Benchmarks by Michael Larabel for a future article.
x86-64-v4 Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 5.19GHz (96 Cores / 192 Threads), Motherboard: HP Z6 G5 A Workstation 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 8 x 16GB DDR5-5200MT/s Hynix HMCG78AGBRA190N, 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: CachyOS rolling, Kernel: 6.7.2-2-cachyos (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20240118 + Clang 16.0.6 + LLVM 16.0.6, File-System: xfs, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,objc,obj-c++ --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnuProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Java Notes: OpenJDK Runtime Environment (build 11.0.22+7)Python Notes: Python 3.11.7Security 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
x86-64-v3 OS: CachyOS rolling, Kernel: 6.7.2-2-cachyos (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20231026 + Clang 16.0.6 + LLVM 16.0.6, File-System: xfs, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,m2,objc,obj-c++ --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnuProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Java Notes: OpenJDK Runtime Environment (build 11.0.22+7)Python Notes: Python 3.11.7Security 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
No v3 or v4 OS: CachyOS rolling, Kernel: 6.7.2-1-cachyos (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20230801 + Clang 16.0.6 + LLVM 16.0.6, File-System: xfs, Screen Resolution: 3840x2160
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating x86-64-v4 x86-64-v3 No v3 or v4 140K 280K 420K 560K 700K SE +/- 1578.02, N = 3 SE +/- 1155.62, N = 3 SE +/- 2181.99, N = 3 652847 662490 664597 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender Blend File: BMW27 - Compute: CPU-Only x86-64-v4 x86-64-v3 No v3 or v4 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 15.33 15.26 15.26
OpenBenchmarking.org Seconds, Fewer Is Better Blender Blend File: Classroom - Compute: CPU-Only x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 27.31 27.11 27.20
OpenBenchmarking.org Seconds, Fewer Is Better Blender Blend File: Fishy Cat - Compute: CPU-Only x86-64-v4 x86-64-v3 No v3 or v4 5 10 15 20 25 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 19.39 19.34 19.32
OpenBenchmarking.org Seconds, Fewer Is Better Blender Blend File: Barbershop - Compute: CPU-Only x86-64-v4 x86-64-v3 No v3 or v4 30 60 90 120 150 SE +/- 0.35, N = 3 SE +/- 0.60, N = 3 SE +/- 0.18, N = 3 130.89 130.71 130.45
OpenBenchmarking.org Seconds, Fewer Is Better Blender Blend File: Pabellon Barcelona - Compute: CPU-Only x86-64-v4 x86-64-v3 No v3 or v4 9 18 27 36 45 SE +/- 0.12, N = 3 SE +/- 0.24, N = 3 SE +/- 0.08, N = 3 39.92 39.79 39.72
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5.02 Mode: CPU x86-64-v4 x86-64-v3 No v3 or v4 20K 40K 60K 80K 100K SE +/- 471.39, N = 3 SE +/- 686.02, N = 3 SE +/- 1175.75, N = 5 106670 107830 106099
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: PMD Source Code Analyzer x86-64-v4 x86-64-v3 No v3 or v4 400 800 1200 1600 2000 SE +/- 15.46, N = 7 SE +/- 12.50, N = 3 SE +/- 7.69, N = 3 1649 1679 1690
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Lucene Search Index x86-64-v4 x86-64-v3 No v3 or v4 600 1200 1800 2400 3000 SE +/- 17.19, N = 3 SE +/- 24.97, N = 3 SE +/- 8.99, N = 3 2731 2800 2696
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Apache Lucene Search Engine x86-64-v4 x86-64-v3 No v3 or v4 300 600 900 1200 1500 SE +/- 13.98, N = 3 SE +/- 4.33, N = 3 SE +/- 6.74, N = 3 1478 1486 1490
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Avrora AVR Simulation Framework x86-64-v4 x86-64-v3 No v3 or v4 1200 2400 3600 4800 6000 SE +/- 39.55, N = 11 SE +/- 70.23, N = 3 SE +/- 55.27, N = 3 5271 5503 5140
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: BioJava Biological Data Framework x86-64-v4 x86-64-v3 No v3 or v4 1000 2000 3000 4000 5000 SE +/- 34.70, N = 11 SE +/- 16.46, N = 3 SE +/- 34.98, N = 10 4615 4678 4634
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: Zxing 1D/2D Barcode Image Processing x86-64-v4 x86-64-v3 No v3 or v4 80 160 240 320 400 SE +/- 7.04, N = 15 SE +/- 8.82, N = 12 SE +/- 1.33, N = 3 348 334 354
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 23.11 Java Test: H2O In-Memory Platform For Machine Learning x86-64-v4 x86-64-v3 No v3 or v4 900 1800 2700 3600 4500 SE +/- 33.93, N = 3 SE +/- 30.28, N = 3 SE +/- 37.37, N = 7 4126 3912 3972
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 4.6.0 Test: Boat - Acceleration: CPU-only x86-64-v4 No v3 or v4 0.3148 0.6296 0.9444 1.2592 1.574 SE +/- 0.014, N = 5 SE +/- 0.015, N = 3 1.329 1.399 Test: Boat - Acceleration: CPU-only
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 4.6.0 Test: Masskrug - Acceleration: CPU-only x86-64-v4 No v3 or v4 0.2806 0.5612 0.8418 1.1224 1.403 SE +/- 0.004, N = 3 SE +/- 0.012, N = 6 1.187 1.247 Test: Masskrug - Acceleration: CPU-only
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 4.6.0 Test: Server Rack - Acceleration: CPU-only x86-64-v4 No v3 or v4 0.0365 0.073 0.1095 0.146 0.1825 SE +/- 0.010, N = 12 SE +/- 0.007, N = 15 0.154 0.162 Test: Server Rack - Acceleration: CPU-only
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 4.6.0 Test: Server Room - Acceleration: CPU-only x86-64-v4 No v3 or v4 0.3074 0.6148 0.9222 1.2296 1.537 SE +/- 0.017, N = 3 SE +/- 0.012, N = 15 1.352 1.366 Test: Server Room - Acceleration: CPU-only
x86-64-v3: The test quit with a non-zero exit status.
G'MIC G'MIC is an open-source framework for image processing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 2D Function Plotting, 1000 Times x86-64-v4 No v3 or v4 30 60 90 120 150 SE +/- 1.10, N = 3 SE +/- 0.38, N = 3 103.54 122.04 Test: 2D Function Plotting, 1000 Times
x86-64-v3: The test quit with a non-zero exit status. E: [0;31;59m[gmic] G'MIC encountered a [1mfatal error[0;0;0m[0;31;59m. Please submit a bug report, at: [1mhttps://github.com/GreycLab/gmic/issues[0;0;0m
OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times x86-64-v4 No v3 or v4 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 10.75 10.63 Test: Plotting Isosurface Of A 3D Volume, 1000 Times
x86-64-v3: The test quit with a non-zero exit status. E: [0;31;59m[gmic] G'MIC encountered a [1mfatal error[0;0;0m[0;31;59m. Please submit a bug report, at: [1mhttps://github.com/GreycLab/gmic/issues[0;0;0m
OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 3D Elevated Function In Random Colors, 100 Times x86-64-v4 No v3 or v4 120 240 360 480 600 SE +/- 0.11, N = 3 SE +/- 0.29, N = 3 560.94 564.95 Test: 3D Elevated Function In Random Colors, 100 Times
x86-64-v3: The test quit with a non-zero exit status. E: [0;31;59m[gmic] G'MIC encountered a [1mfatal error[0;0;0m[0;31;59m. Please submit a bug report, at: [1mhttps://github.com/GreycLab/gmic/issues[0;0;0m
GEGL GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Crop x86-64-v4 No v3 or v4 2 4 6 8 10 SE +/- 0.084, N = 3 SE +/- 0.085, N = 3 6.254 7.410 Operation: Crop
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Scale x86-64-v4 No v3 or v4 2 4 6 8 10 SE +/- 0.094, N = 3 SE +/- 0.083, N = 15 7.873 8.541 Operation: Scale
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Cartoon x86-64-v4 No v3 or v4 15 30 45 60 75 SE +/- 0.22, N = 3 SE +/- 0.10, N = 3 63.83 66.66 Operation: Cartoon
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Reflect x86-64-v4 No v3 or v4 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 22.05 23.51 Operation: Reflect
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Antialias x86-64-v4 No v3 or v4 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 27.83 29.32 Operation: Antialias
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Tile Glass x86-64-v4 No v3 or v4 6 12 18 24 30 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 22.06 23.75 Operation: Tile Glass
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Wavelet Blur x86-64-v4 No v3 or v4 10 20 30 40 50 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 43.19 44.48 Operation: Wavelet Blur
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Color Enhance x86-64-v4 No v3 or v4 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 34.79 37.35 Operation: Color Enhance
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Rotate 90 Degrees x86-64-v4 No v3 or v4 9 18 27 36 45 SE +/- 0.13, N = 3 SE +/- 0.50, N = 3 36.97 40.07 Operation: Rotate 90 Degrees
x86-64-v3: The test quit with a non-zero exit status.
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.36 Test: resize x86-64-v4 No v3 or v4 4 8 12 16 20 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 15.51 15.31 Test: resize
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.36 Test: rotate x86-64-v4 No v3 or v4 3 6 9 12 15 SE +/- 0.11, N = 5 SE +/- 0.06, N = 3 10.36 10.19 Test: rotate
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.36 Test: auto-levels x86-64-v4 No v3 or v4 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 13.04 13.01 Test: auto-levels
x86-64-v3: The test quit with a non-zero exit status.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.36 Test: unsharp-mask x86-64-v4 No v3 or v4 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 16.82 16.79 Test: unsharp-mask
x86-64-v3: The test quit with a non-zero exit status.
Git This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands x86-64-v4 x86-64-v3 No v3 or v4 8 16 24 32 40 SE +/- 0.30, N = 3 SE +/- 0.21, N = 3 SE +/- 0.24, N = 3 35.02 34.65 36.06 1. git version 2.43.0
GNU Octave Benchmark This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 8.4.0 x86-64-v4 No v3 or v4 0.9979 1.9958 2.9937 3.9916 4.9895 SE +/- 0.019, N = 5 SE +/- 0.023, N = 5 4.015 4.435
x86-64-v3: The test quit with a non-zero exit status.
GNU Radio GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Five Back to Back FIR Filters x86-64-v4 x86-64-v3 No v3 or v4 160 320 480 640 800 SE +/- 2.35, N = 3 SE +/- 1.19, N = 3 SE +/- 2.35, N = 3 748.6 744.1 618.7 1. x86-64-v4: 3.10.8.0 2. x86-64-v3: 3.10.9.2 3. No v3 or v4: 3.10.9.2
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Signal Source (Cosine) x86-64-v4 x86-64-v3 No v3 or v4 1000 2000 3000 4000 5000 SE +/- 31.74, N = 3 SE +/- 32.43, N = 3 SE +/- 23.82, N = 3 4635.1 3813.4 4535.0 1. x86-64-v4: 3.10.8.0 2. x86-64-v3: 3.10.9.2 3. No v3 or v4: 3.10.9.2
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FIR Filter x86-64-v4 x86-64-v3 No v3 or v4 300 600 900 1200 1500 SE +/- 7.07, N = 3 SE +/- 17.92, N = 3 SE +/- 9.29, N = 3 1353.9 1248.0 1101.5 1. x86-64-v4: 3.10.8.0 2. x86-64-v3: 3.10.9.2 3. No v3 or v4: 3.10.9.2
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: IIR Filter x86-64-v4 x86-64-v3 No v3 or v4 90 180 270 360 450 SE +/- 1.34, N = 3 SE +/- 2.15, N = 3 SE +/- 2.37, N = 3 385.5 388.0 391.9 1. x86-64-v4: 3.10.8.0 2. x86-64-v3: 3.10.9.2 3. No v3 or v4: 3.10.9.2
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FM Deemphasis Filter x86-64-v4 x86-64-v3 No v3 or v4 200 400 600 800 1000 SE +/- 1.37, N = 3 SE +/- 9.07, N = 3 SE +/- 1.91, N = 3 911.5 879.2 641.3 1. x86-64-v4: 3.10.8.0 2. x86-64-v3: 3.10.9.2 3. No v3 or v4: 3.10.9.2
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Hilbert Transform x86-64-v4 x86-64-v3 No v3 or v4 140 280 420 560 700 SE +/- 4.67, N = 3 SE +/- 10.51, N = 3 SE +/- 4.07, N = 3 655.7 648.0 666.1 1. x86-64-v4: 3.10.8.0 2. x86-64-v3: 3.10.9.2 3. No v3 or v4: 3.10.9.2
Java SciMark This test runs the Java version of SciMark 2, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Composite x86-64-v4 x86-64-v3 No v3 or v4 1200 2400 3600 4800 6000 SE +/- 42.70, N = 3 SE +/- 77.80, N = 3 SE +/- 59.78, N = 3 5542.47 5413.22 5396.91
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Monte Carlo x86-64-v4 x86-64-v3 No v3 or v4 500 1000 1500 2000 2500 SE +/- 25.08, N = 3 SE +/- 31.41, N = 3 SE +/- 27.61, N = 3 2206.89 2155.40 2156.28
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Fast Fourier Transform x86-64-v4 x86-64-v3 No v3 or v4 90 180 270 360 450 SE +/- 0.79, N = 3 SE +/- 1.61, N = 3 SE +/- 0.31, N = 3 418.89 417.06 419.23
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Sparse Matrix Multiply x86-64-v4 x86-64-v3 No v3 or v4 800 1600 2400 3200 4000 SE +/- 47.48, N = 3 SE +/- 61.34, N = 3 SE +/- 55.70, N = 3 3781.55 3666.80 3668.67
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Dense LU Matrix Factorization x86-64-v4 x86-64-v3 No v3 or v4 4K 8K 12K 16K 20K SE +/- 141.80, N = 3 SE +/- 296.34, N = 3 SE +/- 217.21, N = 3 18931.45 18453.29 18369.55
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.2 Computational Test: Jacobi Successive Over-Relaxation x86-64-v4 x86-64-v3 No v3 or v4 500 1000 1500 2000 2500 SE +/- 0.30, N = 3 SE +/- 0.30, N = 3 SE +/- 0.61, N = 3 2373.57 2373.57 2370.81
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.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow x86-64-v4 x86-64-v3 No v3 or v4 10 20 30 40 50 SE +/- 0.45, N = 3 SE +/- 0.44, N = 3 SE +/- 0.45, N = 3 44.20 43.91 43.86 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium x86-64-v4 x86-64-v3 No v3 or v4 10 20 30 40 50 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 44.15 44.07 44.05 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast x86-64-v4 x86-64-v3 No v3 or v4 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.51, N = 3 SE +/- 0.49, N = 3 86.48 86.49 85.95 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast x86-64-v4 x86-64-v3 No v3 or v4 20 40 60 80 100 SE +/- 0.35, N = 3 SE +/- 0.41, N = 3 SE +/- 0.10, N = 3 89.69 89.27 89.07 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast x86-64-v4 x86-64-v3 No v3 or v4 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.59, N = 3 SE +/- 0.75, N = 3 92.84 93.31 92.79 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
librsvg RSVG/librsvg is an SVG vector graphics library. This test profile times how long it takes to complete various operations by rsvg-convert. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better librsvg Operation: SVG Files To PNG x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.14, N = 3 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 24.51 24.40 25.37 1. rsvg-convert version 2.57.1
Llamafile Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: llava-v1.5-7b-q4 - Acceleration: CPU x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.09, N = 3 27.27 27.15 27.23
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU x86-64-v4 x86-64-v3 No v3 or v4 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 18.01 18.08 18.09
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.6 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU x86-64-v4 x86-64-v3 No v3 or v4 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 7.64 7.64 7.64
OpenSCAD OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Pistol x86-64-v4 x86-64-v3 No v3 or v4 11 22 33 44 55 SE +/- 0.51, N = 5 SE +/- 0.42, N = 3 SE +/- 0.03, N = 3 46.56 48.44 48.13 1. OpenSCAD version 2021.01
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Retro Car x86-64-v4 x86-64-v3 No v3 or v4 0.5328 1.0656 1.5984 2.1312 2.664 SE +/- 0.023, N = 3 SE +/- 0.005, N = 3 SE +/- 0.032, N = 3 2.304 2.319 2.368 1. OpenSCAD version 2021.01
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Mini-ITX Case x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.23, N = 3 SE +/- 0.32, N = 15 SE +/- 0.10, N = 3 22.01 23.22 22.62 1. OpenSCAD version 2021.01
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Projector Mount Swivel x86-64-v4 x86-64-v3 No v3 or v4 0.8732 1.7464 2.6196 3.4928 4.366 SE +/- 0.018, N = 3 SE +/- 0.046, N = 3 SE +/- 0.029, N = 3 3.801 3.853 3.881 1. OpenSCAD version 2021.01
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Leonardo Phone Case Slim x86-64-v4 x86-64-v3 No v3 or v4 4 8 12 16 20 SE +/- 0.13, N = 15 SE +/- 0.24, N = 15 SE +/- 0.17, N = 3 14.65 15.48 14.73 1. OpenSCAD version 2021.01
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. The system/openssl test profiles relies on benchmarking the system/OS-supplied openssl binary rather than the pts/openssl test profile that uses the locally-built OpenSSL for benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA256 x86-64-v4 x86-64-v3 No v3 or v4 30000M 60000M 90000M 120000M 150000M SE +/- 223309999.04, N = 3 SE +/- 880306408.22, N = 3 SE +/- 299134484.90, N = 3 131972819647 131490753083 129865031843 1. OpenSSL 3.2.0 23 Nov 2023 (Library: OpenSSL 3.2.0 23 Nov 2023)
OpenBenchmarking.org byte/s, More Is Better OpenSSL Algorithm: SHA512 x86-64-v4 x86-64-v3 No v3 or v4 9000M 18000M 27000M 36000M 45000M SE +/- 8726424.95, N = 3 SE +/- 9950638.77, N = 3 SE +/- 20352444.85, N = 3 43303214713 43384654080 42903236637 1. OpenSSL 3.2.0 23 Nov 2023 (Library: OpenSSL 3.2.0 23 Nov 2023)
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/ao/real_time x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 25.04 25.07 25.58
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/scivis/real_time x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 25.57 25.54 25.98
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/pathtracer/real_time x86-64-v4 x86-64-v3 No v3 or v4 40 80 120 160 200 SE +/- 0.94, N = 3 SE +/- 2.15, N = 12 SE +/- 4.02, N = 9 189.67 181.64 173.25
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/ao/real_time x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 26.16 26.35 26.24
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 25.33 25.51 25.52
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 27.34 27.23 27.36
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite x86-64-v4 x86-64-v3 No v3 or v4 400K 800K 1200K 1600K 2000K SE +/- 10273.45, N = 3 SE +/- 24673.82, N = 3 SE +/- 6816.18, N = 10 2021067 2058126 890814
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times x86-64-v4 x86-64-v3 No v3 or v4 130 260 390 520 650 SE +/- 6.49, N = 3 SE +/- 4.50, N = 15 SE +/- 4.12, N = 15 593 578 585
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes x86-64-v4 x86-64-v3 No v3 or v4 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 43.2 43.1 43.1
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile x86-64-v4 x86-64-v3 No v3 or v4 15 30 45 60 75 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 SE +/- 0.20, N = 3 67.7 68.1 68.1
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template x86-64-v4 x86-64-v3 No v3 or v4 5 10 15 20 25 SE +/- 0.23, N = 5 SE +/- 0.23, N = 4 SE +/- 0.27, N = 4 21.7 21.5 21.7
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pickle_pure_python x86-64-v4 x86-64-v3 No v3 or v4 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 180 176 176
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.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded x86-64-v4 x86-64-v3 No v3 or v4 70K 140K 210K 280K 350K SE +/- 998.41, N = 3 SE +/- 807.68, N = 3 SE +/- 866.09, N = 3 316288.2 314870.6 319756.0 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Scala Dotty x86-64-v4 x86-64-v3 No v3 or v4 120 240 360 480 600 SE +/- 7.00, N = 15 SE +/- 8.05, N = 15 SE +/- 8.75, N = 15 552.5 541.3 537.2 MIN: 412.51 / MAX: 774.54 MIN: 408.84 / MAX: 759.72 MIN: 410.89 / MAX: 786.48
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Random Forest x86-64-v4 x86-64-v3 No v3 or v4 100 200 300 400 500 SE +/- 3.17, N = 3 SE +/- 3.61, N = 3 SE +/- 1.31, N = 3 471.0 471.9 469.9 MIN: 420.64 / MAX: 562.51 MIN: 424.93 / MAX: 575.09 MIN: 420.85 / MAX: 583.22
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: ALS Movie Lens x86-64-v4 x86-64-v3 No v3 or v4 1000 2000 3000 4000 5000 SE +/- 19.27, N = 3 SE +/- 21.15, N = 3 SE +/- 14.43, N = 3 4742.2 4768.6 4744.5 MIN: 4711.41 / MAX: 5065.61 MIN: 4715.96 / MAX: 5078.34 MIN: 4694.14 / MAX: 5052.61
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark ALS x86-64-v4 x86-64-v3 No v3 or v4 300 600 900 1200 1500 SE +/- 11.73, N = 3 SE +/- 5.97, N = 3 SE +/- 4.17, N = 3 1237.8 1236.5 1238.4 MIN: 1157.6 / MAX: 1604.65 MIN: 1160.67 / MAX: 1352.57 MIN: 1163.54 / MAX: 1350.42
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark Bayes x86-64-v4 x86-64-v3 No v3 or v4 100 200 300 400 500 SE +/- 2.63, N = 3 SE +/- 4.69, N = 3 SE +/- 5.05, N = 3 431.5 437.2 440.3 MIN: 284.29 / MAX: 736.97 MIN: 284.03 / MAX: 758.35 MIN: 280.79 / MAX: 900.41
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers such as Mozilla Firefox and Google Chrome. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Firefox x86-64-v4 x86-64-v3 No v3 or v4 110 220 330 440 550 SE +/- 2.51, N = 3 SE +/- 0.72, N = 3 SE +/- 2.47, N = 3 487.5 494.3 494.6 1. firefox 122.0
OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Firefox x86-64-v4 x86-64-v3 No v3 or v4 50 100 150 200 250 SE +/- 0.51, N = 3 SE +/- 1.89, N = 7 SE +/- 1.26, N = 3 217.30 215.81 215.57 1. firefox 122.0
OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Firefox x86-64-v4 x86-64-v3 No v3 or v4 70 140 210 280 350 SE +/- 3.71, N = 3 SE +/- 2.31, N = 3 SE +/- 1.76, N = 3 329 325 320 1. firefox 122.0
OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox x86-64-v4 x86-64-v3 No v3 or v4 500 1000 1500 2000 2500 SE +/- 2.65, N = 3 SE +/- 5.29, N = 3 SE +/- 4.67, N = 3 2351 2352 2369 1. firefox 122.0
OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Firefox x86-64-v4 x86-64-v3 No v3 or v4 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 26.9 27.0 26.9 1. firefox 122.0
OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Firefox x86-64-v4 x86-64-v3 No v3 or v4 60 120 180 240 300 SE +/- 1.15, N = 3 SE +/- 1.82, N = 3 SE +/- 2.71, N = 3 266.2 271.5 269.0 1. firefox 122.0
Speedb Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Read x86-64-v4 x86-64-v3 No v3 or v4 110M 220M 330M 440M 550M SE +/- 1462091.01, N = 3 SE +/- 1013031.83, N = 3 SE +/- 2314109.65, N = 3 529243821 531958100 522454918 -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Update Random x86-64-v4 x86-64-v3 No v3 or v4 110K 220K 330K 440K 550K SE +/- 609.26, N = 3 SE +/- 919.18, N = 3 SE +/- 581.82, N = 3 501800 499920 508411 -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read While Writing x86-64-v4 x86-64-v3 No v3 or v4 3M 6M 9M 12M 15M SE +/- 161851.06, N = 15 SE +/- 146340.80, N = 7 SE +/- 220748.83, N = 3 15742769 16312709 15767159 -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read Random Write Random x86-64-v4 x86-64-v3 No v3 or v4 500K 1000K 1500K 2000K 2500K SE +/- 8901.05, N = 3 SE +/- 14198.75, N = 3 SE +/- 8007.45, N = 3 2515862 2515641 2479906 -lpthread 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 15 Total Time x86-64-v4 x86-64-v3 No v3 or v4 70M 140M 210M 280M 350M SE +/- 6087385.83, N = 15 SE +/- 5719513.31, N = 12 SE +/- 7030584.39, N = 15 316348838 310805004 312914005 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
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.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 4K x86-64-v4 x86-64-v3 No v3 or v4 3 6 9 12 15 SE +/- 0.128, N = 3 SE +/- 0.020, N = 3 SE +/- 0.040, N = 3 9.907 9.942 9.877
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 4K x86-64-v4 x86-64-v3 No v3 or v4 20 40 60 80 100 SE +/- 0.69, N = 3 SE +/- 0.50, N = 3 SE +/- 0.38, N = 3 102.13 104.08 103.39
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 4K x86-64-v4 x86-64-v3 No v3 or v4 50 100 150 200 250 SE +/- 3.01, N = 4 SE +/- 2.11, N = 3 SE +/- 1.46, N = 3 245.07 238.57 247.27
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 4K x86-64-v4 x86-64-v3 No v3 or v4 50 100 150 200 250 SE +/- 1.73, N = 12 SE +/- 2.49, N = 5 SE +/- 2.89, N = 3 242.35 236.44 235.26
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: VGG-16 x86-64-v4 x86-64-v3 No v3 or v4 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 12.08 12.16 12.23
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: VGG-16 x86-64-v4 x86-64-v3 No v3 or v4 16 32 48 64 80 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 72.52 72.45 72.40
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 1 - Model: ResNet-50 x86-64-v4 x86-64-v3 No v3 or v4 1.0778 2.1556 3.2334 4.3112 5.389 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 4.74 4.79 4.77
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 512 - Model: ResNet-50 x86-64-v4 x86-64-v3 No v3 or v4 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 132.30 132.42 132.32
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.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow x86-64-v4 x86-64-v3 No v3 or v4 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 31.34 31.53 31.44
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium x86-64-v4 x86-64-v3 No v3 or v4 8 16 24 32 40 SE +/- 0.17, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 35.11 35.21 35.10
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast x86-64-v4 x86-64-v3 No v3 or v4 16 32 48 64 80 SE +/- 0.09, N = 3 SE +/- 0.21, N = 3 SE +/- 0.18, N = 3 69.74 70.49 70.22
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast x86-64-v4 x86-64-v3 No v3 or v4 16 32 48 64 80 SE +/- 0.21, N = 3 SE +/- 0.27, N = 3 SE +/- 0.15, N = 3 70.52 71.20 71.04
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast x86-64-v4 x86-64-v3 No v3 or v4 16 32 48 64 80 SE +/- 0.14, N = 3 SE +/- 0.23, N = 3 SE +/- 0.09, N = 3 72.72 73.40 72.90
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.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast x86-64-v4 x86-64-v3 No v3 or v4 3 6 9 12 15 SE +/- 0.048, N = 3 SE +/- 0.006, N = 3 SE +/- 0.035, N = 3 9.234 9.269 9.292 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster x86-64-v4 x86-64-v3 No v3 or v4 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 16.24 16.23 16.41 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
WireGuard + Linux Networking Stack Stress Test This is a benchmark of the WireGuard secure VPN tunnel and Linux networking stack stress test. The test runs on the local host but does require root permissions to run. The way it works is it creates three namespaces. ns0 has a loopback device. ns1 and ns2 each have wireguard devices. Those two wireguard devices send traffic through the loopback device of ns0. The end result of this is that tests wind up testing encryption and decryption at the same time -- a pretty CPU and scheduler-heavy workflow. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test x86-64-v4 x86-64-v3 No v3 or v4 50 100 150 200 250 SE +/- 2.53, N = 4 SE +/- 0.69, N = 3 SE +/- 0.30, N = 3 226.94 223.44 224.41
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.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K x86-64-v4 x86-64-v3 No v3 or v4 8 16 24 32 40 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 35.27 35.55 35.18 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
OpenBenchmarking.org Seconds, Fewer Is Better Z3 Theorem Prover 4.12.1 SMT File: 2.smt2 x86-64-v4 x86-64-v3 No v3 or v4 11 22 33 44 55 SE +/- 0.35, N = 3 SE +/- 0.48, N = 3 SE +/- 0.14, N = 3 49.46 48.64 48.13 1. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Compression Speed x86-64-v4 x86-64-v3 No v3 or v4 2K 4K 6K 8K 10K SE +/- 131.14, N = 15 SE +/- 120.71, N = 15 SE +/- 116.38, N = 15 9635.5 9847.8 10052.0 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Decompression Speed x86-64-v4 x86-64-v3 No v3 or v4 1200 2400 3600 4800 6000 SE +/- 24.67, N = 15 SE +/- 14.73, N = 15 SE +/- 16.81, N = 15 5712.1 5653.0 5740.2 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Compression Speed x86-64-v4 x86-64-v3 No v3 or v4 1300 2600 3900 5200 6500 SE +/- 18.22, N = 3 SE +/- 21.70, N = 3 SE +/- 43.49, N = 3 6109.8 6154.3 6220.8 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed x86-64-v4 x86-64-v3 No v3 or v4 1300 2600 3900 5200 6500 SE +/- 61.98, N = 3 SE +/- 38.44, N = 3 SE +/- 6.32, N = 3 5979.5 6035.4 5966.2 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Compression Speed x86-64-v4 x86-64-v3 No v3 or v4 30 60 90 120 150 SE +/- 1.11, N = 8 SE +/- 1.38, N = 5 SE +/- 1.01, N = 15 131.6 132.8 135.3 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed x86-64-v4 x86-64-v3 No v3 or v4 1100 2200 3300 4400 5500 SE +/- 32.81, N = 8 SE +/- 48.89, N = 5 SE +/- 19.12, N = 15 4977.0 4977.7 4882.5 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Compression Speed x86-64-v4 x86-64-v3 No v3 or v4 200 400 600 800 1000 SE +/- 2.12, N = 3 SE +/- 3.79, N = 3 SE +/- 7.81, N = 3 995.9 996.9 982.6 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Decompression Speed x86-64-v4 x86-64-v3 No v3 or v4 1300 2600 3900 5200 6500 SE +/- 27.37, N = 3 SE +/- 78.07, N = 3 SE +/- 14.50, N = 3 6137.1 6132.1 6024.0 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Compression Speed x86-64-v4 x86-64-v3 No v3 or v4 200 400 600 800 1000 SE +/- 0.41, N = 3 SE +/- 2.54, N = 3 SE +/- 0.36, N = 3 1086.6 1088.1 1089.9 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed x86-64-v4 x86-64-v3 No v3 or v4 1400 2800 4200 5600 7000 SE +/- 27.09, N = 3 SE +/- 9.19, N = 3 SE +/- 42.31, N = 3 6368.4 6284.1 6298.1 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed x86-64-v4 x86-64-v3 No v3 or v4 14 28 42 56 70 SE +/- 0.50, N = 15 SE +/- 0.42, N = 3 SE +/- 0.84, N = 3 62.5 64.8 63.4 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed x86-64-v4 x86-64-v3 No v3 or v4 1100 2200 3300 4400 5500 SE +/- 10.69, N = 15 SE +/- 11.53, N = 3 SE +/- 21.31, N = 3 4903.2 4833.7 4843.2 1. *** Zstandard CLI (64-bit) v1.5.5, by Yann Collet ***
x86-64-v4 Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 5.19GHz (96 Cores / 192 Threads), Motherboard: HP Z6 G5 A Workstation 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 8 x 16GB DDR5-5200MT/s Hynix HMCG78AGBRA190N, 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: CachyOS rolling, Kernel: 6.7.2-2-cachyos (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20240118 + Clang 16.0.6 + LLVM 16.0.6, File-System: xfs, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,objc,obj-c++ --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnuProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Java Notes: OpenJDK Runtime Environment (build 11.0.22+7)Python Notes: Python 3.11.7Security 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 31 January 2024 01:37 by user phoronix.
x86-64-v3 Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 5.19GHz (96 Cores / 192 Threads), Motherboard: HP Z6 G5 A Workstation 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 8 x 16GB DDR5-5200MT/s Hynix HMCG78AGBRA190N, 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: CachyOS rolling, Kernel: 6.7.2-2-cachyos (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20231026 + Clang 16.0.6 + LLVM 16.0.6, File-System: xfs, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,m2,objc,obj-c++ --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnuProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Java Notes: OpenJDK Runtime Environment (build 11.0.22+7)Python Notes: Python 3.11.7Security 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 31 January 2024 22:18 by user phoronix.
No v3 or v4 Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 5.19GHz (96 Cores / 192 Threads), Motherboard: HP Z6 G5 A Workstation 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 8 x 16GB DDR5-5200MT/s Hynix HMCG78AGBRA190N, 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: CachyOS rolling, Kernel: 6.7.2-1-cachyos (x86_64), Desktop: GNOME Shell 45.3, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 545.29.06, OpenGL: 4.6.0, Compiler: GCC 13.2.1 20230801 + Clang 16.0.6 + LLVM 16.0.6, File-System: xfs, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --disable-libssp --disable-libstdcxx-pch --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet=auto --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=ada,c,c++,d,fortran,go,lto,m2,objc,obj-c++ --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-build-config=bootstrap-lto --with-linker-hash-style=gnuProcessor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105Java Notes: OpenJDK Runtime Environment (build 11.0.22+7)Python Notes: Python 3.11.7Security 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 1 February 2024 12:53 by user phoronix.