Apple M2 MacBook Air vs. AMD Ryzen 7 PRO 6850U On Linux

Initial Apple M2 MacBook Air benchmarks on Asahi Linux by Michael Larabel compared to an AMD Ryzen 7 6850U PRO via ThinkPad X13 Gen3 AMD. Benchmarks for Phoronix.com in a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2208186-NE-M2MAC493948
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:

Audio Encoding 2 Tests
C/C++ Compiler Tests 9 Tests
Compression Tests 3 Tests
CPU Massive 20 Tests
Creator Workloads 20 Tests
Cryptography 4 Tests
Encoding 5 Tests
Game Development 4 Tests
HPC - High Performance Computing 10 Tests
Imaging 8 Tests
Java 3 Tests
Machine Learning 6 Tests
MPI Benchmarks 2 Tests
Multi-Core 11 Tests
NVIDIA GPU Compute 2 Tests
OpenMPI Tests 2 Tests
Productivity 4 Tests
Programmer / Developer System Benchmarks 8 Tests
Python 4 Tests
Scientific Computing 2 Tests
Software Defined Radio 3 Tests
Server 4 Tests
Server CPU Tests 10 Tests
Single-Threaded 7 Tests
Speech 2 Tests
Telephony 2 Tests
Texture Compression 4 Tests
Video Encoding 3 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
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

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
Apple MacBook Air M2
August 06 2022
  1 Day, 3 Hours, 43 Minutes
Apple MacBook Air M2 - Max Perf
August 17 2022
  1 Day, 7 Hours, 21 Minutes
Ryzen 7 6850U
August 08 2022
  18 Hours, 10 Minutes
Ryzen 7 6850U - Max Perf
August 09 2022
  17 Hours, 22 Minutes
Invert Hiding All Results Option
  23 Hours, 39 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):

Apple MacBook Air M2

Compiler Notes: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: apple-cpufreq schedutil
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8)
Python Notes: Python 3.10.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Apple MacBook Air M2 - Max Perf

Processor: Apple M2 @ 2.42GHz (4 Cores / 8 Threads), Motherboard: Apple MacBook Air (13 h M2 2022), Memory: 8GB, Disk: 251GB APPLE SSD AP0256Z + 2 x 0GB APPLE SSD AP0256Z, Graphics: llvmpipe, Network: Broadcom Device 4433 + Broadcom Device 5f71

OS: Arch rolling, Kernel: 5.19.0-rc7-asahi-2-1-ARCH (aarch64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.1.4 (LLVM 14.0.6 128 bits), Compiler: GCC 12.1.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 2560x1600

Compiler Notes: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: apple-cpufreq performance
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 7 6850U

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa404102 - ACPI Profile: balanced
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8)
Python Notes: Python 3.10.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Ryzen 7 6850U - Max Perf

Processor: AMD Ryzen 7 PRO 6850U @ 2.70GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET46W 1.16 BIOS), Chipset: AMD Device 14b5, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765

OS: Arch rolling, Kernel: 5.18.16-arch1-1 (x86_64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.1.4 (LLVM 14.0.6 DRM 3.46), Vulkan: 1.3.211, Compiler: GCC 12.1.1 20220730 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - Platform Profile: performance - CPU Microcode: 0xa404102 - ACPI Profile: performance
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8)
Python Notes: Python 3.10.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Apple M2 MacBook Air vs. AMD Ryzen 7 PRO 6850U On LinuxProcessorMotherboardMemoryDiskGraphicsNetworkChipsetAudioOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionVulkanApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max PerfApple M2 @ 2.42GHz (4 Cores / 8 Threads)Apple MacBook Air (13 h M2 2022)8GB251GB APPLE SSD AP0256Z + 2 x 0GB APPLE SSD AP0256ZllvmpipeBroadcom Device 4433 + Broadcom Device 5f71Arch rolling5.19.0-rc7-asahi-2-1-ARCH (aarch64)KDE Plasma 5.25.4X Server 1.21.1.44.5 Mesa 22.1.4 (LLVM 14.0.6 128 bits)GCC 12.1.0 + Clang 14.0.6ext42560x1600AMD Ryzen 7 PRO 6850U @ 2.70GHz (8 Cores / 16 Threads)LENOVO 21CM0001US (R22ET46W 1.16 BIOS)AMD Device 14b516GB512GB Micron MTFDKBA512TFKAMD Radeon 680M 1GB (2200/400MHz)AMD Rembrandt Radeon HD AudioQualcomm QCNFA7655.18.16-arch1-1 (x86_64)X Server 1.21.1.4 + Wayland4.6 Mesa 22.1.4 (LLVM 14.0.6 DRM 3.46)1.3.211GCC 12.1.1 20220730 + Clang 14.0.61920x1200OpenBenchmarking.orgCompiler Details- Apple MacBook Air M2: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu - Apple MacBook Air M2 - Max Perf: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu - Ryzen 7 6850U: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu - Ryzen 7 6850U - Max Perf: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu Processor Details- Apple MacBook Air M2: Scaling Governor: apple-cpufreq schedutil- Apple MacBook Air M2 - Max Perf: Scaling Governor: apple-cpufreq performance- Ryzen 7 6850U: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa404102 - ACPI Profile: balanced- Ryzen 7 6850U - Max Perf: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - Platform Profile: performance - CPU Microcode: 0xa404102 - ACPI Profile: performance Java Details- Apple MacBook Air M2, Ryzen 7 6850U, Ryzen 7 6850U - Max Perf: OpenJDK Runtime Environment (build 11.0.16+8)Python Details- Apple MacBook Air M2, Ryzen 7 6850U, Ryzen 7 6850U - Max Perf: Python 3.10.5Security Details- Apple MacBook Air M2: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Apple MacBook Air M2 - Max Perf: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Ryzen 7 6850U: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Ryzen 7 6850U - Max Perf: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected Kernel Details- Ryzen 7 6850U, Ryzen 7 6850U - Max Perf: Transparent Huge Pages: always

Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max PerfLogarithmic Result OverviewPhoronix Test SuiteLAME MP3 EncodingLiquid-DSPEtcpakFLAC Audio Encodingx265LuaRadioCryptsetupASTC EncoderLAMMPS Molecular Dynamics SimulatorPyHPC BenchmarksGNU Octave BenchmarkParallel BZIP2 CompressionGoogle DracoLeelaChessZeroPOV-RayWebP2 Image EncodePrimesieveNode.js V8 Web Tooling BenchmarkCoremarkDaCapo BenchmarkNCNNTensorFlow LiteVP9 libvpx EncodingZstd CompressionNgspiceInkscapeTNNRNNoiseXZ CompressionXmriglibavif avifencNumpy BenchmarkRenaissanceGNU RadioSecureMarksimdjsonOpenSSLlibjpeg-turbo tjbenchGIMPBuild2Java Gradle BuildDarktableApache SparkUnpacking FirefoxWebP Image EncodePyBenchPyPerformanceBasis UniversalGEGLASKAPGit

Apple M2 MacBook Air vs. AMD Ryzen 7 PRO 6850U On Linuxluaradio: Five Back to Back FIR Filterscryptsetup: Serpent-XTS 512b Encryptioncryptsetup: Serpent-XTS 256b Encryptioncryptsetup: Serpent-XTS 256b Decryptiongnuradio: Five Back to Back FIR Filtersencode-mp3: WAV To MP3renaissance: Apache Spark Bayesrenaissance: Genetic Algorithm Using Jenetics + Futurescompress-zstd: 3, Long Mode - Compression Speedliquid-dsp: 16 - 256 - 57liquid-dsp: 1 - 256 - 57renaissance: Finagle HTTP Requestsliquid-dsp: 8 - 256 - 57liquid-dsp: 2 - 256 - 57etcpak: Multi-Threaded - ETC2compress-zstd: 8 - Compression Speedliquid-dsp: 4 - 256 - 57astcenc: Thoroughastcenc: Exhaustiveetcpak: Single-Threaded - ETC2encode-flac: WAV To FLACx265: Bosphorus 4Kx265: Bosphorus 1080pncnn: CPU - resnet18cryptsetup: Twofish-XTS 512b Decryptioncryptsetup: Twofish-XTS 512b Encryptioncryptsetup: Twofish-XTS 256b Decryptioncryptsetup: Twofish-XTS 256b Encryptiongnuradio: Signal Source (Cosine)lammps: 20k Atomspyhpc: CPU - Numpy - 4194304 - Isoneutral Mixingpyhpc: CPU - Numpy - 1048576 - Equation of Statecompress-zstd: 8, Long Mode - Compression Speedtensorflow-lite: Mobilenet Quantspark: 1000000 - 2000 - Calculate Pi Benchmarkpyhpc: CPU - Numpy - 1048576 - Isoneutral Mixingspark: 1000000 - 100 - Calculate Pi Benchmarkwebp2: Quality 100, Compression Effort 5tnn: CPU - DenseNetncnn: CPU - vgg16pyhpc: CPU - Numpy - 4194304 - Equation of Statetensorflow-lite: Inception ResNet V2compress-zstd: 3 - Compression Speedtensorflow-lite: Mobilenet Floatlammps: Rhodopsin Proteinoctave-benchmark: gnuradio: FIR Filterncnn: CPU-v2-v2 - mobilenet-v2draco: Lionrenaissance: Akka Unbalanced Cobwebbed Treecompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionncnn: CPU - yolov4-tinyncnn: CPU - resnet50avifenc: 2webp2: Quality 95, Compression Effort 7povray: Trace Timeavifenc: 0ncnn: CPU-v3-v3 - mobilenet-v3primesieve: 1e13dacapobench: Tradebeansgnuradio: Hilbert Transformwebp2: Quality 75, Compression Effort 7spark: 1000000 - 100 - Group By Test Timedraco: Church Facadencnn: CPU - squeezenet_ssdwebp2: Quality 100, Lossless Compressionspark: 1000000 - 2000 - Group By Test Timevpxenc: Speed 5 - Bosphorus 4Ktnn: CPU - SqueezeNet v1.1ncnn: CPU - shufflenet-v2node-web-tooling: coremark: CoreMark Size 666 - Iterations Per Secondrenaissance: In-Memory Database Shootoutcryptsetup: PBKDF2-sha512ncnn: CPU - efficientnet-b0pyperformance: python_startupspark: 1000000 - 100 - SHA-512 Benchmark Timeastcenc: Mediumdarktable: Boat - CPU-onlyvpxenc: Speed 5 - Bosphorus 1080pngspice: C7552ncnn: CPU - mnasnetdacapobench: Jythoninkscape: SVG Files To PNGrnnoise: darktable: Server Rack - CPU-onlycompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9ncnn: CPU - regnety_400mxmrig: Monero - 1Mopenssl: RSA4096simdjson: DistinctUserIDrenaissance: Rand Forestavifenc: 6gimp: resizedacapobench: Tradesoapdarktable: Server Room - CPU-onlyncnn: CPU - googlenetnumpy: compress-zstd: 8, Long Mode - Decompression Speedspark: 1000000 - 2000 - SHA-512 Benchmark Timecompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Decompression Speedsimdjson: TopTweetcompress-zstd: 19 - Decompression Speedrenaissance: Apache Spark PageRankgnuradio: FM Deemphasis Filteraskap: tConvolve MT - Griddingcompress-zstd: 8 - Decompression Speedaskap: tConvolve OpenMP - Degriddingtnn: CPU - MobileNet v2webp2: Defaultaskap: Hogbom Clean OpenMPsecuremark: SecureMark-TLSaskap: tConvolve MT - Degriddingncnn: CPU - mobilenetncnn: CPU - alexnetrenaissance: ALS Movie Lensgimp: auto-levelsgimp: rotatetjbench: Decompression Throughputrenaissance: Savina Reactors.IOsimdjson: Kostyasimdjson: LargeRandsynthmark: VoiceMark_100avifenc: 6, Losslessopenssl: RSA4096pyperformance: regex_compileopenssl: SHA256simdjson: PartialTweetsavifenc: 10, Losslesscompress-zstd: 19, Long Mode - Compression Speedbuild2: Time To Compilegegl: Scalejava-gradle-perf: Reactorwebp: Quality 100, Losslessgimp: unsharp-maskbasis: UASTC Level 3pyperformance: 2to3pyperformance: pathlibrenaissance: Apache Spark ALSgegl: Tile Glassunpack-firefox: firefox-84.0.source.tar.xzspark: 1000000 - 100 - Broadcast Inner Join Test Timecompress-zstd: 19 - Compression Speedcryptsetup: AES-XTS 256b Decryptioncryptsetup: AES-XTS 256b Encryptioncryptsetup: PBKDF2-whirlpoolpyperformance: crypto_pyaespybench: Total For Average Test Timesluaradio: FM Deemphasis Filterspark: 1000000 - 2000 - Repartition Test Timepyperformance: chaosbasis: UASTC Level 2gegl: Rotate 90 Degreesgegl: Antialiasgegl: Reflectpyperformance: django_templateluaradio: Complex Phasepyperformance: nbodypyperformance: json_loadswebp: Quality 100, Highest Compressionbasis: UASTC Level 0askap: tConvolve OpenMP - Griddinggegl: Wavelet Blurgegl: Cartoongegl: Croppyperformance: floatpyperformance: gopyperformance: pickle_pure_pythoncryptsetup: AES-XTS 512b Encryptioncryptsetup: AES-XTS 512b Decryptionbasis: ETC1Sgegl: Color Enhancepyperformance: raytracegit: Time To Complete Common Git Commandstnn: CPU - SqueezeNet v2compress-zstd: 3 - Decompression Speedncnn: CPU - blazefacetensorflow-lite: NASNet Mobiletensorflow-lite: SqueezeNetspark: 1000000 - 2000 - Calculate Pi Benchmark Using Dataframespark: 1000000 - 100 - Inner Join Test Timespark: 1000000 - 100 - Repartition Test Timespark: 1000000 - 100 - Calculate Pi Benchmark Using Dataframengspice: C2670primesieve: 1e12gnuradio: IIR Filterrenaissance: Scala Dottydacapobench: H2lczero: EigenApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf145.499.699.5103.3155.226.6707761.05968.2265.8137213333237166671697.813700000047434667653.639901.19485600021.5686209.8306119.75327.2704.5021.707.78221.2220.7221.3220.56370.02.5061.2020.145723.02301.54424.630.299401.7512.4035236.78133.400.8351020433620.65693.843.3064.031536.92.2434617664.215.89014.4915.45151.669852.46088.329327.5712.07549.6673878413.9384.2813.05507914.601864.9824.0410.24321.8991.9218.97204530.9287793439.035828363.6710.43.315.54647.31025.2584.5262.21291522.24921.5030.66045.3385.302429.01533.84.19652.915.81110.88237603.40512.69652.695479.74.524531.15241.24.254494.63004.7823.11536.835005.41733.47306.5604.871216.9232522901441.4912.0212.067581.611.68010.897222.6204085433.83.051.04660.05817.942107565.610588226675004.185.52321.7210.7645.390143.37514.99514.97472.60422311.23340.825.15316.8721.9226.24315.94315.878486287.1840380.84.2174.033.81737.90130.58125.29230.7857.998.817.86.1146.0041456.3746.69573.7826.52076.21653054120.54122.624.04442.37035042.24853.2924804.21.8717334.17293.7921.512.233.3021.41175.48038.1471147.1583.64590715240.099.699.5103.3206.55.6867445.81631.0894.3136926667237193331729.213656000047455333654.470899.09490333321.8374208.0822119.77527.1154.9321.986.83221.2220.6221.3220.56444.22.4151.2000.146746.72299.15445.090.298446.4712.9674505.26431.310.8331014173729.85655.293.0453.915559.22.2434687486.916.38214.1914.66150.939900.76593.625316.3182.07561.5472492428.4408.7202.98507312.711966.8023.8910.75321.8361.8920.64204409.3794942746.535848753.637.353.345.70877.85125.9285.0312.21267719.59221.4760.63945.5545.312547.11473.14.19511.616.13210.02737513.44910.16668.565479.24.605230.84.254507.63000.2856.51536.095005.41731.45275.7594.860240.7722523301439.5511.8010.876292.310.5239.866222.6738205278.33.051.0417.840103778.310587388471434.185.84921.8213.4804.864137.83615.01813.06774.35321211.23290.923.47916.2371.9926.74317.44316.778486287.2841383.44.3173.934.35137.35028.81024.20230.6876.998.817.96.1135.9901517.8644.82272.7656.35676.21643044120.74123.024.05341.99935042.04553.3254820.41.8817241.77652.4023.482.293.6221.92117.09441.1421201.0537.926317671320.2903.8880.7888.9945.25.9111859.73688.4590.1409770000734623335252.53867466671409900001755.782325.62442866679.163591.7269292.88111.50310.3348.2915.31494.3492.9494.4490.33039.14.7532.4130.291373.04578.45247.7040355960.575247.6099880867.2862858.25458.991.56259615.61995.63324.095.3367.214969.53.88596512898.110.19424.2724.9396.890586.74361.691215.3003.34382.1423971655.4278.5914.71800619.781386.2145.9314.46219.0502.7714.09277973.3027183935.125307855.157.994.654.19825.88833.80116.8163.05369126.67315.9630.51635.1546.983108.71807.65.42668.613.28112.99748234.37513.05522.014297.05.773567.84155.15.343570.23789.01019.71230.784060.02130.14251.5794.194199.0773085561754.8214.3413.197351.312.66011.868267.2582906304.93.601.23785.94216.111115075.212495286065804.806.39024.8197.4335.595158.25613.09514.46370.03123912.63136.222.67415.2462.0728.64766.64741.186185780.1773412.74.2778.335.18439.64629.27825.62832.4828.710418.75.8496.2611512.8246.31975.7636.58078.61693124057.94076.224.62541.56434741.94453.1931.3810854.34444.4913.502.503.5413.53162.56629.729379.0785.741054611438.5902.6879.0887.9993.45.9051675.01647.2972.2441440000743703334841.34149433331434666671848.402332.02549966678.499384.5533291.10611.40010.6250.1114.80493.4490.6493.2489.23126.05.1092.4100.288379.54241.53225.930.580230.2695054196.8122760.97658.871.55554465.62030.23077.335.6287.206973.83.75591912534.69.52823.2024.2090.734542.61456.955201.8823.32349.7433645658.4257.2354.57795818.981284.0855.7115.08219.0362.6614.50298579.1955893490.025098945.037.954.414.10335.65634.98115.9572.98354026.56315.8580.48934.5736.803183.11930.05.48607.612.40512.65245524.31312.71528.224278.65.523591.34128.05.383563.33720.81028.81234.334084.42130.14249.5843.974196.6993066461751.4513.6312.987000.312.12211.487266.4527075901.73.641.24786.94615.061122833.4124102780776804.856.08825.1185.3395.536152.18913.12313.91365.34524112.72966.022.35115.0341.8529.34743.64712.086098080.6781413.53.9979.732.86539.17729.56325.62432.4829.110318.65.8246.1081479.6046.01975.6406.54178.11683134014.54024.624.12441.70434541.69653.6711.3110274.74079.6012.402.433.4212.57150.91727.111379.8823.93070518OpenBenchmarking.org

LuaRadio

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

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR FiltersApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500SE +/- 1.56, N = 9SE +/- 0.42, N = 3SE +/- 8.89, N = 3SE +/- 5.70, N = 3145.4240.01320.21438.5
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR FiltersApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500Min: 139.1 / Avg: 145.37 / Max: 151.3Min: 239.2 / Avg: 240 / Max: 240.6Min: 1306.6 / Avg: 1320.17 / Max: 1336.9Min: 1428.3 / Avg: 1438.53 / Max: 1448

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 512b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 0.68, N = 3SE +/- 1.60, N = 399.699.6903.8902.6
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 512b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf160320480640800Min: 903.1 / Avg: 903.83 / Max: 905.2Min: 900.8 / Avg: 902.6 / Max: 905.8

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 256b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 21.30, N = 3SE +/- 20.29, N = 399.599.5880.7879.0
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 256b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf150300450600750Min: 99.3 / Avg: 99.5 / Max: 99.6Min: 99.4 / Avg: 99.53 / Max: 99.6Min: 838.1 / Avg: 880.7 / Max: 902.3Min: 838.5 / Avg: 878.97 / Max: 901.9

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 256b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.99, N = 3SE +/- 2.12, N = 3103.3103.3888.9887.9
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupSerpent-XTS 256b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf160320480640800Min: 103.3 / Avg: 103.3 / Max: 103.3Min: 103.3 / Avg: 103.3 / Max: 103.3Min: 887.1 / Avg: 888.93 / Max: 890.5Min: 883.7 / Avg: 887.9 / Max: 890.5

GNU Radio

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

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR FiltersApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 1.07, N = 3SE +/- 0.41, N = 3SE +/- 6.32, N = 3SE +/- 9.05, N = 3155.2206.5945.2993.41. 3.10.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR FiltersApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000Min: 153.1 / Avg: 155.2 / Max: 156.6Min: 205.7 / Avg: 206.47 / Max: 207.1Min: 932.6 / Avg: 945.23 / Max: 951.7Min: 976.9 / Avg: 993.37 / Max: 1008.11. 3.10.2.0

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.007, N = 3SE +/- 0.022, N = 3SE +/- 0.001, N = 3SE +/- 0.012, N = 326.6705.6865.9115.905-O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe-O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe-O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe1. (CC) gcc options: -lncurses -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 26.66 / Avg: 26.67 / Max: 26.68Min: 5.64 / Avg: 5.69 / Max: 5.72Min: 5.91 / Avg: 5.91 / Max: 5.91Min: 5.89 / Avg: 5.91 / Max: 5.931. (CC) gcc options: -lncurses -lm

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark BayesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf17003400510068008500SE +/- 81.89, N = 5SE +/- 101.97, N = 3SE +/- 24.40, N = 3SE +/- 19.75, N = 47761.07445.81859.71675.0MIN: 5753.2 / MAX: 12809.43MIN: 5639.76 / MAX: 8615.58MIN: 1352.97 / MAX: 1895.68MIN: 1210.86 / MAX: 1763.15
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark BayesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf13002600390052006500Min: 7444.56 / Avg: 7761.03 / Max: 7880.55Min: 7262.84 / Avg: 7445.8 / Max: 7615.33Min: 1813.15 / Avg: 1859.68 / Max: 1895.68Min: 1633.69 / Avg: 1674.95 / Max: 1711.84

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Genetic Algorithm Using Jenetics + FuturesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf13002600390052006500SE +/- 78.56, N = 3SE +/- 1.21, N = 3SE +/- 45.66, N = 3SE +/- 19.11, N = 45968.21631.03688.41647.2MIN: 5477.1 / MAX: 6494.18MIN: 1607.27 / MAX: 1663.37MIN: 3487.78 / MAX: 3799.73MIN: 1563.56 / MAX: 1707.59
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Genetic Algorithm Using Jenetics + FuturesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000Min: 5861.33 / Avg: 5968.21 / Max: 6121.38Min: 1628.8 / Avg: 1630.99 / Max: 1632.98Min: 3600.68 / Avg: 3688.42 / Max: 3754.23Min: 1595.05 / Avg: 1647.21 / Max: 1684.44

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 2.90, N = 3SE +/- 7.58, N = 3SE +/- 2.33, N = 3SE +/- 3.26, N = 3265.8894.3590.1972.21. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000Min: 260 / Avg: 265.8 / Max: 268.8Min: 883.8 / Avg: 894.27 / Max: 909Min: 585.8 / Avg: 590.13 / Max: 593.8Min: 965.8 / Avg: 972.2 / Max: 976.51. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90M180M270M360M450MSE +/- 38441.88, N = 3SE +/- 97353.88, N = 3SE +/- 3921305.05, N = 3SE +/- 3668655.52, N = 31372133331369266674097700004414400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf80M160M240M320M400MMin: 137170000 / Avg: 137213333.33 / Max: 137290000Min: 136810000 / Avg: 136926666.67 / Max: 137120000Min: 405470000 / Avg: 409770000 / Max: 417600000Min: 437150000 / Avg: 441440000 / Max: 4487400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf16M32M48M64M80MSE +/- 11680.94, N = 3SE +/- 1666.67, N = 3SE +/- 375385.28, N = 3SE +/- 615640.68, N = 3237166672371933373462333743703331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf13M26M39M52M65MMin: 23704000 / Avg: 23716666.67 / Max: 23740000Min: 23716000 / Avg: 23719333.33 / Max: 23721000Min: 72754000 / Avg: 73462333.33 / Max: 74032000Min: 73144000 / Avg: 74370333.33 / Max: 750790001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Finagle HTTP RequestsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf11002200330044005500SE +/- 17.03, N = 6SE +/- 15.71, N = 3SE +/- 14.11, N = 3SE +/- 20.43, N = 31697.81729.25252.54841.3MIN: 1421.03 / MAX: 2150.12MIN: 1492.96 / MAX: 2254.39MIN: 4895.34 / MAX: 5729.36MIN: 4546.81 / MAX: 5247.29
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Finagle HTTP RequestsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf9001800270036004500Min: 1622.56 / Avg: 1697.82 / Max: 1735.05Min: 1704.2 / Avg: 1729.2 / Max: 1758.19Min: 5233.07 / Avg: 5252.54 / Max: 5279.97Min: 4802.53 / Avg: 4841.3 / Max: 4871.88

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90M180M270M360M450MSE +/- 5773.50, N = 3SE +/- 98149.55, N = 3SE +/- 3199923.61, N = 3SE +/- 3439991.93, N = 31370000001365600003867466674149433331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70M140M210M280M350MMin: 136990000 / Avg: 137000000 / Max: 137010000Min: 136390000 / Avg: 136560000 / Max: 136730000Min: 383300000 / Avg: 386746666.67 / Max: 393140000Min: 411320000 / Avg: 414943333.33 / Max: 4218200001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30M60M90M120M150MSE +/- 1855.92, N = 3SE +/- 1201.85, N = 3SE +/- 811931.85, N = 3SE +/- 926108.94, N = 347434667474553331409900001434666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20M40M60M80M100MMin: 47431000 / Avg: 47434666.67 / Max: 47437000Min: 47453000 / Avg: 47455333.33 / Max: 47457000Min: 139550000 / Avg: 140990000 / Max: 142360000Min: 141970000 / Avg: 143466666.67 / Max: 1451600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Etcpak

Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf400800120016002000SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 7.40, N = 3SE +/- 5.23, N = 3653.64654.471755.781848.40-mcpu=native-mcpu=native-march=native-march=native1. (CXX) g++ options: -O3 -std=c++11 -lpthread
OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500Min: 653.41 / Avg: 653.64 / Max: 653.86Min: 654.31 / Avg: 654.47 / Max: 654.56Min: 1744.31 / Avg: 1755.78 / Max: 1769.61Min: 1839.3 / Avg: 1848.4 / Max: 1857.431. (CXX) g++ options: -O3 -std=c++11 -lpthread

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 9.18, N = 5SE +/- 2.22, N = 3SE +/- 1.35, N = 3SE +/- 0.17, N = 3901.1899.0325.6332.01. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf160320480640800Min: 867.5 / Avg: 901.1 / Max: 922.4Min: 896.6 / Avg: 898.97 / Max: 903.4Min: 323 / Avg: 325.6 / Max: 327.5Min: 331.7 / Avg: 332 / Max: 332.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50M100M150M200M250MSE +/- 1154.70, N = 3SE +/- 4333.33, N = 3SE +/- 1337439.51, N = 3SE +/- 1178223.71, N = 394856000949033332442866672549966671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf40M80M120M160M200MMin: 94854000 / Avg: 94856000 / Max: 94858000Min: 94899000 / Avg: 94903333.33 / Max: 94912000Min: 242740000 / Avg: 244286666.67 / Max: 246950000Min: 253610000 / Avg: 254996666.67 / Max: 2573400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 3.2Preset: ThoroughApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025SE +/- 0.1431, N = 15SE +/- 0.1890, N = 8SE +/- 0.0791, N = 3SE +/- 0.0301, N = 321.568621.83749.16358.49931. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ThoroughApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 19.68 / Avg: 21.57 / Max: 21.84Min: 20.58 / Avg: 21.84 / Max: 22.15Min: 9.02 / Avg: 9.16 / Max: 9.29Min: 8.45 / Avg: 8.5 / Max: 8.561. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ExhaustiveApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50100150200250SE +/- 2.73, N = 3SE +/- 0.63, N = 3SE +/- 0.30, N = 3SE +/- 0.21, N = 3209.83208.0891.7384.551. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ExhaustiveApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf4080120160200Min: 204.37 / Avg: 209.83 / Max: 212.68Min: 206.94 / Avg: 208.08 / Max: 209.11Min: 91.13 / Avg: 91.73 / Max: 92.11Min: 84.13 / Avg: 84.55 / Max: 84.781. (CXX) g++ options: -O3 -flto -pthread

Etcpak

Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Single-Threaded - Configuration: ETC2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60120180240300SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.43, N = 3SE +/- 0.68, N = 3119.75119.78292.88291.11-mcpu=native-mcpu=native-march=native-march=native1. (CXX) g++ options: -O3 -std=c++11 -lpthread
OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Single-Threaded - Configuration: ETC2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50100150200250Min: 119.72 / Avg: 119.75 / Max: 119.79Min: 119.72 / Avg: 119.78 / Max: 119.81Min: 292.42 / Avg: 292.88 / Max: 293.74Min: 290.01 / Avg: 291.11 / Max: 292.371. (CXX) g++ options: -O3 -std=c++11 -lpthread

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format ten times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.3WAV To FLACApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.04, N = 5SE +/- 0.03, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 527.2727.1211.5011.401. (CXX) g++ options: -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.3WAV To FLACApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 27.19 / Avg: 27.27 / Max: 27.44Min: 27.08 / Avg: 27.11 / Max: 27.23Min: 11.46 / Avg: 11.5 / Max: 11.52Min: 11.33 / Avg: 11.4 / Max: 11.451. (CXX) g++ options: -fvisibility=hidden -logg -lm

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 4KApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.03, N = 12SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 34.504.9310.3310.621. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 4.38 / Avg: 4.5 / Max: 4.83Min: 4.83 / Avg: 4.93 / Max: 5.05Min: 10.15 / Avg: 10.33 / Max: 10.44Min: 10.54 / Avg: 10.62 / Max: 10.721. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1122334455SE +/- 0.24, N = 4SE +/- 0.27, N = 3SE +/- 0.30, N = 3SE +/- 0.57, N = 321.7021.9848.2950.111. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1020304050Min: 21.38 / Avg: 21.7 / Max: 22.4Min: 21.66 / Avg: 21.98 / Max: 22.51Min: 47.74 / Avg: 48.29 / Max: 48.79Min: 49.07 / Avg: 50.11 / Max: 51.031. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.20, N = 37.786.8315.3114.80MIN: 5.54 / MAX: 17.88MIN: 5.57 / MAX: 13.08MIN: 14.85 / MAX: 16.4MIN: 14.16 / MAX: 15.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 7.67 / Avg: 7.78 / Max: 7.96Min: 6.78 / Avg: 6.83 / Max: 6.89Min: 15.14 / Avg: 15.31 / Max: 15.63Min: 14.55 / Avg: 14.8 / Max: 15.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 512b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf110220330440550SE +/- 0.00, N = 2SE +/- 0.00, N = 3SE +/- 0.84, N = 3SE +/- 1.16, N = 3221.2221.2494.3493.4
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 512b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90180270360450Min: 221.2 / Avg: 221.2 / Max: 221.2Min: 221.2 / Avg: 221.2 / Max: 221.2Min: 492.9 / Avg: 494.27 / Max: 495.8Min: 491.3 / Avg: 493.43 / Max: 495.3

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 512b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf110220330440550SE +/- 0.00, N = 2SE +/- 0.03, N = 3SE +/- 0.85, N = 2SE +/- 1.07, N = 3220.7220.6492.9490.6
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 512b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90180270360450Min: 220.7 / Avg: 220.7 / Max: 220.7Min: 220.6 / Avg: 220.63 / Max: 220.7Min: 492 / Avg: 492.85 / Max: 493.7Min: 488.6 / Avg: 490.63 / Max: 492.2

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 256b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf110220330440550SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.15, N = 3SE +/- 1.17, N = 3221.3221.3494.4493.2
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 256b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90180270360450Min: 221.3 / Avg: 221.3 / Max: 221.3Min: 221.3 / Avg: 221.3 / Max: 221.3Min: 494.2 / Avg: 494.4 / Max: 494.7Min: 490.9 / Avg: 493.23 / Max: 494.6

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 256b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf110220330440550SE +/- 0.22, N = 3SE +/- 0.17, N = 3SE +/- 1.29, N = 3SE +/- 1.33, N = 3220.5220.5490.3489.2
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupTwofish-XTS 256b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90180270360450Min: 220.1 / Avg: 220.53 / Max: 220.8Min: 220.2 / Avg: 220.53 / Max: 220.7Min: 487.7 / Avg: 490.27 / Max: 491.7Min: 487 / Avg: 489.2 / Max: 491.6

GNU Radio

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

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf14002800420056007000SE +/- 136.41, N = 3SE +/- 129.49, N = 3SE +/- 14.36, N = 3SE +/- 47.69, N = 36370.06444.23039.13126.01. 3.10.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf11002200330044005500Min: 6230.4 / Avg: 6370 / Max: 6642.8Min: 6185.3 / Avg: 6444.23 / Max: 6577.8Min: 3012.1 / Avg: 3039.1 / Max: 3061.1Min: 3060.9 / Avg: 3125.97 / Max: 3218.91. 3.10.2.0

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 23Jun2022Model: 20k AtomsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.14952.2993.44854.5985.7475SE +/- 0.011, N = 3SE +/- 0.019, N = 3SE +/- 0.019, N = 3SE +/- 0.018, N = 32.5062.4154.7535.109-lm-lm1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 2.49 / Avg: 2.51 / Max: 2.53Min: 2.39 / Avg: 2.42 / Max: 2.45Min: 4.72 / Avg: 4.75 / Max: 4.78Min: 5.07 / Avg: 5.11 / Max: 5.131. (CXX) g++ options: -O3 -ldl

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral MixingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.54291.08581.62872.17162.7145SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.022, N = 3SE +/- 0.006, N = 31.2021.2002.4132.410
OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral MixingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 1.2 / Avg: 1.2 / Max: 1.2Min: 1.2 / Avg: 1.2 / Max: 1.2Min: 2.39 / Avg: 2.41 / Max: 2.46Min: 2.4 / Avg: 2.41 / Max: 2.42

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Equation of StateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.06550.1310.19650.2620.3275SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1450.1460.2910.288
OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Equation of StateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf12345Min: 0.15 / Avg: 0.15 / Max: 0.15Min: 0.15 / Avg: 0.15 / Max: 0.15Min: 0.29 / Avg: 0.29 / Max: 0.29Min: 0.29 / Avg: 0.29 / Max: 0.29

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf160320480640800SE +/- 8.47, N = 3SE +/- 3.33, N = 3SE +/- 3.46, N = 3SE +/- 2.43, N = 3723.0746.7373.0379.51. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf130260390520650Min: 706.3 / Avg: 723 / Max: 733.8Min: 740.6 / Avg: 746.67 / Max: 752.1Min: 367.7 / Avg: 373 / Max: 379.5Min: 374.8 / Avg: 379.47 / Max: 3831. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. 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 2022-05-18Model: Mobilenet QuantApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000SE +/- 27.12, N = 15SE +/- 16.02, N = 13SE +/- 32.35, N = 15SE +/- 47.45, N = 152301.542299.154578.454241.53
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000Min: 2077.44 / Avg: 2301.54 / Max: 2440.86Min: 2127.88 / Avg: 2299.15 / Max: 2347.07Min: 4297.8 / Avg: 4578.45 / Max: 4753.73Min: 3957.81 / Avg: 4241.53 / Max: 4531.2

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf100200300400500SE +/- 3.94, N = 3SE +/- 2.20, N = 4SE +/- 1.53, N = 3SE +/- 0.80, N = 3424.63445.09247.70225.93
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf80160240320400Min: 418.37 / Avg: 424.63 / Max: 431.91Min: 441.62 / Avg: 445.09 / Max: 451.04Min: 245.05 / Avg: 247.7 / Max: 250.34Min: 224.44 / Avg: 225.93 / Max: 227.19

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Isoneutral MixingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.13050.2610.39150.5220.6525SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 30.2990.2980.5750.580
OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Isoneutral MixingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 0.3 / Avg: 0.3 / Max: 0.3Min: 0.3 / Avg: 0.3 / Max: 0.3Min: 0.57 / Avg: 0.57 / Max: 0.58Min: 0.58 / Avg: 0.58 / Max: 0.58

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf100200300400500SE +/- 9.33, N = 3SE +/- 4.46, N = 9SE +/- 1.06, N = 3SE +/- 2.02, N = 3401.75446.47247.61230.27
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf80160240320400Min: 386.1 / Avg: 401.75 / Max: 418.39Min: 413.17 / Avg: 446.47 / Max: 455.93Min: 245.71 / Avg: 247.61 / Max: 249.39Min: 227.23 / Avg: 230.27 / Max: 234.09

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Compression Effort 5Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.098, N = 9SE +/- 0.111, N = 8SE +/- 0.012, N = 3SE +/- 0.008, N = 312.40312.9677.2866.812-msse4.2-msse4.21. (CXX) g++ options: -fno-rtti -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Compression Effort 5Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 11.66 / Avg: 12.4 / Max: 12.63Min: 12.24 / Avg: 12.97 / Max: 13.18Min: 7.27 / Avg: 7.29 / Max: 7.31Min: 6.8 / Avg: 6.81 / Max: 6.831. (CXX) g++ options: -fno-rtti -O3

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf11002200330044005500SE +/- 7.80, N = 3SE +/- 1.09, N = 3SE +/- 3.69, N = 3SE +/- 1.95, N = 35236.784505.262858.252760.98MIN: 5104.16 / MAX: 5331.99MIN: 4473.16 / MAX: 4529.26MIN: 2782.67 / MAX: 2921.88MIN: 2689.1 / MAX: 3085.251. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf9001800270036004500Min: 5223.45 / Avg: 5236.78 / Max: 5250.48Min: 4503.53 / Avg: 4505.26 / Max: 4507.27Min: 2850.88 / Avg: 2858.25 / Max: 2862.01Min: 2757.76 / Avg: 2760.98 / Max: 2764.491. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1326395265SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.27, N = 3SE +/- 0.10, N = 333.4031.3158.9958.87MIN: 28.52 / MAX: 43.37MIN: 28.75 / MAX: 35.92MIN: 58.28 / MAX: 63.37MIN: 58.29 / MAX: 72.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1224364860Min: 33.12 / Avg: 33.4 / Max: 33.67Min: 31.23 / Avg: 31.31 / Max: 31.37Min: 58.68 / Avg: 58.99 / Max: 59.54Min: 58.76 / Avg: 58.87 / Max: 59.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of StateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.35150.7031.05451.4061.7575SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.004, N = 30.8350.8331.5621.555
OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of StateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 0.84 / Avg: 0.84 / Max: 0.84Min: 0.83 / Avg: 0.83 / Max: 0.83Min: 1.56 / Avg: 1.56 / Max: 1.56Min: 1.55 / Avg: 1.56 / Max: 1.56

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. 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 2022-05-18Model: Inception ResNet V2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20K40K60K80K100KSE +/- 1184.33, N = 12SE +/- 75.44, N = 3SE +/- 217.28, N = 3SE +/- 265.78, N = 3102043.0101417.059615.654465.6
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20K40K60K80K100KMin: 89744 / Avg: 102042.5 / Max: 106449Min: 101335 / Avg: 101417.33 / Max: 101568Min: 59359.3 / Avg: 59615.63 / Max: 60047.7Min: 53937.3 / Avg: 54465.57 / Max: 54780.8

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression SpeedRyzen 7 6850U - Max PerfApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850U8001600240032004000SE +/- 1.65, N = 3SE +/- 12.25, N = 3SE +/- 25.90, N = 3SE +/- 17.49, N = 32015.53620.63729.81995.61. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression SpeedRyzen 7 6850U - Max PerfApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850U6001200180024003000Min: 2012.8 / Avg: 2015.53 / Max: 2018.5Min: 3597.2 / Avg: 3620.6 / Max: 3638.6Min: 3679 / Avg: 3729.83 / Max: 3763.9Min: 1964 / Avg: 1995.57 / Max: 2024.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. 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 2022-05-18Model: Mobilenet FloatApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf12002400360048006000SE +/- 49.79, N = 7SE +/- 45.90, N = 3SE +/- 6.91, N = 3SE +/- 7.11, N = 35693.845655.293324.093077.33
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000Min: 5452.81 / Avg: 5693.84 / Max: 5882.54Min: 5586.41 / Avg: 5655.29 / Max: 5742.29Min: 3310.51 / Avg: 3324.09 / Max: 3333.12Min: 3063.2 / Avg: 3077.33 / Max: 3085.87

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 23Jun2022Model: Rhodopsin ProteinApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.26632.53263.79895.06526.3315SE +/- 0.039, N = 3SE +/- 0.028, N = 7SE +/- 0.015, N = 3SE +/- 0.012, N = 33.3063.0455.3365.628-lm-lm1. (CXX) g++ options: -O3 -ldl
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 3.27 / Avg: 3.31 / Max: 3.38Min: 3 / Avg: 3.05 / Max: 3.21Min: 5.31 / Avg: 5.34 / Max: 5.36Min: 5.61 / Avg: 5.63 / Max: 5.651. (CXX) g++ options: -O3 -ldl

GNU Octave Benchmark

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

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 7.2.0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810SE +/- 0.032, N = 5SE +/- 0.041, N = 5SE +/- 0.039, N = 5SE +/- 0.047, N = 54.0313.9157.2147.206
OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 7.2.0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 3.97 / Avg: 4.03 / Max: 4.15Min: 3.87 / Avg: 3.91 / Max: 4.08Min: 7.16 / Avg: 7.21 / Max: 7.37Min: 7.15 / Avg: 7.21 / Max: 7.39

GNU Radio

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

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 4.02, N = 3SE +/- 6.78, N = 3SE +/- 0.89, N = 3SE +/- 1.65, N = 3536.9559.2969.5973.81. 3.10.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000Min: 529.5 / Avg: 536.93 / Max: 543.3Min: 548.1 / Avg: 559.2 / Max: 571.5Min: 968.2 / Avg: 969.5 / Max: 971.2Min: 971.8 / Avg: 973.83 / Max: 977.11. 3.10.2.0

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.8731.7462.6193.4924.365SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 32.242.243.883.75MIN: 2.22 / MAX: 2.41MIN: 2.21 / MAX: 3.06MIN: 3.57 / MAX: 4.33MIN: 3.47 / MAX: 4.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 2.24 / Avg: 2.24 / Max: 2.24Min: 2.22 / Avg: 2.24 / Max: 2.25Min: 3.86 / Avg: 3.88 / Max: 3.91Min: 3.72 / Avg: 3.75 / Max: 3.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Google Draco

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

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf13002600390052006500SE +/- 5.70, N = 3SE +/- 4.10, N = 3SE +/- 7.21, N = 3SE +/- 19.74, N = 334613468596559191. (CXX) g++ options: -O3
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000Min: 3454 / Avg: 3460.67 / Max: 3472Min: 3460 / Avg: 3467.67 / Max: 3474Min: 5951 / Avg: 5965 / Max: 5975Min: 5896 / Avg: 5918.67 / Max: 59581. (CXX) g++ options: -O3

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Akka Unbalanced Cobwebbed TreeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3K6K9K12K15KSE +/- 66.25, N = 8SE +/- 23.85, N = 3SE +/- 46.94, N = 3SE +/- 55.52, N = 37664.27486.912898.112534.6MIN: 5243.9 / MAX: 7829.69MIN: 5372.47 / MAX: 7523.42MIN: 10101.42 / MAX: 12974.59MIN: 9881.58 / MAX: 12631.42
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Akka Unbalanced Cobwebbed TreeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2K4K6K8K10KMin: 7253.74 / Avg: 7664.21 / Max: 7829.69Min: 7442.07 / Avg: 7486.92 / Max: 7523.42Min: 12812.73 / Avg: 12898.13 / Max: 12974.59Min: 12439.12 / Avg: 12534.59 / Max: 12631.42

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.180, N = 4SE +/- 0.146, N = 15SE +/- 0.130, N = 3SE +/- 0.020, N = 315.89016.38210.1949.5281. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 15.69 / Avg: 15.89 / Max: 16.43Min: 15.39 / Avg: 16.38 / Max: 17.15Min: 10.03 / Avg: 10.19 / Max: 10.45Min: 9.49 / Avg: 9.53 / Max: 9.551. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.32, N = 3SE +/- 0.41, N = 3SE +/- 0.52, N = 3SE +/- 0.38, N = 314.4914.1924.2723.20MIN: 13.06 / MAX: 22.07MIN: 13.03 / MAX: 18MIN: 22.65 / MAX: 27.35MIN: 21.9 / MAX: 27.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 13.85 / Avg: 14.49 / Max: 14.9Min: 13.37 / Avg: 14.19 / Max: 14.62Min: 23.24 / Avg: 24.27 / Max: 24.82Min: 22.44 / Avg: 23.2 / Max: 23.611. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.16, N = 3SE +/- 0.03, N = 3SE +/- 0.25, N = 3SE +/- 0.23, N = 315.4514.6624.9324.20MIN: 13.48 / MAX: 25.47MIN: 13.4 / MAX: 18.04MIN: 24.08 / MAX: 30.01MIN: 23.32 / MAX: 28.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 15.18 / Avg: 15.45 / Max: 15.73Min: 14.62 / Avg: 14.66 / Max: 14.71Min: 24.65 / Avg: 24.93 / Max: 25.42Min: 23.75 / Avg: 24.2 / Max: 24.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150SE +/- 0.43, N = 3SE +/- 0.20, N = 3SE +/- 0.14, N = 3SE +/- 0.42, N = 3151.67150.9496.8990.731. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150Min: 151.12 / Avg: 151.67 / Max: 152.52Min: 150.53 / Avg: 150.94 / Max: 151.17Min: 96.62 / Avg: 96.89 / Max: 97.08Min: 90.04 / Avg: 90.73 / Max: 91.491. (CXX) g++ options: -O3 -fPIC -lm

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 95, Compression Effort 7Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 8.25, N = 3SE +/- 1.52, N = 3SE +/- 0.46, N = 3SE +/- 0.86, N = 3852.46900.77586.74542.61-msse4.2-msse4.21. (CXX) g++ options: -fno-rtti -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 95, Compression Effort 7Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf160320480640800Min: 841.09 / Avg: 852.46 / Max: 868.51Min: 897.73 / Avg: 900.77 / Max: 902.43Min: 585.82 / Avg: 586.74 / Max: 587.27Min: 541.38 / Avg: 542.61 / Max: 544.271. (CXX) g++ options: -fno-rtti -O3

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100SE +/- 1.20, N = 3SE +/- 0.73, N = 15SE +/- 0.17, N = 3SE +/- 0.13, N = 388.3393.6361.6956.96-lSDL-march=native-march=native1. (CXX) g++ options: -pipe -O3 -ffast-math -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100Min: 85.96 / Avg: 88.33 / Max: 89.79Min: 86.65 / Avg: 93.62 / Max: 98.12Min: 61.34 / Avg: 61.69 / Max: 61.9Min: 56.77 / Avg: 56.96 / Max: 57.211. (CXX) g++ options: -pipe -O3 -ffast-math -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70140210280350SE +/- 4.09, N = 3SE +/- 0.54, N = 3SE +/- 0.29, N = 3SE +/- 0.99, N = 3327.57316.32215.30201.881. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60120180240300Min: 323.08 / Avg: 327.57 / Max: 335.74Min: 315.25 / Avg: 316.32 / Max: 316.99Min: 214.74 / Avg: 215.3 / Max: 215.71Min: 200.09 / Avg: 201.88 / Max: 203.481. (CXX) g++ options: -O3 -fPIC -lm

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.75151.5032.25453.0063.7575SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 32.072.073.343.32MIN: 2.03 / MAX: 2.19MIN: 2.03 / MAX: 2.16MIN: 3.1 / MAX: 3.72MIN: 3.01 / MAX: 4.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 2.04 / Avg: 2.07 / Max: 2.09Min: 2.04 / Avg: 2.07 / Max: 2.09Min: 3.32 / Avg: 3.34 / Max: 3.37Min: 3.28 / Avg: 3.32 / Max: 3.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e13Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf120240360480600SE +/- 4.36, N = 3SE +/- 3.51, N = 3SE +/- 2.22, N = 3SE +/- 0.24, N = 3549.67561.55382.14349.741. (CXX) g++ options: -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e13Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf100200300400500Min: 541.29 / Avg: 549.67 / Max: 555.93Min: 554.77 / Avg: 561.55 / Max: 566.48Min: 377.71 / Avg: 382.14 / Max: 384.63Min: 349.37 / Avg: 349.74 / Max: 350.181. (CXX) g++ options: -O3

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf9001800270036004500SE +/- 45.28, N = 20SE +/- 27.90, N = 4SE +/- 32.32, N = 4SE +/- 22.05, N = 43878249239713645
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf7001400210028003500Min: 3416 / Avg: 3878.2 / Max: 4199Min: 2431 / Avg: 2491.75 / Max: 2559Min: 3918 / Avg: 3970.5 / Max: 4059Min: 3612 / Avg: 3645.25 / Max: 3709

GNU Radio

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

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert TransformApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf140280420560700SE +/- 3.43, N = 3SE +/- 2.13, N = 3SE +/- 1.57, N = 3SE +/- 3.71, N = 3413.9428.4655.4658.41. 3.10.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert TransformApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf120240360480600Min: 407.4 / Avg: 413.87 / Max: 419.1Min: 426.2 / Avg: 428.43 / Max: 432.7Min: 653.8 / Avg: 655.37 / Max: 658.5Min: 651.3 / Avg: 658.43 / Max: 663.81. 3.10.2.0

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 75, Compression Effort 7Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90180270360450SE +/- 6.10, N = 9SE +/- 7.44, N = 9SE +/- 1.08, N = 3SE +/- 0.67, N = 3384.28408.72278.59257.24-msse4.2-msse4.21. (CXX) g++ options: -fno-rtti -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 75, Compression Effort 7Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70140210280350Min: 341.52 / Avg: 384.28 / Max: 398.98Min: 360.86 / Avg: 408.72 / Max: 426.1Min: 276.52 / Avg: 278.59 / Max: 280.18Min: 256.34 / Avg: 257.24 / Max: 258.551. (CXX) g++ options: -fno-rtti -O3

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Group By Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.05982.11963.17944.23925.299SE +/- 0.02, N = 3SE +/- 0.03, N = 9SE +/- 0.07, N = 3SE +/- 0.07, N = 33.052.984.714.57
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Group By Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 3.01 / Avg: 3.05 / Max: 3.08Min: 2.84 / Avg: 2.98 / Max: 3.1Min: 4.58 / Avg: 4.71 / Max: 4.81Min: 4.49 / Avg: 4.57 / Max: 4.71

Google Draco

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

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2K4K6K8K10KSE +/- 5.49, N = 3SE +/- 1.15, N = 3SE +/- 2.89, N = 3SE +/- 9.67, N = 350795073800679581. (CXX) g++ options: -O3
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf14002800420056007000Min: 5069 / Avg: 5078.67 / Max: 5088Min: 5071 / Avg: 5073 / Max: 5075Min: 8001 / Avg: 8006 / Max: 8011Min: 7939 / Avg: 7958.33 / Max: 79681. (CXX) g++ options: -O3

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 314.6012.7119.7818.98MIN: 10.01 / MAX: 24.55MIN: 10.24 / MAX: 17.61MIN: 19.21 / MAX: 20.98MIN: 18.6 / MAX: 19.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 14.57 / Avg: 14.6 / Max: 14.62Min: 12.59 / Avg: 12.71 / Max: 12.85Min: 19.61 / Avg: 19.78 / Max: 20.07Min: 18.9 / Avg: 18.98 / Max: 19.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Lossless CompressionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf400800120016002000SE +/- 3.42, N = 3SE +/- 10.15, N = 3SE +/- 1.26, N = 3SE +/- 1.08, N = 31864.981966.801386.211284.09-msse4.2-msse4.21. (CXX) g++ options: -fno-rtti -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Lossless CompressionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500Min: 1858.18 / Avg: 1864.98 / Max: 1869.05Min: 1948.72 / Avg: 1966.8 / Max: 1983.82Min: 1384.78 / Avg: 1386.21 / Max: 1388.72Min: 1282.08 / Avg: 1284.09 / Max: 1285.791. (CXX) g++ options: -fno-rtti -O3

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Group By Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.33432.66864.00295.33726.6715SE +/- 0.00, N = 3SE +/- 0.08, N = 4SE +/- 0.10, N = 3SE +/- 0.01, N = 34.043.895.935.71
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Group By Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 4.03 / Avg: 4.04 / Max: 4.04Min: 3.74 / Avg: 3.89 / Max: 4.11Min: 5.75 / Avg: 5.93 / Max: 6.08Min: 5.7 / Avg: 5.71 / Max: 5.72

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 310.2410.7514.4615.08-march=armv8-a-march=armv8-a-m64-m641. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 10.21 / Avg: 10.24 / Max: 10.27Min: 10.71 / Avg: 10.75 / Max: 10.78Min: 14.37 / Avg: 14.46 / Max: 14.57Min: 15.04 / Avg: 15.08 / Max: 15.111. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70140210280350SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.21, N = 3321.90321.84219.05219.04MIN: 321.56 / MAX: 322.22MIN: 321.54 / MAX: 322.19MIN: 217.97 / MAX: 220.33MIN: 217.84 / MAX: 220.691. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60120180240300Min: 321.8 / Avg: 321.9 / Max: 322.01Min: 321.77 / Avg: 321.84 / Max: 321.95Min: 218.75 / Avg: 219.05 / Max: 219.31Min: 218.65 / Avg: 219.04 / Max: 219.371. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.62331.24661.86992.49323.1165SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 31.921.892.772.66MIN: 1.87 / MAX: 3.83MIN: 1.87 / MAX: 1.93MIN: 2.45 / MAX: 4.77MIN: 2.35 / MAX: 6.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 1.89 / Avg: 1.92 / Max: 1.95Min: 1.88 / Avg: 1.89 / Max: 1.91Min: 2.72 / Avg: 2.77 / Max: 2.8Min: 2.63 / Avg: 2.66 / Max: 2.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Node.js V8 Web Tooling Benchmark

Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 318.9720.6414.0914.50
OpenBenchmarking.orgruns/s, More Is BetterNode.js V8 Web Tooling BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 18.86 / Avg: 18.97 / Max: 19.05Min: 20.43 / Avg: 20.64 / Max: 20.85Min: 13.96 / Avg: 14.09 / Max: 14.2Min: 14.43 / Avg: 14.5 / Max: 14.55

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 SecondApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60K120K180K240K300KSE +/- 7.69, N = 3SE +/- 199.86, N = 3SE +/- 1212.86, N = 3SE +/- 1005.05, N = 3204530.93204409.38277973.30298579.201. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50K100K150K200K250KMin: 204516.4 / Avg: 204530.93 / Max: 204542.55Min: 204012.24 / Avg: 204409.38 / Max: 204647.2Min: 276712.88 / Avg: 277973.3 / Max: 280398.4Min: 297360.92 / Avg: 298579.2 / Max: 300572.971. (CC) gcc options: -O2 -lrt" -lrt

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: In-Memory Database ShootoutApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000SE +/- 17.86, N = 3SE +/- 14.38, N = 3SE +/- 15.85, N = 3SE +/- 37.14, N = 33439.02746.53935.13490.0MIN: 3163.36 / MAX: 3920.23MIN: 2523.84 / MAX: 3140.59MIN: 3579.24 / MAX: 4254.29MIN: 3174.73 / MAX: 3690.56
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: In-Memory Database ShootoutApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf7001400210028003500Min: 3406.86 / Avg: 3439.02 / Max: 3468.55Min: 2719.29 / Avg: 2746.48 / Max: 2768.19Min: 3903.42 / Avg: 3935.11 / Max: 3951.13Min: 3437.21 / Avg: 3489.97 / Max: 3561.63

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-sha512Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf800K1600K2400K3200K4000KSE +/- 2039.33, N = 3SE +/- 0.00, N = 3SE +/- 6196.08, N = 3SE +/- 20710.08, N = 33582836358487525307852509894
OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-sha512Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf600K1200K1800K2400K3000KMin: 3578757 / Avg: 3582835.67 / Max: 3584875Min: 3584875 / Avg: 3584875 / Max: 3584875Min: 2520615 / Avg: 2530784.67 / Max: 2542002Min: 2487724 / Avg: 2509894 / Max: 2551279

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.15882.31763.47644.63525.794SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 33.673.635.155.03MIN: 3.6 / MAX: 14.01MIN: 3.55 / MAX: 6.64MIN: 4.83 / MAX: 8.01MIN: 4.66 / MAX: 7.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 3.64 / Avg: 3.67 / Max: 3.72Min: 3.59 / Avg: 3.63 / Max: 3.67Min: 5.12 / Avg: 5.15 / Max: 5.2Min: 4.96 / Avg: 5.03 / Max: 5.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.09, N = 15SE +/- 0.07, N = 15SE +/- 0.02, N = 3SE +/- 0.01, N = 310.407.357.997.95
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 9.9 / Avg: 10.39 / Max: 10.9Min: 6.9 / Avg: 7.35 / Max: 7.94Min: 7.95 / Avg: 7.99 / Max: 8.02Min: 7.93 / Avg: 7.95 / Max: 7.96

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.04632.09263.13894.18525.2315SE +/- 0.04, N = 3SE +/- 0.04, N = 9SE +/- 0.05, N = 3SE +/- 0.03, N = 33.313.344.654.41
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 3.24 / Avg: 3.31 / Max: 3.37Min: 3.1 / Avg: 3.34 / Max: 3.48Min: 4.6 / Avg: 4.65 / Max: 4.74Min: 4.35 / Avg: 4.41 / Max: 4.44

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 3.2Preset: MediumApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.28452.5693.85355.1386.4225SE +/- 0.0253, N = 3SE +/- 0.0205, N = 3SE +/- 0.0239, N = 3SE +/- 0.0351, N = 35.54645.70874.19824.10331. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: MediumApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 5.51 / Avg: 5.55 / Max: 5.59Min: 5.68 / Avg: 5.71 / Max: 5.75Min: 4.15 / Avg: 4.2 / Max: 4.24Min: 4.04 / Avg: 4.1 / Max: 4.151. (CXX) g++ options: -O3 -flto -pthread

Darktable

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

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.0.0Test: Boat - Acceleration: CPU-onlyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810SE +/- 0.018, N = 3SE +/- 0.065, N = 8SE +/- 0.004, N = 3SE +/- 0.009, N = 37.3107.8515.8885.656
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.0.0Test: Boat - Acceleration: CPU-onlyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 7.28 / Avg: 7.31 / Max: 7.35Min: 7.46 / Avg: 7.85 / Max: 8.05Min: 5.88 / Avg: 5.89 / Max: 5.9Min: 5.65 / Avg: 5.66 / Max: 5.67

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 1080pApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf816243240SE +/- 0.16, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 325.2525.9233.8034.98-march=armv8-a-march=armv8-a-m64-m641. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 1080pApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf714212835Min: 25.07 / Avg: 25.25 / Max: 25.56Min: 25.63 / Avg: 25.92 / Max: 26.37Min: 33.74 / Avg: 33.8 / Max: 33.88Min: 34.78 / Avg: 34.98 / Max: 35.221. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150SE +/- 0.39, N = 3SE +/- 0.97, N = 4SE +/- 1.33, N = 3SE +/- 0.12, N = 384.5385.03116.82115.961. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE
OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100Min: 83.87 / Avg: 84.53 / Max: 85.2Min: 83.82 / Avg: 85.03 / Max: 87.92Min: 115.23 / Avg: 116.82 / Max: 119.45Min: 115.72 / Avg: 115.96 / Max: 116.11. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.68631.37262.05892.74523.4315SE +/- 0.02, N = 2SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 32.212.213.052.98MIN: 2.18 / MAX: 2.33MIN: 2.17 / MAX: 4.48MIN: 2.83 / MAX: 3.41MIN: 2.69 / MAX: 3.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 2.19 / Avg: 2.21 / Max: 2.23Min: 2.19 / Avg: 2.21 / Max: 2.24Min: 3.02 / Avg: 3.05 / Max: 3.1Min: 2.97 / Avg: 2.98 / Max: 2.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000SE +/- 18.65, N = 4SE +/- 22.10, N = 4SE +/- 28.92, N = 20SE +/- 25.03, N = 42915267736913540
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf6001200180024003000Min: 2886 / Avg: 2915.25 / Max: 2969Min: 2634 / Avg: 2677 / Max: 2730Min: 3530 / Avg: 3691.4 / Max: 3900Min: 3468 / Avg: 3539.5 / Max: 3577

Inkscape

Inkscape is an open-source vector graphics editor. This test profile times how long it takes to complete various operations by Inkscape. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterInkscapeOperation: SVG Files To PNGApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.19, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 322.2519.5926.6726.561. Inkscape 1.2.1 (9c6d41e410, 2022-07-14)
OpenBenchmarking.orgSeconds, Fewer Is BetterInkscapeOperation: SVG Files To PNGApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 22.03 / Avg: 22.25 / Max: 22.63Min: 19.53 / Avg: 19.59 / Max: 19.72Min: 26.6 / Avg: 26.67 / Max: 26.75Min: 26.43 / Avg: 26.56 / Max: 26.681. Inkscape 1.2.1 (9c6d41e410, 2022-07-14)

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 2020-06-28Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 321.5021.4815.9615.861. (CC) gcc options: -O2 -pedantic -fvisibility=hidden -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 21.5 / Avg: 21.5 / Max: 21.52Min: 21.47 / Avg: 21.48 / Max: 21.48Min: 15.85 / Avg: 15.96 / Max: 16.05Min: 15.58 / Avg: 15.86 / Max: 16.061. (CC) gcc options: -O2 -pedantic -fvisibility=hidden -lm

Darktable

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

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.0.0Test: Server Rack - Acceleration: CPU-onlyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.14850.2970.44550.5940.7425SE +/- 0.003, N = 3SE +/- 0.007, N = 4SE +/- 0.001, N = 3SE +/- 0.001, N = 30.6600.6390.5160.489
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.0.0Test: Server Rack - Acceleration: CPU-onlyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 0.65 / Avg: 0.66 / Max: 0.67Min: 0.63 / Avg: 0.64 / Max: 0.66Min: 0.52 / Avg: 0.52 / Max: 0.52Min: 0.49 / Avg: 0.49 / Max: 0.49

XZ Compression

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

OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1020304050SE +/- 0.22, N = 3SE +/- 0.25, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 345.3445.5535.1534.571. (CC) gcc options: -fvisibility=hidden -O2
OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf918273645Min: 45.09 / Avg: 45.34 / Max: 45.77Min: 45.1 / Avg: 45.55 / Max: 45.96Min: 35.11 / Avg: 35.15 / Max: 35.24Min: 34.39 / Avg: 34.57 / Max: 34.691. (CC) gcc options: -fvisibility=hidden -O2

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 35.305.316.986.80MIN: 5.18 / MAX: 5.65MIN: 5.17 / MAX: 6.73MIN: 6.26 / MAX: 7.97MIN: 6.19 / MAX: 7.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 5.2 / Avg: 5.3 / Max: 5.4Min: 5.18 / Avg: 5.31 / Max: 5.42Min: 6.89 / Avg: 6.98 / Max: 7.11Min: 6.78 / Avg: 6.8 / Max: 6.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf7001400210028003500SE +/- 44.02, N = 6SE +/- 12.77, N = 3SE +/- 24.89, N = 3SE +/- 30.36, N = 92429.02547.13108.73183.1-maes-maes1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf6001200180024003000Min: 2300.4 / Avg: 2429.02 / Max: 2559.8Min: 2521.6 / Avg: 2547.07 / Max: 2561.5Min: 3065.2 / Avg: 3108.7 / Max: 3151.4Min: 2994.1 / Avg: 3183.07 / Max: 3268.51. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf400800120016002000SE +/- 11.61, N = 3SE +/- 13.71, N = 7SE +/- 9.40, N = 3SE +/- 10.19, N = 31533.81473.11807.61930.0-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500Min: 1513.4 / Avg: 1533.8 / Max: 1553.6Min: 1448.4 / Avg: 1473.11 / Max: 1548.4Min: 1797.8 / Avg: 1807.6 / Max: 1826.4Min: 1919.2 / Avg: 1930.03 / Max: 1950.41. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.2332.4663.6994.9326.165SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.194.195.425.481. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 4.19 / Avg: 4.19 / Max: 4.19Min: 4.19 / Avg: 4.19 / Max: 4.19Min: 5.4 / Avg: 5.42 / Max: 5.43Min: 5.46 / Avg: 5.48 / Max: 5.51. (CXX) g++ options: -O3

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Random ForestApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf140280420560700SE +/- 3.46, N = 3SE +/- 4.50, N = 3SE +/- 0.89, N = 3SE +/- 2.71, N = 3652.9511.6668.6607.6MIN: 510.8 / MAX: 878.7MIN: 425.56 / MAX: 662.53MIN: 585.53 / MAX: 858.98MIN: 541.35 / MAX: 796.34
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Random ForestApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf120240360480600Min: 646.82 / Avg: 652.89 / Max: 658.79Min: 502.58 / Avg: 511.58 / Max: 516.4Min: 667.16 / Avg: 668.58 / Max: 670.23Min: 602.33 / Avg: 607.62 / Max: 611.27

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.16, N = 15SE +/- 0.16, N = 15SE +/- 0.18, N = 3SE +/- 0.16, N = 315.8116.1313.2812.411. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 13.92 / Avg: 15.81 / Max: 16.35Min: 14.31 / Avg: 16.13 / Max: 16.96Min: 12.92 / Avg: 13.28 / Max: 13.5Min: 12.08 / Avg: 12.4 / Max: 12.611. (CXX) g++ options: -O3 -fPIC -lm

GIMP

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

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: resizeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.04, N = 3SE +/- 0.08, N = 10SE +/- 0.14, N = 4SE +/- 0.14, N = 410.8810.0313.0012.65
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: resizeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 10.84 / Avg: 10.88 / Max: 10.96Min: 9.9 / Avg: 10.03 / Max: 10.7Min: 12.57 / Avg: 13 / Max: 13.15Min: 12.24 / Avg: 12.65 / Max: 12.84

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000SE +/- 19.67, N = 4SE +/- 24.73, N = 4SE +/- 55.90, N = 4SE +/- 30.78, N = 33760375148234552
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000Min: 3714 / Avg: 3759.75 / Max: 3808Min: 3712 / Avg: 3751.25 / Max: 3819Min: 4693 / Avg: 4822.75 / Max: 4933Min: 4496 / Avg: 4552.33 / Max: 4602

Darktable

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

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.0.0Test: Server Room - Acceleration: CPU-onlyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.98441.96882.95323.93764.922SE +/- 0.009, N = 3SE +/- 0.035, N = 3SE +/- 0.010, N = 3SE +/- 0.010, N = 33.4053.4494.3754.313
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.0.0Test: Server Room - Acceleration: CPU-onlyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 3.39 / Avg: 3.4 / Max: 3.42Min: 3.39 / Avg: 3.45 / Max: 3.51Min: 4.36 / Avg: 4.38 / Max: 4.39Min: 4.3 / Avg: 4.31 / Max: 4.33

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.26, N = 312.6910.1613.0512.71MIN: 8.29 / MAX: 25.33MIN: 8.42 / MAX: 12.99MIN: 12.5 / MAX: 13.56MIN: 11.87 / MAX: 14.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 12.64 / Avg: 12.69 / Max: 12.72Min: 10.09 / Avg: 10.16 / Max: 10.29Min: 12.9 / Avg: 13.05 / Max: 13.15Min: 12.34 / Avg: 12.71 / Max: 13.211. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf140280420560700SE +/- 0.84, N = 3SE +/- 1.53, N = 3SE +/- 1.15, N = 3SE +/- 0.46, N = 3652.69668.56522.01528.22
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf120240360480600Min: 651.44 / Avg: 652.69 / Max: 654.28Min: 665.59 / Avg: 668.56 / Max: 670.68Min: 520.36 / Avg: 522.01 / Max: 524.22Min: 527.31 / Avg: 528.22 / Max: 528.71

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf12002400360048006000SE +/- 2.60, N = 3SE +/- 5.37, N = 3SE +/- 11.99, N = 3SE +/- 4.79, N = 35479.75479.24297.04278.61. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000Min: 5474.5 / Avg: 5479.67 / Max: 5482.7Min: 5469.1 / Avg: 5479.2 / Max: 5487.4Min: 4283.7 / Avg: 4296.97 / Max: 4320.9Min: 4269.8 / Avg: 4278.6 / Max: 4286.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - SHA-512 Benchmark TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.29832.59663.89495.19326.4915SE +/- 0.02, N = 3SE +/- 0.06, N = 4SE +/- 0.04, N = 3SE +/- 0.01, N = 34.524.605.775.52
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - SHA-512 Benchmark TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 4.48 / Avg: 4.52 / Max: 4.53Min: 4.47 / Avg: 4.6 / Max: 4.75Min: 5.7 / Avg: 5.77 / Max: 5.82Min: 5.51 / Avg: 5.52 / Max: 5.53

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedApple MacBook Air M2Ryzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000SE +/- 2.92, N = 3SE +/- 19.53, N = 3SE +/- 29.78, N = 34531.13567.83591.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedApple MacBook Air M2Ryzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000Min: 4525.6 / Avg: 4531.13 / Max: 4535.5Min: 3529.7 / Avg: 3567.77 / Max: 3594.4Min: 3550.9 / Avg: 3591.3 / Max: 3649.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf11002200330044005500SE +/- 9.42, N = 3SE +/- 2.78, N = 3SE +/- 8.23, N = 3SE +/- 2.88, N = 35241.25230.84155.14128.01. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf9001800270036004500Min: 5222.4 / Avg: 5241.23 / Max: 5250.9Min: 5226.5 / Avg: 5230.8 / Max: 5236Min: 4141 / Avg: 4155.1 / Max: 4169.5Min: 4124 / Avg: 4128.03 / Max: 4133.61. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.21052.4213.63154.8426.0525SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 34.254.255.345.381. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 4.25 / Avg: 4.25 / Max: 4.25Min: 4.25 / Avg: 4.25 / Max: 4.25Min: 5.33 / Avg: 5.34 / Max: 5.34Min: 5.32 / Avg: 5.38 / Max: 5.411. (CXX) g++ options: -O3

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000SE +/- 20.66, N = 3SE +/- 4.35, N = 3SE +/- 7.32, N = 3SE +/- 5.47, N = 34494.64507.63570.23563.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000Min: 4454.7 / Avg: 4494.57 / Max: 4523.9Min: 4499.3 / Avg: 4507.6 / Max: 4514Min: 3555.6 / Avg: 3570.2 / Max: 3578.4Min: 3557.4 / Avg: 3563.27 / Max: 3574.21. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark PageRankApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000SE +/- 25.39, N = 15SE +/- 21.27, N = 15SE +/- 31.71, N = 3SE +/- 43.38, N = 33004.73000.23789.03720.8MIN: 2466.19 / MAX: 3300.89MIN: 2418.08 / MAX: 3302.43MIN: 3316.64 / MAX: 4168.89MIN: 3392.72 / MAX: 3974.31
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark PageRankApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf7001400210028003500Min: 2803.24 / Avg: 3004.73 / Max: 3183.06Min: 2856.02 / Avg: 3000.22 / Max: 3163.09Min: 3731.05 / Avg: 3788.98 / Max: 3840.32Min: 3634.07 / Avg: 3720.77 / Max: 3766.77

GNU Radio

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

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 15.15, N = 3SE +/- 21.51, N = 3SE +/- 1.39, N = 3SE +/- 3.06, N = 3823.1856.51019.71028.81. 3.10.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000Min: 807.9 / Avg: 823.1 / Max: 853.4Min: 825.4 / Avg: 856.53 / Max: 897.8Min: 1017.2 / Avg: 1019.67 / Max: 1022Min: 1023.6 / Avg: 1028.83 / Max: 1034.21. 3.10.2.0

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500SE +/- 0.64, N = 3SE +/- 0.37, N = 3SE +/- 2.61, N = 3SE +/- 0.12, N = 31536.831536.091230.781234.331. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500Min: 1535.72 / Avg: 1536.83 / Max: 1537.94Min: 1535.72 / Avg: 1536.09 / Max: 1536.83Min: 1225.57 / Avg: 1230.78 / Max: 1233.74Min: 1234.1 / Avg: 1234.33 / Max: 1234.451. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf11002200330044005500SE +/- 4.78, N = 5SE +/- 7.82, N = 3SE +/- 12.14, N = 3SE +/- 28.52, N = 35005.45005.44060.04084.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf9001800270036004500Min: 4986.9 / Avg: 5005.42 / Max: 5013.5Min: 4989.8 / Avg: 5005.4 / Max: 5014.1Min: 4035.7 / Avg: 4059.97 / Max: 4072.6Min: 4047.1 / Avg: 4084.37 / Max: 4140.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf5001000150020002500SE +/- 1.84, N = 15SE +/- 3.72, N = 14SE +/- 9.84, N = 3SE +/- 9.84, N = 31733.471731.452130.142130.141. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf400800120016002000Min: 1717.78 / Avg: 1733.47 / Max: 1740.24Min: 1695.9 / Avg: 1731.45 / Max: 1740.24Min: 2113.14 / Avg: 2130.14 / Max: 2147.23Min: 2113.14 / Avg: 2130.14 / Max: 2147.231. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70140210280350SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.86, N = 3SE +/- 0.16, N = 3306.56275.76251.58249.58MIN: 301.82 / MAX: 307.24MIN: 275.09 / MAX: 276.47MIN: 247.87 / MAX: 255.72MIN: 248.13 / MAX: 251.641. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60120180240300Min: 306.51 / Avg: 306.56 / Max: 306.59Min: 275.71 / Avg: 275.76 / Max: 275.84Min: 250.45 / Avg: 251.58 / Max: 253.26Min: 249.26 / Avg: 249.58 / Max: 249.771. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: DefaultApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.0962.1923.2884.3845.48SE +/- 0.024, N = 3SE +/- 0.023, N = 3SE +/- 0.011, N = 3SE +/- 0.017, N = 34.8714.8604.1943.974-msse4.2-msse4.21. (CXX) g++ options: -fno-rtti -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: DefaultApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 4.83 / Avg: 4.87 / Max: 4.91Min: 4.83 / Avg: 4.86 / Max: 4.91Min: 4.18 / Avg: 4.19 / Max: 4.22Min: 3.95 / Avg: 3.97 / Max: 4.011. (CXX) g++ options: -fno-rtti -O3

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50100150200250SE +/- 0.54, N = 3SE +/- 0.39, N = 3SE +/- 0.80, N = 3SE +/- 3.15, N = 12216.92240.77199.08196.701. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf4080120160200Min: 215.98 / Avg: 216.92 / Max: 217.87Min: 240.39 / Avg: 240.77 / Max: 241.55Min: 197.63 / Avg: 199.08 / Max: 200.4Min: 162.87 / Avg: 196.7 / Max: 202.841. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

SecureMark

SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70K140K210K280K350KSE +/- 187.56, N = 3SE +/- 110.09, N = 3SE +/- 93.21, N = 3SE +/- 893.87, N = 32522902523303085563066461. (CC) gcc options: -pedantic -O3
OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50K100K150K200K250KMin: 251989.69 / Avg: 252290.19 / Max: 252634.88Min: 252199.42 / Avg: 252329.85 / Max: 252548.69Min: 308376.81 / Avg: 308556.04 / Max: 308690.06Min: 305082.63 / Avg: 306646.05 / Max: 308178.631. (CC) gcc options: -pedantic -O3

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf400800120016002000SE +/- 1.17, N = 3SE +/- 1.17, N = 3SE +/- 1.34, N = 3SE +/- 2.64, N = 31441.491439.551754.821751.451. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500Min: 1439.22 / Avg: 1441.49 / Max: 1443.12Min: 1437.28 / Avg: 1439.55 / Max: 1441.17Min: 1753.13 / Avg: 1754.82 / Max: 1757.47Min: 1748.81 / Avg: 1751.45 / Max: 1756.741. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 312.0211.8014.3413.63MIN: 8.15 / MAX: 25.34MIN: 8.17 / MAX: 16.71MIN: 13.75 / MAX: 15.27MIN: 13 / MAX: 14.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 11.78 / Avg: 12.02 / Max: 12.35Min: 11.61 / Avg: 11.8 / Max: 12.08Min: 14.19 / Avg: 14.34 / Max: 14.42Min: 13.44 / Avg: 13.63 / Max: 13.741. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 312.0610.8713.1912.98MIN: 9.09 / MAX: 20.86MIN: 9.1 / MAX: 13.69MIN: 12.89 / MAX: 13.68MIN: 12.59 / MAX: 15.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 11.96 / Avg: 12.06 / Max: 12.19Min: 10.86 / Avg: 10.87 / Max: 10.88Min: 13.17 / Avg: 13.19 / Max: 13.2Min: 12.93 / Avg: 12.98 / Max: 13.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: ALS Movie LensApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf16003200480064008000SE +/- 21.46, N = 3SE +/- 41.24, N = 3SE +/- 13.71, N = 3SE +/- 42.32, N = 37581.66292.37351.37000.3MIN: 7540.84 / MAX: 8294.24MIN: 6212.62 / MAX: 7155.96MIN: 7323.83 / MAX: 8250.43MIN: 6915.31 / MAX: 7837
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: ALS Movie LensApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf13002600390052006500Min: 7540.84 / Avg: 7581.57 / Max: 7613.64Min: 6212.62 / Avg: 6292.28 / Max: 6350.61Min: 7323.83 / Avg: 7351.26 / Max: 7365.18Min: 6917.15 / Avg: 7000.3 / Max: 7055.54

GIMP

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

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: auto-levelsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 311.6810.5212.6612.12
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: auto-levelsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 11.61 / Avg: 11.68 / Max: 11.75Min: 10.52 / Avg: 10.52 / Max: 10.53Min: 12.62 / Avg: 12.66 / Max: 12.69Min: 12.1 / Avg: 12.12 / Max: 12.14

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: rotateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.018, N = 3SE +/- 0.022, N = 3SE +/- 0.063, N = 3SE +/- 0.007, N = 310.8979.86611.86811.487
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: rotateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 10.86 / Avg: 10.9 / Max: 10.92Min: 9.83 / Avg: 9.87 / Max: 9.91Min: 11.8 / Avg: 11.87 / Max: 11.99Min: 11.47 / Avg: 11.49 / Max: 11.5

libjpeg-turbo tjbench

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

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression ThroughputApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60120180240300SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.24, N = 3222.62222.67267.26266.451. (CC) gcc options: -O3 -rdynamic
OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression ThroughputApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50100150200250Min: 222.58 / Avg: 222.62 / Max: 222.67Min: 222.6 / Avg: 222.67 / Max: 222.74Min: 267.17 / Avg: 267.26 / Max: 267.4Min: 266.14 / Avg: 266.45 / Max: 266.931. (CC) gcc options: -O3 -rdynamic

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Savina Reactors.IOApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf14002800420056007000SE +/- 62.21, N = 12SE +/- 62.11, N = 3SE +/- 26.72, N = 3SE +/- 50.44, N = 35433.85278.36304.95901.7MIN: 5084.52 / MAX: 9675.5MIN: 5210.31 / MAX: 8127.23MIN: 6256.81 / MAX: 8680.32MIN: 5842.96 / MAX: 8932.44
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Savina Reactors.IOApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf11002200330044005500Min: 5084.52 / Avg: 5433.8 / Max: 5764.83Min: 5210.31 / Avg: 5278.35 / Max: 5402.37Min: 6256.81 / Avg: 6304.93 / Max: 6349.13Min: 5842.96 / Avg: 5901.73 / Max: 6002.11

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.8191.6382.4573.2764.095SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.053.053.603.641. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 3.05 / Avg: 3.05 / Max: 3.05Min: 3.04 / Avg: 3.05 / Max: 3.05Min: 3.58 / Avg: 3.6 / Max: 3.62Min: 3.63 / Avg: 3.64 / Max: 3.651. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.2790.5580.8371.1161.395SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.041.041.231.241. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 1.04 / Avg: 1.04 / Max: 1.04Min: 1.04 / Avg: 1.04 / Max: 1.04Min: 1.23 / Avg: 1.23 / Max: 1.23Min: 1.24 / Avg: 1.24 / Max: 1.241. (CXX) g++ options: -O3

Google SynthMark

SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100Apple MacBook Air M2Ryzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 0.26, N = 3SE +/- 4.90, N = 3SE +/- 1.81, N = 3660.06785.94786.951. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100Apple MacBook Air M2Ryzen 7 6850URyzen 7 6850U - Max Perf140280420560700Min: 659.65 / Avg: 660.06 / Max: 660.55Min: 780.61 / Avg: 785.94 / Max: 795.73Min: 784.16 / Avg: 786.95 / Max: 790.341. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

Test: VoiceMark_100

Apple MacBook Air M2 - Max Perf: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.13, N = 11SE +/- 0.24, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 317.9417.8416.1115.061. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 16.84 / Avg: 17.94 / Max: 18.7Min: 17.36 / Avg: 17.84 / Max: 18.11Min: 15.76 / Avg: 16.11 / Max: 16.29Min: 14.88 / Avg: 15.06 / Max: 15.161. (CXX) g++ options: -O3 -fPIC -lm

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30K60K90K120K150KSE +/- 671.78, N = 3SE +/- 728.62, N = 7SE +/- 23.83, N = 3SE +/- 100.57, N = 3107565.6103778.3115075.2122833.4-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20K40K60K80K100KMin: 106373.2 / Avg: 107565.6 / Max: 108698Min: 102174.7 / Avg: 103778.29 / Max: 107604.1Min: 115029 / Avg: 115075.23 / Max: 115108.4Min: 122634.3 / Avg: 122833.43 / Max: 122957.61. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3105105124124
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100Min: 105 / Avg: 105 / Max: 105Min: 105 / Avg: 105 / Max: 105Min: 124 / Avg: 124 / Max: 124Min: 124 / Avg: 124.33 / Max: 125

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2000M4000M6000M8000M10000MSE +/- 64974857.43, N = 3SE +/- 99007623.30, N = 3SE +/- 12977196.86, N = 3SE +/- 6697473.83, N = 388226675008738847143952860658010278077680-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2000M4000M6000M8000M10000MMin: 8697243900 / Avg: 8822667500 / Max: 8914822240Min: 8582013690 / Avg: 8738847143.33 / Max: 8921953790Min: 9502732540 / Avg: 9528606580 / Max: 9543310930Min: 10268933150 / Avg: 10278077680 / Max: 102911264801. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.09132.18263.27394.36525.4565SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 34.184.184.804.851. (CXX) g++ options: -O3
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 4.18 / Avg: 4.18 / Max: 4.18Min: 4.18 / Avg: 4.18 / Max: 4.18Min: 4.78 / Avg: 4.8 / Max: 4.82Min: 4.8 / Avg: 4.85 / Max: 4.871. (CXX) g++ options: -O3

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810SE +/- 0.028, N = 3SE +/- 0.062, N = 5SE +/- 0.015, N = 3SE +/- 0.025, N = 35.5235.8496.3906.0881. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 5.49 / Avg: 5.52 / Max: 5.58Min: 5.62 / Avg: 5.85 / Max: 5.94Min: 6.36 / Avg: 6.39 / Max: 6.41Min: 6.05 / Avg: 6.09 / Max: 6.141. (CXX) g++ options: -O3 -fPIC -lm

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedApple MacBook Air M2 - Max PerfApple MacBook Air M2Ryzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 322.221.724.825.11. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedApple MacBook Air M2 - Max PerfApple MacBook Air M2Ryzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 22 / Avg: 22.23 / Max: 22.6Min: 21.5 / Avg: 21.73 / Max: 22Min: 24.7 / Avg: 24.8 / Max: 24.9Min: 25 / Avg: 25.13 / Max: 25.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

Build2

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50100150200250SE +/- 1.51, N = 12SE +/- 2.30, N = 12SE +/- 0.44, N = 3SE +/- 0.31, N = 3210.76213.48197.43185.34
OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf4080120160200Min: 195.24 / Avg: 210.76 / Max: 216.3Min: 194.41 / Avg: 213.48 / Max: 224.66Min: 196.56 / Avg: 197.43 / Max: 197.9Min: 184.96 / Avg: 185.34 / Max: 185.96

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1.25892.51783.77675.03566.2945SE +/- 0.011, N = 3SE +/- 0.027, N = 3SE +/- 0.006, N = 3SE +/- 0.035, N = 35.3904.8645.5955.536
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 5.37 / Avg: 5.39 / Max: 5.41Min: 4.83 / Avg: 4.86 / Max: 4.92Min: 5.58 / Avg: 5.6 / Max: 5.61Min: 5.47 / Avg: 5.54 / Max: 5.57

Java Gradle Build

This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactorApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150SE +/- 1.64, N = 12SE +/- 0.27, N = 3SE +/- 1.81, N = 12SE +/- 1.97, N = 12143.38137.84158.26152.19
OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactorApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150Min: 136.43 / Avg: 143.38 / Max: 157.08Min: 137.52 / Avg: 137.84 / Max: 138.37Min: 152.33 / Avg: 158.26 / Max: 176.04Min: 146.55 / Avg: 152.19 / Max: 171.52

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, LosslessApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 315.0015.0213.1013.121. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 14.99 / Avg: 15 / Max: 15Min: 15 / Avg: 15.02 / Max: 15.06Min: 13.09 / Avg: 13.1 / Max: 13.11Min: 13.06 / Avg: 13.12 / Max: 13.21. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

GIMP

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

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: unsharp-maskApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 314.9713.0714.4613.91
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.32Test: unsharp-maskApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 14.87 / Avg: 14.97 / Max: 15.17Min: 13.06 / Avg: 13.07 / Max: 13.08Min: 14.37 / Avg: 14.46 / Max: 14.52Min: 13.87 / Avg: 13.91 / Max: 14

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100SE +/- 0.95, N = 3SE +/- 0.87, N = 4SE +/- 0.15, N = 3SE +/- 0.20, N = 372.6074.3570.0365.351. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1428425670Min: 71.05 / Avg: 72.6 / Max: 74.34Min: 71.93 / Avg: 74.35 / Max: 75.68Min: 69.75 / Avg: 70.03 / Max: 70.25Min: 64.95 / Avg: 65.34 / Max: 65.581. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf50100150200250SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3223212239241
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: 2to3Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf4080120160200Min: 222 / Avg: 223 / Max: 224Min: 212 / Avg: 212.33 / Max: 213Min: 238 / Avg: 238.67 / Max: 239Min: 240 / Avg: 240.67 / Max: 241

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 311.211.212.612.7
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 11.2 / Avg: 11.2 / Max: 11.2Min: 11.2 / Avg: 11.2 / Max: 11.2Min: 12.6 / Avg: 12.63 / Max: 12.7Min: 12.7 / Avg: 12.7 / Max: 12.7

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark ALSApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf7001400210028003500SE +/- 30.77, N = 15SE +/- 36.47, N = 5SE +/- 6.70, N = 3SE +/- 3.35, N = 33340.83290.93136.22966.0MIN: 2901.87 / MAX: 3813.56MIN: 3034.39 / MAX: 3572.44MIN: 2971.75 / MAX: 3358.15MIN: 2760.82 / MAX: 3249.25
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark ALSApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf6001200180024003000Min: 3047.23 / Avg: 3340.77 / Max: 3461.28Min: 3166.45 / Avg: 3290.9 / Max: 3367.12Min: 3123.51 / Avg: 3136.18 / Max: 3146.31Min: 2959.54 / Avg: 2966.01 / Max: 2970.73

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Tile GlassApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 325.1523.4822.6722.35
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Tile GlassApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 25.07 / Avg: 25.15 / Max: 25.23Min: 23.37 / Avg: 23.48 / Max: 23.67Min: 22.63 / Avg: 22.67 / Max: 22.72Min: 22.33 / Avg: 22.35 / Max: 22.37

Unpacking Firefox

This simple test profile measures how long it takes to extract the .tar.xz source package of the Mozilla Firefox Web Browser. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking Firefox 84.0Extracting: firefox-84.0.source.tar.xzApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620SE +/- 0.11, N = 4SE +/- 0.08, N = 4SE +/- 0.13, N = 8SE +/- 0.03, N = 416.8716.2415.2515.03
OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking Firefox 84.0Extracting: firefox-84.0.source.tar.xzApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf48121620Min: 16.67 / Avg: 16.87 / Max: 17.19Min: 16.13 / Avg: 16.24 / Max: 16.47Min: 15.02 / Avg: 15.25 / Max: 16.13Min: 14.99 / Avg: 15.03 / Max: 15.12

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.46580.93161.39741.86322.329SE +/- 0.06, N = 3SE +/- 0.02, N = 9SE +/- 0.01, N = 3SE +/- 0.03, N = 31.921.992.071.85
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 1.84 / Avg: 1.92 / Max: 2.03Min: 1.94 / Avg: 1.99 / Max: 2.09Min: 2.04 / Avg: 2.07 / Max: 2.09Min: 1.79 / Avg: 1.85 / Max: 1.89

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf714212835SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.26, N = 3SE +/- 0.27, N = 326.226.728.629.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 26 / Avg: 26.23 / Max: 26.4Min: 26.4 / Avg: 26.7 / Max: 27.1Min: 28.2 / Avg: 28.63 / Max: 29.1Min: 28.8 / Avg: 29.33 / Max: 29.71. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000SE +/- 6.78, N = 3SE +/- 2.76, N = 3SE +/- 23.59, N = 3SE +/- 36.24, N = 34315.94317.44766.64743.6
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000Min: 4302.5 / Avg: 4315.93 / Max: 4324.3Min: 4311.9 / Avg: 4317.37 / Max: 4320.8Min: 4721.6 / Avg: 4766.6 / Max: 4801.4Min: 4676.7 / Avg: 4743.6 / Max: 4801.2

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000SE +/- 6.68, N = 3SE +/- 2.58, N = 3SE +/- 43.16, N = 3SE +/- 19.05, N = 34315.84316.74741.14712.0
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 256b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000Min: 4302.8 / Avg: 4315.8 / Max: 4325Min: 4311.5 / Avg: 4316.67 / Max: 4319.4Min: 4658.4 / Avg: 4741.1 / Max: 4803.9Min: 4674.4 / Avg: 4712 / Max: 4736.1

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-whirlpoolApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf200K400K600K800K1000KSE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 2502.89, N = 3SE +/- 5913.21, N = 3784862784862861857860980
OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-whirlpoolApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf150K300K450K600K750KMin: 784862 / Avg: 784862 / Max: 784862Min: 784862 / Avg: 784862 / Max: 784862Min: 858081 / Avg: 861857 / Max: 866591Min: 852500 / Avg: 860980 / Max: 872359

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 387.187.280.180.6
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100Min: 87 / Avg: 87.07 / Max: 87.1Min: 87.1 / Avg: 87.17 / Max: 87.2Min: 79.9 / Avg: 80.13 / Max: 80.4Min: 80.5 / Avg: 80.63 / Max: 80.8

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 4.18, N = 3SE +/- 1.15, N = 3840841773781
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf150300450600750Min: 838 / Avg: 839.67 / Max: 841Min: 840 / Avg: 841.33 / Max: 842Min: 765 / Avg: 773.33 / Max: 778Min: 779 / Avg: 781 / Max: 783

LuaRadio

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

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf90180270360450SE +/- 0.42, N = 9SE +/- 0.07, N = 3SE +/- 0.85, N = 3SE +/- 0.12, N = 3380.8383.4412.7413.5
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70140210280350Min: 378.8 / Avg: 380.83 / Max: 382.9Min: 383.3 / Avg: 383.37 / Max: 383.5Min: 411.1 / Avg: 412.7 / Max: 414Min: 413.3 / Avg: 413.5 / Max: 413.7

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Repartition Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.96981.93962.90943.87924.849SE +/- 0.05, N = 3SE +/- 0.10, N = 4SE +/- 0.05, N = 3SE +/- 0.07, N = 34.214.314.273.99
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Repartition Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 4.13 / Avg: 4.21 / Max: 4.29Min: 4.14 / Avg: 4.31 / Max: 4.58Min: 4.17 / Avg: 4.27 / Max: 4.34Min: 3.9 / Avg: 3.99 / Max: 4.13

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 3SE +/- 0.20, N = 374.073.978.379.7
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: chaosApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1530456075Min: 73.9 / Avg: 74 / Max: 74.1Min: 73.9 / Avg: 73.93 / Max: 74Min: 77.8 / Avg: 78.27 / Max: 78.6Min: 79.4 / Avg: 79.73 / Max: 80.1

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf816243240SE +/- 0.35, N = 3SE +/- 0.27, N = 3SE +/- 0.21, N = 3SE +/- 0.19, N = 333.8234.3535.1832.871. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf816243240Min: 33.24 / Avg: 33.82 / Max: 34.44Min: 33.91 / Avg: 34.35 / Max: 34.84Min: 34.77 / Avg: 35.18 / Max: 35.39Min: 32.49 / Avg: 32.87 / Max: 33.121. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf918273645SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.11, N = 337.9037.3539.6539.18
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf816243240Min: 37.64 / Avg: 37.9 / Max: 38.16Min: 37.13 / Avg: 37.35 / Max: 37.48Min: 39.33 / Avg: 39.65 / Max: 39.86Min: 38.95 / Avg: 39.18 / Max: 39.32

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: AntialiasApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf714212835SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.32, N = 330.5828.8129.2829.56
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: AntialiasApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf714212835Min: 30.53 / Avg: 30.58 / Max: 30.62Min: 28.7 / Avg: 28.81 / Max: 28.91Min: 29.24 / Avg: 29.28 / Max: 29.32Min: 28.92 / Avg: 29.56 / Max: 29.94

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ReflectApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 325.2924.2025.6325.62
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ReflectApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 25.17 / Avg: 25.29 / Max: 25.36Min: 24.11 / Avg: 24.2 / Max: 24.39Min: 25.49 / Avg: 25.63 / Max: 25.71Min: 25.58 / Avg: 25.62 / Max: 25.66

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf816243240SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 330.730.632.432.4
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf714212835Min: 30.7 / Avg: 30.73 / Max: 30.8Min: 30.5 / Avg: 30.63 / Max: 30.9Min: 32.3 / Avg: 32.4 / Max: 32.5Min: 32.3 / Avg: 32.37 / Max: 32.5

LuaRadio

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

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex PhaseApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 5.89, N = 9SE +/- 2.20, N = 3SE +/- 8.02, N = 3SE +/- 5.53, N = 3857.9876.9828.7829.1
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex PhaseApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf150300450600750Min: 835.5 / Avg: 857.88 / Max: 882.7Min: 873.2 / Avg: 876.87 / Max: 880.8Min: 812.7 / Avg: 828.7 / Max: 837.7Min: 819.2 / Avg: 829.13 / Max: 838.3

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 398.898.8104.0103.0
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100Min: 98.7 / Avg: 98.8 / Max: 98.9Min: 98.8 / Avg: 98.8 / Max: 98.8Min: 103 / Avg: 104 / Max: 105Min: 102 / Avg: 102.67 / Max: 103

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 317.817.918.718.6
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 17.8 / Avg: 17.83 / Max: 17.9Min: 17.8 / Avg: 17.87 / Max: 17.9Min: 18.7 / Avg: 18.73 / Max: 18.8Min: 18.6 / Avg: 18.63 / Max: 18.7

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 CompressionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810SE +/- 0.007, N = 3SE +/- 0.005, N = 3SE +/- 0.027, N = 3SE +/- 0.032, N = 36.1146.1135.8495.8241. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 6.1 / Avg: 6.11 / Max: 6.13Min: 6.11 / Avg: 6.11 / Max: 6.12Min: 5.82 / Avg: 5.85 / Max: 5.9Min: 5.78 / Avg: 5.82 / Max: 5.891. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810SE +/- 0.019, N = 3SE +/- 0.017, N = 3SE +/- 0.001, N = 3SE +/- 0.029, N = 36.0045.9906.2616.1081. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 0Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 5.97 / Avg: 6 / Max: 6.03Min: 5.97 / Avg: 5.99 / Max: 6.02Min: 6.26 / Avg: 6.26 / Max: 6.26Min: 6.08 / Avg: 6.11 / Max: 6.171. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500SE +/- 20.29, N = 15SE +/- 14.46, N = 14SE +/- 0.00, N = 3SE +/- 17.25, N = 31456.371517.861512.821479.601. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500Min: 1331.28 / Avg: 1456.37 / Max: 1548Min: 1344.73 / Avg: 1517.86 / Max: 1557.05Min: 1512.82 / Avg: 1512.82 / Max: 1512.82Min: 1454.95 / Avg: 1479.6 / Max: 1512.821. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Wavelet BlurApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1122334455SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 346.7044.8246.3246.02
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Wavelet BlurApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1020304050Min: 46.59 / Avg: 46.7 / Max: 46.83Min: 44.79 / Avg: 44.82 / Max: 44.89Min: 46.13 / Avg: 46.32 / Max: 46.42Min: 45.95 / Avg: 46.02 / Max: 46.15

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CartoonApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.19, N = 373.7872.7775.7675.64
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CartoonApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1530456075Min: 73.59 / Avg: 73.78 / Max: 74.12Min: 72.74 / Avg: 72.76 / Max: 72.82Min: 75.61 / Avg: 75.76 / Max: 75.91Min: 75.26 / Avg: 75.64 / Max: 75.85

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CropApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810SE +/- 0.039, N = 3SE +/- 0.078, N = 3SE +/- 0.045, N = 3SE +/- 0.032, N = 36.5206.3566.5806.541
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CropApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3691215Min: 6.47 / Avg: 6.52 / Max: 6.6Min: 6.21 / Avg: 6.36 / Max: 6.48Min: 6.53 / Avg: 6.58 / Max: 6.67Min: 6.51 / Avg: 6.54 / Max: 6.61

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf20406080100SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.25, N = 3SE +/- 0.15, N = 376.276.278.678.1
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1530456075Min: 76.2 / Avg: 76.23 / Max: 76.3Min: 76.2 / Avg: 76.2 / Max: 76.2Min: 78.3 / Avg: 78.6 / Max: 79.1Min: 77.8 / Avg: 78.07 / Max: 78.3

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf4080120160200SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3165164169168
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150Min: 165 / Avg: 165 / Max: 165Min: 164 / Avg: 164.33 / Max: 165Min: 169 / Avg: 169 / Max: 169Min: 167 / Avg: 168 / Max: 169

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf70140210280350SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3305304312313
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60120180240300Min: 304 / Avg: 304.67 / Max: 306Min: 304 / Avg: 304 / Max: 304Min: 311 / Avg: 312 / Max: 313Min: 312 / Avg: 313 / Max: 314

Cryptsetup

This is a test profile for running the cryptsetup benchmark to report on the system's cryptography performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf9001800270036004500SE +/- 5.63, N = 3SE +/- 0.95, N = 3SE +/- 26.47, N = 3SE +/- 11.01, N = 34120.54120.74057.94014.5
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b EncryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf7001400210028003500Min: 4109.7 / Avg: 4120.53 / Max: 4128.6Min: 4119.3 / Avg: 4120.67 / Max: 4122.5Min: 4010.4 / Avg: 4057.93 / Max: 4101.9Min: 4000 / Avg: 4014.5 / Max: 4036.1

OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf9001800270036004500SE +/- 5.30, N = 3SE +/- 0.99, N = 3SE +/- 7.75, N = 3SE +/- 17.72, N = 34122.64123.04076.24024.6
OpenBenchmarking.orgMiB/s, More Is BetterCryptsetupAES-XTS 512b DecryptionApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf7001400210028003500Min: 4112.3 / Avg: 4122.6 / Max: 4129.9Min: 4121.9 / Avg: 4123.03 / Max: 4125Min: 4061.6 / Avg: 4076.23 / Max: 4088Min: 3991 / Avg: 4024.63 / Max: 4051.1

Basis Universal

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1SApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 324.0424.0524.6324.121. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1SApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430Min: 23.91 / Avg: 24.04 / Max: 24.14Min: 23.84 / Avg: 24.05 / Max: 24.29Min: 24.52 / Avg: 24.62 / Max: 24.71Min: 24.05 / Avg: 24.12 / Max: 24.231. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1020304050SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 342.3742.0041.5641.70
OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf918273645Min: 42.21 / Avg: 42.37 / Max: 42.56Min: 41.9 / Avg: 42 / Max: 42.14Min: 41.47 / Avg: 41.56 / Max: 41.68Min: 41.64 / Avg: 41.7 / Max: 41.74

PyPerformance

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

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf80160240320400SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 1.15, N = 3350350347345
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf60120180240300Min: 349 / Avg: 349.67 / Max: 350Min: 350 / Avg: 350.33 / Max: 351Min: 346 / Avg: 347.33 / Max: 348Min: 343 / Avg: 345 / Max: 347

Git

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

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1020304050SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 342.2542.0541.9441.701. Apple MacBook Air M2: git version 2.37.12. Apple MacBook Air M2 - Max Perf: git version 2.37.23. Ryzen 7 6850U: git version 2.37.14. Ryzen 7 6850U - Max Perf: git version 2.37.1
OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf918273645Min: 42.24 / Avg: 42.25 / Max: 42.26Min: 42.03 / Avg: 42.04 / Max: 42.06Min: 41.76 / Avg: 41.94 / Max: 42.3Min: 41.63 / Avg: 41.7 / Max: 41.741. Apple MacBook Air M2: git version 2.37.12. Apple MacBook Air M2 - Max Perf: git version 2.37.23. Ryzen 7 6850U: git version 2.37.14. Ryzen 7 6850U - Max Perf: git version 2.37.1

TNN

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

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1224364860SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 353.2953.3353.1953.67MIN: 53.25 / MAX: 53.38MIN: 53.27 / MAX: 53.46MIN: 52.86 / MAX: 53.53MIN: 53.17 / MAX: 54.061. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf1122334455Min: 53.28 / Avg: 53.29 / Max: 53.31Min: 53.3 / Avg: 53.33 / Max: 53.37Min: 53.07 / Avg: 53.19 / Max: 53.3Min: 53.35 / Avg: 53.67 / Max: 53.931. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max Perf10002000300040005000SE +/- 3.71, N = 3SE +/- 1.66, N = 34804.24820.41. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Decompression SpeedApple MacBook Air M2Apple MacBook Air M2 - Max Perf8001600240032004000Min: 4799 / Avg: 4804.23 / Max: 4811.4Min: 4817.1 / Avg: 4820.4 / Max: 4822.31. (CC) gcc options: -O3 -pthread -lz -llzma -llz4

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.4230.8461.2691.6922.115SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 31.871.881.381.31MIN: 1.02 / MAX: 7.77MIN: 1.02 / MAX: 5.48MIN: 1.17 / MAX: 1.74MIN: 1.14 / MAX: 2.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 1.8 / Avg: 1.87 / Max: 1.96Min: 1.84 / Avg: 1.88 / Max: 1.94Min: 1.33 / Avg: 1.38 / Max: 1.42Min: 1.21 / Avg: 1.31 / Max: 1.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. 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 2022-05-18Model: NASNet MobileApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf4K8K12K16K20KSE +/- 314.02, N = 12SE +/- 114.49, N = 15SE +/- 15.59, N = 3SE +/- 23.00, N = 317334.117241.710854.310274.7
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf3K6K9K12K15KMin: 16017.1 / Avg: 17334.08 / Max: 19137.3Min: 16381.1 / Avg: 17241.71 / Max: 18060.1Min: 10825.6 / Avg: 10854.3 / Max: 10879.2Min: 10228.9 / Avg: 10274.7 / Max: 10301.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf16003200480064008000SE +/- 134.59, N = 15SE +/- 140.94, N = 15SE +/- 11.95, N = 3SE +/- 13.51, N = 37293.797652.404444.494079.60
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf13002600390052006500Min: 5956.54 / Avg: 7293.79 / Max: 8071.26Min: 6341.33 / Avg: 7652.4 / Max: 8449.42Min: 4421.8 / Avg: 4444.49 / Max: 4462.34Min: 4052.75 / Avg: 4079.6 / Max: 4095.63

Apache Spark

This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf612182430SE +/- 0.04, N = 3SE +/- 1.28, N = 4SE +/- 0.03, N = 3SE +/- 0.05, N = 321.5123.4813.5012.40
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 2000 - Calculate Pi Benchmark Using DataframeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 21.43 / Avg: 21.51 / Max: 21.55Min: 21.19 / Avg: 23.48 / Max: 25.74Min: 13.45 / Avg: 13.5 / Max: 13.54Min: 12.32 / Avg: 12.4 / Max: 12.5

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Inner Join Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.56251.1251.68752.252.8125SE +/- 0.10, N = 3SE +/- 0.04, N = 9SE +/- 0.10, N = 3SE +/- 0.11, N = 32.232.292.502.43
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Inner Join Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 2.03 / Avg: 2.23 / Max: 2.36Min: 2.04 / Avg: 2.29 / Max: 2.41Min: 2.31 / Avg: 2.5 / Max: 2.63Min: 2.28 / Avg: 2.43 / Max: 2.64

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Repartition Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf0.81451.6292.44353.2584.0725SE +/- 0.19, N = 3SE +/- 0.04, N = 9SE +/- 0.09, N = 3SE +/- 0.05, N = 33.303.623.543.42
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Repartition Test TimeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf246810Min: 2.92 / Avg: 3.3 / Max: 3.51Min: 3.31 / Avg: 3.62 / Max: 3.75Min: 3.38 / Avg: 3.54 / Max: 3.68Min: 3.32 / Avg: 3.42 / Max: 3.47

OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025SE +/- 0.03, N = 3SE +/- 0.76, N = 9SE +/- 0.02, N = 3SE +/- 0.07, N = 321.4121.9213.5312.57
OpenBenchmarking.orgSeconds, Fewer Is BetterApache Spark 3.3Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using DataframeApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf510152025Min: 21.37 / Avg: 21.41 / Max: 21.47Min: 20.04 / Avg: 21.92 / Max: 27.06Min: 13.5 / Avg: 13.53 / Max: 13.56Min: 12.49 / Avg: 12.57 / Max: 12.72

Ngspice

Ngspice is an open-source SPICE circuit simulator. Ngspice was originally based on the Berkeley SPICE electronic circuit simulator. Ngspice supports basic threading using OpenMP. This test profile is making use of the ISCAS 85 benchmark circuits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf4080120160200SE +/- 6.45, N = 9SE +/- 1.31, N = 3SE +/- 1.89, N = 12SE +/- 1.31, N = 3175.48117.09162.57150.921. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE
OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf306090120150Min: 127.28 / Avg: 175.48 / Max: 186.46Min: 114.49 / Avg: 117.09 / Max: 118.62Min: 153.9 / Avg: 162.57 / Max: 178.53Min: 148.3 / Avg: 150.92 / Max: 152.451. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e12Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf918273645SE +/- 0.54, N = 12SE +/- 1.01, N = 15SE +/- 0.21, N = 3SE +/- 0.21, N = 338.1541.1429.7327.111. (CXX) g++ options: -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e12Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf918273645Min: 35.62 / Avg: 38.15 / Max: 43.08Min: 35.58 / Avg: 41.14 / Max: 47.43Min: 29.32 / Avg: 29.73 / Max: 29.97Min: 26.69 / Avg: 27.11 / Max: 27.351. (CXX) g++ options: -O3

GNU Radio

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

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf30060090012001500SE +/- 51.19, N = 3SE +/- 20.36, N = 3SE +/- 1.31, N = 3SE +/- 0.73, N = 31147.11201.0379.0379.81. 3.10.2.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR FilterApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000Min: 1094.3 / Avg: 1147.13 / Max: 1249.5Min: 1179.8 / Avg: 1201 / Max: 1241.7Min: 376.5 / Avg: 379 / Max: 380.9Min: 379.1 / Avg: 379.83 / Max: 381.31. 3.10.2.0

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Scala DottyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf2004006008001000SE +/- 1.32, N = 3SE +/- 8.91, N = 15SE +/- 3.50, N = 3SE +/- 11.68, N = 15583.6537.9785.7823.9MIN: 384.17 / MAX: 865.73MIN: 369.98 / MAX: 954.56MIN: 612.31 / MAX: 2066.61MIN: 609.99 / MAX: 2048.83
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Scala DottyApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf140280420560700Min: 581.89 / Avg: 583.58 / Max: 586.18Min: 479.49 / Avg: 537.94 / Max: 590.23Min: 780.92 / Avg: 785.73 / Max: 792.54Min: 772.15 / Avg: 823.88 / Max: 903.25

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf10002000300040005000SE +/- 62.55, N = 20SE +/- 29.43, N = 20SE +/- 25.22, N = 20SE +/- 25.06, N = 204590263141053070
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Apple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf8001600240032004000Min: 4039 / Avg: 4590.25 / Max: 5186Min: 2346 / Avg: 2630.55 / Max: 2848Min: 3938 / Avg: 4104.65 / Max: 4292Min: 2878 / Avg: 3069.5 / Max: 3296

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 0.28Backend: EigenApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf170340510680850SE +/- 16.66, N = 9SE +/- 29.28, N = 9SE +/- 4.80, N = 9SE +/- 5.59, N = 57157674615181. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenApple MacBook Air M2Apple MacBook Air M2 - Max PerfRyzen 7 6850URyzen 7 6850U - Max Perf130260390520650Min: 651 / Avg: 714.78 / Max: 819Min: 692 / Avg: 766.78 / Max: 962Min: 446 / Avg: 460.78 / Max: 487Min: 508 / Avg: 518 / Max: 5391. (CXX) g++ options: -flto -pthread

190 Results Shown

LuaRadio
Cryptsetup:
  Serpent-XTS 512b Encryption
  Serpent-XTS 256b Encryption
  Serpent-XTS 256b Decryption
GNU Radio
LAME MP3 Encoding
Renaissance:
  Apache Spark Bayes
  Genetic Algorithm Using Jenetics + Futures
Zstd Compression
Liquid-DSP:
  16 - 256 - 57
  1 - 256 - 57
Renaissance
Liquid-DSP:
  8 - 256 - 57
  2 - 256 - 57
Etcpak
Zstd Compression
Liquid-DSP
ASTC Encoder:
  Thorough
  Exhaustive
Etcpak
FLAC Audio Encoding
x265:
  Bosphorus 4K
  Bosphorus 1080p
NCNN
Cryptsetup:
  Twofish-XTS 512b Decryption
  Twofish-XTS 512b Encryption
  Twofish-XTS 256b Decryption
  Twofish-XTS 256b Encryption
GNU Radio
LAMMPS Molecular Dynamics Simulator
PyHPC Benchmarks:
  CPU - Numpy - 4194304 - Isoneutral Mixing
  CPU - Numpy - 1048576 - Equation of State
Zstd Compression
TensorFlow Lite
Apache Spark
PyHPC Benchmarks
Apache Spark
WebP2 Image Encode
TNN
NCNN
PyHPC Benchmarks
TensorFlow Lite
Zstd Compression
TensorFlow Lite
LAMMPS Molecular Dynamics Simulator
GNU Octave Benchmark
GNU Radio
NCNN
Google Draco
Renaissance
Parallel BZIP2 Compression
NCNN:
  CPU - yolov4-tiny
  CPU - resnet50
libavif avifenc
WebP2 Image Encode
POV-Ray
libavif avifenc
NCNN
Primesieve
DaCapo Benchmark
GNU Radio
WebP2 Image Encode
Apache Spark
Google Draco
NCNN
WebP2 Image Encode
Apache Spark
VP9 libvpx Encoding
TNN
NCNN
Node.js V8 Web Tooling Benchmark
Coremark
Renaissance
Cryptsetup
NCNN
PyPerformance
Apache Spark
ASTC Encoder
Darktable
VP9 libvpx Encoding
Ngspice
NCNN
DaCapo Benchmark
Inkscape
RNNoise
Darktable
XZ Compression
NCNN
Xmrig
OpenSSL
simdjson
Renaissance
libavif avifenc
GIMP
DaCapo Benchmark
Darktable
NCNN
Numpy Benchmark
Zstd Compression
Apache Spark
Zstd Compression:
  19, Long Mode - Decompression Speed
  3, Long Mode - Decompression Speed
simdjson
Zstd Compression
Renaissance
GNU Radio
ASKAP
Zstd Compression
ASKAP
TNN
WebP2 Image Encode
ASKAP
SecureMark
ASKAP
NCNN:
  CPU - mobilenet
  CPU - alexnet
Renaissance
GIMP:
  auto-levels
  rotate
libjpeg-turbo tjbench
Renaissance
simdjson:
  Kostya
  LargeRand
Google SynthMark
libavif avifenc
OpenSSL
PyPerformance
OpenSSL
simdjson
libavif avifenc
Zstd Compression
Build2
GEGL
Java Gradle Build
WebP Image Encode
GIMP
Basis Universal
PyPerformance:
  2to3
  pathlib
Renaissance
GEGL
Unpacking Firefox
Apache Spark
Zstd Compression
Cryptsetup:
  AES-XTS 256b Decryption
  AES-XTS 256b Encryption
  PBKDF2-whirlpool
PyPerformance
PyBench
LuaRadio
Apache Spark
PyPerformance
Basis Universal
GEGL:
  Rotate 90 Degrees
  Antialias
  Reflect
PyPerformance
LuaRadio
PyPerformance:
  nbody
  json_loads
WebP Image Encode
Basis Universal
ASKAP
GEGL:
  Wavelet Blur
  Cartoon
  Crop
PyPerformance:
  float
  go
  pickle_pure_python
Cryptsetup:
  AES-XTS 512b Encryption
  AES-XTS 512b Decryption
Basis Universal
GEGL
PyPerformance
Git
TNN
Zstd Compression
NCNN
TensorFlow Lite:
  NASNet Mobile
  SqueezeNet
Apache Spark:
  1000000 - 2000 - Calculate Pi Benchmark Using Dataframe
  1000000 - 100 - Inner Join Test Time
  1000000 - 100 - Repartition Test Time
  1000000 - 100 - Calculate Pi Benchmark Using Dataframe
Ngspice
Primesieve
GNU Radio
Renaissance
DaCapo Benchmark
LeelaChessZero

Apple MacBook Air M2

Compiler Notes: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: apple-cpufreq schedutil
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8)
Python Notes: Python 3.10.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 6 August 2022 18:44 by user phoronix.

Apple MacBook Air M2 - Max Perf

Processor: Apple M2 @ 2.42GHz (4 Cores / 8 Threads), Motherboard: Apple MacBook Air (13 h M2 2022), Memory: 8GB, Disk: 251GB APPLE SSD AP0256Z + 2 x 0GB APPLE SSD AP0256Z, Graphics: llvmpipe, Network: Broadcom Device 4433 + Broadcom Device 5f71

OS: Arch rolling, Kernel: 5.19.0-rc7-asahi-2-1-ARCH (aarch64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4, OpenGL: 4.5 Mesa 22.1.4 (LLVM 14.0.6 128 bits), Compiler: GCC 12.1.0 + Clang 14.0.6, File-System: ext4, Screen Resolution: 2560x1600

Compiler Notes: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++ --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: apple-cpufreq performance
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 17 August 2022 09:23 by user phoronix.

Ryzen 7 6850U

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa404102 - ACPI Profile: balanced
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8)
Python Notes: Python 3.10.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 8 August 2022 22:19 by user pts.

Ryzen 7 6850U - Max Perf

Processor: AMD Ryzen 7 PRO 6850U @ 2.70GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET46W 1.16 BIOS), Chipset: AMD Device 14b5, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765

OS: Arch rolling, Kernel: 5.18.16-arch1-1 (x86_64), Desktop: KDE Plasma 5.25.4, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 22.1.4 (LLVM 14.0.6 DRM 3.46), Vulkan: 1.3.211, Compiler: GCC 12.1.1 20220730 + Clang 14.0.6, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,ada,fortran,go,lto,objc,obj-c++,d --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnu
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - Platform Profile: performance - CPU Microcode: 0xa404102 - ACPI Profile: performance
Java Notes: OpenJDK Runtime Environment (build 11.0.16+8)
Python Notes: Python 3.10.5
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 August 2022 13:50 by user pts.