GCC Clang Compiler Benchmarks Zen 4 Threadripper

GCC and Clang compiler benchmarks by Michael Larabel for year end 2023 future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2312240-PTS-COMPILER73
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 4 Tests
AV1 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C++ Boost Tests 2 Tests
Chess Test Suite 2 Tests
C/C++ Compiler Tests 18 Tests
Compression Tests 3 Tests
CPU Massive 16 Tests
Creator Workloads 18 Tests
Cryptography 6 Tests
Database Test Suite 3 Tests
Encoding 11 Tests
Fortran Tests 2 Tests
HPC - High Performance Computing 7 Tests
Imaging 4 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 2 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 4 Tests
Multi-Core 17 Tests
NVIDIA GPU Compute 2 Tests
OpenMPI Tests 4 Tests
Programmer / Developer System Benchmarks 3 Tests
Python Tests 4 Tests
Raytracing 2 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server 5 Tests
Server CPU Tests 9 Tests
Single-Threaded 3 Tests
Video Encoding 7 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
GCC 13.2
December 21 2023
  9 Hours, 39 Minutes
Clang 17.0.2
December 22 2023
  9 Hours, 13 Minutes
Clang 18 23 Dec
December 23 2023
  14 Hours, 50 Minutes
GCC 14 23 Dec
December 24 2023
  4 Hours, 53 Minutes
Invert Hiding All Results Option
  9 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):

GCC 13.2

Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads), Motherboard: HP 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1, Graphics: NVIDIA RTX A4000 16GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Clang 17.0.2

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: Clang 17.0.2, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Clang 18 23 Dec

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: Clang 18.0.0, File-System: ext4, Screen Resolution: 3840x2160

GCC 14 23 Dec

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: GCC 14.0.0 20231224, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --disable-multilib --enable-checking=release --enable-languages=c,c++
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

GCC Clang Compiler Benchmarks Zen 4 ThreadripperOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads)HP 8B24 (U65 Ver. 01.01.04 BIOS)AMD Device 14a4128GB2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1NVIDIA RTX A4000 16GBNVIDIA GA104 HD AudioASUS VP28URealtek RTL8111/8168/8411Ubuntu 23.106.5.0-14-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.7NVIDIA 535.129.034.6.0OpenCL 3.0 CUDA 12.2.147GCC 13.2.0Clang 17.0.2Clang 18.0.0GCC 14.0.0 20231224ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilersFile-SystemScreen ResolutionGCC Clang Compiler Benchmarks Zen 4 Threadripper PerformanceSystem Logs- Transparent Huge Pages: madvise- CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"- GCC 13.2: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - GCC 14 23 Dec: --disable-multilib --enable-checking=release --enable-languages=c,c++- Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105- GPU Compute Cores: 6144- Python 3.11.6- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

GCC 13.2Clang 17.0.2Clang 18 23 DecGCC 14 23 DecResult OverviewPhoronix Test Suite100%110%120%130%140%C-RayTSCPminiBUDEGraphicsMagickCoremarkLiquid-DSPStargate Digital Audio WorkstationSecureMarkOpenSSLRedisFLAC Audio EncodingSMHasherLAME MP3 EncodingC-BloscPostgreSQLx265WebP Image EncodeOpus Codec EncodingGPAWKvazaaruvg266libavif avifencTimed MrBayes AnalysisSVT-VP9SVT-AV1John The RipperLZ4 CompressionMemcachedZstd CompressionXmrigOpenJPEG

GCC Clang Compiler Benchmarks Zen 4 Threadrippersmhasher: SHA3-256openssl: ChaCha20-Poly1305openssl: ChaCha20graphics-magick: HWB Color Spacec-ray: Total Time - 4K, 16 Rays Per Pixelgraphics-magick: Swirlgraphics-magick: Noise-Gaussianlczero: Eigensmhasher: FarmHash32 x86_64 AVXliquid-dsp: 1 - 256 - 512webp: Quality 100, Highest Compressiongraphics-magick: Enhancedtscp: AI Chess Performanceminibude: OpenMP - BM2minibude: OpenMP - BM2john-the-ripper: WPA PSKcryptopp: Unkeyed Algorithmsliquid-dsp: 128 - 256 - 32coremark: CoreMark Size 666 - Iterations Per Secondliquid-dsp: 192 - 256 - 32liquid-dsp: 1 - 256 - 32astcenc: Mediumsimdjson: LargeRandstargate: 96000 - 1024stargate: 96000 - 512stargate: 44100 - 512stargate: 192000 - 1024stargate: 192000 - 512stargate: 44100 - 1024liquid-dsp: 128 - 256 - 512securemark: SecureMark-TLSsimdjson: DistinctUserIDblosc: blosclz shuffle - 256MBsimdjson: Kostyaopenjpeg: NASA Curiosity Panorama M34quantlib: Single-Threadedencode-flac: WAV To FLACkvazaar: Bosphorus 4K - Slowencode-mp3: WAV To MP3smhasher: FarmHash128redis: GET - 500kvazaar: Bosphorus 4K - Mediumpgbench: 100 - 1000 - Read Onlyquantlib: Multi-Threadedpgbench: 100 - 1000 - Read Only - Average Latencyblosc: blosclz noshuffle - 256MBsimdjson: PartialTweetsavifenc: 6, Losslessuvg266: Bosphorus 4K - Very Fastgraphics-magick: Sharpencompress-lz4: 9 - Compression Speedx265: Bosphorus 4Kjohn-the-ripper: MD5blosc: blosclz bitshuffle - 256MBvvenc: Bosphorus 4K - Fasterwebp: Defaultcryptopp: Keyed Algorithmsencode-opus: WAV To Opus Encodesvt-av1: Preset 8 - Bosphorus 4Kgpaw: Carbon Nanotubejohn-the-ripper: bcryptkvazaar: Bosphorus 4K - Super Fastopenvino: Person Vehicle Bike Detection FP16 - CPUgromacs: MPI CPU - water_GMX50_bareopenvino: Person Vehicle Bike Detection FP16 - CPUsvt-vp9: Visual Quality Optimized - Bosphorus 4Kuvg266: Bosphorus 4K - Super Fastopenssl: SHA256kvazaar: Bosphorus 4K - Very Fastjohn-the-ripper: Blowfishwebp: Quality 100, Losslessvvenc: Bosphorus 4K - Fastopenvino: Handwritten English Recognition FP16-INT8 - CPUuvg266: Bosphorus 4K - Slowopenvino: Handwritten English Recognition FP16-INT8 - CPUavifenc: 0avifenc: 2mrbayes: Primate Phylogeny Analysiscompress-zstd: 12 - Decompression Speeduvg266: Bosphorus 4K - Mediumpovray: Trace Timegraphics-magick: Rotatesvt-av1: Preset 12 - Bosphorus 4Kuvg266: Bosphorus 4K - Ultra Fastwebp: Quality 100compress-zstd: 19 - Decompression Speedmemcached: 1:10avifenc: 6svt-av1: Preset 4 - Bosphorus 4Kopenssl: SHA512compress-zstd: 12 - Compression Speedliquid-dsp: 192 - 256 - 512smhasher: MeowHash x86_64 AES-NIsimdjson: TopTweetsvt-av1: Preset 13 - Bosphorus 4Klammps: 20k Atomsxmrig: KawPow - 1Mopenvino: Face Detection Retail FP16-INT8 - CPUcompress-lz4: 9 - Decompression Speedopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUastcenc: Thoroughopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUxmrig: GhostRider - 1Mopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenssl: RSA4096webp: Quality 100, Lossless, Highest Compressioncompress-zstd: 19, Long Mode - Decompression Speedmemcached: 1:100compress-zstd: 19 - Compression Speedastcenc: Exhaustiveopenssl: AES-256-GCMsmhasher: t1ha0_aes_avx2 x86_64kvazaar: Bosphorus 4K - Ultra Fastxmrig: CryptoNight-Femto UPX2 - 1Mcompress-zstd: 19, Long Mode - Compression Speedxmrig: Monero - 1Mxmrig: CryptoNight-Heavy - 1Mopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenssl: AES-128-GCMpetsc: Streamsopenssl: RSA4096openvino: Weld Porosity Detection FP16-INT8 - CPUxmrig: Wownero - 1Mopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUredis: SET - 500svt-vp9: PSNR/SSIM Optimized - Bosphorus 4Ksmhasher: MeowHash x86_64 AES-NIsmhasher: t1ha0_aes_avx2 x86_64smhasher: FarmHash32 x86_64 AVXsmhasher: FarmHash128smhasher: SHA3-256GCC 13.2Clang 17.0.2Clang 18 23 DecGCC 14 23 Dec290.6536130103978751244201647310694.950260081767151654.97177814004.51163822163454581.390183.256613307539.17220542280333333955168.745941551830000048601000426.48571.705.6018315.1313787.4030373.6579153.2586747.98704712932333333924478.678137.15.45820084151.012.23142.444.74729054.814484373.843.543780387308069.50.2657804.79.014.17667.31103867.0139.38145266677649.316.49225.65848.07385220.03194.71037.89017391389.125480.2511.2038.75199.5469.5412862938722386.891737602.049.03840.4530.822372.4049.18426.596113.1062212.934.056.050690212.00171.3715.241895.85921751.452.1169.58943028797080416.1149610000068597.569.72208.82442.44856883.518002.3417018.55.320.6269.835825.451883.5713592.0141.26339.371541833.50.791795.57695223.1524.97.2724819163695240131074.9894.7056592.811.756279.656361.093.18514.54113554.50487.7998.10946233938740183886.950050251.79.771242.78.035964.989919.183079293.25224.1234.25815.63520.18935.5441353.924459.022291282599033359099317277516.848198762381640846.89219746675.60147924588695376.447215.058511546450.46276550403000003332695.383619654393333356815750499.39091.596.4743125.9226978.5273284.2046933.7388949.12452714479666674429029.738125.55.25756304578.811.12346.655.20926974.454242865.9247.383570369329638.60.2807735.79.643.91770.8198565.1840.43151650007628.015.57727.08873.13343319.12899.21237.61618257092.525230.4910.8169.16190.7971.8412452619710789.691801701.988.74739.3832.012436.0247.78725.652109.1162151.035.235.868685208.92473.2515.731856.66092998.102.0879.87243131468240414.4149583333367078.439.59208.70742.36757018.317698.6217310.25.410.6370.009225.821856.6713628.9142.62336.161538339.50.791774.37774340.3025.07.2323816930832563132159.7794.2956300.811.855888.656105.993.05515.15112991.73490.2097.62944090667870183268.528250097.79.6771216.18.055952.839912.532829400.83232.2834.10815.25122.55925.128812.789463.942289036332603358862215877476.896196662385741578.48222390005.39145727080025572.326222.893518594533.22722549946000003642203.842569654143333356732000482.38221.466.3714755.8273548.4152514.1227843.7032949.03074714698333334206879.727795.94.877434311.14345.545.07426494.224649256.846.7635119280.2857496.29.514.05371.7697769.1941.05153996677454.226.81894.48590019.28794.44436.40318140092.025271.5210.6959.09194.9272.6212980044751389.001810911.9638.9431.582463.9147.36925.619109.5832173.334.665.848675205.93373.7215.371866.66108890.582.1499.66743912408803405.5152876666767945.389.51204.32841.65856651.017696.8617044.45.410.6368.898025.801857.8313438.4143.24334.691552460.90.791776.67679397.0924.77.1900811977109867130792.8394.5956023.011.855839.555924.593.71511.63113505.56489.6697.72944539664203183176.558150206.99.6771240.68.055951.959909.423090972.67235.7634.75615.56522.07225.247817.895287.8636404162924351353663005310484.912244680750400.25179500674.48133122462604789.291191.57261644742625000003955659.2911685587766667480680005.9518285.3881267.5305933.9552023.4797228.11192813012000004062827258.5829854504.611.84643.434.81928278.494589226.344.323593163331562.30.2787291.94.10667.98100366.3238.70147300007218.116.34526.0720.15296.12938.23017706288.23199.2969.7112538462683386.051755442.019.10231.6048.04826.165110.5582136.234.91667205.09871.6215.651837.35956401.512.1429.71742698789480411.4149146666768248.31205.98257660.117246.013625.21532147.30.781773.27735938.6624.7821035343690132218.2693.7256155.211.855867.956126.394857368608050065.071393.63175906.7218.0234.17515.43319.86035.6811356.534OpenBenchmarking.org

SMHasher

SMHasher is a hash function tester supporting various algorithms and able to make use of AVX and other modern CPU instruction set extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: SHA3-256GCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec100200300400500SE +/- 2.29, N = 3SE +/- 3.50, N = 4SE +/- 4.14, N = 7SE +/- 3.98, N = 3287.86290.65459.02463.94-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects-flto=thin-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: SHA3-256GCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.230060090012001500SE +/- 8.88, N = 3SE +/- 14.31, N = 4SE +/- 8.35, N = 3SE +/- 7.46, N = 71356.531353.92817.90812.79-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects-flto=thin-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: SHA3-256GCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec80160240320400Min: 283.97 / Avg: 287.86 / Max: 291.91Min: 285.33 / Avg: 290.65 / Max: 300.91Min: 441.58 / Avg: 459.02 / Max: 471.28Min: 457.62 / Avg: 463.94 / Max: 471.291. (CXX) g++ options: -O3 -march=native

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 3.1Algorithm: ChaCha20-Poly1305Clang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec80000M160000M240000M320000M400000MSE +/- 143870310.16, N = 3SE +/- 74912722.41, N = 3SE +/- 138801171.04, N = 3SE +/- 38965461.92, N = 3228903633260229128259903361301039787364041629243-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305Clang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec60000M120000M180000M240000M300000MMin: 228661509050 / Avg: 228903633260 / Max: 229159335250Min: 228981886980 / Avg: 229128259903.33 / Max: 229229140650Min: 361024282620 / Avg: 361301039786.67 / Max: 361458163990Min: 363963889530 / Avg: 364041629243.33 / Max: 3640852239701. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20Clang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec110000M220000M330000M440000M550000MSE +/- 195079194.35, N = 3SE +/- 201482071.29, N = 3SE +/- 264097935.23, N = 3SE +/- 289414516.97, N = 3335886221587335909931727512442016473513536630053-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20Clang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec90000M180000M270000M360000M450000MMin: 335533500010 / Avg: 335886221586.67 / Max: 336207006380Min: 335514013420 / Avg: 335909931726.67 / Max: 336172864690Min: 511987962680 / Avg: 512442016473.33 / Max: 512902751570Min: 513137525280 / Avg: 513536630053.33 / Max: 5140992510601. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: HWB Color SpaceClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.22004006008001000SE +/- 0.58, N = 3SE +/- 3.18, N = 3SE +/- 5.13, N = 3SE +/- 5.24, N = 3747751104810691. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: HWB Color SpaceClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.22004006008001000Min: 746 / Avg: 747 / Max: 748Min: 745 / Avg: 750.67 / Max: 756Min: 1038 / Avg: 1048 / Max: 1055Min: 1059 / Avg: 1069.33 / Max: 10761. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelClang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec246810SE +/- 0.067, N = 3SE +/- 0.068, N = 3SE +/- 0.029, N = 3SE +/- 0.029, N = 36.8966.8484.9504.9121. (CC) gcc options: -lm -lpthread -O3 -march=native
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelClang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec3691215Min: 6.78 / Avg: 6.9 / Max: 7.02Min: 6.73 / Avg: 6.85 / Max: 6.97Min: 4.91 / Avg: 4.95 / Max: 5.01Min: 4.86 / Avg: 4.91 / Max: 4.961. (CC) gcc options: -lm -lpthread -O3 -march=native

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SwirlClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.26001200180024003000SE +/- 2.89, N = 3SE +/- 1.33, N = 3SE +/- 0.88, N = 3SE +/- 3.93, N = 319661987244626001. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SwirlClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.25001000150020002500Min: 1961 / Avg: 1966 / Max: 1971Min: 1984 / Avg: 1986.67 / Max: 1988Min: 2445 / Avg: 2446.33 / Max: 2448Min: 2592 / Avg: 2599.67 / Max: 26051. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: Noise-GaussianClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.22004006008001000SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 5.04, N = 3SE +/- 4.33, N = 36236238078171. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: Noise-GaussianClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.2140280420560700Min: 623 / Avg: 623.33 / Max: 624Min: 623 / Avg: 623.33 / Max: 624Min: 800 / Avg: 807.33 / Max: 817Min: 810 / Avg: 817.33 / Max: 8251. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

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 0.30Backend: EigenGCC 13.2Clang 17.0.2Clang 18 23 Dec2004006008001000SE +/- 6.34, N = 9SE +/- 11.58, N = 9SE +/- 7.84, N = 36718168571. (CXX) g++ options: -flto -O3 -march=native -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.30Backend: EigenGCC 13.2Clang 17.0.2Clang 18 23 Dec150300450600750Min: 645 / Avg: 671.22 / Max: 707Min: 769 / Avg: 815.56 / Max: 881Min: 844 / Avg: 856.67 / Max: 8711. (CXX) g++ options: -flto -O3 -march=native -pthread

Backend: Eigen

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./lc0: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./lc0)

SMHasher

SMHasher is a hash function tester supporting various algorithms and able to make use of AVX and other modern CPU instruction set extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.211K22K33K44K55KSE +/- 439.18, N = 3SE +/- 372.44, N = 3SE +/- 531.14, N = 3SE +/- 264.89, N = 340846.8941578.4850400.2551654.97-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec510152025SE +/- 0.09, N = 3SE +/- 0.21, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 322.5622.0720.1919.86-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.29K18K27K36K45KMin: 40046.42 / Avg: 40846.89 / Max: 41560.29Min: 40906.29 / Avg: 41578.48 / Max: 42192.53Min: 49354.15 / Avg: 50400.25 / Max: 51083.28Min: 51299.38 / Avg: 51654.97 / Max: 52172.871. (CXX) g++ options: -O3 -march=native

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 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec5M10M15M20M25MSE +/- 127219.34, N = 15SE +/- 235451.13, N = 15SE +/- 88706.13, N = 3SE +/- 100374.30, N = 3177814001795006721974667222390001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec4M8M12M16M20MMin: 16494000 / Avg: 17781400 / Max: 18243000Min: 14945000 / Avg: 17950066.67 / Max: 18763000Min: 21852000 / Avg: 21974666.67 / Max: 22147000Min: 22079000 / Avg: 22239000 / Max: 224240001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

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.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.21.262.523.785.046.3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 34.484.515.395.60-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.2246810Min: 4.46 / Avg: 4.48 / Max: 4.49Min: 4.46 / Avg: 4.51 / Max: 4.57Min: 5.34 / Avg: 5.39 / Max: 5.42Min: 5.53 / Avg: 5.6 / Max: 5.661. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: EnhancedGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.2400800120016002000SE +/- 5.84, N = 3SE +/- 2.65, N = 3SE +/- 1.53, N = 3SE +/- 4.04, N = 313311457147916381. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: EnhancedGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.230060090012001500Min: 1325 / Avg: 1331.33 / Max: 1343Min: 1453 / Avg: 1457 / Max: 1462Min: 1477 / Avg: 1479 / Max: 1482Min: 1633 / Avg: 1638 / Max: 16461. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

TSCP

This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec600K1200K1800K2400K3000KSE +/- 21601.14, N = 5SE +/- 3431.38, N = 5SE +/- 4909.07, N = 5SE +/- 9910.25, N = 522163452246260245886927080021. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec500K1000K1500K2000K2500KMin: 2176988 / Avg: 2216345.2 / Max: 2294908Min: 2238934 / Avg: 2246260 / Max: 2257286Min: 2447902 / Avg: 2458869.2 / Max: 2469856Min: 2673679 / Avg: 2708001.8 / Max: 27266231. (CC) gcc options: -O3 -march=native

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec12002400360048006000SE +/- 51.09, N = 3SE +/- 52.09, N = 5SE +/- 62.02, N = 3SE +/- 24.10, N = 34581.394789.295376.455572.331. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec10002000300040005000Min: 4492.19 / Avg: 4581.39 / Max: 4669.15Min: 4713.66 / Avg: 4789.29 / Max: 4993.39Min: 5279.2 / Avg: 5376.45 / Max: 5491.76Min: 5524.41 / Avg: 5572.33 / Max: 5600.821. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec50100150200250SE +/- 2.04, N = 3SE +/- 2.08, N = 5SE +/- 2.48, N = 3SE +/- 0.96, N = 3183.26191.57215.06222.891. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec4080120160200Min: 179.69 / Avg: 183.26 / Max: 186.77Min: 188.55 / Avg: 191.57 / Max: 199.74Min: 211.17 / Avg: 215.06 / Max: 219.67Min: 220.98 / Avg: 222.89 / Max: 224.031. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec130K260K390K520K650KSE +/- 4559.35, N = 3SE +/- 5465.43, N = 3SE +/- 2497.30, N = 3SE +/- 3178.61, N = 35115465185946133076164471. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec110K220K330K440K550KMin: 506915 / Avg: 511545.67 / Max: 520664Min: 510191 / Avg: 518594.33 / Max: 528850Min: 609281 / Avg: 613307.33 / Max: 617880Min: 612966 / Avg: 616446.67 / Max: 6227941. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

Crypto++

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

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.8Test: Unkeyed AlgorithmsClang 17.0.2Clang 18 23 DecGCC 13.2120240360480600SE +/- 0.49, N = 3SE +/- 2.74, N = 3SE +/- 0.95, N = 3450.46533.23539.17-fno-devirtualize1. (CXX) g++ options: -g2 -fPIC -pthread -pipe -O3 -march=native
OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.8Test: Unkeyed AlgorithmsClang 17.0.2Clang 18 23 DecGCC 13.2100200300400500Min: 449.48 / Avg: 450.46 / Max: 450.96Min: 530.13 / Avg: 533.23 / Max: 538.69Min: 537.98 / Avg: 539.17 / Max: 541.051. (CXX) g++ options: -g2 -fPIC -pthread -pipe -O3 -march=native

Test: Unkeyed Algorithms

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./cryptest.exe: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./cryptest.exe)

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 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21100M2200M3300M4400M5500MSE +/- 12640191.63, N = 3SE +/- 43594839.14, N = 3SE +/- 37430513.40, N = 3SE +/- 38722904.51, N = 342280333334262500000499460000050403000001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2900M1800M2700M3600M4500MMin: 4207400000 / Avg: 4228033333.33 / Max: 4251000000Min: 4212900000 / Avg: 4262500000 / Max: 4349400000Min: 4953000000 / Avg: 4994600000 / Max: 5069300000Min: 4991600000 / Avg: 5040300000 / Max: 51168000001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

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 SecondClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec800K1600K2400K3200K4000KSE +/- 19620.88, N = 3SE +/- 34986.71, N = 3SE +/- 27949.92, N = 3SE +/- 38604.00, N = 33332695.383642203.843955168.753955659.291. (CC) gcc options: -O2 -O3 -march=native -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec700K1400K2100K2800K3500KMin: 3307208.68 / Avg: 3332695.38 / Max: 3371279.74Min: 3593038.49 / Avg: 3642203.84 / Max: 3709905.96Min: 3923171.23 / Avg: 3955168.75 / Max: 4010862.75Min: 3906408.95 / Avg: 3955659.29 / Max: 4031778.251. (CC) gcc options: -O2 -O3 -march=native -lrt" -lrt

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 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 32GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21400M2800M4200M5600M7000MSE +/- 32255852.18, N = 3SE +/- 36511383.31, N = 3SE +/- 42403157.64, N = 3SE +/- 23899256.15, N = 355183000005587766667654143333365439333331. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 32GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21100M2200M3300M4400M5500MMin: 5473500000 / Avg: 5518300000 / Max: 5580900000Min: 5534600000 / Avg: 5587766666.67 / Max: 5657700000Min: 6487600000 / Avg: 6541433333.33 / Max: 6625100000Min: 6509600000 / Avg: 6543933333.33 / Max: 65899000001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32GCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.212M24M36M48M60MSE +/- 134747.91, N = 3SE +/- 13747.73, N = 3SE +/- 61098.28, N = 3SE +/- 705129.82, N = 4480680004860100056732000568157501. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32GCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.210M20M30M40M50MMin: 47874000 / Avg: 48068000 / Max: 48327000Min: 48574000 / Avg: 48601000 / Max: 48619000Min: 56665000 / Avg: 56732000 / Max: 56854000Min: 55892000 / Avg: 56815750 / Max: 588740001. (CC) gcc options: -O3 -march=native -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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumGCC 13.2Clang 18 23 DecClang 17.0.2110220330440550SE +/- 0.80, N = 3SE +/- 1.39, N = 3SE +/- 0.56, N = 3426.49482.38499.391. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumGCC 13.2Clang 18 23 DecClang 17.0.290180270360450Min: 425.34 / Avg: 426.49 / Max: 428.02Min: 480.37 / Avg: 482.38 / Max: 485.05Min: 498.71 / Avg: 499.39 / Max: 500.51. (CXX) g++ options: -O3 -march=native -flto -pthread

Preset: Medium

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./astcenc: 2: ./astc-encoder-4.0.0/build/Source/astcenc-avx2: not found

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: LargeRandomClang 18 23 DecClang 17.0.2GCC 13.20.38250.7651.14751.531.9125SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.461.591.701. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomClang 18 23 DecClang 17.0.2GCC 13.2246810Min: 1.44 / Avg: 1.46 / Max: 1.47Min: 1.58 / Avg: 1.59 / Max: 1.6Min: 1.69 / Avg: 1.7 / Max: 1.71. (CXX) g++ options: -O3 -march=native

Throughput Test: LargeRandom

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./bench_ondemand: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./bench_ondemand)

Stargate Digital Audio Workstation

Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 1024GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2246810SE +/- 0.009825, N = 3SE +/- 0.007988, N = 3SE +/- 0.009480, N = 3SE +/- 0.004464, N = 35.6018315.9518286.3714756.4743121. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 1024GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.23691215Min: 5.59 / Avg: 5.6 / Max: 5.62Min: 5.94 / Avg: 5.95 / Max: 5.97Min: 6.35 / Avg: 6.37 / Max: 6.39Min: 6.47 / Avg: 6.47 / Max: 6.481. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 512GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21.33262.66523.99785.33046.663SE +/- 0.011976, N = 3SE +/- 0.012082, N = 3SE +/- 0.003453, N = 3SE +/- 0.004937, N = 35.1313785.3881265.8273545.9226971. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 512GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2246810Min: 5.11 / Avg: 5.13 / Max: 5.14Min: 5.37 / Avg: 5.39 / Max: 5.41Min: 5.82 / Avg: 5.83 / Max: 5.83Min: 5.91 / Avg: 5.92 / Max: 5.931. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 44100 - Buffer Size: 512GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2246810SE +/- 0.067600, N = 3SE +/- 0.023956, N = 3SE +/- 0.038112, N = 3SE +/- 0.051637, N = 37.4030377.5305938.4152518.5273281. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 44100 - Buffer Size: 512GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.23691215Min: 7.27 / Avg: 7.4 / Max: 7.49Min: 7.48 / Avg: 7.53 / Max: 7.57Min: 8.34 / Avg: 8.42 / Max: 8.46Min: 8.42 / Avg: 8.53 / Max: 8.581. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 1024GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.20.94611.89222.83833.78444.7305SE +/- 0.008117, N = 3SE +/- 0.006090, N = 3SE +/- 0.020650, N = 3SE +/- 0.018365, N = 33.6579153.9552024.1227844.2046931. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 1024GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2246810Min: 3.64 / Avg: 3.66 / Max: 3.67Min: 3.94 / Avg: 3.96 / Max: 3.97Min: 4.08 / Avg: 4.12 / Max: 4.15Min: 4.17 / Avg: 4.2 / Max: 4.231. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 512GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.20.84131.68262.52393.36524.2065SE +/- 0.007583, N = 3SE +/- 0.001538, N = 3SE +/- 0.002560, N = 3SE +/- 0.004927, N = 33.2586743.4797223.7032943.7388941. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 512GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2246810Min: 3.24 / Avg: 3.26 / Max: 3.27Min: 3.48 / Avg: 3.48 / Max: 3.48Min: 3.7 / Avg: 3.7 / Max: 3.71Min: 3.73 / Avg: 3.74 / Max: 3.741. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 44100 - Buffer Size: 1024GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.23691215SE +/- 0.011137, N = 3SE +/- 0.013114, N = 3SE +/- 0.018602, N = 3SE +/- 0.009153, N = 37.9870478.1119289.0307479.1245271. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 44100 - Buffer Size: 1024GCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.23691215Min: 7.98 / Avg: 7.99 / Max: 8.01Min: 8.09 / Avg: 8.11 / Max: 8.13Min: 9 / Avg: 9.03 / Max: 9.06Min: 9.11 / Avg: 9.12 / Max: 9.141. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

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 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec300M600M900M1200M1500MSE +/- 3447865.68, N = 3SE +/- 1882374.39, N = 3SE +/- 5446813.54, N = 3SE +/- 3295114.23, N = 312932333331301200000144796666714698333331. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec300M600M900M1200M1500MMin: 1286800000 / Avg: 1293233333.33 / Max: 1298600000Min: 1297800000 / Avg: 1301200000 / Max: 1304300000Min: 1440600000 / Avg: 1447966666.67 / Max: 1458600000Min: 1464300000 / Avg: 1469833333.33 / Max: 14757000001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

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-TLSGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.290K180K270K360K450KSE +/- 25.96, N = 3SE +/- 996.80, N = 3SE +/- 3191.95, N = 3SE +/- 3387.50, N = 33924474062824206874429021. (CC) gcc options: -pedantic -O3
OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.280K160K240K320K400KMin: 392405.19 / Avg: 392447.2 / Max: 392494.63Min: 404315.63 / Avg: 406282.28 / Max: 407548.53Min: 414328.66 / Avg: 420686.69 / Max: 424362.91Min: 436170.97 / Avg: 442902.38 / Max: 446932.591. (CC) gcc options: -pedantic -O3

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: DistinctUserIDGCC 13.2Clang 18 23 DecClang 17.0.23691215SE +/- 0.03, N = 3SE +/- 0.08, N = 15SE +/- 0.09, N = 78.679.729.731. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDGCC 13.2Clang 18 23 DecClang 17.0.23691215Min: 8.62 / Avg: 8.67 / Max: 8.72Min: 9.34 / Avg: 9.72 / Max: 10.17Min: 9.45 / Avg: 9.73 / Max: 10.091. (CXX) g++ options: -O3 -march=native

Throughput Test: DistinctUserID

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./bench_ondemand: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./bench_ondemand)

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C that focuses on compression of binary data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 256MBGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.22K4K6K8K10KSE +/- 37.76, N = 3SE +/- 34.63, N = 3SE +/- 23.87, N = 3SE +/- 15.55, N = 37258.57795.98125.58137.1-std=gnu99 -ldl -lrt -lm-march=native-march=native-std=gnu99 -lrt -ldl -lm1. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz shuffle - Buffer Size: 256MBGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.214002800420056007000Min: 7185.3 / Avg: 7258.5 / Max: 7311.2Min: 7732.6 / Avg: 7795.9 / Max: 7851.9Min: 8088.1 / Avg: 8125.5 / Max: 8169.9Min: 8118.6 / Avg: 8137.1 / Max: 81681. (CC) gcc options: -O3

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: KostyaClang 18 23 DecClang 17.0.2GCC 13.21.22632.45263.67894.90526.1315SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 34.875.255.451. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaClang 18 23 DecClang 17.0.2GCC 13.2246810Min: 4.78 / Avg: 4.87 / Max: 4.94Min: 5.14 / Avg: 5.25 / Max: 5.32Min: 5.39 / Avg: 5.45 / Max: 5.511. (CXX) g++ options: -O3 -march=native

Throughput Test: Kostya

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./bench_ondemand: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./bench_ondemand)

OpenJPEG

OpenJPEG is an open-source JPEG 2000 codec written in the C programming language. The default input for this test profile is the NASA/JPL-Caltech/MSSS Curiosity panorama 717MB TIFF image file converting to JPEG2000 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34GCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec20K40K60K80K100KSE +/- 1022.49, N = 4SE +/- 357.19, N = 3SE +/- 34.27, N = 3SE +/- 627.99, N = 3829858200875630743431. (CXX) g++ options: -O3 -march=native -rdynamic
OpenBenchmarking.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34GCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec14K28K42K56K70KMin: 80695 / Avg: 82984.5 / Max: 84816Min: 81509 / Avg: 82007.67 / Max: 82700Min: 75563 / Avg: 75630 / Max: 75676Min: 73618 / Avg: 74343.33 / Max: 755941. (CXX) g++ options: -O3 -march=native -rdynamic

QuantLib

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

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedGCC 13.2GCC 14 23 DecClang 17.0.210002000300040005000SE +/- 33.97, N = 3SE +/- 30.04, N = 3SE +/- 40.89, N = 34151.04504.64578.81. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedGCC 13.2GCC 14 23 DecClang 17.0.28001600240032004000Min: 4084.3 / Avg: 4150.97 / Max: 4195.6Min: 4446.5 / Avg: 4504.6 / Max: 4546.9Min: 4497.3 / Avg: 4578.83 / Max: 4625.21. (CXX) g++ options: -O3 -march=native -fPIE -pie

Configuration: Single-Threaded

Clang 18 23 Dec: The test quit with a non-zero exit status. E: ./quantlib: line 3: ./test-suite/quantlib-benchmark: No such file or directory

FLAC Audio Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.4WAV To FLACGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.23691215SE +/- 0.04, N = 5SE +/- 0.06, N = 5SE +/- 0.05, N = 5SE +/- 0.02, N = 512.2311.8511.1411.121. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.4WAV To FLACGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.248121620Min: 12.12 / Avg: 12.23 / Max: 12.31Min: 11.71 / Avg: 11.85 / Max: 12Min: 11.01 / Avg: 11.14 / Max: 11.28Min: 11.04 / Avg: 11.12 / Max: 11.171. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21122334455SE +/- 0.46, N = 3SE +/- 0.16, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 342.4443.4345.5446.65-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21020304050Min: 41.52 / Avg: 42.44 / Max: 42.92Min: 43.1 / Avg: 43.43 / Max: 43.6Min: 45.36 / Avg: 45.54 / Max: 45.7Min: 46.58 / Avg: 46.65 / Max: 46.751. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

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 MP3Clang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.21.1722.3443.5164.6885.86SE +/- 0.022, N = 3SE +/- 0.047, N = 3SE +/- 0.059, N = 3SE +/- 0.051, N = 35.2095.0744.8194.747-ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr-ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr1. (CC) gcc options: -O3 -pipe -march=native -lncurses -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Clang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.2246810Min: 5.18 / Avg: 5.21 / Max: 5.25Min: 5 / Avg: 5.07 / Max: 5.16Min: 4.75 / Avg: 4.82 / Max: 4.94Min: 4.66 / Avg: 4.75 / Max: 4.831. (CC) gcc options: -O3 -pipe -march=native -lncurses -lm

SMHasher

SMHasher is a hash function tester supporting various algorithms and able to make use of AVX and other modern CPU instruction set extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash128Clang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.26K12K18K24K30KSE +/- 100.64, N = 3SE +/- 227.32, N = 3SE +/- 311.86, N = 3SE +/- 187.58, N = 1526494.2226974.4528278.4929054.81-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: FarmHash128GCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.2816243240SE +/- 0.12, N = 3SE +/- 0.17, N = 15SE +/- 0.14, N = 3SE +/- 0.07, N = 335.6835.5425.2525.13-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects-flto=thin-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash128Clang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.25K10K15K20K25KMin: 26325.26 / Avg: 26494.22 / Max: 26673.44Min: 26521.17 / Avg: 26974.45 / Max: 27231.62Min: 27835.25 / Avg: 28278.49 / Max: 28880.13Min: 28139.04 / Avg: 29054.81 / Max: 30554.91. (CXX) g++ options: -O3 -march=native

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500Clang 17.0.2GCC 13.2GCC 14 23 DecClang 18 23 Dec1000K2000K3000K4000K5000KSE +/- 37859.85, N = 15SE +/- 47771.21, N = 4SE +/- 33944.52, N = 15SE +/- 27204.42, N = 34242865.924484373.804589226.304649256.801. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: GET - Parallel Connections: 500Clang 17.0.2GCC 13.2GCC 14 23 DecClang 18 23 Dec800K1600K2400K3200K4000KMin: 3976214.5 / Avg: 4242865.92 / Max: 4492040Min: 4421336.5 / Avg: 4484373.75 / Max: 4626713.5Min: 4428777.5 / Avg: 4589226.33 / Max: 4808703.5Min: 4610077 / Avg: 4649256.83 / Max: 4701541.51. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21122334455SE +/- 0.21, N = 3SE +/- 0.11, N = 3SE +/- 0.22, N = 3SE +/- 0.23, N = 343.5444.3246.7647.38-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.21020304050Min: 43.33 / Avg: 43.54 / Max: 43.97Min: 44.1 / Avg: 44.32 / Max: 44.43Min: 46.35 / Avg: 46.76 / Max: 47.11Min: 47.14 / Avg: 47.38 / Max: 47.841. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.2800K1600K2400K3200K4000KSE +/- 23217.69, N = 3SE +/- 34138.17, N = 3SE +/- 7434.99, N = 3SE +/- 14867.69, N = 335119283570369359316337803871. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.2700K1400K2100K2800K3500KMin: 3468038.76 / Avg: 3511928.07 / Max: 3547005.88Min: 3504600.34 / Avg: 3570369.03 / Max: 3619131.17Min: 3578672.88 / Avg: 3593162.96 / Max: 3603300.31Min: 3755973.22 / Avg: 3780386.72 / Max: 3807294.851. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lm

QuantLib

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

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedGCC 13.2Clang 17.0.2GCC 14 23 Dec70K140K210K280K350KSE +/- 819.02, N = 3SE +/- 1401.25, N = 3SE +/- 1487.52, N = 3308069.5329638.6331562.31. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedGCC 13.2Clang 17.0.2GCC 14 23 Dec60K120K180K240K300KMin: 306441.4 / Avg: 308069.47 / Max: 309039.8Min: 326855.7 / Avg: 329638.63 / Max: 331316.4Min: 328633.4 / Avg: 331562.27 / Max: 333478.91. (CXX) g++ options: -O3 -march=native -fPIE -pie

Configuration: Multi-Threaded

Clang 18 23 Dec: The test quit with a non-zero exit status. E: ./quantlib: line 3: ./test-suite/quantlib-benchmark: No such file or directory

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.20.06410.12820.19230.25640.3205SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.2850.2800.2780.2651. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.212345Min: 0.28 / Avg: 0.28 / Max: 0.29Min: 0.28 / Avg: 0.28 / Max: 0.29Min: 0.28 / Avg: 0.28 / Max: 0.28Min: 0.26 / Avg: 0.26 / Max: 0.271. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lm

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C that focuses on compression of binary data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 256MBGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.22K4K6K8K10KSE +/- 3.92, N = 3SE +/- 0.87, N = 3SE +/- 10.30, N = 3SE +/- 17.86, N = 37291.97496.27735.77804.7-std=gnu99 -ldl -lrt -lm-march=native-march=native-std=gnu99 -lrt -ldl -lm1. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz noshuffle - Buffer Size: 256MBGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.214002800420056007000Min: 7286.2 / Avg: 7291.9 / Max: 7299.4Min: 7494.6 / Avg: 7496.17 / Max: 7497.6Min: 7715.8 / Avg: 7735.67 / Max: 7750.3Min: 7769 / Avg: 7804.7 / Max: 7823.31. (CC) gcc options: -O3

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: PartialTweetsGCC 13.2Clang 18 23 DecClang 17.0.23691215SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 159.019.519.641. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsGCC 13.2Clang 18 23 DecClang 17.0.23691215Min: 8.93 / Avg: 9.01 / Max: 9.07Min: 9.31 / Avg: 9.51 / Max: 9.7Min: 8.36 / Avg: 9.64 / Max: 10.261. (CXX) g++ options: -O3 -march=native

Throughput Test: PartialTweets

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./bench_ondemand: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./bench_ondemand)

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 1.0Encoder Speed: 6, LosslessGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.20.93961.87922.81883.75844.698SE +/- 0.004, N = 3SE +/- 0.014, N = 3SE +/- 0.027, N = 3SE +/- 0.004, N = 34.1764.1064.0533.9171. (CXX) g++ options: -O3 -fPIC -march=native -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6, LosslessGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2246810Min: 4.17 / Avg: 4.18 / Max: 4.18Min: 4.08 / Avg: 4.11 / Max: 4.13Min: 4 / Avg: 4.05 / Max: 4.09Min: 3.91 / Avg: 3.92 / Max: 3.921. (CXX) g++ options: -O3 -fPIC -march=native -lm

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1632486480SE +/- 0.11, N = 3SE +/- 0.27, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 367.3167.9870.8171.761. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1428425670Min: 67.12 / Avg: 67.31 / Max: 67.5Min: 67.52 / Avg: 67.98 / Max: 68.45Min: 70.64 / Avg: 70.81 / Max: 71.05Min: 71.49 / Avg: 71.76 / Max: 72.131. (CXX) g++ options: -O3 -march=native

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SharpenClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.22004006008001000SE +/- 4.10, N = 3SE +/- 2.00, N = 3SE +/- 0.67, N = 3SE +/- 1.73, N = 3977985100310381. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SharpenClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.22004006008001000Min: 971 / Avg: 977.33 / Max: 985Min: 983 / Avg: 985 / Max: 989Min: 1002 / Avg: 1003.33 / Max: 1004Min: 1035 / Avg: 1038 / Max: 10411. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

LZ4 Compression

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

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedClang 17.0.2GCC 14 23 DecGCC 13.2Clang 18 23 Dec1530456075SE +/- 0.89, N = 3SE +/- 0.69, N = 3SE +/- 0.67, N = 5SE +/- 0.58, N = 365.1866.3267.0169.191. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedClang 17.0.2GCC 14 23 DecGCC 13.2Clang 18 23 Dec1326395265Min: 63.56 / Avg: 65.18 / Max: 66.61Min: 65.17 / Avg: 66.32 / Max: 67.54Min: 64.88 / Avg: 67.01 / Max: 69.12Min: 68.04 / Avg: 69.19 / Max: 69.791. (CC) gcc options: -O3

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec918273645SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.29, N = 3SE +/- 0.09, N = 338.7039.3840.4341.051. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec918273645Min: 38.49 / Avg: 38.7 / Max: 39.06Min: 39.06 / Avg: 39.38 / Max: 39.62Min: 39.91 / Avg: 40.43 / Max: 40.92Min: 40.88 / Avg: 41.05 / Max: 41.171. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec3M6M9M12M15MSE +/- 43498.40, N = 3SE +/- 75020.00, N = 3SE +/- 114054.08, N = 3SE +/- 133559.39, N = 3145266671473000015165000153996671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec3M6M9M12M15MMin: 14466000 / Avg: 14526666.67 / Max: 14611000Min: 14610000 / Avg: 14730000 / Max: 14868000Min: 14940000 / Avg: 15165000 / Max: 15310000Min: 15138000 / Avg: 15399666.67 / Max: 155770001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C that focuses on compression of binary data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 256MBGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.216003200480064008000SE +/- 20.20, N = 3SE +/- 15.49, N = 3SE +/- 30.25, N = 3SE +/- 30.09, N = 37218.17454.27628.07649.3-std=gnu99 -ldl -lrt -lm-march=native-march=native-std=gnu99 -lrt -ldl -lm1. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.11Test: blosclz bitshuffle - Buffer Size: 256MBGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.213002600390052006500Min: 7187.6 / Avg: 7218.1 / Max: 7256.3Min: 7430.4 / Avg: 7454.23 / Max: 7483.3Min: 7567.6 / Avg: 7628 / Max: 7661.1Min: 7595.3 / Avg: 7649.27 / Max: 7699.31. (CC) gcc options: -O3

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterClang 17.0.2GCC 14 23 DecGCC 13.248121620SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 315.5816.3516.49-flto=thin-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterClang 17.0.2GCC 14 23 DecGCC 13.248121620Min: 15.51 / Avg: 15.58 / Max: 15.67Min: 16.3 / Avg: 16.34 / Max: 16.42Min: 16.46 / Avg: 16.49 / Max: 16.561. (CXX) g++ options: -O3 -march=native

Video Input: Bosphorus 4K - Video Preset: Faster

Clang 18 23 Dec: The test quit with a non-zero exit status. E: ./vvenc: 2: ./vvenc-1.9.0/bin/release-static/vvencapp: not found

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.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2612182430SE +/- 0.22, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.06, N = 325.6526.0726.8127.08-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2612182430Min: 25.26 / Avg: 25.65 / Max: 26.03Min: 25.97 / Avg: 26.07 / Max: 26.26Min: 26.61 / Avg: 26.81 / Max: 27.09Min: 26.97 / Avg: 27.08 / Max: 27.181. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

Crypto++

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

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.8Test: Keyed AlgorithmsGCC 13.2Clang 17.0.2Clang 18 23 Dec2004006008001000SE +/- 1.20, N = 3SE +/- 0.30, N = 3SE +/- 0.92, N = 3848.07873.13894.49-fno-devirtualize1. (CXX) g++ options: -g2 -fPIC -pthread -pipe -O3 -march=native
OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.8Test: Keyed AlgorithmsGCC 13.2Clang 17.0.2Clang 18 23 Dec160320480640800Min: 845.68 / Avg: 848.07 / Max: 849.48Min: 872.53 / Avg: 873.13 / Max: 873.45Min: 892.7 / Avg: 894.49 / Max: 895.781. (CXX) g++ options: -g2 -fPIC -pthread -pipe -O3 -march=native

Test: Keyed Algorithms

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./cryptest.exe: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./cryptest.exe)

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus five times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.4WAV To Opus EncodeGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.2510152025SE +/- 0.01, N = 5SE +/- 0.13, N = 5SE +/- 0.07, N = 5SE +/- 0.10, N = 520.1520.0319.2919.131. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.4WAV To Opus EncodeGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.2510152025Min: 20.11 / Avg: 20.15 / Max: 20.19Min: 19.71 / Avg: 20.03 / Max: 20.26Min: 19.03 / Avg: 19.29 / Max: 19.42Min: 18.87 / Avg: 19.13 / Max: 19.471. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KClang 18 23 DecGCC 13.2GCC 14 23 DecClang 17.0.220406080100SE +/- 1.06, N = 4SE +/- 0.65, N = 15SE +/- 1.18, N = 3SE +/- 0.81, N = 394.4494.7196.1399.211. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KClang 18 23 DecGCC 13.2GCC 14 23 DecClang 17.0.220406080100Min: 92.4 / Avg: 94.44 / Max: 97.44Min: 89.56 / Avg: 94.71 / Max: 98.11Min: 94.21 / Avg: 96.13 / Max: 98.27Min: 97.66 / Avg: 99.21 / Max: 100.381. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec918273645SE +/- 0.27, N = 3SE +/- 0.52, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 338.2337.8937.6236.401. (CC) gcc options: -shared -fwrapv -O2 -O3 -march=native -lxc -lblas -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec816243240Min: 37.85 / Avg: 38.23 / Max: 38.76Min: 36.86 / Avg: 37.89 / Max: 38.54Min: 37.35 / Avg: 37.62 / Max: 38.01Min: 36.29 / Avg: 36.4 / Max: 36.531. (CC) gcc options: -shared -fwrapv -O2 -O3 -march=native -lxc -lblas -lmpi

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.240K80K120K160K200KSE +/- 798.06, N = 3SE +/- 2123.51, N = 4SE +/- 1771.90, N = 6SE +/- 2054.27, N = 31739131770621814001825701. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.230K60K90K120K150KMin: 173030 / Avg: 173913 / Max: 175506Min: 174297 / Avg: 177061.5 / Max: 183340Min: 177753 / Avg: 181399.83 / Max: 189964Min: 180400 / Avg: 182569.67 / Max: 1866761. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.220406080100SE +/- 0.29, N = 3SE +/- 0.68, N = 3SE +/- 0.58, N = 3SE +/- 0.65, N = 388.2389.1292.0292.52-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.220406080100Min: 87.68 / Avg: 88.23 / Max: 88.68Min: 87.95 / Avg: 89.12 / Max: 90.3Min: 91.15 / Avg: 92.02 / Max: 93.13Min: 91.62 / Avg: 92.52 / Max: 93.771. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.212002400360048006000SE +/- 37.89, N = 3SE +/- 37.06, N = 3SE +/- 61.07, N = 45230.495271.525480.25-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.210002000300040005000Min: 5164.75 / Avg: 5230.49 / Max: 5296.01Min: 5233.47 / Avg: 5271.52 / Max: 5345.63Min: 5360.71 / Avg: 5480.25 / Max: 5650.61. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareClang 18 23 DecClang 17.0.2GCC 13.23691215SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 310.7010.8211.201. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareClang 18 23 DecClang 17.0.2GCC 13.23691215Min: 10.65 / Avg: 10.7 / Max: 10.76Min: 10.76 / Avg: 10.82 / Max: 10.87Min: 11.17 / Avg: 11.2 / Max: 11.261. (CXX) g++ options: -O3 -march=native

Implementation: MPI CPU - Input: water_GMX50_bare

GCC 14 23 Dec: The test quit with a non-zero exit status. E: /mpi-build/bin/gmx_mpi: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by mpi-build/bin/../lib/libgromacs_mpi.so.8)

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.23691215SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 49.169.098.75MIN: 5.67 / MAX: 27.63MIN: 5.51 / MAX: 25.76-fno-strict-overflow -fwrapv - MIN: 5.37 / MAX: 26.491. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.23691215Min: 9.04 / Avg: 9.16 / Max: 9.27Min: 8.96 / Avg: 9.09 / Max: 9.15Min: 8.48 / Avg: 8.75 / Max: 8.941. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.24080120160200SE +/- 1.99, N = 3SE +/- 1.78, N = 15SE +/- 2.39, N = 4SE +/- 2.26, N = 15190.79194.92199.29199.541. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.24080120160200Min: 187.13 / Avg: 190.79 / Max: 193.96Min: 185.3 / Avg: 194.92 / Max: 207.64Min: 194.52 / Avg: 199.29 / Max: 203.67Min: 187.7 / Avg: 199.54 / Max: 219.831. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1632486480SE +/- 0.14, N = 3SE +/- 0.45, N = 3SE +/- 0.25, N = 3SE +/- 0.29, N = 369.5469.7171.8472.621. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1428425670Min: 69.27 / Avg: 69.54 / Max: 69.74Min: 69.22 / Avg: 69.71 / Max: 70.6Min: 71.37 / Avg: 71.84 / Max: 72.23Min: 72.21 / Avg: 72.62 / Max: 73.191. (CXX) g++ options: -O3 -march=native

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 3.1Algorithm: SHA256Clang 17.0.2GCC 14 23 DecGCC 13.2Clang 18 23 Dec30000M60000M90000M120000M150000MSE +/- 323275121.51, N = 3SE +/- 271320016.95, N = 3SE +/- 321788378.42, N = 3SE +/- 366849309.72, N = 3124526197107125384626833128629387223129800447513-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256Clang 17.0.2GCC 14 23 DecGCC 13.2Clang 18 23 Dec20000M40000M60000M80000M100000MMin: 123976793480 / Avg: 124526197106.67 / Max: 125096088950Min: 124886936050 / Avg: 125384626833.33 / Max: 125820746270Min: 128176956520 / Avg: 128629387223.33 / Max: 129251990170Min: 129272284510 / Avg: 129800447513.33 / Max: 1305055711101. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.220406080100SE +/- 0.65, N = 3SE +/- 1.06, N = 3SE +/- 0.40, N = 3SE +/- 0.37, N = 386.0586.8989.0089.69-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastGCC 14 23 DecGCC 13.2Clang 18 23 DecClang 17.0.220406080100Min: 84.85 / Avg: 86.05 / Max: 87.09Min: 85.6 / Avg: 86.89 / Max: 88.99Min: 88.21 / Avg: 89 / Max: 89.46Min: 88.94 / Avg: 89.69 / Max: 90.091. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec40K80K120K160K200KSE +/- 164.19, N = 3SE +/- 258.75, N = 3SE +/- 1555.73, N = 3SE +/- 1422.62, N = 31737601755441801701810911. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec30K60K90K120K150KMin: 173433 / Avg: 173759.67 / Max: 173952Min: 175044 / Avg: 175544.33 / Max: 175909Min: 178502 / Avg: 180170.33 / Max: 183279Min: 179364 / Avg: 181091.33 / Max: 1839131. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

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.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.20.4590.9181.3771.8362.295SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 31.961.982.012.04-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.2246810Min: 1.94 / Avg: 1.96 / Max: 1.98Min: 1.97 / Avg: 1.98 / Max: 2Min: 1.98 / Avg: 2.01 / Max: 2.04Min: 2.02 / Avg: 2.04 / Max: 2.041. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastClang 17.0.2GCC 13.2GCC 14 23 Dec3691215SE +/- 0.023, N = 3SE +/- 0.090, N = 3SE +/- 0.019, N = 38.7479.0389.102-flto=thin-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastClang 17.0.2GCC 13.2GCC 14 23 Dec3691215Min: 8.7 / Avg: 8.75 / Max: 8.77Min: 8.86 / Avg: 9.04 / Max: 9.16Min: 9.07 / Avg: 9.1 / Max: 9.141. (CXX) g++ options: -O3 -march=native

Video Input: Bosphorus 4K - Video Preset: Fast

Clang 18 23 Dec: The test quit with a non-zero exit status. E: ./vvenc: 2: ./vvenc-1.9.0/bin/release-static/vvencapp: not found

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUGCC 13.2Clang 17.0.2Clang 18 23 Dec918273645SE +/- 0.43, N = 5SE +/- 0.04, N = 3SE +/- 0.22, N = 340.4539.3838.94-fno-strict-overflow -fwrapv - MIN: 20.38 / MAX: 57.81MIN: 24.17 / MAX: 80.88MIN: 26.83 / MAX: 59.81. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUGCC 13.2Clang 17.0.2Clang 18 23 Dec816243240Min: 39.78 / Avg: 40.45 / Max: 42.15Min: 39.31 / Avg: 39.38 / Max: 39.45Min: 38.58 / Avg: 38.94 / Max: 39.331. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.2714212835SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.18, N = 3SE +/- 0.20, N = 330.8231.5831.6032.011. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.2714212835Min: 30.73 / Avg: 30.82 / Max: 30.98Min: 31.38 / Avg: 31.58 / Max: 31.92Min: 31.38 / Avg: 31.6 / Max: 31.95Min: 31.8 / Avg: 32.01 / Max: 32.411. (CXX) g++ options: -O3 -march=native

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUGCC 13.2Clang 17.0.2Clang 18 23 Dec5001000150020002500SE +/- 24.51, N = 5SE +/- 2.50, N = 3SE +/- 13.82, N = 32372.402436.022463.91-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUGCC 13.2Clang 17.0.2Clang 18 23 Dec400800120016002000Min: 2275.69 / Avg: 2372.4 / Max: 2411.85Min: 2431.6 / Avg: 2436.02 / Max: 2440.25Min: 2439.28 / Avg: 2463.91 / Max: 2487.071. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1122334455SE +/- 0.28, N = 3SE +/- 0.42, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 349.1848.0547.7947.371. (CXX) g++ options: -O3 -fPIC -march=native -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1020304050Min: 48.75 / Avg: 49.18 / Max: 49.7Min: 47.39 / Avg: 48.05 / Max: 48.84Min: 47.71 / Avg: 47.79 / Max: 47.84Min: 47.17 / Avg: 47.37 / Max: 47.491. (CXX) g++ options: -O3 -fPIC -march=native -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec612182430SE +/- 0.23, N = 3SE +/- 0.23, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 326.6026.1725.6525.621. (CXX) g++ options: -O3 -fPIC -march=native -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec612182430Min: 26.27 / Avg: 26.6 / Max: 27.05Min: 25.85 / Avg: 26.16 / Max: 26.61Min: 25.35 / Avg: 25.65 / Max: 25.84Min: 25.52 / Avg: 25.62 / Max: 25.781. (CXX) g++ options: -O3 -fPIC -march=native -lm

Timed MrBayes Analysis

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.2306090120150SE +/- 1.70, N = 15SE +/- 0.79, N = 3SE +/- 0.68, N = 3SE +/- 0.58, N = 3113.11110.56109.58109.12-mabm-mabm1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mrdrnd -mbmi -mbmi2 -madx -O3 -std=c99 -pedantic -march=native -lm -lreadline
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisGCC 13.2GCC 14 23 DecClang 18 23 DecClang 17.0.220406080100Min: 109.67 / Avg: 113.11 / Max: 136.55Min: 109.04 / Avg: 110.56 / Max: 111.71Min: 108.59 / Avg: 109.58 / Max: 110.9Min: 107.97 / Avg: 109.12 / Max: 109.781. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mrdrnd -mbmi -mbmi2 -madx -O3 -std=c99 -pedantic -march=native -lm -lreadline

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.25001000150020002500SE +/- 10.68, N = 3SE +/- 29.73, N = 3SE +/- 30.79, N = 3SE +/- 26.26, N = 32136.22151.02173.32212.9-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Decompression SpeedGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.2400800120016002000Min: 2117.5 / Avg: 2136.17 / Max: 2154.5Min: 2100.9 / Avg: 2151.03 / Max: 2203.8Min: 2115.4 / Avg: 2173.33 / Max: 2220.4Min: 2184 / Avg: 2212.87 / Max: 2265.31. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.2816243240SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 334.0534.6634.9135.231. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.2816243240Min: 33.83 / Avg: 34.05 / Max: 34.4Min: 34.55 / Avg: 34.66 / Max: 34.88Min: 34.72 / Avg: 34.91 / Max: 35.02Min: 35.11 / Avg: 35.23 / Max: 35.441. (CXX) g++ options: -O3 -march=native

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 TimeGCC 13.2Clang 17.0.2Clang 18 23 Dec246810SE +/- 0.037, N = 3SE +/- 0.033, N = 3SE +/- 0.061, N = 36.0505.8685.8481. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeGCC 13.2Clang 17.0.2Clang 18 23 Dec246810Min: 6.01 / Avg: 6.05 / Max: 6.12Min: 5.82 / Avg: 5.87 / Max: 5.93Min: 5.77 / Avg: 5.85 / Max: 5.971. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Trace Time

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./povray: 3: ./unix/povray: not found

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: RotateGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.2150300450600750SE +/- 1.20, N = 3SE +/- 2.33, N = 3SE +/- 1.73, N = 3SE +/- 0.67, N = 36676756856901. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: RotateGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.2120240360480600Min: 665 / Avg: 666.67 / Max: 669Min: 671 / Avg: 674.67 / Max: 679Min: 682 / Avg: 685 / Max: 688Min: 689 / Avg: 690.33 / Max: 6911. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.250100150200250SE +/- 1.12, N = 3SE +/- 1.52, N = 3SE +/- 1.47, N = 13SE +/- 0.51, N = 3205.10205.93208.92212.001. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KGCC 14 23 DecClang 18 23 DecClang 17.0.2GCC 13.24080120160200Min: 203.21 / Avg: 205.1 / Max: 207.07Min: 203.66 / Avg: 205.93 / Max: 208.81Min: 196.1 / Avg: 208.92 / Max: 217.43Min: 211.1 / Avg: 212 / Max: 212.861. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1632486480SE +/- 0.51, N = 3SE +/- 0.15, N = 3SE +/- 0.27, N = 3SE +/- 0.24, N = 371.3771.6273.2573.721. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastGCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1428425670Min: 70.5 / Avg: 71.37 / Max: 72.28Min: 71.39 / Avg: 71.62 / Max: 71.89Min: 72.79 / Avg: 73.25 / Max: 73.72Min: 73.27 / Avg: 73.72 / Max: 74.091. (CXX) g++ options: -O3 -march=native

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.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100GCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.248121620SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 315.2415.3715.6515.73-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100GCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.248121620Min: 15.03 / Avg: 15.24 / Max: 15.45Min: 15.36 / Avg: 15.37 / Max: 15.39Min: 15.51 / Avg: 15.65 / Max: 15.82Min: 15.65 / Avg: 15.73 / Max: 15.831. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.2400800120016002000SE +/- 18.21, N = 3SE +/- 14.06, N = 3SE +/- 5.93, N = 3SE +/- 2.12, N = 31837.31856.61866.61895.8-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.230060090012001500Min: 1803.8 / Avg: 1837.33 / Max: 1866.4Min: 1831.9 / Avg: 1856.63 / Max: 1880.6Min: 1855.3 / Avg: 1866.63 / Max: 1875.3Min: 1891.6 / Avg: 1895.83 / Max: 1898.21. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1.3M2.6M3.9M5.2M6.5MSE +/- 44027.28, N = 3SE +/- 50152.31, N = 3SE +/- 18523.18, N = 3SE +/- 27110.93, N = 35921751.455956401.516092998.106108890.581. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10GCC 13.2GCC 14 23 DecClang 17.0.2Clang 18 23 Dec1.1M2.2M3.3M4.4M5.5MMin: 5843611.29 / Avg: 5921751.45 / Max: 5995975.35Min: 5856107.24 / Avg: 5956401.51 / Max: 6007796.93Min: 6065797.33 / Avg: 6092998.1 / Max: 6128379.52Min: 6069850.38 / Avg: 6108890.58 / Max: 6160997.551. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 1.0Encoder Speed: 6Clang 18 23 DecGCC 14 23 DecGCC 13.2Clang 17.0.20.48350.9671.45051.9342.4175SE +/- 0.006, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 32.1492.1422.1162.0871. (CXX) g++ options: -O3 -fPIC -march=native -lm
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6Clang 18 23 DecGCC 14 23 DecGCC 13.2Clang 17.0.2246810Min: 2.14 / Avg: 2.15 / Max: 2.16Min: 2.13 / Avg: 2.14 / Max: 2.15Min: 2.11 / Avg: 2.12 / Max: 2.12Min: 2.08 / Avg: 2.09 / Max: 2.091. (CXX) g++ options: -O3 -fPIC -march=native -lm

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.23691215SE +/- 0.076, N = 3SE +/- 0.065, N = 3SE +/- 0.096, N = 5SE +/- 0.063, N = 39.5899.6679.7179.8721. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.23691215Min: 9.48 / Avg: 9.59 / Max: 9.73Min: 9.54 / Avg: 9.67 / Max: 9.76Min: 9.36 / Avg: 9.72 / Max: 9.92Min: 9.75 / Avg: 9.87 / Max: 9.951. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 3.1Algorithm: SHA512GCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec9000M18000M27000M36000M45000MSE +/- 7258386.62, N = 3SE +/- 55003825.70, N = 3SE +/- 29437974.38, N = 3SE +/- 11847693.41, N = 342698789480430287970804313146824043912408803-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512GCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec8000M16000M24000M32000M40000MMin: 42686016260 / Avg: 42698789480 / Max: 42711149880Min: 42919726040 / Avg: 43028797080 / Max: 43095737990Min: 43072734780 / Avg: 43131468240 / Max: 43164380180Min: 43889581310 / Avg: 43912408803.33 / Max: 439293255201. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.290180270360450SE +/- 4.56, N = 3SE +/- 3.96, N = 3SE +/- 2.30, N = 3SE +/- 4.45, N = 3405.5411.4414.4416.1-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 12 - Compression SpeedClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.270140210280350Min: 397.7 / Avg: 405.53 / Max: 413.5Min: 404.6 / Avg: 411.4 / Max: 418.3Min: 409.9 / Avg: 414.43 / Max: 417.4Min: 407.5 / Avg: 416.1 / Max: 422.41. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

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 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 512GCC 14 23 DecClang 17.0.2GCC 13.2Clang 18 23 Dec300M600M900M1200M1500MSE +/- 7348998.42, N = 3SE +/- 4870432.33, N = 3SE +/- 5921430.01, N = 3SE +/- 4115148.17, N = 314914666671495833333149610000015287666671. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 512GCC 14 23 DecClang 17.0.2GCC 13.2Clang 18 23 Dec300M600M900M1200M1500MMin: 1482300000 / Avg: 1491466666.67 / Max: 1506000000Min: 1488600000 / Avg: 1495833333.33 / Max: 1505100000Min: 1487900000 / Avg: 1496100000 / Max: 1507600000Min: 1523200000 / Avg: 1528766666.67 / Max: 15368000001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

SMHasher

SMHasher is a hash function tester supporting various algorithms and able to make use of AVX and other modern CPU instruction set extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: MeowHash x86_64 AES-NIClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.215K30K45K60K75KSE +/- 966.63, N = 3SE +/- 980.00, N = 3SE +/- 626.56, N = 6SE +/- 715.67, N = 367078.4367945.3868248.3168597.56-flto=thin-flto=thin-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: MeowHash x86_64 AES-NIClang 18 23 DecGCC 13.2GCC 14 23 DecClang 17.0.2816243240SE +/- 0.45, N = 3SE +/- 0.24, N = 3SE +/- 0.24, N = 6SE +/- 0.40, N = 334.7634.2634.1834.11-flto=thin-flto=auto -fno-fat-lto-objects-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: MeowHash x86_64 AES-NIClang 17.0.2Clang 18 23 DecGCC 14 23 DecGCC 13.212K24K36K48K60KMin: 65180.17 / Avg: 67078.43 / Max: 68344.66Min: 66594.89 / Avg: 67945.38 / Max: 69850.79Min: 66126.38 / Avg: 68248.31 / Max: 69598.66Min: 67367.16 / Avg: 68597.56 / Max: 69846.11. (CXX) g++ options: -O3 -march=native

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: TopTweetClang 18 23 DecClang 17.0.2GCC 13.23691215SE +/- 0.09, N = 6SE +/- 0.10, N = 3SE +/- 0.04, N = 39.519.599.721. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetClang 18 23 DecClang 17.0.2GCC 13.23691215Min: 9.3 / Avg: 9.51 / Max: 9.84Min: 9.45 / Avg: 9.59 / Max: 9.79Min: 9.65 / Avg: 9.72 / Max: 9.771. (CXX) g++ options: -O3 -march=native

Throughput Test: TopTweet

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./bench_ondemand: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ./bench_ondemand)

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.250100150200250SE +/- 2.03, N = 3SE +/- 1.82, N = 15SE +/- 0.72, N = 3SE +/- 0.96, N = 3204.33205.98208.71208.821. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.24080120160200Min: 200.32 / Avg: 204.33 / Max: 206.86Min: 194.01 / Avg: 205.98 / Max: 225.27Min: 207.27 / Avg: 208.71 / Max: 209.55Min: 207.06 / Avg: 208.82 / Max: 210.381. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 AtomsClang 18 23 DecClang 17.0.2GCC 13.21020304050SE +/- 0.23, N = 3SE +/- 0.22, N = 3SE +/- 0.20, N = 341.6642.3742.451. (CXX) g++ options: -O3 -march=native -lm -ldl
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsClang 18 23 DecClang 17.0.2GCC 13.2918273645Min: 41.27 / Avg: 41.66 / Max: 42.07Min: 42.1 / Avg: 42.37 / Max: 42.8Min: 42.06 / Avg: 42.45 / Max: 42.721. (CXX) g++ options: -O3 -march=native -lm -ldl

Model: 20k Atoms

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ../b/lmp: /lib/x86_64-linux-gnu/libstdc++.so.6: version `CXXABI_1.3.15' not found (required by ../b/lmp)

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 Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MClang 18 23 DecGCC 13.2Clang 17.0.2GCC 14 23 Dec12K24K36K48K60KSE +/- 529.15, N = 3SE +/- 417.45, N = 3SE +/- 640.77, N = 3SE +/- 668.49, N = 356651.056883.557018.357660.1-funroll-loops-static-libgcc -static-libstdc++-funroll-loops-static-libgcc -static-libstdc++1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MClang 18 23 DecGCC 13.2Clang 17.0.2GCC 14 23 Dec10K20K30K40K50KMin: 55903.4 / Avg: 56651 / Max: 57673.5Min: 56420.7 / Avg: 56883.5 / Max: 57716.7Min: 55947.2 / Avg: 57018.27 / Max: 58163.2Min: 56522.7 / Avg: 57660.13 / Max: 58837.41. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.24K8K12K16K20KSE +/- 15.90, N = 3SE +/- 14.36, N = 3SE +/- 35.94, N = 317696.8617698.6218002.34-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.23K6K9K12K15KMin: 17678.82 / Avg: 17696.86 / Max: 17728.55Min: 17680.52 / Avg: 17698.62 / Max: 17726.99Min: 17937.2 / Avg: 18002.34 / Max: 18061.211. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

LZ4 Compression

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

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.24K8K12K16K20KSE +/- 22.99, N = 5SE +/- 42.11, N = 3SE +/- 98.79, N = 3SE +/- 45.07, N = 317018.517044.417246.017310.21. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedGCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.23K6K9K12K15KMin: 16952.8 / Avg: 17018.46 / Max: 17094.9Min: 16969.5 / Avg: 17044.37 / Max: 17115.2Min: 17146.2 / Avg: 17246.03 / Max: 17443.6Min: 17256.4 / Avg: 17310.17 / Max: 17399.71. (CC) gcc options: -O3

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.21.21732.43463.65194.86926.0865SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.415.415.32MIN: 3.22 / MAX: 23.18MIN: 2.92 / MAX: 24.06-fno-strict-overflow -fwrapv - MIN: 3.18 / MAX: 23.991. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.2246810Min: 5.4 / Avg: 5.41 / Max: 5.42Min: 5.4 / Avg: 5.41 / Max: 5.42Min: 5.3 / Avg: 5.32 / Max: 5.341. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.20.14180.28360.42540.56720.709SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 30.630.630.62MIN: 0.21 / MAX: 18.55MIN: 0.18 / MAX: 18.68-fno-strict-overflow -fwrapv - MIN: 0.2 / MAX: 20.881. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.2246810Min: 0.62 / Avg: 0.63 / Max: 0.63Min: 0.62 / Avg: 0.63 / Max: 0.64Min: 0.61 / Avg: 0.62 / Max: 0.621. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughClang 18 23 DecGCC 13.2Clang 17.0.21632486480SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 368.9069.8470.011. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughClang 18 23 DecGCC 13.2Clang 17.0.21428425670Min: 68.73 / Avg: 68.9 / Max: 69.02Min: 69.72 / Avg: 69.84 / Max: 69.91Min: 69.91 / Avg: 70.01 / Max: 70.131. (CXX) g++ options: -O3 -march=native -flto -pthread

Preset: Thorough

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./astcenc: 2: ./astc-encoder-4.0.0/build/Source/astcenc-avx2: not found

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.2612182430SE +/- 0.13, N = 3SE +/- 0.16, N = 3SE +/- 0.06, N = 325.8225.8025.45MIN: 12.71 / MAX: 45.92MIN: 13.56 / MAX: 46.4-fno-strict-overflow -fwrapv - MIN: 13.56 / MAX: 47.821. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.2612182430Min: 25.57 / Avg: 25.82 / Max: 26.01Min: 25.48 / Avg: 25.8 / Max: 25.97Min: 25.34 / Avg: 25.45 / Max: 25.541. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.2400800120016002000SE +/- 9.44, N = 3SE +/- 11.87, N = 3SE +/- 4.24, N = 31856.671857.831883.57-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.230060090012001500Min: 1842.56 / Avg: 1856.67 / Max: 1874.58Min: 1845.28 / Avg: 1857.83 / Max: 1881.56Min: 1876.92 / Avg: 1883.57 / Max: 1891.451. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MClang 18 23 DecGCC 13.2GCC 14 23 DecClang 17.0.23K6K9K12K15KSE +/- 17.51, N = 3SE +/- 43.77, N = 3SE +/- 11.65, N = 3SE +/- 36.45, N = 313438.413592.013625.213628.9-funroll-loops-static-libgcc -static-libstdc++-static-libgcc -static-libstdc++-funroll-loops1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MClang 18 23 DecGCC 13.2GCC 14 23 DecClang 17.0.22K4K6K8K10KMin: 13412.2 / Avg: 13438.37 / Max: 13471.6Min: 13514.6 / Avg: 13592 / Max: 13666.1Min: 13610.6 / Avg: 13625.17 / Max: 13648.2Min: 13569.8 / Avg: 13628.87 / Max: 13695.41. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.2306090120150SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.40, N = 3143.24142.62141.26MIN: 53.57 / MAX: 210.54MIN: 60.05 / MAX: 210.86-fno-strict-overflow -fwrapv - MIN: 43.59 / MAX: 209.891. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.2306090120150Min: 143.22 / Avg: 143.24 / Max: 143.25Min: 142.42 / Avg: 142.62 / Max: 142.78Min: 140.52 / Avg: 141.26 / Max: 141.891. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.270140210280350SE +/- 0.04, N = 3SE +/- 0.30, N = 3SE +/- 1.01, N = 3334.69336.16339.37-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.260120180240300Min: 334.62 / Avg: 334.69 / Max: 334.75Min: 335.7 / Avg: 336.16 / Max: 336.71Min: 337.76 / Avg: 339.37 / Max: 341.241. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

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 3.1Algorithm: RSA4096GCC 14 23 DecClang 17.0.2GCC 13.2Clang 18 23 Dec300K600K900K1200K1500KSE +/- 4067.66, N = 3SE +/- 3224.17, N = 3SE +/- 1093.03, N = 3SE +/- 595.23, N = 31532147.31538339.51541833.51552460.9-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096GCC 14 23 DecClang 17.0.2GCC 13.2Clang 18 23 Dec300K600K900K1200K1500KMin: 1527250.6 / Avg: 1532147.33 / Max: 1540221.9Min: 1534924.8 / Avg: 1538339.5 / Max: 1544784Min: 1540098.3 / Avg: 1541833.5 / Max: 1543852.6Min: 1551270.7 / Avg: 1552460.93 / Max: 1553076.61. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

WebP Image Encode

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

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec0.17780.35560.53340.71120.889SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.780.790.790.79-lpng16 -ljpeg -ltiff-lpng16 -ljpeg -ltiff1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec246810Min: 0.77 / Avg: 0.78 / Max: 0.79Min: 0.77 / Avg: 0.79 / Max: 0.8Min: 0.78 / Avg: 0.79 / Max: 0.79Min: 0.78 / Avg: 0.79 / Max: 0.791. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.2400800120016002000SE +/- 21.40, N = 3SE +/- 23.70, N = 3SE +/- 21.26, N = 3SE +/- 19.09, N = 31773.21774.31776.61795.5-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.230060090012001500Min: 1730.9 / Avg: 1773.23 / Max: 1799.8Min: 1736.1 / Avg: 1774.33 / Max: 1817.7Min: 1735.8 / Avg: 1776.63 / Max: 1807.3Min: 1774.8 / Avg: 1795.47 / Max: 1833.61. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Clang 18 23 DecGCC 13.2GCC 14 23 DecClang 17.0.21.7M3.4M5.1M6.8M8.5MSE +/- 7633.51, N = 3SE +/- 9027.10, N = 3SE +/- 44302.45, N = 3SE +/- 54728.52, N = 37679397.097695223.157735938.667774340.301. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100Clang 18 23 DecGCC 13.2GCC 14 23 DecClang 17.0.21.3M2.6M3.9M5.2M6.5MMin: 7666881.64 / Avg: 7679397.09 / Max: 7693226.75Min: 7680165.58 / Avg: 7695223.15 / Max: 7711378.52Min: 7688076.21 / Avg: 7735938.66 / Max: 7824445.5Min: 7666613.18 / Avg: 7774340.3 / Max: 7844990.311. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedClang 18 23 DecGCC 14 23 DecGCC 13.2Clang 17.0.2612182430SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 324.724.724.925.0-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedClang 18 23 DecGCC 14 23 DecGCC 13.2Clang 17.0.2612182430Min: 24.6 / Avg: 24.67 / Max: 24.7Min: 24.6 / Avg: 24.7 / Max: 24.8Min: 24.8 / Avg: 24.93 / Max: 25.1Min: 24.8 / Avg: 25.03 / Max: 25.21. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveClang 18 23 DecClang 17.0.2GCC 13.2246810SE +/- 0.0210, N = 3SE +/- 0.0190, N = 3SE +/- 0.0327, N = 37.19007.23237.27241. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveClang 18 23 DecClang 17.0.2GCC 13.23691215Min: 7.15 / Avg: 7.19 / Max: 7.23Min: 7.2 / Avg: 7.23 / Max: 7.27Min: 7.23 / Avg: 7.27 / Max: 7.341. (CXX) g++ options: -O3 -march=native -flto -pthread

Preset: Exhaustive

GCC 14 23 Dec: The test quit with a non-zero exit status. E: ./astcenc: 2: ./astc-encoder-4.0.0/build/Source/astcenc-avx2: not found

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 3.1Algorithm: AES-256-GCMClang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec200000M400000M600000M800000M1000000MSE +/- 745364268.21, N = 3SE +/- 367647705.83, N = 3SE +/- 617348183.36, N = 3SE +/- 458494386.59, N = 3811977109867816930832563819163695240821035343690-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMClang 18 23 DecClang 17.0.2GCC 13.2GCC 14 23 Dec140000M280000M420000M560000M700000MMin: 810875379170 / Avg: 811977109866.67 / Max: 813397656640Min: 816544583680 / Avg: 816930832563.33 / Max: 817665808790Min: 818362221180 / Avg: 819163695240 / Max: 820377811540Min: 820119168340 / Avg: 821035343690 / Max: 8215268731601. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

SMHasher

SMHasher is a hash function tester supporting various algorithms and able to make use of AVX and other modern CPU instruction set extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: t1ha0_aes_avx2 x86_64Clang 18 23 DecGCC 13.2Clang 17.0.2GCC 14 23 Dec30K60K90K120K150KSE +/- 954.34, N = 3SE +/- 759.57, N = 3SE +/- 1814.82, N = 3SE +/- 1656.41, N = 3130792.83131074.98132159.77132218.26-flto=thin-flto=auto -fno-fat-lto-objects-flto=thin-flto=auto -fno-fat-lto-objects1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2022-08-22Hash: t1ha0_aes_avx2 x86_64GCC 13.2Clang 18 23 DecGCC 14 23 DecClang 17.0.248121620SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 315.6415.5715.4315.25-flto=auto -fno-fat-lto-objects-flto=thin-flto=auto -fno-fat-lto-objects-flto=thin1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: t1ha0_aes_avx2 x86_64Clang 18 23 DecGCC 13.2Clang 17.0.2GCC 14 23 Dec20K40K60K80K100KMin: 129203.74 / Avg: 130792.83 / Max: 132503.01Min: 130195.89 / Avg: 131074.98 / Max: 132587.48Min: 128533.91 / Avg: 132159.77 / Max: 134116.14Min: 129369.44 / Avg: 132218.26 / Max: 135106.991. (CXX) g++ options: -O3 -march=native

Kvazaar

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

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.220406080100SE +/- 0.73, N = 3SE +/- 0.35, N = 3SE +/- 0.18, N = 3SE +/- 0.61, N = 393.7294.2994.5994.70-lpthread-lpthread1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Ultra FastGCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.220406080100Min: 92.43 / Avg: 93.72 / Max: 94.95Min: 93.6 / Avg: 94.29 / Max: 94.77Min: 94.34 / Avg: 94.59 / Max: 94.94Min: 93.59 / Avg: 94.7 / Max: 95.71. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt

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 Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.212K24K36K48K60KSE +/- 216.50, N = 3SE +/- 136.66, N = 3SE +/- 155.80, N = 3SE +/- 150.17, N = 356023.056155.256300.856592.8-funroll-loops-static-libgcc -static-libstdc++-funroll-loops-static-libgcc -static-libstdc++1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.210K20K30K40K50KMin: 55732 / Avg: 56023.03 / Max: 56446.2Min: 55944.1 / Avg: 56155.2 / Max: 56411.1Min: 56000.4 / Avg: 56300.8 / Max: 56522.7Min: 56353.9 / Avg: 56592.83 / Max: 56869.91. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedGCC 13.2Clang 17.0.2Clang 18 23 DecGCC 14 23 Dec3691215SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 311.711.811.811.8-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedGCC 13.2Clang 17.0.2Clang 18 23 DecGCC 14 23 Dec3691215Min: 11.7 / Avg: 11.73 / Max: 11.8Min: 11.8 / Avg: 11.83 / Max: 11.9Min: 11.7 / Avg: 11.8 / Max: 11.9Min: 11.7 / Avg: 11.77 / Max: 11.91. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

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 Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.212K24K36K48K60KSE +/- 215.49, N = 3SE +/- 234.92, N = 3SE +/- 154.69, N = 3SE +/- 228.27, N = 355839.555867.955888.656279.6-funroll-loops-static-libgcc -static-libstdc++-funroll-loops-static-libgcc -static-libstdc++1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MClang 18 23 DecGCC 14 23 DecClang 17.0.2GCC 13.210K20K30K40K50KMin: 55567.9 / Avg: 55839.5 / Max: 56265.1Min: 55571 / Avg: 55867.9 / Max: 56331.7Min: 55632.8 / Avg: 55888.63 / Max: 56167.2Min: 55900.3 / Avg: 56279.63 / Max: 56689.31. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.212K24K36K48K60KSE +/- 91.23, N = 3SE +/- 146.78, N = 3SE +/- 185.10, N = 3SE +/- 147.72, N = 355924.556105.956126.356361.0-funroll-loops-funroll-loops-static-libgcc -static-libstdc++-static-libgcc -static-libstdc++1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MClang 18 23 DecClang 17.0.2GCC 14 23 DecGCC 13.210K20K30K40K50KMin: 55806.7 / Avg: 55924.53 / Max: 56104.1Min: 55937.8 / Avg: 56105.93 / Max: 56398.4Min: 55865.9 / Avg: 56126.33 / Max: 56484.4Min: 56069.5 / Avg: 56361.03 / Max: 56548.31. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUClang 18 23 DecGCC 13.2Clang 17.0.220406080100SE +/- 0.33, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 393.7193.1893.05MIN: 39.51 / MAX: 151.45-fno-strict-overflow -fwrapv - MIN: 45.56 / MAX: 146.45MIN: 43.63 / MAX: 147.751. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUClang 18 23 DecGCC 13.2Clang 17.0.220406080100Min: 93.07 / Avg: 93.71 / Max: 94.18Min: 93.02 / Avg: 93.18 / Max: 93.3Min: 92.92 / Avg: 93.05 / Max: 93.151. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUClang 18 23 DecGCC 13.2Clang 17.0.2110220330440550SE +/- 1.83, N = 3SE +/- 0.42, N = 3SE +/- 0.40, N = 3511.63514.54515.15-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUClang 18 23 DecGCC 13.2Clang 17.0.290180270360450Min: 509.02 / Avg: 511.63 / Max: 515.15Min: 513.97 / Avg: 514.54 / Max: 515.35Min: 514.46 / Avg: 515.15 / Max: 515.851. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.220K40K60K80K100KSE +/- 567.66, N = 3SE +/- 50.71, N = 3SE +/- 733.05, N = 3112991.73113505.56113554.50-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.220K40K60K80K100KMin: 112260.49 / Avg: 112991.73 / Max: 114109.48Min: 113427.04 / Avg: 113505.56 / Max: 113600.4Min: 112546.41 / Avg: 113554.5 / Max: 114980.441. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.2110220330440550SE +/- 0.30, N = 3SE +/- 0.22, N = 3SE +/- 0.75, N = 3490.20489.66487.79MIN: 249.93 / MAX: 516.28MIN: 381.31 / MAX: 514.98-fno-strict-overflow -fwrapv - MIN: 394.16 / MAX: 515.771. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.290180270360450Min: 489.72 / Avg: 490.2 / Max: 490.76Min: 489.39 / Avg: 489.66 / Max: 490.09Min: 486.5 / Avg: 487.79 / Max: 489.091. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.220406080100SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 397.6297.7298.10-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUClang 17.0.2Clang 18 23 DecGCC 13.220406080100Min: 97.53 / Avg: 97.62 / Max: 97.7Min: 97.64 / Avg: 97.72 / Max: 97.76Min: 97.82 / Avg: 98.1 / Max: 98.441. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

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 3.1Algorithm: AES-128-GCMClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec200000M400000M600000M800000M1000000MSE +/- 1012640703.78, N = 3SE +/- 712012274.52, N = 3SE +/- 926361343.56, N = 3SE +/- 227590943.13, N = 3944090667870944539664203946233938740948573686080-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec160000M320000M480000M640000M800000MMin: 942121613990 / Avg: 944090667870 / Max: 945485613740Min: 943751113930 / Avg: 944539664203.33 / Max: 945960840400Min: 944717538650 / Avg: 946233938740 / Max: 947914003250Min: 948143740790 / Avg: 948573686080 / Max: 9489180928701. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

PETSc

PETSc, the Portable, Extensible Toolkit for Scientific Computation, is for the scalable (parallel) solution of scientific applications modeled by partial differential equations. This test profile runs the PETSc "make streams" benchmark and records the throughput rate when all available cores are utilized for the MPI Streams build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsClang 18 23 DecClang 17.0.2GCC 13.240K80K120K160K200KSE +/- 20.67, N = 3SE +/- 138.55, N = 3SE +/- 272.88, N = 3183176.56183268.53183886.95-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -fPIC -O3 -O2 -lpthread -lpciaccess -lm
OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsClang 18 23 DecClang 17.0.2GCC 13.230K60K90K120K150KMin: 183139.96 / Avg: 183176.56 / Max: 183211.49Min: 183060.48 / Avg: 183268.53 / Max: 183531.07Min: 183386.84 / Avg: 183886.95 / Max: 184326.241. (CC) gcc options: -fPIC -O3 -O2 -lpthread -lpciaccess -lm

Test: Streams

GCC 14 23 Dec: The test run did not produce a result. E: /usr/bin/ld: petsc-3.19.0/arch-linux-c-opt/lib/libpetsc.so: undefined reference to `__cxa_call_terminate'

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 3.1Algorithm: RSA4096GCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.211K22K33K44K55KSE +/- 103.69, N = 3SE +/- 91.28, N = 3SE +/- 80.27, N = 3SE +/- 84.27, N = 350065.050097.750206.950251.7-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096GCC 14 23 DecClang 17.0.2Clang 18 23 DecGCC 13.29K18K27K36K45KMin: 49882.1 / Avg: 50064.97 / Max: 50241.1Min: 49980.1 / Avg: 50097.67 / Max: 50277.4Min: 50083.6 / Avg: 50206.9 / Max: 50357.6Min: 50091.5 / Avg: 50251.73 / Max: 50377.11. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUGCC 13.2Clang 18 23 DecClang 17.0.23691215SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 39.709.679.67-fno-strict-overflow -fwrapv - MIN: 4.82 / MAX: 28.19MIN: 5.1 / MAX: 28.3MIN: 4.96 / MAX: 29.011. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUGCC 13.2Clang 18 23 DecClang 17.0.23691215Min: 9.6 / Avg: 9.67 / Max: 9.7Min: 9.62 / Avg: 9.67 / Max: 9.7Min: 9.61 / Avg: 9.67 / Max: 9.721. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

Xmrig

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

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec15K30K45K60K75KSE +/- 205.42, N = 3SE +/- 267.90, N = 3SE +/- 161.43, N = 3SE +/- 161.46, N = 371216.171240.671242.771393.6-funroll-loops-funroll-loops-static-libgcc -static-libstdc++-static-libgcc -static-libstdc++1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MClang 17.0.2Clang 18 23 DecGCC 13.2GCC 14 23 Dec12K24K36K48K60KMin: 70846.6 / Avg: 71216.13 / Max: 71556.4Min: 70726.4 / Avg: 71240.63 / Max: 71628.1Min: 70942.1 / Avg: 71242.73 / Max: 71495Min: 71164.2 / Avg: 71393.57 / Max: 71705.11. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.2246810SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 38.058.058.03MIN: 4.56 / MAX: 25.34MIN: 4.4 / MAX: 25.17-fno-strict-overflow -fwrapv - MIN: 4.11 / MAX: 25.571. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.23691215Min: 7.99 / Avg: 8.05 / Max: 8.1Min: 7.97 / Avg: 8.05 / Max: 8.1Min: 7.98 / Avg: 8.03 / Max: 8.081. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.213002600390052006500SE +/- 23.74, N = 3SE +/- 28.17, N = 3SE +/- 20.52, N = 35951.955952.835964.98-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.210002000300040005000Min: 5914.83 / Avg: 5951.95 / Max: 5996.14Min: 5913.49 / Avg: 5952.83 / Max: 6007.42Min: 5930.01 / Avg: 5964.98 / Max: 6001.061. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.22K4K6K8K10KSE +/- 27.69, N = 3SE +/- 35.14, N = 3SE +/- 32.34, N = 39909.429912.539919.18-fno-strict-overflow -fwrapv1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUClang 18 23 DecClang 17.0.2GCC 13.22K4K6K8K10KMin: 9879.6 / Avg: 9909.42 / Max: 9964.74Min: 9864.11 / Avg: 9912.53 / Max: 9980.85Min: 9886.23 / Avg: 9919.18 / Max: 9983.861. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500Clang 17.0.2GCC 13.2Clang 18 23 DecGCC 14 23 Dec700K1400K2100K2800K3500KSE +/- 37397.13, N = 15SE +/- 53058.07, N = 15SE +/- 21571.11, N = 3SE +/- 22198.55, N = 32829400.833079293.253090972.673175906.701. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 7.0.4Test: SET - Parallel Connections: 500Clang 17.0.2GCC 13.2Clang 18 23 DecGCC 14 23 Dec600K1200K1800K2400K3000KMin: 2481680.25 / Avg: 2829400.83 / Max: 3045492.75Min: 2670702.75 / Avg: 3079293.25 / Max: 3312634Min: 3056289.25 / Avg: 3090972.67 / Max: 3130534.5Min: 3131691.5 / Avg: 3175906.67 / Max: 3201491.51. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec50100150200250SE +/- 0.67, N = 3SE +/- 8.63, N = 12SE +/- 0.19, N = 3SE +/- 1.77, N = 3218.02224.12232.28235.761. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KGCC 14 23 DecGCC 13.2Clang 17.0.2Clang 18 23 Dec4080120160200Min: 216.87 / Avg: 218.02 / Max: 219.18Min: 131.34 / Avg: 224.12 / Max: 239.35Min: 232.03 / Avg: 232.28 / Max: 232.66Min: 232.35 / Avg: 235.76 / Max: 238.271. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

135 Results Shown

SMHasher
OpenSSL:
  ChaCha20-Poly1305
  ChaCha20
GraphicsMagick
C-Ray
GraphicsMagick:
  Swirl
  Noise-Gaussian
LeelaChessZero
SMHasher
Liquid-DSP
WebP Image Encode
GraphicsMagick
TSCP
miniBUDE:
  OpenMP - BM2:
    GFInst/s
    Billion Interactions/s
John The Ripper
Crypto++
Liquid-DSP
Coremark
Liquid-DSP:
  192 - 256 - 32
  1 - 256 - 32
ASTC Encoder
simdjson
Stargate Digital Audio Workstation:
  96000 - 1024
  96000 - 512
  44100 - 512
  192000 - 1024
  192000 - 512
  44100 - 1024
Liquid-DSP
SecureMark
simdjson
C-Blosc
simdjson
OpenJPEG
QuantLib
FLAC Audio Encoding
Kvazaar
LAME MP3 Encoding
SMHasher
Redis
Kvazaar
PostgreSQL
QuantLib
PostgreSQL
C-Blosc
simdjson
libavif avifenc
uvg266
GraphicsMagick
LZ4 Compression
x265
John The Ripper
C-Blosc
VVenC
WebP Image Encode
Crypto++
Opus Codec Encoding
SVT-AV1
GPAW
John The Ripper
Kvazaar
OpenVINO
GROMACS
OpenVINO
SVT-VP9
uvg266
OpenSSL
Kvazaar
John The Ripper
WebP Image Encode
VVenC
OpenVINO
uvg266
OpenVINO
libavif avifenc:
  0
  2
Timed MrBayes Analysis
Zstd Compression
uvg266
POV-Ray
GraphicsMagick
SVT-AV1
uvg266
WebP Image Encode
Zstd Compression
Memcached
libavif avifenc
SVT-AV1
OpenSSL
Zstd Compression
Liquid-DSP
SMHasher
simdjson
SVT-AV1
LAMMPS Molecular Dynamics Simulator
Xmrig
OpenVINO
LZ4 Compression
OpenVINO:
  Face Detection Retail FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
ASTC Encoder
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
Xmrig
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
OpenSSL
WebP Image Encode
Zstd Compression
Memcached
Zstd Compression
ASTC Encoder
OpenSSL
SMHasher
Kvazaar
Xmrig
Zstd Compression
Xmrig:
  Monero - 1M
  CryptoNight-Heavy - 1M
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
OpenSSL
PETSc
OpenSSL
OpenVINO
Xmrig
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    FPS
Redis
SVT-VP9

GCC 13.2

Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads), Motherboard: HP 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1, Graphics: NVIDIA RTX A4000 16GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 21 December 2023 20:26 by user pts.

Clang 17.0.2

Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads), Motherboard: HP 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1, Graphics: NVIDIA RTX A4000 16GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: Clang 17.0.2, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 22 December 2023 17:43 by user pts.

Clang 18 23 Dec

Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads), Motherboard: HP 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1, Graphics: NVIDIA RTX A4000 16GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: Clang 18.0.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 December 2023 11:11 by user pts.

GCC 14 23 Dec

Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads), Motherboard: HP 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1, Graphics: NVIDIA RTX A4000 16GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 23.10, Kernel: 6.5.0-14-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: GCC 14.0.0 20231224, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"
Compiler Notes: --disable-multilib --enable-checking=release --enable-languages=c,c++
Processor Notes: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 December 2023 02:35 by user pts.