min: 1028.46 / Avg: 1030.42 / Max: 1033.39Min: 1032.53 / Avg: 1033.21 / Max: 1034.111. (CXX) g++ options: -O2 -lOpenCL

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: Cylinder1322004006008001000SE +/- 1.73, N = 3SE +/- 0.65, N = 3SE +/- 1.12, N = 3986.67987.47988.301. (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: Cylinder1322004006008001000Min: 983.24 / Avg: 986.67 / Max: 988.79Min: 986.42 / Avg: 987.47 / Max: 988.66Min: 986.4 / Avg: 988.3 / Max: 990.271. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Exhaustive1232004006008001000SE +/- 0.37, N = 3SE +/- 0.35, N = 3SE +/- 3.85, N = 3969.61977.84984.981. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Exhaustive1232004006008001000Min: 969.24 / Avg: 969.61 / Max: 970.36Min: 977.15 / Avg: 977.84 / Max: 978.27Min: 980.6 / Avg: 984.98 / Max: 992.651. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

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 Benchmark1230.08980.17960.26940.35920.449SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 30.3990.3960.3951. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water Benchmark12312345Min: 0.39 / Avg: 0.4 / Max: 0.4Min: 0.39 / Avg: 0.4 / Max: 0.4Min: 0.39 / Avg: 0.4 / Max: 0.41. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

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: Medium1320.3150.630.9451.261.575SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.401.391.391. (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: Medium132246810Min: 1.4 / Avg: 1.4 / Max: 1.4Min: 1.39 / Avg: 1.39 / Max: 1.39Min: 1.39 / Avg: 1.39 / Max: 1.391. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 2020-09-291322004006008001000100910071006

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 tau100.012390180270360450SE +/- 0.88, N = 3SE +/- 0.33, N = 33943943941. (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 tau100.012370140210280350Min: 393 / Avg: 394.33 / Max: 396Min: 394 / Avg: 394.33 / Max: 3951. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -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 Leukocyte31280160240320400SE +/- 1.10, N = 3SE +/- 1.06, N = 3SE +/- 0.99, N = 3372.66372.77372.961. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Leukocyte31270140210280350Min: 371.55 / Avg: 372.66 / Max: 374.86Min: 371.7 / Avg: 372.77 / Max: 374.88Min: 371.53 / Avg: 372.96 / Max: 374.851. (CXX) g++ options: -O2 -lOpenCL

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: Eigen321150300450600750SE +/- 6.67, N = 3SE +/- 0.88, N = 3SE +/- 3.71, N = 36876876791. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: Eigen321120240360480600Min: 680 / Avg: 686.67 / Max: 700Min: 685 / Avg: 686.67 / Max: 688Min: 672 / Avg: 679.33 / Max: 6841. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLAS312150300450600750SE +/- 3.48, N = 3SE +/- 7.54, N = 37167116951. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLAS312130260390520650Min: 705 / Avg: 711.33 / Max: 717Min: 683 / Avg: 695.33 / Max: 7091. (CXX) g++ options: -flto -pthread

Timed Clash Compilation

Build the clash-lang Haskell to VHDL/Verilog/SystemVerilog compiler with GHC 8.10.1 Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Clash CompilationTime To Compile12370140210280350SE +/- 0.78, N = 3SE +/- 1.06, N = 3SE +/- 0.97, N = 3335.59336.79337.77
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Clash CompilationTime To Compile12360120180240300Min: 334.2 / Avg: 335.59 / Max: 336.89Min: 335.43 / Avg: 336.79 / Max: 338.88Min: 336.78 / Avg: 337.77 / Max: 339.71

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No12370140210280350SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.18, N = 3319.58319.80320.66
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No12360120180240300Min: 319.45 / Avg: 319.58 / Max: 319.68Min: 319.74 / Avg: 319.8 / Max: 319.83Min: 320.31 / Avg: 320.66 / Max: 320.94

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark31260120180240300SE +/- 0.51, N = 3SE +/- 0.41, N = 3SE +/- 0.66, N = 3253.80252.51251.87
OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark31250100150200250Min: 253.23 / Avg: 253.8 / Max: 254.83Min: 252.03 / Avg: 252.51 / Max: 253.33Min: 250.69 / Avg: 251.87 / Max: 252.99

Apache CouchDB

This is a bulk insertion benchmark of Apache CouchDB. CouchDB is a document-oriented NoSQL database implemented in Erlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 2413250100150200250SE +/- 3.03, N = 5SE +/- 3.43, N = 3SE +/- 1.75, N = 3243.25245.81251.321. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD
OpenBenchmarking.orgSeconds, Fewer Is BetterApache CouchDB 3.1.1Bulk Size: 100 - Inserts: 1000 - Rounds: 2413250100150200250Min: 234.88 / Avg: 243.25 / Max: 250.36Min: 241.6 / Avg: 245.81 / Max: 252.61Min: 247.96 / Avg: 251.32 / Max: 253.861. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD

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 Atoms312246810SE +/- 0.00266, N = 3SE +/- 0.00239, N = 3SE +/- 0.02474, N = 36.062866.065966.09024
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms312246810Min: 6.06 / Avg: 6.06 / Max: 6.07Min: 6.06 / Avg: 6.07 / Max: 6.07Min: 6.06 / Avg: 6.09 / Max: 6.14

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: 193213691215SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 712.312.312.31. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 1932148121620Min: 12.2 / Avg: 12.3 / Max: 12.4Min: 12.2 / Avg: 12.27 / Max: 12.3Min: 11.5 / Avg: 12.3 / Max: 12.51. (CC) gcc options: -O3 -pthread -lz -llzma

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: Crown1320.54421.08841.63262.17682.721SE +/- 0.0031, N = 3SE +/- 0.0048, N = 3SE +/- 0.0065, N = 32.41882.41792.4144MIN: 2.39 / MAX: 2.45MIN: 2.4 / MAX: 2.45MIN: 2.4 / MAX: 2.45
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Crown132246810Min: 2.41 / Avg: 2.42 / Max: 2.42Min: 2.41 / Avg: 2.42 / Max: 2.42Min: 2.41 / Avg: 2.41 / Max: 2.43

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon Obj1230.61571.23141.84712.46283.0785SE +/- 0.0011, N = 3SE +/- 0.0015, N = 3SE +/- 0.0019, N = 32.73662.72992.7254MIN: 2.73 / MAX: 2.76MIN: 2.72 / MAX: 2.75MIN: 2.72 / MAX: 2.75
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon Obj123246810Min: 2.73 / Avg: 2.74 / Max: 2.74Min: 2.73 / Avg: 2.73 / Max: 2.73Min: 2.72 / Avg: 2.73 / Max: 2.73

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth3211.5M3M4.5M6M7.5MSE +/- 76431.15, N = 3SE +/- 52799.51, N = 3SE +/- 38258.52, N = 3700856469829086915903
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth3211.2M2.4M3.6M4.8M6MMin: 6872996 / Avg: 7008563.67 / Max: 7137513Min: 6920540 / Avg: 6982907.67 / Max: 7087889Min: 6866464 / Avg: 6915903 / Max: 6991199

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 313250100150200250SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3226.27226.60226.671. (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 31324080120160200Min: 226.23 / Avg: 226.27 / Max: 226.33Min: 226.52 / Avg: 226.6 / Max: 226.68Min: 226.63 / Avg: 226.67 / Max: 226.731. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -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: Crown1230.62191.24381.86572.48763.1095SE +/- 0.0067, N = 3SE +/- 0.0070, N = 3SE +/- 0.0073, N = 32.76412.75692.7553MIN: 2.74 / MAX: 2.8MIN: 2.74 / MAX: 2.8MIN: 2.73 / MAX: 2.8
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Crown123246810Min: 2.75 / Avg: 2.76 / Max: 2.78Min: 2.75 / Avg: 2.76 / Max: 2.77Min: 2.74 / Avg: 2.76 / Max: 2.77

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon Obj2130.72321.44642.16962.89283.616SE +/- 0.0074, N = 3SE +/- 0.0011, N = 3SE +/- 0.0029, N = 33.21413.21353.2074MIN: 3.2 / MAX: 3.25MIN: 3.2 / MAX: 3.24MIN: 3.2 / MAX: 3.24
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon Obj213246810Min: 3.2 / Avg: 3.21 / Max: 3.23Min: 3.21 / Avg: 3.21 / Max: 3.22Min: 3.2 / Avg: 3.21 / Max: 3.21

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon2310.67121.34242.01362.68483.356SE +/- 0.0107, N = 3SE +/- 0.0147, N = 3SE +/- 0.0183, N = 32.98332.97322.9529MIN: 2.92 / MAX: 3.04MIN: 2.9 / MAX: 3.03MIN: 2.89 / MAX: 3.03
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon231246810Min: 2.96 / Avg: 2.98 / Max: 3Min: 2.94 / Avg: 2.97 / Max: 2.99Min: 2.93 / Avg: 2.95 / Max: 2.99

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To Compile1324080120160200SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 1.85, N = 3191.00191.43193.28
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To Compile1324080120160200Min: 190.98 / Avg: 191 / Max: 191.02Min: 191.36 / Avg: 191.43 / Max: 191.47Min: 191.41 / Avg: 193.28 / Max: 196.98

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 Dragon1230.80791.61582.42373.23164.0395SE +/- 0.0028, N = 3SE +/- 0.0041, N = 3SE +/- 0.0026, N = 33.59083.55843.5541MIN: 3.53 / MAX: 3.67MIN: 3.51 / MAX: 3.63MIN: 3.51 / MAX: 3.63
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon123246810Min: 3.59 / Avg: 3.59 / Max: 3.6Min: 3.55 / Avg: 3.56 / Max: 3.56Min: 3.55 / Avg: 3.55 / Max: 3.56

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 ResNet V22132M4M6M8M10MSE +/- 312.48, N = 3SE +/- 2061.37, N = 3SE +/- 3300.88, N = 3864853786509508653077
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V22131.5M3M4.5M6M7.5MMin: 8647930 / Avg: 8648536.67 / Max: 8648970Min: 8648760 / Avg: 8650950 / Max: 8655070Min: 8649260 / Avg: 8653076.67 / Max: 8659650

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V41322M4M6M8M10MSE +/- 454.10, N = 3SE +/- 561.07, N = 3SE +/- 4469.39, N = 3955298395531409557647
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V41321.7M3.4M5.1M6.8M8.5MMin: 9552170 / Avg: 9552983.33 / Max: 9553740Min: 9552020 / Avg: 9553140 / Max: 9553760Min: 9552910 / Avg: 9557646.67 / Max: 9566580

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 Fast2130.86181.72362.58543.44724.309SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.833.833.821. (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 Fast213246810Min: 3.82 / Avg: 3.83 / Max: 3.83Min: 3.83 / Avg: 3.83 / Max: 3.83Min: 3.81 / Avg: 3.82 / Max: 3.821. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 Search132306090120150SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3156.76156.78156.811. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 3.3.1Pfam Database Search132306090120150Min: 156.66 / Avg: 156.76 / Max: 156.91Min: 156.72 / Avg: 156.78 / Max: 156.87Min: 156.75 / Avg: 156.81 / Max: 156.931. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm

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 HotSpot3D123306090120150SE +/- 0.27, N = 3SE +/- 0.17, N = 3SE +/- 0.34, N = 3153.37153.37153.471. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3D123306090120150Min: 152.98 / Avg: 153.37 / Max: 153.9Min: 153.04 / Avg: 153.37 / Max: 153.58Min: 153.07 / Avg: 153.47 / Max: 154.161. (CXX) g++ options: -O2 -lOpenCL

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory21330060090012001500SE +/- 13.06, N = 15SE +/- 21.43, N = 12SE +/- 26.75, N = 12123110468861. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory2132004006008001000Min: 1145 / Avg: 1230.8 / Max: 1328Min: 931 / Avg: 1045.5 / Max: 1168Min: 785 / Avg: 886.33 / Max: 11221. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory2135001000150020002500SE +/- 26.14, N = 15SE +/- 42.77, N = 12SE +/- 53.45, N = 122469209817801. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory213400800120016002000Min: 2297 / Avg: 2468.87 / Max: 2664Min: 1870 / Avg: 2097.92 / Max: 2343Min: 1577 / Avg: 1780.17 / Max: 22511. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Thorough123306090120150SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3122.64123.14123.281. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Thorough12320406080100Min: 122.63 / Avg: 122.64 / Max: 122.64Min: 123.11 / Avg: 123.14 / Max: 123.18Min: 123.2 / Avg: 123.28 / Max: 123.41. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: Yes123306090120150SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3127.10127.36127.55
OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: Yes12320406080100Min: 127.06 / Avg: 127.1 / Max: 127.15Min: 127.35 / Avg: 127.36 / Max: 127.36Min: 127.49 / Avg: 127.55 / Max: 127.62

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 21236M12M18M24M30MSE +/- 84290.77, N = 3SE +/- 78236.04, N = 3SE +/- 95265.46, N = 329465235.629461805.629340852.0
OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 21235M10M15M20M25MMin: 29296785.2 / Avg: 29465235.6 / Max: 29555218.5Min: 29305409.8 / Avg: 29461805.63 / Max: 29544233.1Min: 29178085.2 / Avg: 29340851.97 / Max: 29508006.9

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 4K2131.15432.30863.46294.61725.7715SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 35.135.135.121. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4K213246810Min: 5.11 / Avg: 5.13 / Max: 5.15Min: 5.1 / Avg: 5.13 / Max: 5.19Min: 5.11 / Avg: 5.12 / Max: 5.131. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 deg231306090120150SE +/- 0.07, N = 3SE +/- 0.31, N = 3SE +/- 0.61, N = 3116.19116.37116.651. (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 deg23120406080100Min: 116.05 / Avg: 116.19 / Max: 116.27Min: 115.99 / Avg: 116.37 / Max: 116.98Min: 115.94 / Avg: 116.65 / Max: 117.881. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU1322K4K6K8K10KSE +/- 4.48, N = 3SE +/- 21.70, N = 3SE +/- 23.82, N = 39559.909589.849612.96MIN: 9334.11MIN: 9368.88MIN: 9367.571. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU1322K4K6K8K10KMin: 9553.28 / Avg: 9559.9 / Max: 9568.45Min: 9561.16 / Avg: 9589.84 / Max: 9632.39Min: 9577.9 / Avg: 9612.96 / Max: 9658.421. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU3122K4K6K8K10KSE +/- 15.76, N = 3SE +/- 12.86, N = 3SE +/- 3.21, N = 39548.819555.339603.43MIN: 9341.73MIN: 9332.93MIN: 9393.751. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU31217003400510068008500Min: 9517.4 / Avg: 9548.81 / Max: 9566.73Min: 9530.88 / Avg: 9555.33 / Max: 9574.45Min: 9597.5 / Avg: 9603.43 / Max: 9608.511. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU1322K4K6K8K10KSE +/- 6.54, N = 3SE +/- 9.83, N = 3SE +/- 1.18, N = 39555.139557.409603.24MIN: 9341.18MIN: 9356.9MIN: 9381.441. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU13217003400510068008500Min: 9542.98 / Avg: 9555.13 / Max: 9565.38Min: 9538.99 / Avg: 9557.4 / Max: 9572.59Min: 9601.17 / Avg: 9603.24 / Max: 9605.241. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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: ETC1S123306090120150SE +/- 0.07, N = 3SE +/- 0.16, N = 3SE +/- 0.22, N = 3111.77112.03112.111. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1S12320406080100Min: 111.68 / Avg: 111.77 / Max: 111.91Min: 111.73 / Avg: 112.03 / Max: 112.29Min: 111.86 / Avg: 112.11 / Max: 112.551. (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 213220406080100SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3110.73110.77110.831. (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 213220406080100Min: 110.73 / Avg: 110.73 / Max: 110.74Min: 110.7 / Avg: 110.77 / Max: 110.82Min: 110.81 / Avg: 110.83 / Max: 110.841. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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 1080231110220330440550490482469

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: Medium132246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 36.186.166.161. (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: Medium132246810Min: 6.18 / Avg: 6.18 / Max: 6.19Min: 6.16 / Avg: 6.16 / Max: 6.17Min: 6.15 / Avg: 6.16 / Max: 6.161. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression Speed32116003200480064008000SE +/- 1.04, N = 3SE +/- 8.76, N = 3SE +/- 1.48, N = 37389.07384.57377.71. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression Speed32113002600390052006500Min: 7387.5 / Avg: 7389 / Max: 7391Min: 7367.6 / Avg: 7384.47 / Max: 7397Min: 7375.3 / Avg: 7377.73 / Max: 7380.41. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression Speed231816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 333.4533.3333.331. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression Speed231714212835Min: 33.44 / Avg: 33.45 / Max: 33.46Min: 33.31 / Avg: 33.33 / Max: 33.35Min: 33.32 / Avg: 33.33 / Max: 33.331. (CC) gcc options: -O3

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total Time2131.1M2.2M3.3M4.4M5.5MSE +/- 39880.86, N = 3SE +/- 52052.28, N = 3SE +/- 28938.12, N = 34915626487606347902061. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total Time213900K1800K2700K3600K4500KMin: 4859188 / Avg: 4915626 / Max: 4992656Min: 4815143 / Avg: 4876063.33 / Max: 4979632Min: 4736845 / Avg: 4790206.33 / Max: 48362951. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression Speed31216003200480064008000SE +/- 22.49, N = 3SE +/- 1.44, N = 3SE +/- 5.10, N = 37415.07400.57374.41. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression Speed31213002600390052006500Min: 7375.9 / Avg: 7414.97 / Max: 7453.8Min: 7397.8 / Avg: 7400.53 / Max: 7402.7Min: 7364.2 / Avg: 7374.37 / Max: 7380.11. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression Speed312816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 334.2834.2834.101. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression Speed312714212835Min: 34.27 / Avg: 34.28 / Max: 34.29Min: 34.27 / Avg: 34.28 / Max: 34.29Min: 34.01 / Avg: 34.1 / Max: 34.141. (CC) gcc options: -O3

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU31211002200330044005500SE +/- 4.73, N = 3SE +/- 7.80, N = 3SE +/- 7.92, N = 35245.245275.375284.39MIN: 5108.55MIN: 5110.58MIN: 5126.961. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU3129001800270036004500Min: 5237.71 / Avg: 5245.24 / Max: 5253.96Min: 5260.7 / Avg: 5275.37 / Max: 5287.32Min: 5275.25 / Avg: 5284.39 / Max: 5300.161. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU31211002200330044005500SE +/- 1.91, N = 3SE +/- 10.87, N = 3SE +/- 1.92, N = 35250.855261.535297.19MIN: 5127.19MIN: 5116.63MIN: 5157.921. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU3129001800270036004500Min: 5247.19 / Avg: 5250.85 / Max: 5253.61Min: 5240.46 / Avg: 5261.53 / Max: 5276.69Min: 5293.48 / Avg: 5297.19 / Max: 5299.931. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU13211002200330044005500SE +/- 1.62, N = 3SE +/- 8.84, N = 3SE +/- 12.39, N = 35266.775267.025294.83MIN: 5131.76MIN: 5139.56MIN: 5153.041. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1329001800270036004500Min: 5263.71 / Avg: 5266.77 / Max: 5269.23Min: 5256.39 / Avg: 5267.02 / Max: 5284.57Min: 5274.29 / Avg: 5294.83 / Max: 5317.11. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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 Fast123246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.906.896.881. (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 Fast1233691215Min: 6.88 / Avg: 6.9 / Max: 6.92Min: 6.89 / Avg: 6.89 / Max: 6.9Min: 6.87 / Avg: 6.88 / Max: 6.891. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 51320.1730.3460.5190.6920.865SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 30.7690.7670.766
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 5132246810Min: 0.77 / Avg: 0.77 / Max: 0.77Min: 0.77 / Avg: 0.77 / Max: 0.77Min: 0.76 / Avg: 0.77 / Max: 0.77

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second21316K32K48K64K80KSE +/- 177.93, N = 3SE +/- 723.27, N = 15SE +/- 842.50, N = 1577004.5275749.2575150.851. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second21313K26K39K52K65KMin: 76716.53 / Avg: 77004.52 / Max: 77329.55Min: 70804.81 / Avg: 75749.25 / Max: 81289.8Min: 70216.5 / Avg: 75150.85 / Max: 80364.321. (CC) gcc options: -O2 -lrt" -lrt

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 6.0.1632140K80K120K160K200KSE +/- 886.71, N = 3SE +/- 1082.63, N = 3SE +/- 1172.61, N = 3198990.69198980.76196823.751. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 6.0.1632130K60K90K120K150KMin: 197235.12 / Avg: 198990.69 / Max: 200085.77Min: 197269.74 / Avg: 198980.76 / Max: 200985.42Min: 194636.72 / Avg: 196823.75 / Max: 198650.581. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 Solver1231530456075SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 367.6067.6567.661. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solver1231326395265Min: 67.47 / Avg: 67.6 / Max: 67.74Min: 67.59 / Avg: 67.64 / Max: 67.71Min: 67.61 / Avg: 67.66 / Max: 67.711. (CXX) g++ options: -O2 -lOpenCL

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 Benchmark213510152025SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 318.9418.9418.921. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing Benchmark213510152025Min: 18.93 / Avg: 18.94 / Max: 18.95Min: 18.93 / Avg: 18.94 / Max: 18.94Min: 18.91 / Avg: 18.92 / Max: 18.931. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-Pass3210.0360.0720.1080.1440.18SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.160.160.161. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 0 Two-Pass32112345Min: 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 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 Compression1321428425670SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 360.7960.9661.121. (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 Compression1321224364860Min: 60.76 / Avg: 60.79 / Max: 60.82Min: 60.89 / Avg: 60.96 / Max: 61.09Min: 61.03 / Avg: 61.12 / Max: 61.21. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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: SqueezeNet123140K280K420K560K700KSE +/- 83.51, N = 3SE +/- 21.18, N = 3SE +/- 60.68, N = 3663351663491663532
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNet123120K240K360K480K600KMin: 663265 / Avg: 663351 / Max: 663518Min: 663457 / Avg: 663491.33 / Max: 663530Min: 663451 / Avg: 663532.33 / Max: 663651

DDraceNetwork

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap - Total Frame Time213510152025Min: 2.55 / Avg: 5.93 / Max: 19.72Min: 2.98 / Avg: 5.96 / Max: 17.94Min: 3.6 / Avg: 5.98 / Max: 16.281. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap2134080120160200SE +/- 0.43, N = 3SE +/- 0.64, N = 3SE +/- 0.08, N = 3169.32168.86167.37MIN: 50.72 / MAX: 391.85MIN: 55.74 / MAX: 335.35MIN: 61.44 / MAX: 320.821. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap213306090120150Min: 168.72 / Avg: 169.32 / Max: 170.15Min: 168.13 / Avg: 168.86 / Max: 170.14Min: 167.26 / Avg: 167.37 / Max: 167.521. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

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: Mobilenet Quant123100K200K300K400K500KSE +/- 27.76, N = 3SE +/- 130.28, N = 3SE +/- 154.18, N = 3462175462425462594
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quant12380K160K240K320K400KMin: 462125 / Avg: 462174.67 / Max: 462221Min: 462204 / Avg: 462424.67 / Max: 462655Min: 462413 / Avg: 462594.33 / Max: 462901

DDraceNetwork

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.0 - Zoom: Default - Demo: Multeasymap - Total Frame Time21348121620Min: 5.05 / Avg: 6.74 / Max: 17.01Min: 4.31 / Avg: 6.76 / Max: 16.36Min: 4.66 / Avg: 6.77 / Max: 12.351. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.0 - Zoom: Default - Demo: Multeasymap213306090120150SE +/- 1.12, N = 3SE +/- 0.51, N = 3SE +/- 0.28, N = 3148.26148.00147.42MIN: 46.51 / MAX: 225.78MIN: 51.95 / MAX: 232.18MIN: 46.02 / MAX: 420.71. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.0 - Zoom: Default - Demo: Multeasymap213306090120150Min: 146.19 / Avg: 148.26 / Max: 150.03Min: 147.01 / Avg: 148 / Max: 148.72Min: 146.97 / Avg: 147.42 / Max: 147.941. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.0 - Zoom: Default - Demo: RaiNyMore2 - Total Frame Time213510152025Min: 9.89 / Avg: 11.12 / Max: 21.27Min: 9.93 / Avg: 11.13 / Max: 20.87Min: 10 / Avg: 11.19 / Max: 22.51. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.0 - Zoom: Default - Demo: RaiNyMore212320406080100SE +/- 0.18, N = 3SE +/- 0.39, N = 3SE +/- 0.61, N = 389.8189.5088.94MIN: 48.34 / MAX: 300.03MIN: 53.3 / MAX: 346.38MIN: 49.67 / MAX: 355.371. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.0 - Zoom: Default - Demo: RaiNyMore212320406080100Min: 89.57 / Avg: 89.81 / Max: 90.17Min: 88.91 / Avg: 89.5 / Max: 90.24Min: 87.74 / Avg: 88.94 / Max: 89.721. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

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: Mobilenet Float123100K200K300K400K500KSE +/- 7.23, N = 3SE +/- 83.73, N = 3SE +/- 154.64, N = 3451389451452451801
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Float12380K160K240K320K400KMin: 451376 / Avg: 451389 / Max: 451401Min: 451309 / Avg: 451452.33 / Max: 451599Min: 451615 / Avg: 451801 / Max: 452108

DDraceNetwork

OpenBenchmarking.orgMilliseconds, Fewer Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore2 - Total Frame Time231612182430Min: 13.11 / Avg: 13.59 / Max: 19.42Min: 13.2 / Avg: 13.6 / Max: 26.07Min: 11.65 / Avg: 13.65 / Max: 23.181. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore22311632486480SE +/- 0.25, N = 3SE +/- 0.16, N = 3SE +/- 0.08, N = 373.9173.5873.34MIN: 67.57 / MAX: 77.36MIN: 67.7 / MAX: 79.42MIN: 62.12 / MAX: 85.871. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.orgFrames Per Second, More Is BetterDDraceNetwork 15.2.3Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore22311428425670Min: 73.62 / Avg: 73.91 / Max: 74.42Min: 73.31 / Avg: 73.58 / Max: 73.86Min: 73.25 / Avg: 73.34 / Max: 73.51. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Sharpen3217142128353030301. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

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: NASNet Mobile123100K200K300K400K500KSE +/- 59.68, N = 3SE +/- 58.89, N = 3SE +/- 93.46, N = 3480624480671480828
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobile12380K160K240K320K400KMin: 480541 / Avg: 480624.33 / Max: 480740Min: 480553 / Avg: 480670.67 / Max: 480734Min: 480643 / Avg: 480828.33 / Max: 480942

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Swirl321204060801001011011011. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-Gaussian32114284256706161611. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Resizing13260120180240300SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 1.33, N = 32912902901. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Resizing13250100150200250Min: 290 / Avg: 291.33 / Max: 292Min: 289 / Avg: 289.67 / Max: 290Min: 289 / Avg: 290.33 / Max: 2931. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color Space213100200300400500SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 6.51, N = 34414404341. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color Space21380160240320400Min: 440 / Avg: 440.67 / Max: 441Min: 439 / Avg: 440 / Max: 441Min: 421 / Avg: 434 / Max: 4411. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Rotate123120240360480600SE +/- 0.33, N = 35725595571. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Rotate123100200300400500Min: 556 / Avg: 556.67 / Max: 5571. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Enhanced32113263952655757571. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 63210.23090.46180.69270.92361.1545SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 31.0261.0251.025
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 6321246810Min: 1.03 / Avg: 1.03 / Max: 1.03Min: 1.02 / Avg: 1.03 / Max: 1.03Min: 1.03 / Avg: 1.03 / Max: 1.03

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Realtime2313691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 310.9210.8910.881. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Realtime2313691215Min: 10.9 / Avg: 10.92 / Max: 10.94Min: 10.85 / Avg: 10.89 / Max: 10.92Min: 10.84 / Avg: 10.88 / Max: 10.91. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -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 Synthesis123918273645SE +/- 0.09, N = 4SE +/- 0.03, N = 4SE +/- 0.15, N = 440.1740.4940.501. (CC) gcc options: -O2 -std=c99
OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech Synthesis123816243240Min: 39.94 / Avg: 40.17 / Max: 40.36Min: 40.41 / Avg: 40.49 / Max: 40.54Min: 40.28 / Avg: 40.5 / Max: 40.951. (CC) gcc options: -O2 -std=c99

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 Streamcluster1321122334455SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 347.8948.0248.051. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamcluster1321020304050Min: 47.86 / Avg: 47.89 / Max: 47.91Min: 47.99 / Avg: 48.02 / Max: 48.04Min: 48.01 / Avg: 48.05 / Max: 48.091. (CXX) g++ options: -O2 -lOpenCL

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Two-Pass1320.50851.0171.52552.0342.5425SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.262.252.251. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 6 Two-Pass132246810Min: 2.26 / Avg: 2.26 / Max: 2.26Min: 2.24 / Avg: 2.25 / Max: 2.25Min: 2.24 / Avg: 2.25 / Max: 2.251. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 101230.51981.03961.55942.07922.599SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 32.3102.3082.301
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4 AlphaSpeed: 10123246810Min: 2.31 / Avg: 2.31 / Max: 2.31Min: 2.31 / Avg: 2.31 / Max: 2.31Min: 2.29 / Avg: 2.3 / Max: 2.31

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 Fast13248121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 315.7015.6615.651. (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 Fast13248121620Min: 15.68 / Avg: 15.7 / Max: 15.71Min: 15.64 / Avg: 15.66 / Max: 15.7Min: 15.59 / Avg: 15.65 / Max: 15.691. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Betsy GPU Compressor

Betsy is an open-source GPU compressor of various GPU compression techniques. Betsy is written in GLSL for Vulkan/OpenGL (compute shader) support for GPU-based texture compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: Highest2313691215SE +/- 0.32, N = 12SE +/- 0.05, N = 3SE +/- 0.42, N = 1510.6611.1511.411. (CXX) g++ options: -O3 -O2 -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC1 - Quality: Highest2313691215Min: 7.2 / Avg: 10.66 / Max: 11.11Min: 11.1 / Avg: 11.15 / Max: 11.25Min: 10.84 / Avg: 11.41 / Max: 17.231. (CXX) g++ options: -O3 -O2 -lpthread -ldl

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 2020-06-28132816243240SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 336.0736.1036.231. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28132816243240Min: 36.01 / Avg: 36.07 / Max: 36.1Min: 36.05 / Avg: 36.1 / Max: 36.13Min: 36.07 / Avg: 36.23 / Max: 36.491. (CC) gcc options: -O2 -pedantic -fvisibility=hidden

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Compile3212004006008001000SE +/- 2.97, N = 3SE +/- 11.10, N = 3SE +/- 10.84, N = 5917.72898.32873.13
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Compile321160320480640800Min: 911.8 / Avg: 917.72 / Max: 920.98Min: 877.45 / Avg: 898.32 / Max: 915.32Min: 830.07 / Avg: 873.13 / Max: 888.46

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression Speed31216003200480064008000SE +/- 12.26, N = 3SE +/- 9.29, N = 3SE +/- 6.70, N = 37613.57600.87579.51. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression Speed31213002600390052006500Min: 7596.5 / Avg: 7613.5 / Max: 7637.3Min: 7583.8 / Avg: 7600.77 / Max: 7615.8Min: 7567.8 / Avg: 7579.53 / Max: 75911. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression Speed23113002600390052006500SE +/- 21.47, N = 3SE +/- 6.54, N = 3SE +/- 3.72, N = 36154.746138.656133.001. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression Speed23111002200330044005500Min: 6121.77 / Avg: 6154.74 / Max: 6195.05Min: 6125.65 / Avg: 6138.65 / Max: 6146.45Min: 6126.54 / Avg: 6133 / Max: 6139.441. (CC) gcc options: -O3

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 4 Two-Pass3120.31730.63460.95191.26921.5865SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 31.411.411.401. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 4 Two-Pass312246810Min: 1.41 / Avg: 1.41 / Max: 1.41Min: 1.41 / Avg: 1.41 / Max: 1.41Min: 1.38 / Avg: 1.4 / Max: 1.411. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Crafty

This is a performance test of Crafty, an advanced open-source chess engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time3211.2M2.4M3.6M4.8M6MSE +/- 6522.43, N = 3SE +/- 8864.87, N = 3SE +/- 33754.21, N = 35830763582484057958521. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time3211000K2000K3000K4000K5000KMin: 5818381 / Avg: 5830763.33 / Max: 5840509Min: 5813782 / Avg: 5824840 / Max: 5842371Min: 5728370 / Avg: 5795851.67 / Max: 58312381. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory32150K100K150K200K250K2520002520002520001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory3122004006008001000SE +/- 0.33, N = 3SE +/- 0.33, N = 39859859841. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory3122004006008001000Min: 984 / Avg: 984.67 / Max: 985Min: 984 / Avg: 984.33 / Max: 9851. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory12360K120K180K240K300KSE +/- 333.33, N = 3SE +/- 2728.45, N = 3SE +/- 1201.85, N = 32813332806672796671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory12350K100K150K200K250KMin: 281000 / Avg: 281333.33 / Max: 282000Min: 277000 / Avg: 280666.67 / Max: 286000Min: 278000 / Avg: 279666.67 / Max: 2820001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory1232004006008001000SE +/- 1.45, N = 3SE +/- 10.60, N = 3SE +/- 4.70, N = 31098109710931. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory1232004006008001000Min: 1096 / Avg: 1098.33 / Max: 1101Min: 1084 / Avg: 1097 / Max: 1118Min: 1087 / Avg: 1092.67 / Max: 11021. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory123130260390520650SE +/- 0.88, N = 35905845761. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory123100200300400500Min: 588 / Avg: 589.67 / Max: 5911. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory12330060090012001500SE +/- 2.19, N = 31186117611591. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory1232004006008001000Min: 1182 / Avg: 1186.33 / Max: 11891. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

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: 32135001000150020002500SE +/- 4.06, N = 3SE +/- 6.94, N = 3SE +/- 6.40, N = 32271.62271.62270.01. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3213400800120016002000Min: 2263.5 / Avg: 2271.6 / Max: 2276.1Min: 2258.2 / Avg: 2271.57 / Max: 2281.5Min: 2257.2 / Avg: 2270 / Max: 2276.61. (CC) gcc options: -O3 -pthread -lz -llzma

Flexible IO Tester

FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory1322004006008001000SE +/- 0.67, N = 3SE +/- 1.67, N = 3SE +/- 0.58, N = 37927837741. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory132140280420560700Min: 791 / Avg: 792.33 / Max: 793Min: 780 / Avg: 783.33 / Max: 785Min: 773 / Avg: 774 / Max: 7751. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory13230060090012001500SE +/- 1.33, N = 3SE +/- 3.06, N = 3SE +/- 1.45, N = 31592157415551. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory13230060090012001500Min: 1589 / Avg: 1591.67 / Max: 1593Min: 1568 / Avg: 1574 / Max: 1578Min: 1552 / Avg: 1554.67 / Max: 15571. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory1232004006008001000SE +/- 4.63, N = 3SE +/- 0.88, N = 3SE +/- 3.18, N = 38838828531. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory123150300450600750Min: 875 / Avg: 882.67 / Max: 891Min: 881 / Avg: 882.33 / Max: 884Min: 847 / Avg: 852.67 / Max: 8581. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory213400800120016002000SE +/- 1.76, N = 3SE +/- 8.96, N = 3SE +/- 6.39, N = 31773177317131. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory21330060090012001500Min: 1770 / Avg: 1772.67 / Max: 1776Min: 1758 / Avg: 1773 / Max: 1789Min: 1701 / Avg: 1712.67 / Max: 17231. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory21380K160K240K320K400KSE +/- 666.67, N = 33640003640003626671. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory21360K120K180K240K300KMin: 362000 / Avg: 362666.67 / Max: 3640001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory21330060090012001500SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 1.67, N = 31422142214171. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory2132004006008001000Min: 1421 / Avg: 1422 / Max: 1423Min: 1421 / Avg: 1421.67 / Max: 1423Min: 1415 / Avg: 1416.67 / Max: 14201. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory32180K160K240K320K400KSE +/- 333.33, N = 3SE +/- 333.33, N = 3SE +/- 5000.00, N = 33733333713333680001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory32160K120K180K240K300KMin: 373000 / Avg: 373333.33 / Max: 374000Min: 371000 / Avg: 371333.33 / Max: 372000Min: 358000 / Avg: 368000 / Max: 3730001. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory32130060090012001500SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 19.50, N = 31459145114371. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.25Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory32130060090012001500Min: 1458 / Avg: 1459 / Max: 1460Min: 1450 / Avg: 1451 / Max: 1452Min: 1398 / Avg: 1437 / Max: 14571. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native

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 Dynamics213714212835SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 327.6727.7527.75
OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid Dynamics213612182430Min: 27.62 / Avg: 27.67 / Max: 27.71Min: 27.6 / Avg: 27.75 / Max: 27.89Min: 27.63 / Avg: 27.75 / Max: 27.97

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 1080p132510152025SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 322.1121.9921.911. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080p132510152025Min: 21.98 / Avg: 22.11 / Max: 22.17Min: 21.94 / Avg: 21.99 / Max: 22.09Min: 21.8 / Avg: 21.91 / Max: 21.961. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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, Lossless312612182430SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 325.0025.0425.171. (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, Lossless312612182430Min: 24.99 / Avg: 25 / Max: 25.01Min: 25.03 / Avg: 25.04 / Max: 25.05Min: 25.16 / Avg: 25.17 / Max: 25.191. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Medium123510152025SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 318.8118.8718.871. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Medium123510152025Min: 18.78 / Avg: 18.81 / Max: 18.84Min: 18.86 / Avg: 18.87 / Max: 18.89Min: 18.85 / Avg: 18.87 / Max: 18.891. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

AOM AV1

This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 Realtime213714212835SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 327.6827.6127.601. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.0Encoder Mode: Speed 8 Realtime213612182430Min: 27.62 / Avg: 27.68 / Max: 27.77Min: 27.59 / Avg: 27.61 / Max: 27.64Min: 27.53 / Avg: 27.6 / Max: 27.641. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 Fast213714212835SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 327.7627.7627.751. (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 Fast213612182430Min: 27.71 / Avg: 27.76 / Max: 27.82Min: 27.7 / Avg: 27.76 / Max: 27.85Min: 27.72 / Avg: 27.75 / Max: 27.771. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU312510152025SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 319.3819.4019.41MIN: 19.28MIN: 19.33MIN: 19.331. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU312510152025Min: 19.34 / Avg: 19.38 / Max: 19.4Min: 19.38 / Avg: 19.4 / Max: 19.41Min: 19.37 / Avg: 19.41 / Max: 19.441. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU13248121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 314.9715.0315.04MIN: 14.86MIN: 14.94MIN: 14.921. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU13248121620Min: 14.93 / Avg: 14.97 / Max: 15.02Min: 15.02 / Avg: 15.03 / Max: 15.05Min: 15.01 / Avg: 15.04 / Max: 15.11. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: No21348121620SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 317.1217.1417.17
OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: No21348121620Min: 17.12 / Avg: 17.12 / Max: 17.14Min: 17.03 / Avg: 17.14 / Max: 17.3Min: 17.14 / Avg: 17.17 / Max: 17.19

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1323691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 310.8710.8910.90MIN: 10.77MIN: 10.78MIN: 10.791. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1323691215Min: 10.82 / Avg: 10.87 / Max: 10.91Min: 10.87 / Avg: 10.89 / Max: 10.93Min: 10.84 / Avg: 10.9 / Max: 10.951. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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 012348121620SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 315.0915.0915.101. (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 012348121620Min: 15.09 / Avg: 15.09 / Max: 15.09Min: 15.09 / Avg: 15.09 / Max: 15.1Min: 15.09 / Avg: 15.1 / Max: 15.111. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU231246810SE +/- 0.00317, N = 3SE +/- 0.00224, N = 3SE +/- 0.01208, N = 37.365507.367047.36778MIN: 7.33MIN: 7.33MIN: 7.321. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU2313691215Min: 7.36 / Avg: 7.37 / Max: 7.37Min: 7.36 / Avg: 7.37 / Max: 7.37Min: 7.35 / Avg: 7.37 / Max: 7.391. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNA21348121620SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 314.7514.7614.791. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNA21348121620Min: 14.64 / Avg: 14.75 / Max: 14.85Min: 14.73 / Avg: 14.76 / Max: 14.84Min: 14.7 / Avg: 14.79 / Max: 14.91. (CC) gcc options: -std=c99 -O3 -lm -lpthread

ASTC Encoder

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

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Fast132246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 37.527.557.571. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Fast1323691215Min: 7.51 / Avg: 7.52 / Max: 7.53Min: 7.52 / Avg: 7.55 / Max: 7.57Min: 7.56 / Avg: 7.57 / Max: 7.571. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU1231.25442.50883.76325.01766.272SE +/- 0.00091, N = 3SE +/- 0.00642, N = 3SE +/- 0.02268, N = 35.514775.534005.57500MIN: 5.43MIN: 5.44MIN: 5.441. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU123246810Min: 5.51 / Avg: 5.51 / Max: 5.52Min: 5.52 / Avg: 5.53 / Max: 5.54Min: 5.53 / Avg: 5.58 / Max: 5.611. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU1323691215SE +/- 0.00550, N = 3SE +/- 0.00204, N = 3SE +/- 0.01374, N = 39.903899.967029.97722MIN: 9.84MIN: 9.91MIN: 9.911. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU1323691215Min: 9.9 / Avg: 9.9 / Max: 9.91Min: 9.96 / Avg: 9.97 / Max: 9.97Min: 9.96 / Avg: 9.98 / Max: 101. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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: Sequential Fill231510152025SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.20, N = 321.9622.0022.731. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential Fill231510152025Min: 21.88 / Avg: 21.96 / Max: 22.06Min: 21.84 / Avg: 22 / Max: 22.09Min: 22.42 / Avg: 22.73 / Max: 23.111. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential Fill231510152025SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.18, N = 320.120.019.41. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential Fill231510152025Min: 20 / Avg: 20.07 / Max: 20.1Min: 19.9 / Avg: 20.03 / Max: 20.2Min: 19.1 / Avg: 19.43 / Max: 19.71. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Delete231510152025SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 321.7121.9422.511. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Delete231510152025Min: 21.67 / Avg: 21.71 / Max: 21.81Min: 21.84 / Avg: 21.94 / Max: 22.13Min: 22.31 / Avg: 22.51 / Max: 22.811. (CXX) g++ options: -O3 -lsnappy -lpthread

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 Compression1233691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 310.6010.6110.671. (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, Highest Compression1233691215Min: 10.59 / Avg: 10.6 / Max: 10.62Min: 10.59 / Avg: 10.61 / Max: 10.63Min: 10.6 / Avg: 10.67 / Max: 10.821. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU1321.07492.14983.22474.29965.3745SE +/- 0.01176, N = 3SE +/- 0.00740, N = 3SE +/- 0.00501, N = 34.732144.768574.77714MIN: 4.56MIN: 4.64MIN: 4.681. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU132246810Min: 4.72 / Avg: 4.73 / Max: 4.76Min: 4.76 / Avg: 4.77 / Max: 4.78Min: 4.77 / Avg: 4.78 / Max: 4.791. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU1233691215SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 312.5112.7012.83MIN: 10.95MIN: 11.23MIN: 11.351. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU12348121620Min: 12.42 / Avg: 12.51 / Max: 12.61Min: 12.64 / Avg: 12.7 / Max: 12.73Min: 12.77 / Avg: 12.83 / Max: 12.871. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

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 Threads23148121620SE +/- 0.10, N = 3SE +/- 0.22, N = 5SE +/- 0.18, N = 918.0618.0818.271. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threads231510152025Min: 17.87 / Avg: 18.06 / Max: 18.19Min: 17.72 / Avg: 18.08 / Max: 18.95Min: 17.82 / Avg: 18.27 / Max: 19.231. (CC) gcc options: -lm

yquake2

This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: Software CPU - Resolution: 1920 x 10802311632486480SE +/- 0.09, N = 3SE +/- 0.43, N = 3SE +/- 0.40, N = 373.873.672.51. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: Software CPU - Resolution: 1920 x 10802311428425670Min: 73.6 / Avg: 73.77 / Max: 73.9Min: 72.7 / Avg: 73.57 / Max: 74Min: 72 / Avg: 72.5 / Max: 73.31. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

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 29Oct2020Model: Rhodopsin Protein3210.4840.9681.4521.9362.42SE +/- 0.002, N = 3SE +/- 0.006, N = 3SE +/- 0.003, N = 32.1512.1452.1421. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Protein321246810Min: 2.15 / Avg: 2.15 / Max: 2.15Min: 2.14 / Avg: 2.15 / Max: 2.16Min: 2.14 / Avg: 2.14 / Max: 2.151. (CXX) g++ options: -O3 -pthread -lm

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU132510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 320.8821.0421.04MIN: 20.65MIN: 20.93MIN: 20.911. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU132510152025Min: 20.85 / Avg: 20.88 / Max: 20.94Min: 21.01 / Avg: 21.04 / Max: 21.09Min: 21.02 / Avg: 21.04 / Max: 21.091. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU132510152025SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 321.3021.3521.42MIN: 21.16MIN: 21.22MIN: 21.281. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU132510152025Min: 21.24 / Avg: 21.3 / Max: 21.37Min: 21.3 / Avg: 21.35 / Max: 21.44Min: 21.38 / Avg: 21.42 / Max: 21.481. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -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: Fill Sync13213002600390052006500SE +/- 16.49, N = 3SE +/- 16.17, N = 3SE +/- 37.01, N = 35987.145991.576005.581. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill Sync13210002000300040005000Min: 5954.69 / Avg: 5987.14 / Max: 6008.47Min: 5962.43 / Avg: 5991.57 / Max: 6018.28Min: 5965.68 / Avg: 6005.58 / Max: 6079.511. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill Sync3210.02250.0450.06750.090.1125SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.10.10.11. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill Sync32112345Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.11. (CXX) g++ options: -O3 -lsnappy -lpthread

Betsy GPU Compressor

Betsy is an open-source GPU compressor of various GPU compression techniques. Betsy is written in GLSL for Vulkan/OpenGL (compute shader) support for GPU-based texture compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: Highest2310.57241.14481.71722.28962.862SE +/- 0.008, N = 3SE +/- 0.009, N = 3SE +/- 0.446, N = 152.0652.0892.5441. (CXX) g++ options: -O3 -O2 -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterBetsy GPU Compressor 1.1 BetaCodec: ETC2 RGB - Quality: Highest231246810Min: 2.05 / Avg: 2.06 / Max: 2.08Min: 2.07 / Avg: 2.09 / Max: 2.11Min: 2.06 / Avg: 2.54 / Max: 8.781. (CXX) g++ options: -O3 -O2 -lpthread -ldl

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 Files231510152025SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 320.4320.4520.551. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Files231510152025Min: 20.34 / Avg: 20.43 / Max: 20.59Min: 20.37 / Avg: 20.45 / Max: 20.54Min: 20.49 / Avg: 20.55 / Max: 20.611. (CC) gcc options: -lm

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations21320406080100SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3102.51104.39104.721. (CC) gcc options: -lm
OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations21320406080100Min: 102.51 / Avg: 102.51 / Max: 102.52Min: 104.28 / Avg: 104.39 / Max: 104.53Min: 104.61 / Avg: 104.72 / Max: 104.891. (CC) gcc options: -lm

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programs123306090120150SE +/- 0.11, N = 3SE +/- 0.56, N = 3SE +/- 0.44, N = 3112.87113.13113.231. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programs12320406080100Min: 112.73 / Avg: 112.87 / Max: 113.09Min: 112.09 / Avg: 113.13 / Max: 114.03Min: 112.37 / Avg: 113.23 / Max: 113.771. (CC) gcc options: -lm

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processes312714212835SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.38, N = 331.1431.4931.731. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processes312714212835Min: 31.01 / Avg: 31.14 / Max: 31.26Min: 31.37 / Avg: 31.49 / Max: 31.62Min: 31.07 / Avg: 31.73 / Max: 32.371. (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 Decompression1230.96731.93462.90193.86924.8365SE +/- 0.023, N = 3SE +/- 0.023, N = 3SE +/- 0.024, N = 34.2854.2984.299
OpenBenchmarking.orgSeconds, Fewer Is BetterSystem GZIP Decompression123246810Min: 4.26 / Avg: 4.29 / Max: 4.33Min: 4.27 / Avg: 4.3 / Max: 4.34Min: 4.27 / Avg: 4.3 / Max: 4.35

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 1001320.79971.59942.39913.19883.9985SE +/- 0.002, N = 3SE +/- 0.005, N = 3SE +/- 0.006, N = 33.5473.5523.5541. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100132246810Min: 3.54 / Avg: 3.55 / Max: 3.55Min: 3.55 / Avg: 3.55 / Max: 3.56Min: 3.55 / Avg: 3.55 / Max: 3.571. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

yquake2

This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 3.x - Resolution: 1920 x 108023160120180240300SE +/- 0.38, N = 3SE +/- 0.47, N = 3SE +/- 0.81, N = 3270.4267.7261.31. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 3.x - Resolution: 1920 x 108023150100150200250Min: 269.7 / Avg: 270.4 / Max: 271Min: 266.8 / Avg: 267.7 / Max: 268.4Min: 259.9 / Avg: 261.27 / Max: 262.71. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU23148121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 314.7414.7514.77MIN: 14.69MIN: 14.69MIN: 14.71. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU23148121620Min: 14.72 / Avg: 14.74 / Max: 14.75Min: 14.73 / Avg: 14.75 / Max: 14.77Min: 14.74 / Avg: 14.77 / Max: 14.81. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU31248121620SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 318.1218.2118.25MIN: 17.95MIN: 18.08MIN: 18.131. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU312510152025Min: 18.02 / Avg: 18.12 / Max: 18.19Min: 18.17 / Avg: 18.21 / Max: 18.22Min: 18.2 / Avg: 18.25 / Max: 18.31. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

yquake2

This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 1.x - Resolution: 1920 x 108023160120180240300SE +/- 0.71, N = 3SE +/- 0.96, N = 3SE +/- 0.52, N = 3297.8294.6285.41. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
OpenBenchmarking.orgFrames Per Second, More Is Betteryquake2 7.45Renderer: OpenGL 1.x - Resolution: 1920 x 108023150100150200250Min: 296.4 / Avg: 297.77 / Max: 298.8Min: 292.7 / Avg: 294.57 / Max: 295.9Min: 284.4 / Avg: 285.43 / Max: 286.11. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -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: Default3120.52921.05841.58762.11682.646SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 32.2602.2622.3521. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Default312246810Min: 2.26 / Avg: 2.26 / Max: 2.26Min: 2.26 / Avg: 2.26 / Max: 2.27Min: 2.35 / Avg: 2.35 / Max: 2.361. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff

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 Random3120.54771.09541.64312.19082.7385SE +/- 0.003, N = 3SE +/- 0.005, N = 3SE +/- 0.011, N = 32.4152.4252.4341. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek Random312246810Min: 2.41 / Avg: 2.42 / Max: 2.42Min: 2.42 / Avg: 2.42 / Max: 2.43Min: 2.42 / Avg: 2.43 / Max: 2.451. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Fill321612182430SE +/- 0.11, N = 3SE +/- 0.33, N = 3SE +/- 0.06, N = 322.7323.1123.301. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Fill321510152025Min: 22.59 / Avg: 22.73 / Max: 22.95Min: 22.63 / Avg: 23.11 / Max: 23.73Min: 23.18 / Avg: 23.29 / Max: 23.371. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random Fill321510152025SE +/- 0.09, N = 3SE +/- 0.26, N = 3SE +/- 0.03, N = 319.419.118.91. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random Fill321510152025Min: 19.2 / Avg: 19.37 / Max: 19.5Min: 18.6 / Avg: 19.1 / Max: 19.5Min: 18.9 / Avg: 18.93 / Max: 191. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Overwrite321612182430SE +/- 0.15, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 323.0123.0323.641. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Overwrite321612182430Min: 22.71 / Avg: 23.01 / Max: 23.16Min: 22.71 / Avg: 23.03 / Max: 23.22Min: 23.62 / Avg: 23.64 / Max: 23.681. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Overwrite321510152025SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 319.219.118.71. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Overwrite321510152025Min: 19 / Avg: 19.17 / Max: 19.4Min: 19 / Avg: 19.13 / Max: 19.4Min: 18.6 / Avg: 18.67 / Max: 18.71. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot Read1320.43610.87221.30831.74442.1805SE +/- 0.014, N = 3SE +/- 0.015, N = 3SE +/- 0.028, N = 41.8971.8981.9381. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot Read132246810Min: 1.88 / Avg: 1.9 / Max: 1.93Min: 1.88 / Avg: 1.9 / Max: 1.93Min: 1.9 / Avg: 1.94 / Max: 2.021. (CXX) g++ options: -O3 -lsnappy -lpthread

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 Routine1233K6K9K12K15KSE +/- 28.65, N = 3SE +/- 21.29, N = 3SE +/- 62.36, N = 315355.2915246.0915203.721. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT Routine1233K6K9K12K15KMin: 15299.83 / Avg: 15355.29 / Max: 15395.48Min: 15206.96 / Avg: 15246.09 / Max: 15280.18Min: 15120.96 / Avg: 15203.72 / Max: 15325.91. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

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 Read2130.42910.85821.28731.71642.1455SE +/- 0.016, N = 3SE +/- 0.013, N = 3SE +/- 0.003, N = 31.8981.9011.9071. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Read213246810Min: 1.87 / Avg: 1.9 / Max: 1.92Min: 1.88 / Avg: 1.9 / Max: 1.92Min: 1.9 / Avg: 1.91 / Max: 1.911. (CXX) g++ options: -O3 -lsnappy -lpthread

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled Tree2312004006008001000SE +/- 11.44, N = 3SE +/- 6.83, N = 3SE +/- 12.24, N = 31141.921046.371037.77
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled Tree2312004006008001000Min: 1119.92 / Avg: 1141.92 / Max: 1158.34Min: 1033.06 / Avg: 1046.37 / Max: 1055.73Min: 1013.33 / Avg: 1037.77 / Max: 1051.27

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial Create21380160240320400SE +/- 5.95, N = 3SE +/- 2.89, N = 3SE +/- 2.71, N = 3347.09342.41341.68
OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial Create21360120180240300Min: 335.95 / Avg: 347.09 / Max: 356.28Min: 337.25 / Avg: 342.41 / Max: 347.26Min: 336.34 / Avg: 341.68 / Max: 345.18

161 Results Shown

Timed LLVM Compilation
RealSR-NCNN
Rodinia
Incompact3D
ASTC Encoder
GROMACS
Kvazaar
VkFFT
Monte Carlo Simulations of Ionised Nebulae
Rodinia
LeelaChessZero:
  Eigen
  BLAS
Timed Clash Compilation
RealSR-NCNN
Numpy Benchmark
Apache CouchDB
NAMD
Zstd Compression
Embree:
  Pathtracer - Crown
  Pathtracer - Asian Dragon Obj
asmFish
Basis Universal
Embree:
  Pathtracer ISPC - Crown
  Pathtracer ISPC - Asian Dragon Obj
  Pathtracer - Asian Dragon
Timed FFmpeg Compilation
Embree
TensorFlow Lite:
  Inception ResNet V2
  Inception V4
Kvazaar
Timed HMMer Search
Rodinia
Flexible IO Tester:
  Seq Read - IO_uring - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
ASTC Encoder
Waifu2x-NCNN Vulkan
BYTE Unix Benchmark
x265
Montage Astronomical Image Mosaic Engine
oneDNN:
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
Basis Universal:
  ETC1S
  UASTC Level 2
GLmark2
Kvazaar
LZ4 Compression:
  9 - Decompression Speed
  9 - Compression Speed
Stockfish
LZ4 Compression:
  3 - Decompression Speed
  3 - Compression Speed
oneDNN:
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
Kvazaar
rav1e
Coremark
KeyDB
Rodinia
LibRaw
AOM AV1
WebP Image Encode
TensorFlow Lite
DDraceNetwork
DDraceNetwork
TensorFlow Lite
DDraceNetwork
DDraceNetwork
DDraceNetwork
DDraceNetwork
TensorFlow Lite
DDraceNetwork
DDraceNetwork
GraphicsMagick
TensorFlow Lite
GraphicsMagick:
  Swirl
  Noise-Gaussian
  Resizing
  HWB Color Space
  Rotate
  Enhanced
rav1e
AOM AV1
eSpeak-NG Speech Engine
Rodinia
AOM AV1
rav1e
Kvazaar
Betsy GPU Compressor
RNNoise
Compile Bench
LZ4 Compression:
  1 - Decompression Speed
  1 - Compression Speed
AOM AV1
Crafty
Flexible IO Tester:
  Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Seq Read - IO_uring - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Read - IO_uring - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
Zstd Compression
Flexible IO Tester:
  Rand Write - IO_uring - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Seq Write - IO_uring - No - Yes - 2MB - Default Test Directory:
    IOPS
    MB/s
  Seq Write - IO_uring - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
  Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory:
    IOPS
    MB/s
Dolfyn
x265
WebP Image Encode
ASTC Encoder
AOM AV1
Kvazaar
oneDNN:
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
Waifu2x-NCNN Vulkan
oneDNN
Basis Universal
oneDNN
Timed MAFFT Alignment
ASTC Encoder
oneDNN:
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
LevelDB:
  Seq Fill:
    Microseconds Per Op
    MB/s
  Rand Delete:
    Microseconds Per Op
WebP Image Encode
oneDNN:
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 3D - f32 - CPU
OSBench
yquake2
LAMMPS Molecular Dynamics Simulator
oneDNN:
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
LevelDB:
  Fill Sync:
    Microseconds Per Op
    MB/s
Betsy GPU Compressor
OSBench:
  Create Files
  Memory Allocations
  Launch Programs
  Create Processes
System GZIP Decompression
WebP Image Encode
yquake2
oneDNN:
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
yquake2
WebP Image Encode
LevelDB:
  Seek Rand
  Rand Fill
  Rand Fill
  Overwrite
  Overwrite
  Hot Read
FFTE
LevelDB
Compile Bench:
  Read Compiled Tree
  Initial Create

1

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xdc - Thermald 1.9.1
Java Notes: OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04)
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + 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: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

Testing initiated at 12 December 2020 17:41 by user phoronix.

2

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + 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: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

Testing initiated at 13 December 2020 17:39 by user phoronix.

3

Processor: Intel Xeon E3-1235L v5 @ 3.00GHz (4 Cores), Motherboard: ASRockRack C236M WS (P2.60 BIOS), Chipset: Intel Xeon E3-1200 v5/E3-1500, Memory: 8GB, Disk: Samsung SSD 960 EVO 500GB + 123GB Ultra Luxe, Graphics: Intel HD 530 3GB (1000MHz), Audio: Realtek ALC1150, Monitor: DELL S2409W, Network: Intel I219-LM + Intel I210

OS: Ubuntu 20.04, Kernel: 5.8.0-050800-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.4, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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
Disk Notes: NONE / errors=remount-ro,relatime,rw / Block Size: 4096
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 1.9.1
Python Notes: Python 3.8.5
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Mitigation of Clear buffers; SMT disabled + 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: disabled RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Mitigation of Clear buffers; SMT disabled

Testing initiated at 14 December 2020 15:14 by user phoronix.