Core i9 10900K vs. Ryzen 9 3900X/3950X Linux Benchmarks
Tests fot a future article on Phoronix by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2005283-PTS-BIGCOMPA49&obr_sgm=y&obr_swl=y&sor&grr.
Pennant
Test: sedovbig
NWChem
Input: C240 Buckyball
Pennant
Test: leblancbig
Selenium
Benchmark: Basemark - Browser: Google Chrome
Selenium
Benchmark: Basemark - Browser: Firefox
Selenium
Benchmark: MotionMark - Browser: Firefox
Renaissance
Test: Akka Unbalanced Cobwebbed Tree
Timed GCC Compilation
Time To Compile
Crypto++
Test: All Algorithms
Renaissance
Test: Savina Reactors.IO
Renaissance
Test: Apache Spark Bayes
Numenta Anomaly Benchmark
Detector: EXPoSE
PlaidML
FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU
Basis Universal
Settings: UASTC Level 2 + RDO Post-Processing
Polyhedron Fortran Benchmarks
Benchmark: gas_dyn2
Renaissance
Test: Apache Spark PageRank
Selenium
Benchmark: WebXPRT - Browser: Firefox
Selenium
Benchmark: WebXPRT - Browser: Google Chrome
Renaissance
Test: Random Forest
Polyhedron Fortran Benchmarks
Benchmark: mp_prop_design
Timed LLVM Compilation
Time To Compile
LeelaChessZero
Backend: BLAS
Blender
Blend File: Barbershop - Compute: CPU-Only
Polyhedron Fortran Benchmarks
Benchmark: fatigue2
Java Gradle Build
Gradle Build: Reactor
libgav1
Video Input: Chimera 1080p 10-bit
Crypto++
Test: Keyed Algorithms
Blender
Blend File: Pabellon Barcelona - Compute: CPU-Only
Renaissance
Test: In-Memory Database Shootout
LeelaChessZero
Backend: Eigen
Polyhedron Fortran Benchmarks
Benchmark: test_fpu2
LeelaChessZero
Backend: Random
Core-Latency
Average Latency Between CPU Cores
FFTW
Build: Float + SSE - Size: 2D FFT Size 4096
Facebook RocksDB
Test: Random Fill
PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
Selenium
Benchmark: CanvasMark - Browser: Firefox
Blender
Blend File: Classroom - Compute: CPU-Only
Crypto++
Test: Integer + Elliptic Curve Public Key Algorithms
Unigine Heaven
Resolution: 1920 x 1080 - Mode: Windowed - Renderer: OpenGL
Renaissance
Test: Genetic Algorithm Using Jenetics + Futures
libgav1
Video Input: Chimera 1080p
BRL-CAD
VGR Performance Metric
High Performance Conjugate Gradient
PlaidML
FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU
Selenium
Benchmark: Jetstream 2 - Browser: Firefox
Numpy Benchmark
Algebraic Multi-Grid Benchmark
Hierarchical INTegration
Test: FLOAT
Unigine Valley
Resolution: 1920 x 1080 - Mode: Windowed - Renderer: OpenGL
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Windowed - Quality: Ultra - Renderer: OpenGL
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Windowed - Quality: High - Renderer: OpenGL
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Windowed - Quality: Medium - Renderer: OpenGL
Unigine Superposition
Resolution: 1920 x 1080 - Mode: Windowed - Quality: Low - Renderer: OpenGL
Radiance Benchmark
Test: Serial
FFTW
Build: Stock - Size: 2D FFT Size 4096
Selenium
Benchmark: Jetstream - Browser: Firefox
CacheBench
Test: Read
Selenium
Benchmark: Jetstream - Browser: Google Chrome
asmFish
1024 Hash Memory, 26 Depth
Appleseed
Scene: Emily
CP2K Molecular Dynamics
Fayalite-FIST Data
Hackbench
Count: 32 - Type: Process
Parboil
Test: OpenMP LBM
GROMACS
Water Benchmark
Polyhedron Fortran Benchmarks
Benchmark: rnflow
Blender
Blend File: Fishy Cat - Compute: CPU-Only
Selenium
Benchmark: Jetstream 2 - Browser: Google Chrome
Facebook RocksDB
Test: Random Fill Sync
Polyhedron Fortran Benchmarks
Benchmark: channel2
Facebook RocksDB
Test: Read While Writing
libgav1
Video Input: Summer Nature 4K
PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
Renaissance
Test: Scala Dotty
PlaidML
FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU
CacheBench
Test: Read / Modify / Write
CacheBench
Test: Write
NAS Parallel Benchmarks
Test / Class: BT.C
Selenium
Benchmark: ARES-6 - Browser: Firefox
Numenta Anomaly Benchmark
Detector: Earthgecko Skyline
Mlpack Benchmark
Benchmark: scikit_qda
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
dav1d
Video Input: Chimera 1080p 10-bit
dav1d
Video Input: Chimera 1080p 10-bit
Parboil
Test: OpenMP MRI Gridding
Stress-NG
Test: CPU Cache
Polyhedron Fortran Benchmarks
Benchmark: induct2
Blender
Blend File: BMW27 - Compute: CPU-Only
Fhourstones
Complex Connect-4 Solving
ACES DGEMM
Sustained Floating-Point Rate
Selenium
Benchmark: StyleBench - Browser: Google Chrome
Renaissance
Test: Apache Spark ALS
Appleseed
Scene: Disney Material
Appleseed
Scene: Material Tester
Minion
Benchmark: Quasigroup
YafaRay
Total Time For Sample Scene
Polyhedron Fortran Benchmarks
Benchmark: protein
OpenVKL
Benchmark: vklBenchmark
Timed GDB GNU Debugger Compilation
Time To Compile
GEGL
Operation: Cartoon
Timed Linux Kernel Compilation
Time To Compile
Selenium
Benchmark: Speedometer - Browser: Firefox
Build2
Time To Compile
VP9 libvpx Encoding
Speed: Speed 0
Gzip Compression
Linux Source Tree Archiving To .tar.gz
Zstd Compression
Compression Level: 19
Perl Benchmarks
Test: Pod2html
Stress-NG
Test: Atomic
NAMD
ATPase Simulation - 327,506 Atoms
PyPerformance
Benchmark: raytrace
Timed MrBayes Analysis
Primate Phylogeny Analysis
Crypto++
Test: Unkeyed Algorithms
Stockfish
Total Time
Selenium
Benchmark: CanvasMark - Browser: Google Chrome
ASKAP
Test: tConvolve MT - Degridding
ASKAP
Test: tConvolve MT - Gridding
toyBrot Fractal Generator
Implementation: OpenMP
toyBrot Fractal Generator
Implementation: TBB
toyBrot Fractal Generator
Implementation: C++ Threads
toyBrot Fractal Generator
Implementation: C++ Tasks
Himeno Benchmark
Poisson Pressure Solver
LuxCoreRender
Scene: DLSC
LuxCoreRender
Scene: Rainbow Colors and Prism
IndigoBench
Scene: Bedroom
IndigoBench
Scene: Supercar
John The Ripper
Test: MD5
GraphicsMagick
Operation: Sharpen
GraphicsMagick
Operation: Enhanced
GraphicsMagick
Operation: Noise-Gaussian
Facebook RocksDB
Test: Random Read
GraphicsMagick
Operation: Resizing
GraphicsMagick
Operation: Swirl
GraphicsMagick
Operation: Rotate
GraphicsMagick
Operation: HWB Color Space
Selenium
Benchmark: Speedometer - Browser: Google Chrome
oneDNN MKL-DNN
Harness: IP Batch All - Data Type: f32
oneDNN MKL-DNN
Harness: IP Batch All - Data Type: u8s8f32
Radiance Benchmark
Test: SMP Parallel
Selenium
Benchmark: StyleBench - Browser: Firefox
Tachyon
Total Time
GEGL
Operation: Wavelet Blur
Minion
Benchmark: Solitaire
Polyhedron Fortran Benchmarks
Benchmark: aermod
ASKAP
Test: tConvolve MPI - Degridding
ASKAP
Test: tConvolve MPI - Gridding
Mlpack Benchmark
Benchmark: scikit_ica
RawTherapee
Total Benchmark Time
Perl Benchmarks
Test: Interpreter
Basemark GPU
Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: High
GEGL
Operation: Color Enhance
SQLite Speedtest
Timed Time - Size 1,000
ET: Legacy
Renderer: Renderer2 - Resolution: 3840 x 2160
NAS Parallel Benchmarks
Test / Class: SP.B
Mlpack Benchmark
Benchmark: scikit_linearridgeregression
Sockperf
Test: Throughput
PyPerformance
Benchmark: 2to3
LibreOffice
Test: 20 Documents To PDF
FLAC Audio Encoding
WAV To FLAC
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32
Polyhedron Fortran Benchmarks
Benchmark: mdbx
Git
Time To Complete Common Git Commands
Selenium
Benchmark: ARES-6 - Browser: Google Chrome
Embree
Binary: Pathtracer - Model: Asian Dragon Obj
DeepSpeech
Acceleration: CPU
Basemark GPU
Renderer: OpenGL - Resolution: 3840 x 2160 - Graphics Preset: High
m-queens
Time To Solve
Renaissance
Test: Twitter HTTP Requests
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
Selenium
Benchmark: Octane - Browser: Firefox
Timed PHP Compilation
Time To Compile
Java SciMark
Computational Test: Composite
Cpuminer-Opt
Algorithm: skein
Basis Universal
Settings: ETC1S
PyPerformance
Benchmark: go
C-Ray
Total Time - 4K, 16 Rays Per Pixel
Selenium
Benchmark: Octane - Browser: Google Chrome
NAS Parallel Benchmarks
Test / Class: FT.C
Timed FFmpeg Compilation
Time To Compile
Basis Universal
Settings: UASTC Level 3
Minion
Benchmark: Graceful
libgav1
Video Input: Summer Nature 1080p
Xonotic
Resolution: 3840 x 2160 - Effects Quality: Ultimate
Redis
Test: SET
C-Blosc
Compressor: blosclz
Cython benchmark
oneDNN MKL-DNN
Harness: Recurrent Neural Network Training - Data Type: f32
G'MIC
Test: Plotting Isosurface Of A 3D Volume, 1000 Times
oneDNN MKL-DNN
Harness: Recurrent Neural Network Inference - Data Type: f32
GEGL
Operation: Rotate 90 Degrees
LULESH
Embree
Binary: Pathtracer - Model: Crown
Cpuminer-Opt
Algorithm: m7m
lzbench
Test: XZ 0 - Process: Decompression
lzbench
Test: XZ 0 - Process: Compression
GEGL
Operation: Antialias
Embree
Binary: Pathtracer ISPC - Model: Crown
PyPerformance
Benchmark: django_template
Cpuminer-Opt
Algorithm: deep
ParaView
Test: Many Spheres - Resolution: 3840 x 2160
ParaView
Test: Many Spheres - Resolution: 3840 x 2160
7-Zip Compression
Compress Speed Test
Embree
Binary: Pathtracer - Model: Asian Dragon
Stress-NG
Test: Context Switching
PyPerformance
Benchmark: crypto_pyaes
Polyhedron Fortran Benchmarks
Benchmark: ac
Xonotic
Resolution: 3840 x 2160 - Effects Quality: Ultra
Sockperf
Test: Latency Ping Pong
Tesseract
Resolution: 3840 x 2160
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Cpuminer-Opt
Algorithm: sha256t
Cpuminer-Opt
Algorithm: lbry
PyPerformance
Benchmark: nbody
ASKAP
Test: tConvolve OpenMP - Degridding
ASKAP
Test: tConvolve OpenMP - Gridding
Numenta Anomaly Benchmark
Detector: Bayesian Changepoint
Polyhedron Fortran Benchmarks
Benchmark: air
PyPerformance
Benchmark: float
Polyhedron Fortran Benchmarks
Benchmark: doduc
Stress-NG
Test: CPU Stress
John The Ripper
Test: Blowfish
AOM AV1
Encoder Mode: Speed 0 Two-Pass
Aircrack-ng
Stress-NG
Test: Crypto
Stress-NG
Test: Matrix Math
Stress-NG
Test: Socket Activity
Stress-NG
Test: Vector Math
Xonotic
Resolution: 3840 x 2160 - Effects Quality: High
AOBench
Size: 2048 x 2048 - Total Time
PyPerformance
Benchmark: regex_compile
AOM AV1
Encoder Mode: Speed 6 Realtime
Coremark
CoreMark Size 666 - Iterations Per Second
lzbench
Test: Zstd 8 - Process: Decompression
lzbench
Test: Zstd 8 - Process: Compression
lzbench
Test: Crush 0 - Process: Decompression
lzbench
Test: Crush 0 - Process: Compression
GEGL
Operation: Reflect
Zstd Compression
Compression Level: 3
GEGL
Operation: Tile Glass
Selenium
Benchmark: Kraken - Browser: Firefox
Selenium
Benchmark: Kraken - Browser: Google Chrome
Timed MPlayer Compilation
Time To Compile
PyPerformance
Benchmark: json_loads
Xonotic
Resolution: 3840 x 2160 - Effects Quality: Low
AOM AV1
Encoder Mode: Speed 6 Two-Pass
TTSIOD 3D Renderer
Phong Rendering With Soft-Shadow Mapping
lzbench
Test: Brotli 2 - Process: Decompression
lzbench
Test: Brotli 2 - Process: Compression
XZ Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9
Tungsten Renderer
Scene: Water Caustic
PyPerformance
Benchmark: pickle_pure_python
Xsbench
Timed ImageMagick Compilation
Time To Compile
Botan
Test: AES-256
Mlpack Benchmark
Benchmark: scikit_svm
DaCapo Benchmark
Java Test: Tradebeans
lzbench
Test: Libdeflate 1 - Process: Decompression
lzbench
Test: Libdeflate 1 - Process: Compression
VP9 libvpx Encoding
Speed: Speed 5
Basis Universal
Settings: UASTC Level 2
ebizzy
lzbench
Test: Brotli 0 - Process: Decompression
lzbench
Test: Brotli 0 - Process: Compression
lzbench
Test: Zstd 1 - Process: Decompression
lzbench
Test: Zstd 1 - Process: Compression
Rodinia
Test: OpenMP Streamcluster
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_1d - Data Type: f32
Botan
Test: Blowfish
Botan
Test: Twofish
dav1d
Video Input: Summer Nature 4K
Botan
Test: CAST-256
Botan
Test: KASUMI
OpenSSL
RSA 4096-bit Performance
PyBench
Total For Average Test Times
Facebook RocksDB
Test: Sequential Fill
Timed Apache Compilation
Time To Compile
dav1d
Video Input: Chimera 1080p
Selenium
Benchmark: PSPDFKit WASM - Browser: Firefox
DaCapo Benchmark
Java Test: H2
Rodinia
Test: OpenMP LavaMD
Zstd Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19
dav1d
Video Input: Summer Nature 4K
OSBench
Test: Create Threads
Selenium
Benchmark: Maze Solver - Browser: Firefox
AOM AV1
Encoder Mode: Speed 4 Two-Pass
dav1d
Video Input: Chimera 1080p
Selenium
Benchmark: WASM collisionDetection - Browser: Firefox
Selenium
Benchmark: PSPDFKit WASM - Browser: Google Chrome
Tungsten Renderer
Scene: Hair
Intel Open Image Denoise
Scene: Memorial
Parboil
Test: OpenMP Stencil
Polyhedron Fortran Benchmarks
Benchmark: linpk
Swet
Average
Numenta Anomaly Benchmark
Detector: Relative Entropy
Go Benchmarks
Test: json
NAS Parallel Benchmarks
Test / Class: MG.C
oneDNN MKL-DNN
Harness: IP Batch 1D - Data Type: f32
oneDNN MKL-DNN
Harness: IP Batch 1D - Data Type: u8s8f32
Primesieve
1e12 Prime Number Generation
AOM AV1
Encoder Mode: Speed 8 Realtime
Selenium
Benchmark: Maze Solver - Browser: Google Chrome
Rodinia
Test: OpenMP CFD Solver
GIMP
Test: unsharp-mask
Nebular Empirical Analysis Tool
Selenium
Benchmark: WASM collisionDetection - Browser: Google Chrome
Basemark GPU
Renderer: Vulkan - Resolution: 3840 x 2160 - Graphics Preset: Medium
Bork File Encrypter
File Encryption Time
Redis
Test: GET
GIMP
Test: auto-levels
rays1bench
Large Scene
DaCapo Benchmark
Java Test: Tradesoap
GIMP
Test: rotate
GnuPG
2GB File Encryption
Sysbench
Test: CPU
Selenium
Benchmark: WASM imageConvolute - Browser: Firefox
Go Benchmarks
Test: garbage
x265
H.265 1080p Video Encoding
N-Queens
Elapsed Time
Scikit-Learn
IPC_benchmark
Type: Unnamed Unix Domain Socket - Message Bytes: 4096
NeatBench
Acceleration: CPU
Numenta Anomaly Benchmark
Detector: Windowed Gaussian
GEGL
Operation: Crop
IPC_benchmark
Type: TCP Socket - Message Bytes: 4096
Selenium
Benchmark: WASM imageConvolute - Browser: Google Chrome
Basis Universal
Settings: UASTC Level 0
LAME MP3 Encoding
WAV To MP3
Smallpt
Global Illumination Renderer; 128 Samples
Tungsten Renderer
Scene: Volumetric Caustic
DaCapo Benchmark
Java Test: Jython
GIMP
Test: resize
dav1d
Video Input: Summer Nature 1080p
FFmpeg
H.264 HD To NTSC DV
libjpeg-turbo tjbench
Test: Decompression Throughput
dav1d
Video Input: Summer Nature 1080p
OSBench
Test: Create Files
Tungsten Renderer
Scene: Non-Exponential
OSBench
Test: Memory Allocations
OSBench
Test: Create Processes
OSBench
Test: Launch Programs
GEGL
Operation: Scale
Timed HMMer Search
Pfam Database Search
ParaView
Test: Wavelet Contour - Resolution: 3840 x 2160
ParaView
Test: Wavelet Contour - Resolution: 3840 x 2160
IPC_benchmark
Type: Unnamed Pipe - Message Bytes: 4096
IPC_benchmark
Type: FIFO Named Pipe - Message Bytes: 4096
ParaView
Test: Wavelet Volume - Resolution: 3840 x 2160
ParaView
Test: Wavelet Volume - Resolution: 3840 x 2160
Nettle
Test: aes256
x264
H.264 Video Encoding
Multichase Pointer Chaser
Test: 1GB Array, 256 Byte Stride, 4 Threads
Bullet Physics Engine
Test: Raytests
Multichase Pointer Chaser
Test: 1GB Array, 256 Byte Stride, 2 Threads
Multichase Pointer Chaser
Test: 1GB Array, 256 Byte Stride
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32
Multichase Pointer Chaser
Test: 256MB Array, 256 Byte Stride
oneDNN MKL-DNN
Harness: Deconvolution Batch deconv_3d - Data Type: f32
Multichase Pointer Chaser
Test: 4MB Array, 64 Byte Stride
Parallel BZIP2 Compression
256MB File Compression
Nettle
Test: sha512
Hackbench
Count: 1 - Type: Thread
Hackbench
Count: 1 - Type: Process
Optcarrot
Optimized Benchmark
Parboil
Test: OpenMP CUTCP
TSCP
AI Chess Performance
IOR
Read Test
IOR
Write Test
Nettle
Test: chacha
ctx_clock
Context Switch Time
Nettle
Test: poly1305-aes
BLAKE2
Bullet Physics Engine
Test: Convex Trimesh
Bullet Physics Engine
Test: Prim Trimesh
Bullet Physics Engine
Test: 136 Ragdolls
Bullet Physics Engine
Test: 1000 Convex
Bullet Physics Engine
Test: 1000 Stack
Bullet Physics Engine
Test: 3000 Fall
Java SciMark
Computational Test: Jacobi Successive Over-Relaxation
Java SciMark
Computational Test: Dense LU Matrix Factorization
Java SciMark
Computational Test: Sparse Matrix Multiply
Java SciMark
Computational Test: Fast Fourier Transform
Java SciMark
Computational Test: Monte Carlo
Geometric Mean Of All Test Results
Result Composite - Core i9 10900K vs. Ryzen 9 3900X/3950X Linux Benchmarks
Number Of First Place Finishes
Wins - 381 Tests
Number Of Last Place Finishes
Losses - 381 Tests
Phoronix Test Suite v10.8.5