AMD Threadripper 3960X vs. Intel Core i9 10980XE
Intel Core i9-10980XE benchmarks against AMD Ryzen Threadripper 3960X. Benchmarks by Michael Larabel on Ubuntu 19.10 Linux.
HTML result view exported from: https://openbenchmarking.org/result/1911270-HU-THREADRIP09&obr_sgm=y&obr_swl=y&sro&grr.
Pennant
Test: sedovbig
Pennant
Test: leblancbig
SPECjbb 2015
SPECjbb2015-Composite critical-jOPS
SPECjbb 2015
SPECjbb2015-Composite max-jOPS
HPC Challenge
Test / Class: G-HPL
Apache Cassandra
Test: Mixed 1:3
CppPerformanceBenchmarks
Test: Random Numbers
Timed GCC Compilation
Time To Compile
MKL-DNN DNNL
Harness: Convolution Batch conv_all - Data Type: f32
libgav1
Video Input: Chimera 1080p 10-bit
QMCPACK
SVT-AV1
Encoder Mode: Enc Mode 0 - Input: 1080p
Apache Cassandra
Test: Reads
PostgreSQL pgbench
Scaling: Buffer Test - Test: Normal Load - Mode: Read Write
MKL-DNN DNNL
Harness: Deconvolution Batch deconv_all - Data Type: f32
Blender
Blend File: Barbershop - Compute: CPU-Only
BRL-CAD
VGR Performance Metric
FFTW
Build: Float + SSE - Size: 2D FFT Size 4096
Memtier_benchmark
Protocol: Redis
CppPerformanceBenchmarks
Test: Math Library
Blender
Blend File: Pabellon Barcelona - Compute: CPU-Only
libgav1
Video Input: Chimera 1080p
Renaissance
Test: Savina Reactors.IO
CP2K Molecular Dynamics
Fayalite-FIST Data
LZMA Compression
256MB File Compression
Tinymembench
Standard Memset
Tinymembench
Standard Memcpy
libgav1
Video Input: Summer Nature 4K
dav1d
Video Input: Chimera 1080p 10-bit
Blender
Blend File: Classroom - Compute: CPU-Only
Minion
Benchmark: Solitaire
Radiance Benchmark
Test: Serial
Selenium
Benchmark: Jetstream - Browser: Firefox
FFTW
Build: Stock - Size: 2D FFT Size 4096
Selenium
Benchmark: Jetstream - Browser: Google Chrome
SQLite
Threads / Copies: 8
LuxCoreRender
Scene: Rainbow Colors and Prism
Hackbench
Count: 32 - Type: Process
Selenium
Benchmark: ARES-6 - Browser: Firefox
asmFish
1024 Hash Memory, 26 Depth
Appleseed
Scene: Emily
MKL-DNN DNNL
Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32
CacheBench
Test: Read / Modify / Write
CacheBench
Test: Write
CacheBench
Test: Read
OSPray
Demo: XFrog Forest - Renderer: SciVis
BYTE Unix Benchmark
Computational Test: Dhrystone 2
OSPray
Demo: XFrog Forest - Renderer: Path Tracer
Blender
Blend File: Fishy Cat - Compute: CPU-Only
VP9 libvpx Encoding
vpxenc VP9 1080p Video Encode
POV-Ray
Trace Time
Selenium
Benchmark: StyleBench - Browser: Google Chrome
OSPray
Demo: San Miguel - Renderer: Path Tracer
Minion
Benchmark: Quasigroup
GROMACS
Water Benchmark
OSPray
Demo: San Miguel - Renderer: SciVis
Apache Cassandra
Test: Writes
Timed MrBayes Analysis
Primate Phylogeny Analysis
Facebook RocksDB
Test: Sequential Fill
Stress-NG
Test: Glibc C String Functions
Stress-NG
Test: Context Switching
Renaissance
Test: Akka Unbalanced Cobwebbed Tree
Selenium
Benchmark: Speedometer - Browser: Firefox
Appleseed
Scene: Material Tester
Parboil
Test: OpenMP MRI Gridding
Apache Siege
Concurrent Users: 200
Hackbench
Count: 16 - Type: Thread
PostgreSQL pgbench
Scaling: Buffer Test - Test: Normal Load - Mode: Read Only
CppPerformanceBenchmarks
Test: Stepanov Vector
Blender
Blend File: BMW27 - Compute: CPU-Only
OpenCV Benchmark
ASKAP
Test: tConvolve MT - Degridding
ASKAP
Test: tConvolve MT - Gridding
Timed Linux Kernel Compilation
Time To Compile
Appleseed
Scene: Disney Material
Selenium
Benchmark: StyleBench - Browser: Firefox
libgav1
Video Input: Summer Nature 1080p
NAS Parallel Benchmarks
Test / Class: EP.D
Selenium
Benchmark: Speedometer - Browser: Google Chrome
FFTW
Build: Float + SSE - Size: 2D FFT Size 2048
Hackbench
Count: 8 - Type: Process
Chaos Group V-RAY
Mode: CPU
OSPray
Demo: NASA Streamlines - Renderer: Path Tracer
Build2
Time To Compile
NAS Parallel Benchmarks
Test / Class: BT.C
Renaissance
Test: Apache Spark PageRank
IndigoBench
Scene: Bedroom
Radiance Benchmark
Test: SMP Parallel
LuxCoreRender
Scene: DLSC
IndigoBench
Scene: Supercar
Facebook RocksDB
Test: Read While Writing
GraphicsMagick
Operation: Enhanced
GraphicsMagick
Operation: Resizing
GraphicsMagick
Operation: Noise-Gaussian
Facebook RocksDB
Test: Random Read
GraphicsMagick
Operation: Sharpen
GraphicsMagick
Operation: Swirl
GraphicsMagick
Operation: Rotate
GraphicsMagick
Operation: HWB Color Space
Timed LLVM Compilation
Time To Compile
SQLite Speedtest
Timed Time - Size 1,000
Stockfish
Total Time
NAS Parallel Benchmarks
Test / Class: SP.B
CppPerformanceBenchmarks
Test: Atol
LibreOffice
Test: 20 Documents To PDF
NAMD
ATPase Simulation - 327,506 Atoms
ASKAP
Test: tConvolve MPI - Degridding
ASKAP
Test: tConvolve MPI - Gridding
Renaissance
Test: Apache Spark Bayes
eSpeak Speech Engine
Text-To-Speech Synthesis
MBW
Test: Memory Copy - Array Size: 4096 MiB
NGINX Benchmark
Static Web Page Serving
rav1e
1080p To AV1 Video Encode
LeelaChessZero
Backend: BLAS
Selenium
Benchmark: ARES-6 - Browser: Google Chrome
MKL-DNN DNNL
Harness: IP Batch All - Data Type: f32
Selenium
Benchmark: Octane - Browser: Firefox
FFTW
Build: Stock - Size: 2D FFT Size 2048
MBW
Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB
NAS Parallel Benchmarks
Test / Class: LU.C
Timed PHP Compilation
Time To Compile
Minion
Benchmark: Graceful
Selenium
Benchmark: Octane - Browser: Google Chrome
Java SciMark
Computational Test: Composite
7-Zip Compression
Compress Speed Test
Himeno Benchmark
Poisson Pressure Solver
Renaissance
Test: In-Memory Database Shootout
MKL-DNN DNNL
Harness: Convolution Batch conv_3d - Data Type: f32
Stream
Type: Copy
Embree
Binary: Pathtracer - Model: Asian Dragon Obj
miniFE
Problem Size: Small
dcraw
RAW To PPM Image Conversion
MKL-DNN DNNL
Harness: Recurrent Neural Network Training - Data Type: f32
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
Rust Mandelbrot
Time To Complete Serial/Parallel Mandelbrot
GNU Octave Benchmark
m-queens
Time To Solve
Gzip Compression
Linux Source Tree Archiving To .tar.gz
MBW
Test: Memory Copy - Array Size: 1024 MiB
Hackbench
Count: 16 - Type: Process
Redis
Test: SET
Redis
Test: GET
Go Benchmarks
Test: http
Hackbench
Count: 4 - Type: Thread
Apache Benchmark
Static Web Page Serving
Coremark
CoreMark Size 666 - Iterations Per Second
glibc bench
Benchmark: exp
dav1d
Video Input: Chimera 1080p
ASKAP
Test: tConvolve OpenMP - Degridding
ASKAP
Test: tConvolve OpenMP - Gridding
Stress-NG
Test: CPU Stress
Stress-NG
Test: Semaphores
Stress-NG
Test: Crypto
Stress-NG
Test: Forking
Stress-NG
Test: Vector Math
Stress-NG
Test: Matrix Math
Stress-NG
Test: Socket Activity
Stress-NG
Test: Glibc Qsort Data Sorting
CppPerformanceBenchmarks
Test: Ctype
C-Ray
Total Time - 4K, 16 Rays Per Pixel
ACES DGEMM
Sustained Floating-Point Rate
CppPerformanceBenchmarks
Test: Stepanov Abstraction
Hackbench
Count: 4 - Type: Process
TTSIOD 3D Renderer
Phong Rendering With Soft-Shadow Mapping
Embree
Binary: Pathtracer - Model: Crown
Renaissance
Test: Apache Spark ALS
Tungsten Renderer
Scene: Non-Exponential
Embree
Binary: Pathtracer ISPC - Model: Crown
SciMark
Computational Test: Composite
MKL-DNN DNNL
Harness: IP Batch 1D - Data Type: f32
Tesseract OCR
Time To OCR 7 Images
Embree
Binary: Pathtracer - Model: Asian Dragon
NAS Parallel Benchmarks
Test / Class: FT.C
Tensorflow
Build: Cifar10
GIMP
Test: unsharp-mask
Go Benchmarks
Test: build
Tungsten Renderer
Scene: Water Caustic
Crafty
Elapsed Time
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Selenium
Benchmark: PSPDFKit WASM - Browser: Firefox
PyBench
Total For Average Test Times
MKL-DNN DNNL
Harness: Deconvolution Batch deconv_1d - Data Type: f32
OSPray
Demo: Magnetic Reconnection - Renderer: SciVis
glibc bench
Benchmark: cos
glibc bench
Benchmark: sincos
glibc bench
Benchmark: sin
XZ Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9
FFTW
Build: Float + SSE - Size: 2D FFT Size 1024
Selenium
Benchmark: PSPDFKit WASM - Browser: Google Chrome
Hackbench
Count: 8 - Type: Thread
Selenium
Benchmark: Maze Solver - Browser: Firefox
RAMspeed SMP
Type: Triad - Benchmark: Floating Point
GIMP
Test: auto-levels
Timed ImageMagick Compilation
Time To Compile
RAMspeed SMP
Type: Average - Benchmark: Integer
FFTW
Build: Float + SSE - Size: 1D FFT Size 256
RAMspeed SMP
Type: Copy - Benchmark: Floating Point
SQLite
Threads / Copies: 1
RAMspeed SMP
Type: Scale - Benchmark: Floating Point
RAMspeed SMP
Type: Add - Benchmark: Floating Point
RAMspeed SMP
Type: Average - Benchmark: Floating Point
RAMspeed SMP
Type: Add - Benchmark: Integer
RAMspeed SMP
Type: Copy - Benchmark: Integer
RAMspeed SMP
Type: Scale - Benchmark: Integer
RAMspeed SMP
Type: Triad - Benchmark: Integer
ParaView
Test: Many Spheres - Resolution: 2560 x 1440
ParaView
Test: Many Spheres - Resolution: 2560 x 1440
dav1d
Video Input: Summer Nature 4K
DaCapo Benchmark
Java Test: Tradebeans
OSPray
Demo: NASA Streamlines - Renderer: SciVis
MKL-DNN DNNL
Harness: Convolution Batch conv_alexnet - Data Type: f32
Xsbench
Selenium
Benchmark: Maze Solver - Browser: Google Chrome
FFTW
Build: Stock - Size: 1D FFT Size 64
FLAC Audio Encoding
WAV To FLAC
GIMP
Test: rotate
PHPBench
PHP Benchmark Suite
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
NeatBench
Acceleration: CPU
glibc bench
Benchmark: ffs
CppPerformanceBenchmarks
Test: Function Objects
Go Benchmarks
Test: json
Rodinia
Test: OpenMP LavaMD
Tungsten Renderer
Scene: Hair
DaCapo Benchmark
Java Test: Tradesoap
Zstd Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19
DaCapo Benchmark
Java Test: H2
Opus Codec Encoding
WAV, Opus Encode, Opus Decode
x265
H.265 1080p Video Encoding
Rust Prime Benchmark
Prime Number Test To 200,000,000
MBW
Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB
LeelaChessZero
Backend: Random
NAS Parallel Benchmarks
Test / Class: EP.C
FFTW
Build: Stock - Size: 2D FFT Size 1024
Rodinia
Test: OpenMP CFD Solver
glibc bench
Benchmark: atanh
glibc bench
Benchmark: sqrt
glibc bench
Benchmark: modf
glibc bench
Benchmark: log2
glibc bench
Benchmark: tanh
glibc bench
Benchmark: pthread_once
glibc bench
Benchmark: asinh
glibc bench
Benchmark: sinh
glibc bench
Benchmark: ffsll
GIMP
Test: resize
SVT-VP9
Tuning: VMAF Optimized - Input: Bosphorus 1080p
NAS Parallel Benchmarks
Test / Class: MG.C
Parboil
Test: OpenMP Stencil
Go Benchmarks
Test: garbage
Darktable
Test: Boat - Acceleration: CPU-only
dav1d
Video Input: Summer Nature 1080p
FFTW
Build: Float + SSE - Size: 2D FFT Size 64
FFTW
Build: Float + SSE - Size: 1D FFT Size 64
LAME MP3 Encoding
WAV To MP3
FFTW
Build: Stock - Size: 2D FFT Size 32
FFTW
Build: Float + SSE - Size: 2D FFT Size 32
N-Queens
Elapsed Time
Sunflow Rendering System
Global Illumination + Image Synthesis
Hackbench
Count: 1 - Type: Process
DaCapo Benchmark
Java Test: Jython
FFTW
Build: Float + SSE - Size: 1D FFT Size 4096
OSPray
Demo: Magnetic Reconnection - Renderer: Path Tracer
Bork File Encrypter
File Encryption Time
FFTW
Build: Float + SSE - Size: 2D FFT Size 512
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
x264
H.264 Video Encoding
ParaView
Test: Wavelet Volume - Resolution: 2560 x 1440
ParaView
Test: Wavelet Volume - Resolution: 2560 x 1440
Tungsten Renderer
Scene: Volumetric Caustic
MBW
Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB
FFTW
Build: Float + SSE - Size: 1D FFT Size 2048
ParaView
Test: Wavelet Contour - Resolution: 2560 x 1440
ParaView
Test: Wavelet Contour - Resolution: 2560 x 1440
OSBench
Test: Create Files
Intel Open Image Denoise
Scene: Memorial
Git
Time To Complete Common Git Commands
OSBench
Test: Memory Allocations
OSBench
Test: Create Processes
OSBench
Test: Launch Programs
OSBench
Test: Create Threads
FFTW
Build: Stock - Size: 1D FFT Size 4096
FFTW
Build: Float + SSE - Size: 1D FFT Size 1024
FFTW
Build: Stock - Size: 2D FFT Size 64
Darktable
Test: Masskrug - Acceleration: CPU-only
Smallpt
Global Illumination Renderer; 128 Samples
FFTW
Build: Float + SSE - Size: 1D FFT Size 512
FFTW
Build: Float + SSE - Size: 2D FFT Size 256
MBW
Test: Memory Copy - Array Size: 512 MiB
FFTW
Build: Stock - Size: 2D FFT Size 512
Bullet Physics Engine
Test: Raytests
Hackbench
Count: 2 - Type: Thread
FFTW
Build: Stock - Size: 2D FFT Size 256
FFTW
Build: Stock - Size: 1D FFT Size 2048
FFTW
Build: Stock - Size: 2D FFT Size 128
FFTW
Build: Float + SSE - Size: 2D FFT Size 128
Hackbench
Count: 2 - Type: Process
FFTW
Build: Stock - Size: 1D FFT Size 128
Darktable
Test: Server Room - Acceleration: CPU-only
FFTW
Build: Stock - Size: 1D FFT Size 256
FFTW
Build: Float + SSE - Size: 1D FFT Size 32
FFTW
Build: Stock - Size: 1D FFT Size 32
MKL-DNN DNNL
Harness: Deconvolution Batch deconv_3d - Data Type: f32
FFTW
Build: Stock - Size: 1D FFT Size 1024
Optcarrot
Optimized Benchmark
Hackbench
Count: 1 - Type: Thread
FFTW
Build: Stock - Size: 1D FFT Size 512
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 1080p
FFTW
Build: Float + SSE - Size: 1D FFT Size 128
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p
Darktable
Test: Server Rack - Acceleration: CPU-only
Tachyon
Total Time
TSCP
AI Chess Performance
MBW
Test: Memory Copy - Array Size: 128 MiB
Parboil
Test: OpenMP CUTCP
MBW
Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB
ctx_clock
Context Switch Time
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
HPC Challenge
Test / Class: Max Ping Pong Bandwidth
HPC Challenge
Test / Class: Random Ring Bandwidth
HPC Challenge
Test / Class: Random Ring Latency
HPC Challenge
Test / Class: G-Random Access
HPC Challenge
Test / Class: EP-STREAM Triad
HPC Challenge
Test / Class: G-Ptrans
HPC Challenge
Test / Class: EP-DGEMM
HPC Challenge
Test / Class: G-Ffte
HPC Challenge
Test / Class: G-Ffte
Stream
Type: Add
Stream
Type: Triad
Stream
Type: Scale
Geometric Mean Of All Test Results
Result Composite - AMD Threadripper 3960X vs. Intel Core i9 10980XE
Number Of First Place Finishes
Wins - 334 Tests
Number Of Last Place Finishes
Losses - 334 Tests
Phoronix Test Suite v10.8.4