Ryzen 9 3900XT Ubuntu 20.04 LTS vs. Ubuntu 20.10
Benchmarks by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2010126-FI-2010058FI68&grt.
7-Zip Compression
Compress Speed Test
Algebraic Multi-Grid Benchmark
AOBench
Size: 2048 x 2048 - Total Time
AOM AV1
Encoder Mode: Speed 0 Two-Pass
AOM AV1
Encoder Mode: Speed 4 Two-Pass
AOM AV1
Encoder Mode: Speed 6 Realtime
AOM AV1
Encoder Mode: Speed 6 Two-Pass
AOM AV1
Encoder Mode: Speed 8 Realtime
Apache Benchmark
Static Web Page Serving
Apache CouchDB
Bulk Size: 100 - Inserts: 1000 - Rounds: 24
Apache Siege
Concurrent Users: 10
Apache Siege
Concurrent Users: 50
Apache Siege
Concurrent Users: 100
Apache Siege
Concurrent Users: 200
Apache Siege
Concurrent Users: 250
Appleseed
Scene: Emily
Appleseed
Scene: Disney Material
Appleseed
Scene: Material Tester
ASKAP
Test: tConvolve MT - Gridding
ASKAP
Test: tConvolve MT - Degridding
ASKAP
Test: tConvolve MPI - Gridding
ASKAP
Test: tConvolve MPI - Degridding
ASKAP
Test: tConvolve OpenMP - Gridding
ASKAP
Test: tConvolve OpenMP - Degridding
asmFish
1024 Hash Memory, 26 Depth
ASTC Encoder
Preset: Fast
ASTC Encoder
Preset: Medium
ASTC Encoder
Preset: Thorough
ASTC Encoder
Preset: Exhaustive
Basemark GPU
Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: High
Basemark GPU
Renderer: Vulkan - Resolution: 2560 x 1440 - Graphics Preset: High
Basemark GPU
Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: High
Basemark GPU
Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Medium
Basemark GPU
Renderer: Vulkan - Resolution: 2560 x 1440 - Graphics Preset: Medium
Basemark GPU
Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: Medium
Basis Universal
Settings: ETC1S
Basis Universal
Settings: UASTC Level 0
Basis Universal
Settings: UASTC Level 2
Basis Universal
Settings: UASTC Level 3
Basis Universal
Settings: UASTC Level 2 + RDO Post-Processing
Bork File Encrypter
File Encryption Time
Botan
Test: KASUMI
Botan
Test: AES-256
Botan
Test: Twofish
Botan
Test: Blowfish
Botan
Test: CAST-256
BRL-CAD
VGR Performance Metric
Build2
Time To Compile
Bullet Physics Engine
Test: Raytests
Bullet Physics Engine
Test: 3000 Fall
Bullet Physics Engine
Test: 1000 Stack
Bullet Physics Engine
Test: 1000 Convex
Bullet Physics Engine
Test: 136 Ragdolls
Bullet Physics Engine
Test: Prim Trimesh
Bullet Physics Engine
Test: Convex Trimesh
BYTE Unix Benchmark
Computational Test: Dhrystone 2
C-Blosc
Compressor: blosclz
C-Ray
Total Time - 4K, 16 Rays Per Pixel
CacheBench
Test: Read
CacheBench
Test: Write
CacheBench
Test: Read / Modify / Write
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 100
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 200
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 100
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 200
Chaos Group V-RAY
Mode: CPU
CLOMP
Static OMP Speedup
CloverLeaf
Lagrangian-Eulerian Hydrodynamics
Compile Bench
Test: Compile
Compile Bench
Test: Initial Create
Compile Bench
Test: Read Compiled Tree
Coremark
CoreMark Size 666 - Iterations Per Second
CP2K Molecular Dynamics
Fayalite-FIST Data
Crafty
Elapsed Time
ctx_clock
Context Switch Time
Cython benchmark
DaCapo Benchmark
Java Test: H2
DaCapo Benchmark
Java Test: Jython
DaCapo Benchmark
Java Test: Tradesoap
DaCapo Benchmark
Java Test: Tradebeans
Darktable
Test: Boat - Acceleration: CPU-only
Darktable
Test: Masskrug - Acceleration: CPU-only
Darktable
Test: Server Rack - Acceleration: CPU-only
Darktable
Test: Server Room - Acceleration: CPU-only
Darktable
Test: Boat - Acceleration: CPU-only
Darktable
Test: Masskrug - Acceleration: CPU-only
Darktable
Test: Server Rack - Acceleration: CPU-only
Darktable
Test: Server Room - Acceleration: CPU-only
dav1d
Video Input: Chimera 1080p
dav1d
Video Input: Summer Nature 4K
dav1d
Video Input: Summer Nature 1080p
dav1d
Video Input: Chimera 1080p 10-bit
DeepSpeech
Acceleration: CPU
Dolfyn
Computational Fluid Dynamics
ebizzy
Embree
Binary: Pathtracer - Model: Crown
Embree
Binary: Pathtracer ISPC - Model: Crown
Embree
Binary: Pathtracer - Model: Asian Dragon
Embree
Binary: Pathtracer - Model: Asian Dragon Obj
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
ET: Legacy
Renderer: Renderer2 - Resolution: 3840 x 2160
FFTE
N=256, 3D Complex FFT Routine
FFTW
Build: Stock - Size: 2D FFT Size 4096
FFTW
Build: Float + SSE - Size: 2D FFT Size 4096
FLAC Audio Encoding
WAV To FLAC
FS-Mark
Test: 1000 Files, 1MB Size
FS-Mark
Test: 5000 Files, 1MB Size, 4 Threads
FS-Mark
Test: 4000 Files, 32 Sub Dirs, 1MB Size
G'MIC
Test: Plotting Isosurface Of A 3D Volume, 1000 Times
G'MIC
Test: 3D Elevated Function In Random Colors, 100 Times
GIMP
Test: resize
GIMP
Test: rotate
GIMP
Test: auto-levels
GIMP
Test: unsharp-mask
Git
Time To Complete Common Git Commands
glibc bench
Benchmark: cos
glibc bench
Benchmark: exp
glibc bench
Benchmark: ffs
glibc bench
Benchmark: sin
glibc bench
Benchmark: log2
glibc bench
Benchmark: modf
glibc bench
Benchmark: sinh
glibc bench
Benchmark: sqrt
glibc bench
Benchmark: tanh
glibc bench
Benchmark: asinh
glibc bench
Benchmark: atanh
glibc bench
Benchmark: ffsll
glibc bench
Benchmark: sincos
glibc bench
Benchmark: pthread_once
GLmark2
Resolution: 1920 x 1080
GLmark2
Resolution: 2560 x 1440
GLmark2
Resolution: 3840 x 2160
GNU Octave Benchmark
GnuPG
2GB File Encryption
Go Benchmarks
Test: http
Go Benchmarks
Test: json
Go Benchmarks
Test: build
Go Benchmarks
Test: garbage
GPAW
Input: Carbon Nanotube
GraphicsMagick
Operation: Swirl
GraphicsMagick
Operation: Rotate
GraphicsMagick
Operation: Sharpen
GraphicsMagick
Operation: Enhanced
GraphicsMagick
Operation: Resizing
GraphicsMagick
Operation: Noise-Gaussian
GraphicsMagick
Operation: HWB Color Space
GROMACS
Water Benchmark
Gzip Compression
Linux Source Tree Archiving To .tar.gz
Hackbench
Count: 1 - Type: Thread
Hackbench
Count: 2 - Type: Thread
Hackbench
Count: 4 - Type: Thread
Hackbench
Count: 8 - Type: Thread
Hackbench
Count: 1 - Type: Process
Hackbench
Count: 16 - Type: Thread
Hackbench
Count: 2 - Type: Process
Hackbench
Count: 4 - Type: Process
Hackbench
Count: 8 - Type: Process
Hackbench
Count: 16 - Type: Process
Hackbench
Count: 32 - Type: Process
Hierarchical INTegration
Test: FLOAT
High Performance Conjugate Gradient
Himeno Benchmark
Poisson Pressure Solver
Hugin
Panorama Photo Assistant + Stitching Time
Incompact3D
Input: Cylinder
InfluxDB
Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000
InfluxDB
Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000
InfluxDB
Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000
Inkscape
Operation: SVG Files To PNG
Intel Open Image Denoise
Scene: Memorial
IOR
Write Test
IOR
Read Test
Java 2D Microbenchmark
Rendering Test: Text Rendering
Java 2D Microbenchmark
Rendering Test: Image Rendering
Java 2D Microbenchmark
Rendering Test: All Rendering Tests
Java 2D Microbenchmark
Rendering Test: Vector Graphics Rendering
Java Gradle Build
Gradle Build: Reactor
Java SciMark
Computational Test: Composite
Java SciMark
Computational Test: Monte Carlo
Java SciMark
Computational Test: Fast Fourier Transform
Java SciMark
Computational Test: Sparse Matrix Multiply
Java SciMark
Computational Test: Dense LU Matrix Factorization
Java SciMark
Computational Test: Jacobi Successive Over-Relaxation
John The Ripper
Test: Blowfish
John The Ripper
Test: MD5
KeyDB
LAME MP3 Encoding
WAV To MP3
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
LevelDB
Benchmark: Hot Read
LevelDB
Benchmark: Fill Sync
LevelDB
Benchmark: Fill Sync
LevelDB
Benchmark: Overwrite
LevelDB
Benchmark: Overwrite
LevelDB
Benchmark: Random Fill
LevelDB
Benchmark: Random Fill
LevelDB
Benchmark: Random Read
LevelDB
Benchmark: Seek Random
LevelDB
Benchmark: Random Delete
LevelDB
Benchmark: Sequential Fill
LevelDB
Benchmark: Sequential Fill
libavif avifenc
Encoder Speed: 0
libavif avifenc
Encoder Speed: 2
libavif avifenc
Encoder Speed: 8
libavif avifenc
Encoder Speed: 10
libjpeg-turbo tjbench
Test: Decompression Throughput
LibRaw
Post-Processing Benchmark
LibreOffice
Test: 20 Documents To PDF
librsvg
Operation: SVG Files To PNG
LuaJIT
Test: Composite
LuaJIT
Test: Monte Carlo
LuaJIT
Test: Fast Fourier Transform
LuaJIT
Test: Sparse Matrix Multiply
LuaJIT
Test: Dense LU Matrix Factorization
LuaJIT
Test: Jacobi Successive Over-Relaxation
LuxCoreRender
Scene: DLSC
LuxCoreRender
Scene: Rainbow Colors and Prism
m-queens
Time To Solve
Memtier_benchmark
Protocol: Redis
miniFE
Problem Size: Small
Minion
Benchmark: Graceful
Minion
Benchmark: Solitaire
Minion
Benchmark: Quasigroup
Mlpack Benchmark
Benchmark: scikit_ica
Mlpack Benchmark
Benchmark: scikit_qda
Mlpack Benchmark
Benchmark: scikit_svm
Mlpack Benchmark
Benchmark: scikit_linearridgeregression
Mobile Neural Network
Model: SqueezeNetV1.0
Mobile Neural Network
Model: resnet-v2-50
Mobile Neural Network
Model: MobileNetV2_224
Mobile Neural Network
Model: mobilenet-v1-1.0
Mobile Neural Network
Model: inception-v3
Montage Astronomical Image Mosaic Engine
Mosaic of M17, K band, 1.5 deg x 1.5 deg
Monte Carlo Simulations of Ionised Nebulae
Input: Dust 2D tau100.0
MPV
Video Input: Big Buck Bunny Sunflower 4K - Decode: Software Only
MPV
Video Input: Big Buck Bunny Sunflower 1080p - Decode: Software Only
N-Queens
Elapsed Time
NAMD
ATPase Simulation - 327,506 Atoms
NeatBench
Acceleration: CPU
Nebular Empirical Analysis Tool
Nettle
Test: aes256
Nettle
Test: chacha
Nettle
Test: sha512
Nettle
Test: poly1305-aes
NGINX Benchmark
Static Web Page Serving
Numpy Benchmark
OCRMyPDF
Processing 60 Page PDF Document
OCRMyPDF
Processing 60 Page PDF Document
Ogg Encoding
WAV To Ogg
oneDNN
Harness: IP Batch 1D - Data Type: f32 - Engine: CPU
oneDNN
Harness: IP Batch All - Data Type: f32 - Engine: CPU
oneDNN
Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
OpenSSL
RSA 4096-bit Performance
OpenVKL
Benchmark: vklBenchmark
OSPray
Demo: San Miguel - Renderer: SciVis
OSPray
Demo: XFrog Forest - Renderer: SciVis
OSPray
Demo: San Miguel - Renderer: Path Tracer
OSPray
Demo: NASA Streamlines - Renderer: SciVis
OSPray
Demo: XFrog Forest - Renderer: Path Tracer
OSPray
Demo: Magnetic Reconnection - Renderer: SciVis
OSPray
Demo: NASA Streamlines - Renderer: Path Tracer
OSPray
Demo: Magnetic Reconnection - Renderer: Path Tracer
ParaView
Test: Many Spheres - Resolution: 1920 x 1080
ParaView
Test: Many Spheres - Resolution: 1920 x 1080
ParaView
Test: Wavelet Volume - Resolution: 1920 x 1080
ParaView
Test: Wavelet Volume - Resolution: 1920 x 1080
ParaView
Test: Wavelet Contour - Resolution: 1920 x 1080
ParaView
Test: Wavelet Contour - Resolution: 1920 x 1080
Perl Benchmarks
Test: Pod2html
Perl Benchmarks
Test: Interpreter
PHPBench
PHP Benchmark Suite
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU
PolyBench-C
Test: Covariance Computation
PolyBench-C
Test: Correlation Computation
PolyBench-C
Test: 3 Matrix Multiplications
Polyhedron Fortran Benchmarks
Benchmark: ac
Polyhedron Fortran Benchmarks
Benchmark: air
Polyhedron Fortran Benchmarks
Benchmark: mdbx
Polyhedron Fortran Benchmarks
Benchmark: doduc
Polyhedron Fortran Benchmarks
Benchmark: linpk
Polyhedron Fortran Benchmarks
Benchmark: tfft2
Polyhedron Fortran Benchmarks
Benchmark: aermod
Polyhedron Fortran Benchmarks
Benchmark: rnflow
Polyhedron Fortran Benchmarks
Benchmark: induct2
Polyhedron Fortran Benchmarks
Benchmark: protein
Polyhedron Fortran Benchmarks
Benchmark: capacita
Polyhedron Fortran Benchmarks
Benchmark: channel2
Polyhedron Fortran Benchmarks
Benchmark: fatigue2
Polyhedron Fortran Benchmarks
Benchmark: gas_dyn2
Polyhedron Fortran Benchmarks
Benchmark: test_fpu2
Polyhedron Fortran Benchmarks
Benchmark: mp_prop_design
POV-Ray
Trace Time
Primesieve
1e12 Prime Number Generation
PyBench
Total For Average Test Times
PyPerformance
Benchmark: go
PyPerformance
Benchmark: 2to3
PyPerformance
Benchmark: chaos
PyPerformance
Benchmark: float
PyPerformance
Benchmark: nbody
PyPerformance
Benchmark: pathlib
PyPerformance
Benchmark: raytrace
PyPerformance
Benchmark: json_loads
PyPerformance
Benchmark: crypto_pyaes
PyPerformance
Benchmark: regex_compile
PyPerformance
Benchmark: python_startup
PyPerformance
Benchmark: django_template
PyPerformance
Benchmark: pickle_pure_python
Radiance Benchmark
Test: Serial
Radiance Benchmark
Test: SMP Parallel
RawTherapee
Total Benchmark Time
RealSR-NCNN
Scale: 4x - TAA: No
Redis
Test: LPOP
Redis
Test: SADD
Redis
Test: LPUSH
Redis
Test: GET
Redis
Test: SET
RNNoise
Scikit-Learn
SciMark
Computational Test: Composite
SciMark
Computational Test: Monte Carlo
SciMark
Computational Test: Fast Fourier Transform
SciMark
Computational Test: Sparse Matrix Multiply
SciMark
Computational Test: Dense LU Matrix Factorization
SciMark
Computational Test: Jacobi Successive Over-Relaxation
Selenium
Benchmark: ARES-6 - Browser: Firefox
Selenium
Benchmark: Kraken - Browser: Firefox
Selenium
Benchmark: Octane - Browser: Firefox
Selenium
Benchmark: WebXPRT - Browser: Firefox
Selenium
Benchmark: Basemark - Browser: Firefox
Selenium
Benchmark: Jetstream - Browser: Firefox
Selenium
Benchmark: CanvasMark - Browser: Firefox
Selenium
Benchmark: MotionMark - Browser: Firefox
Selenium
Benchmark: StyleBench - Browser: Firefox
Selenium
Benchmark: Jetstream 2 - Browser: Firefox
Selenium
Benchmark: Maze Solver - Browser: Firefox
Selenium
Benchmark: Speedometer - Browser: Firefox
Selenium
Benchmark: PSPDFKit WASM - Browser: Firefox
Selenium
Benchmark: WASM imageConvolute - Browser: Firefox
Selenium
Benchmark: WASM collisionDetection - Browser: Firefox
Smallpt
Global Illumination Renderer; 128 Samples
SQLite
Threads / Copies: 1
SQLite Speedtest
Timed Time - Size 1,000
Stockfish
Total Time
Sudokut
Total Time
SVT-AV1
Encoder Mode: Enc Mode 0 - Input: 1080p
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
SVT-HEVC
1080p 8-bit YUV To HEVC Video Encode
SVT-VP9
Tuning: VMAF Optimized - Input: Bosphorus 1080p
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 1080p
Systemd Total Boot Time
Test: Total
Systemd Total Boot Time
Test: Kernel
Systemd Total Boot Time
Test: Loader
Systemd Total Boot Time
Test: Firmware
Systemd Total Boot Time
Test: Userspace
TensorFlow Lite
Model: SqueezeNet
TensorFlow Lite
Model: Inception V4
TensorFlow Lite
Model: NASNet Mobile
TensorFlow Lite
Model: Mobilenet Float
TensorFlow Lite
Model: Mobilenet Quant
TensorFlow Lite
Model: Inception ResNet V2
Tesseract
Resolution: 1920 x 1080
Tesseract
Resolution: 2560 x 1440
Tesseract
Resolution: 3840 x 2160
Tesseract OCR
Time To OCR 7 Images
Timed Apache Compilation
Time To Compile
Timed FFmpeg Compilation
Time To Compile
Timed HMMer Search
Pfam Database Search
Timed ImageMagick Compilation
Time To Compile
Timed Linux Kernel Compilation
Time To Compile
Timed MAFFT Alignment
Multiple Sequence Alignment - LSU RNA
Timed MrBayes Analysis
Primate Phylogeny Analysis
TNN
Target: CPU - Model: MobileNet v2
TNN
Target: CPU - Model: SqueezeNet v1.1
TSCP
AI Chess Performance
TTSIOD 3D Renderer
Phong Rendering With Soft-Shadow Mapping
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Low - Renderer: OpenGL
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGL
VkFFT
WireGuard + Linux Networking Stack Stress Test
x265
H.265 1080p Video Encoding
Xonotic
Resolution: 3840 x 2160 - Effects Quality: Low
Xonotic
Resolution: 3840 x 2160 - Effects Quality: High
Xonotic
Resolution: 3840 x 2160 - Effects Quality: Ultra
Xonotic
Resolution: 3840 x 2160 - Effects Quality: Ultimate
XZ Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9
YafaRay
Total Time For Sample Scene
Zstd Compression
Compression Level: 3
Zstd Compression
Compression Level: 19
Phoronix Test Suite v10.8.5