amd-ryzen-9-5900x-on-linux-ubuntu-2010
Tests for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2011121-FI-AMDRYZEN928&grs&sro.
LULESH
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
QMCPACK
Pennant
Test: leblancbig
Pennant
Test: sedovbig
OSPray
Demo: Magnetic Reconnection - Renderer: Path Tracer
OpenVKL
Benchmark: vklBenchmark
OSPray
Demo: San Miguel - Renderer: SciVis
NCNN
Target: CPU - Model: shufflenet-v2
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
oneDNN MKL-DNN
Harness: IP Batch All - Data Type: u8s8f32
Aircrack-ng
rays1bench
Large Scene
Smallpt
Global Illumination Renderer; 128 Samples
OSPray
Demo: XFrog Forest - Renderer: SciVis
Embree
Binary: Pathtracer - Model: Crown
N-Queens
Elapsed Time
OpenSSL
RSA 4096-bit Performance
John The Ripper
Test: MD5
Chaos Group V-RAY
Mode: CPU
GraphicsMagick
Operation: Sharpen
OSPray
Demo: NASA Streamlines - Renderer: Path Tracer
Tachyon
Total Time
OSPray
Demo: NASA Streamlines - Renderer: SciVis
oneDNN
Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU
Stockfish
Total Time
IndigoBench
Scene: Supercar
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32
IndigoBench
Scene: Bedroom
Embree
Binary: Pathtracer ISPC - Model: Crown
C-Ray
Total Time - 4K, 16 Rays Per Pixel
Blender
Blend File: Barbershop - Compute: CPU-Only
m-queens
Time To Solve
OSPray
Demo: XFrog Forest - Renderer: Path Tracer
Blender
Blend File: Pabellon Barcelona - Compute: CPU-Only
Primesieve
1e12 Prime Number Generation
Blender
Blend File: Classroom - Compute: CPU-Only
GraphicsMagick
Operation: Enhanced
OSPray
Demo: San Miguel - Renderer: Path Tracer
LuxCoreRender
Scene: Rainbow Colors and Prism
LuxCoreRender
Scene: DLSC
Blender
Blend File: Fishy Cat - Compute: CPU-Only
OSPray
Demo: Magnetic Reconnection - Renderer: SciVis
Blender
Blend File: BMW27 - Compute: CPU-Only
GraphicsMagick
Operation: Swirl
SVT-HEVC
1080p 8-bit YUV To HEVC Video Encode
NAMD
ATPase Simulation - 327,506 Atoms
ASTC Encoder
Preset: Exhaustive
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
POV-Ray
Trace Time
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_1d - Data Type: f32
Appleseed
Scene: Disney Material
oneDNN
Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU
ASTC Encoder
Preset: Thorough
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
TensorFlow Lite
Model: Inception ResNet V2
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32
oneDNN
Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU
TensorFlow Lite
Model: Inception V4
oneDNN
Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU
Appleseed
Scene: Emily
GraphicsMagick
Operation: Resizing
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
Timed Linux Kernel Compilation
Time To Compile
YafaRay
Total Time For Sample Scene
Timed MPlayer Compilation
Time To Compile
Basis Universal
Settings: UASTC Level 3
asmFish
1024 Hash Memory, 26 Depth
TensorFlow Lite
Model: SqueezeNet
TensorFlow Lite
Model: Mobilenet Float
TensorFlow Lite
Model: Mobilenet Quant
Numenta Anomaly Benchmark
Detector: Earthgecko Skyline
Numenta Anomaly Benchmark
Detector: Windowed Gaussian
BRL-CAD
VGR Performance Metric
x264
H.264 Video Encoding
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Redis
Test: LPOP
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
Timed FFmpeg Compilation
Time To Compile
Embree
Binary: Pathtracer - Model: Asian Dragon
Basis Universal
Settings: UASTC Level 2
oneDNN MKL-DNN
Harness: IP Batch 1D - Data Type: u8s8f32
Mlpack Benchmark
Benchmark: scikit_linearridgeregression
Numenta Anomaly Benchmark
Detector: Relative Entropy
Embree
Binary: Pathtracer - Model: Asian Dragon Obj
Appleseed
Scene: Material Tester
Intel Open Image Denoise
Scene: Memorial
oneDNN
Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU
Timed LLVM Compilation
Time To Compile
Incompact3D
Input: Cylinder
GraphicsMagick
Operation: Noise-Gaussian
FFmpeg
H.264 HD To NTSC DV
oneDNN
Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_3d - Data Type: f32
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Medium
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Slow
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 1080p
oneDNN MKL-DNN
Harness: Recurrent Neural Network Inference - Data Type: f32
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Very Fast
oneDNN
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
Sunflow Rendering System
Global Illumination + Image Synthesis
oneDNN MKL-DNN
Harness: Recurrent Neural Network Training - Data Type: f32
x265
Video Input: Bosphorus 4K
TTSIOD 3D Renderer
Phong Rendering With Soft-Shadow Mapping
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Ultra Fast
Timed ImageMagick Compilation
Time To Compile
libavif avifenc
Encoder Speed: 0
libavif avifenc
Encoder Speed: 2
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Medium
SVT-VP9
Tuning: VMAF Optimized - Input: Bosphorus 1080p
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Slow
NCNN
Target: CPU-v3-v3 - Model: mobilenet-v3
oneDNN
Harness: IP Batch All - Data Type: f32 - Engine: CPU
GROMACS
Water Benchmark
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p
oneDNN MKL-DNN
Harness: IP Batch All - Data Type: f32
TensorFlow Lite
Model: NASNet Mobile
NCNN
Target: CPU - Model: mnasnet
Mobile Neural Network
Model: SqueezeNetV1.0
NCNN
Target: CPU-v2-v2 - Model: mobilenet-v2
OCRMyPDF
Processing 60 Page PDF Document
G'MIC
Test: 2D Function Plotting, 1000 Times
Timed PHP Compilation
Time To Compile
Nebular Empirical Analysis Tool
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
CP2K Molecular Dynamics
Fayalite-FIST Data
oneDNN
Harness: IP Batch 1D - Data Type: f32 - Engine: CPU
oneDNN MKL-DNN
Harness: IP Batch 1D - Data Type: f32
Selenium
Benchmark: Basemark - Browser: Firefox
Mobile Neural Network
Model: mobilenet-v1-1.0
Numenta Anomaly Benchmark
Detector: Bayesian Changepoint
Mobile Neural Network
Model: MobileNetV2_224
OpenVKL
Benchmark: vklBenchmarkStructuredVolume
ASTC Encoder
Preset: Medium
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Ultra Fast
CloverLeaf
Lagrangian-Eulerian Hydrodynamics
dav1d
Video Input: Summer Nature 4K
Timed GCC Compilation
Time To Compile
ECP-CANDLE
Benchmark: P3B2
NCNN
Target: CPU - Model: efficientnet-b0
OpenVKL
Benchmark: vklBenchmarkVdbVolume
NeatBench
libgav1
Video Input: Chimera 1080p
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Very Fast
GraphicsMagick
Operation: HWB Color Space
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Points2Image
librsvg
Operation: SVG Files To PNG
Mobile Neural Network
Model: inception-v3
Darktable
Test: Masskrug - Acceleration: CPU-only
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
x265
Video Input: Bosphorus 1080p
Timed GDB GNU Debugger Compilation
Time To Compile
dav1d
Video Input: Chimera 1080p
ASTC Encoder
Preset: Fast
libgav1
Video Input: Chimera 1080p 10-bit
NCNN
Target: CPU - Model: googlenet
libavif avifenc
Encoder Speed: 8
Timed MAFFT Alignment
Multiple Sequence Alignment - LSU RNA
dav1d
Video Input: Summer Nature 1080p
libgav1
Video Input: Summer Nature 4K
Selenium
Benchmark: CanvasMark - Browser: Firefox
NCNN
Target: CPU - Model: alexnet
RawTherapee
Total Benchmark Time
DeepSpeech
Acceleration: CPU
GIMP
Test: unsharp-mask
Basis Universal
Settings: UASTC Level 0
Basis Universal
Settings: ETC1S
NCNN
Target: CPU - Model: resnet50
SVT-AV1
Encoder Mode: Enc Mode 0 - Input: 1080p
libavif avifenc
Encoder Speed: 10
LeelaChessZero
Backend: BLAS
Numenta Anomaly Benchmark
Detector: EXPoSE
miniFE
Problem Size: Small
R Benchmark
Tesseract OCR
Time To OCR 7 Images
ECP-CANDLE
Benchmark: P3B1
Scikit-Learn
Darktable
Test: Server Rack - Acceleration: CPU-only
AOM AV1
Encoder Mode: Speed 0 Two-Pass
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Euclidean Cluster
libgav1
Video Input: Summer Nature 1080p
Monte Carlo Simulations of Ionised Nebulae
Input: Dust 2D tau100.0
NCNN
Target: CPU - Model: yolov4-tiny
NCNN
Target: CPU - Model: squeezenet
Timed Apache Compilation
Time To Compile
FFTW
Build: Stock - Size: 2D FFT Size 32
ECP-CANDLE
Benchmark: P1B2
PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
Mobile Neural Network
Model: resnet-v2-50
Darktable
Test: Server Room - Acceleration: CPU-only
Selenium
Benchmark: WebXPRT - Browser: Firefox
Botan
Test: CAST-256
PyPerformance
Benchmark: python_startup
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: NDT Mapping
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 200
LibRaw
Post-Processing Benchmark
FFTW
Build: Float + SSE - Size: 2D FFT Size 32
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 100
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 1000
dav1d
Video Input: Chimera 1080p 10-bit
Himeno Benchmark
Poisson Pressure Solver
Darktable
Test: Boat - Acceleration: CPU-only
GIMP
Test: resize
Mlpack Benchmark
Benchmark: scikit_ica
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 200
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 100
FFTW
Build: Float + SSE - Size: 2D FFT Size 4096
LuaJIT
Test: Jacobi Successive Over-Relaxation
Timed MrBayes Analysis
Primate Phylogeny Analysis
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 1000
VP9 libvpx Encoding
Speed: Speed 5
Selenium
Benchmark: StyleBench - Browser: Firefox
GraphicsMagick
Operation: Rotate
Redis
Test: GET
Hugin
Panorama Photo Assistant + Stitching Time
Timed HMMer Search
Pfam Database Search
LuaJIT
Test: Fast Fourier Transform
Botan
Test: AES-256
AOBench
Size: 2048 x 2048 - Total Time
NCNN
Target: Vulkan GPU - Model: vgg16
GIMP
Test: auto-levels
Selenium
Benchmark: Basemark - Browser: Google Chrome
LuaJIT
Test: Composite
FFTW
Build: Float + SSE - Size: 1D FFT Size 4096
Ogg Encoding
WAV To Ogg
Botan
Test: Twofish
PyPerformance
Benchmark: json_loads
TSCP
AI Chess Performance
Botan
Test: KASUMI
SQLite Speedtest
Timed Time - Size 1,000
FFTW
Build: Float + SSE - Size: 1D FFT Size 32
NCNN
Target: Vulkan GPU - Model: yolov4-tiny
LuaJIT
Test: Dense LU Matrix Factorization
LuaJIT
Test: Monte Carlo
LAME MP3 Encoding
WAV To MP3
WebP Image Encode
Encode Settings: Default
Selenium
Benchmark: MotionMark - Browser: Google Chrome
PyBench
Total For Average Test Times
WebP Image Encode
Encode Settings: Quality 100, Lossless
Mlpack Benchmark
Benchmark: scikit_qda
Swet
Average
GEGL
Operation: Wavelet Blur
LuaJIT
Test: Sparse Matrix Multiply
NCNN
Target: Vulkan GPU - Model: efficientnet-b0
G'MIC
Test: Plotting Isosurface Of A 3D Volume, 1000 Times
Redis
Test: LPUSH
GEGL
Operation: Tile Glass
Selenium
Benchmark: ARES-6 - Browser: Google Chrome
RNNoise
TNN
Target: CPU - Model: SqueezeNet v1.1
FFTW
Build: Stock - Size: 1D FFT Size 4096
PyPerformance
Benchmark: chaos
Numpy Benchmark
Botan
Test: Blowfish
Selenium
Benchmark: WebXPRT - Browser: Google Chrome
NCNN
Target: Vulkan GPU - Model: squeezenet
Radiance Benchmark
Test: Serial
AOM AV1
Encoder Mode: Speed 6 Two-Pass
AOM AV1
Encoder Mode: Speed 4 Two-Pass
FFTW
Build: Stock - Size: 2D FFT Size 4096
GIMP
Test: rotate
NCNN
Target: CPU - Model: resnet18
dcraw
RAW To PPM Image Conversion
VP9 libvpx Encoding
Speed: Speed 0
Crafty
Elapsed Time
libjpeg-turbo tjbench
WebP Image Encode
Encode Settings: Quality 100, Highest Compression
Redis
Test: SET
Redis
Test: SADD
NCNN
Target: Vulkan GPU - Model: mnasnet
BYTE Unix Benchmark
Computational Test: Dhrystone 2
GEGL
Operation: Crop
FFTW
Build: Stock - Size: 1D FFT Size 32
GEGL
Operation: Cartoon
GEGL
Operation: Rotate 90 Degrees
PyPerformance
Benchmark: regex_compile
WebP Image Encode
Encode Settings: Quality 100
NCNN
Target: Vulkan GPU - Model: alexnet
PyPerformance
Benchmark: crypto_pyaes
NCNN
Target: Vulkan GPU - Model: mobilenet
PyPerformance
Benchmark: raytrace
PyPerformance
Benchmark: pathlib
Selenium
Benchmark: Octane - Browser: Google Chrome
Radiance Benchmark
Test: SMP Parallel
Selenium
Benchmark: WASM imageConvolute - Browser: Google Chrome
NCNN
Target: CPU - Model: vgg16
OpenVKL
Benchmark: vklBenchmarkUnstructuredVolume
AOM AV1
Encoder Mode: Speed 6 Realtime
PyPerformance
Benchmark: float
NCNN
Target: Vulkan GPU - Model: shufflenet-v2
Selenium
Benchmark: Jetstream - Browser: Firefox
WebP Image Encode
Encode Settings: Quality 100, Lossless, Highest Compression
Selenium
Benchmark: Octane - Browser: Firefox
Selenium
Benchmark: WASM collisionDetection - Browser: Google Chrome
Selenium
Benchmark: ARES-6 - Browser: Firefox
NCNN
Target: Vulkan GPU - Model: resnet50
PyPerformance
Benchmark: 2to3
PyPerformance
Benchmark: pickle_pure_python
Selenium
Benchmark: WASM collisionDetection - Browser: Firefox
GEGL
Operation: Color Enhance
Selenium
Benchmark: Maze Solver - Browser: Firefox
PyPerformance
Benchmark: nbody
Selenium
Benchmark: StyleBench - Browser: Google Chrome
yquake2
Renderer: OpenGL 1.x - Resolution: 1920 x 1080
PyPerformance
Benchmark: django_template
GEGL
Operation: Antialias
Dolfyn
Computational Fluid Dynamics
Mlpack Benchmark
Benchmark: scikit_svm
Selenium
Benchmark: Kraken - Browser: Google Chrome
TNN
Target: CPU - Model: MobileNet v2
Selenium
Benchmark: Jetstream - Browser: Google Chrome
PyPerformance
Benchmark: go
NCNN
Target: Vulkan GPU - Model: resnet18
Basis Universal
Settings: UASTC Level 2 + RDO Post-Processing
GEGL
Operation: Scale
Selenium
Benchmark: Speedometer - Browser: Firefox
Optcarrot
Optimized Benchmark
Selenium
Benchmark: Jetstream 2 - Browser: Firefox
Selenium
Benchmark: Jetstream 2 - Browser: Google Chrome
G'MIC
Test: 3D Elevated Function In Random Colors, 100 Times
GEGL
Operation: Reflect
NCNN
Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3
Selenium
Benchmark: Speedometer - Browser: Google Chrome
GNU Octave Benchmark
AOM AV1
Encoder Mode: Speed 8 Realtime
NCNN
Target: Vulkan GPU - Model: googlenet
Selenium
Benchmark: Kraken - Browser: Firefox
Selenium
Benchmark: WASM imageConvolute - Browser: Firefox
NCNN
Target: Vulkan GPU - Model: blazeface
yquake2
Renderer: Software CPU - Resolution: 1920 x 1080
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGL
yquake2
Renderer: OpenGL 3.x - Resolution: 1920 x 1080
Unigine Heaven
Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Low - Renderer: OpenGL
Selenium
Benchmark: Maze Solver - Browser: Google Chrome
NWChem
Input: C240 Buckyball
John The Ripper
Test: Blowfish
OpenCV
Test: DNN - Deep Neural Network
Selenium
Benchmark: CanvasMark - Browser: Google Chrome
Selenium
Benchmark: MotionMark - Browser: Firefox
NCNN
Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2
NCNN
Target: CPU - Model: blazeface
NCNN
Target: CPU - Model: mobilenet
LibreOffice
Test: 20 Documents To PDF
eSpeak-NG Speech Engine
Text-To-Speech Synthesis
FLAC Audio Encoding
WAV To FLAC
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
Phoronix Test Suite v10.8.4