EPYC 2021 Benchmarks
Tests for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2102219-HA-EB716339316&sro&grw.
toyBrot Fractal Generator
Implementation: TBB
toyBrot Fractal Generator
Implementation: OpenMP
toyBrot Fractal Generator
Implementation: C++ Tasks
toyBrot Fractal Generator
Implementation: C++ Threads
TSCP
AI Chess Performance
Crypto++
Test: Unkeyed Algorithms
Crypto++
Test: Keyed Algorithms
Crypto++
Test: Integer + Elliptic Curve Public Key Algorithms
LZ4 Compression
Compression Level: 3 - Compression Speed
LZ4 Compression
Compression Level: 3 - Decompression Speed
LZ4 Compression
Compression Level: 9 - Compression Speed
LZ4 Compression
Compression Level: 9 - Decompression Speed
Crafty
Elapsed Time
XZ Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9
MBW
Test: Memory Copy - Array Size: 8192 MiB
Tinymembench
Standard Memset
ctx_clock
Context Switch Time
Stress-NG
Test: CPU Stress
Stress-NG
Test: Crypto
Stress-NG
Test: Vector Math
Stress-NG
Test: Matrix Math
Stress-NG
Test: Socket Activity
Stress-NG
Test: Context Switching
Stress-NG
Test: CPU Cache
Stream
Type: Copy
Stream
Type: Scale
Stream
Type: Add
Stream
Type: Triad
Hierarchical INTegration
Test: FLOAT
Botan
Test: AES-256
Botan
Test: Blowfish
Botan
Test: CAST-256
Botan
Test: KASUMI
Botan
Test: Twofish
Basis Universal
Settings: UASTC Level 2
Basis Universal
Settings: UASTC Level 3
BRL-CAD
VGR Performance Metric
Ngspice
Circuit: C2670
Ngspice
Circuit: C7552
ASTC Encoder
Preset: Thorough
ASTC Encoder
Preset: Exhaustive
Etcpak
Configuration: ETC2
Etcpak
Configuration: DXT1
Hugin
Panorama Photo Assistant + Stitching Time
JPEG XL
Input: PNG - Encode Speed: 5
JPEG XL
Input: PNG - Encode Speed: 7
JPEG XL
Input: PNG - Encode Speed: 8
JPEG XL
Input: JPEG - Encode Speed: 5
JPEG XL
Input: JPEG - Encode Speed: 7
JPEG XL
Input: JPEG - Encode Speed: 8
JPEG XL Decoding
CPU Threads: 1
JPEG XL Decoding
CPU Threads: All
LibRaw
Post-Processing Benchmark
Montage Astronomical Image Mosaic Engine
Mosaic of M17, K band, 1.5 deg x 1.5 deg
RawTherapee
Total Benchmark Time
WebP2 Image Encode
Encode Settings: Quality 75, Compression Effort 7
WebP2 Image Encode
Encode Settings: Quality 95, Compression Effort 7
WebP2 Image Encode
Encode Settings: Quality 100, Compression Effort 5
OCRMyPDF
Processing 60 Page PDF Document
eSpeak-NG Speech Engine
Text-To-Speech Synthesis
Google SynthMark
Test: VoiceMark_100
QuantLib
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Euclidean Cluster
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: NDT Mapping
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Points2Image
Timed MrBayes Analysis
Primate Phylogeny Analysis
Himeno Benchmark
Poisson Pressure Solver
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
LeelaChessZero
Backend: BLAS
LeelaChessZero
Backend: Eigen
Numenta Anomaly Benchmark
Detector: Bayesian Changepoint
Numenta Anomaly Benchmark
Detector: Windowed Gaussian
Numenta Anomaly Benchmark
Detector: Relative Entropy
Numenta Anomaly Benchmark
Detector: Earthgecko Skyline
Numpy Benchmark
CloverLeaf
Lagrangian-Eulerian Hydrodynamics
AI Benchmark Alpha
Device Inference Score
AI Benchmark Alpha
Device Training Score
AI Benchmark Alpha
Device AI Score
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
ONNX Runtime
Model: yolov4 - Device: OpenMP CPU
ONNX Runtime
Model: fcn-resnet101-11 - Device: OpenMP CPU
ONNX Runtime
Model: shufflenet-v2-10 - Device: OpenMP CPU
ONNX Runtime
Model: super-resolution-10 - Device: OpenMP CPU
ONNX Runtime
Model: bertsquad-10 - Device: OpenMP CPU
TensorFlow Lite
Model: Mobilenet Float
TensorFlow Lite
Model: Mobilenet Quant
TensorFlow Lite
Model: NASNet Mobile
TensorFlow Lite
Model: SqueezeNet
TensorFlow Lite
Model: Inception ResNet V2
TensorFlow Lite
Model: Inception V4
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 200
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 200
GROMACS
Water Benchmark
GROMACS
Input: water_GMX50_bare
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
High Performance Conjugate Gradient
Parboil
Test: OpenMP LBM
NAS Parallel Benchmarks
Test / Class: EP.C
NAS Parallel Benchmarks
Test / Class: EP.D
NAS Parallel Benchmarks
Test / Class: FT.C
NAS Parallel Benchmarks
Test / Class: LU.C
NAS Parallel Benchmarks
Test / Class: IS.D
NAS Parallel Benchmarks
Test / Class: MG.C
NAS Parallel Benchmarks
Test / Class: CG.C
Rodinia
Test: OpenMP CFD Solver
Rodinia
Test: OpenMP LavaMD
Rodinia
Test: OpenMP Leukocyte
Rodinia
Test: OpenMP Streamcluster
NAMD
ATPase Simulation - 327,506 Atoms
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU
oneDNN
Harness: IP Shapes 3D - 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
oneDNN
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
OpenVINO
Model: Face Detection 0106 FP16 - Device: CPU
OpenVINO
Model: Face Detection 0106 FP16 - Device: CPU
OpenVINO
Model: Face Detection 0106 FP32 - Device: CPU
OpenVINO
Model: Face Detection 0106 FP32 - Device: CPU
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
OpenVINO
Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU
OpenVINO
Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU
OpenVINO
Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU
OpenVINO
Model: Person Detection 0106 FP16 - Device: CPU
OpenVINO
Model: Person Detection 0106 FP16 - Device: CPU
OpenVINO
Model: Person Detection 0106 FP32 - Device: CPU
OpenVINO
Model: Person Detection 0106 FP32 - Device: CPU
ASKAP
Test: tConvolve MPI - Degridding
ASKAP
Test: tConvolve MPI - Gridding
ASKAP
Test: tConvolve OpenMP - Gridding
ASKAP
Test: tConvolve OpenMP - Degridding
ACES DGEMM
Sustained Floating-Point Rate
Pennant
Test: leblancbig
Pennant
Test: sedovbig
Algebraic Multi-Grid Benchmark
FFTE
N=256, 3D Complex FFT Routine
Kripke
LULESH
NWChem
Input: C240 Buckyball
OpenFOAM
Input: Motorbike 30M
OpenFOAM
Input: Motorbike 60M
Monte Carlo Simulations of Ionised Nebulae
Input: Dust 2D tau100.0
Incompact3D
Input: Cylinder
miniFE
Problem Size: Small
GPAW
Input: Carbon Nanotube
Quantum ESPRESSO
Input: AUSURF112
Coremark
CoreMark Size 666 - Iterations Per Second
Aircrack-ng
Timed FFmpeg Compilation
Time To Compile
Timed ImageMagick Compilation
Time To Compile
Timed MPlayer Compilation
Time To Compile
Stockfish
Total Time
7-Zip Compression
Compress Speed Test
John The Ripper
Test: MD5
John The Ripper
Test: Blowfish
Timed LLVM Compilation
Time To Compile
Timed PHP Compilation
Time To Compile
Zstd Compression
Compression Level: 3
Zstd Compression
Compression Level: 19
asmFish
1024 Hash Memory, 26 Depth
m-queens
Time To Solve
Cpuminer-Opt
Algorithm: x25x
Cpuminer-Opt
Algorithm: Garlicoin
Cpuminer-Opt
Algorithm: Deepcoin
Cpuminer-Opt
Algorithm: Skeincoin
Timed Linux Kernel Compilation
Time To Compile
Sysbench
Test: CPU
Sysbench
Test: Memory
Swet
Average
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Medium
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Very Fast
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Ultra Fast
Tungsten Renderer
Scene: Hair
Tungsten Renderer
Scene: Water Caustic
Tachyon
Total Time
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 1080p
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p
x264
H.264 Video Encoding
dav1d
Video Input: Summer Nature 1080p
dav1d
Video Input: Summer Nature 4K
dav1d
Video Input: Chimera 1080p
dav1d
Video Input: Chimera 1080p 10-bit
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
x265
Video Input: Bosphorus 4K
C-Ray
Total Time - 4K, 16 Rays Per Pixel
Chaos Group V-RAY
Mode: CPU
Chaos Group V-RAY
Mode: CPU
Blender
Blend File: BMW27 - Compute: CPU-Only
Blender
Blend File: Classroom - Compute: CPU-Only
Blender
Blend File: Fishy Cat - Compute: CPU-Only
Blender
Blend File: Pabellon Barcelona - Compute: CPU-Only
Blender
Blend File: Barbershop - Compute: CPU-Only
POV-Ray
Trace Time
Timed Godot Game Engine Compilation
Time To Compile
Intel Open Image Denoise
Scene: Memorial
OpenVKL
Benchmark: vklBenchmark
IndigoBench
Acceleration: CPU - Scene: Supercar
IndigoBench
Acceleration: CPU - Scene: Bedroom
LuxCoreRender
Scene: DLSC
LuxCoreRender
Scene: Rainbow Colors and Prism
OSPray
Demo: Magnetic Reconnection - Renderer: SciVis
OSPray
Demo: XFrog Forest - Renderer: SciVis
OSPray
Demo: XFrog Forest - Renderer: Path Tracer
OSPray
Demo: NASA Streamlines - Renderer: SciVis
OSPray
Demo: NASA Streamlines - Renderer: Path Tracer
OSPray
Demo: San Miguel - Renderer: SciVis
OSPray
Demo: San Miguel - Renderer: Path Tracer
rays1bench
Large Scene
YafaRay
Total Time For Sample Scene
Appleseed
Scene: Emily
Appleseed
Scene: Disney Material
Build2
Time To Compile
FinanceBench
Benchmark: Bonds OpenMP
FinanceBench
Benchmark: Repo OpenMP
C-Blosc
Compressor: blosclz
PyPerformance
Benchmark: crypto_pyaes
PyPerformance
Benchmark: django_template
PyPerformance
Benchmark: float
PyPerformance
Benchmark: nbody
PyPerformance
Benchmark: pathlib
PyPerformance
Benchmark: regex_compile
BlogBench
Test: Read
PHPBench
PHP Benchmark Suite
Apache CouchDB
Bulk Size: 100 - Inserts: 1000 - Rounds: 24
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
KeyDB
Redis
Test: SET
Redis
Test: GET
Facebook RocksDB
Test: Random Fill Sync
Facebook RocksDB
Test: Random Read
Facebook RocksDB
Test: Read While Writing
Apache Cassandra
Test: Writes
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 100 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 100 - Mode: Read Only
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency
Stream-Dynamic
- Triad
Stream-Dynamic
- Scale
Stream-Dynamic
- Add
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Only
Stream-Dynamic
- Copy
PostgreSQL pgbench
Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency
ebizzy
simdjson
Throughput Test: PartialTweets
simdjson
Throughput Test: LargeRandom
simdjson
Throughput Test: Kostya
simdjson
Throughput Test: DistinctUserID
Perl Benchmarks
Test: Pod2html
Perl Benchmarks
Test: Interpreter
PyBench
Total For Average Test Times
OSPray
Demo: Magnetic Reconnection - Renderer: SciVis
OSPray
Demo: XFrog Forest - Renderer: SciVis
OSPray
Demo: XFrog Forest - Renderer: Path Tracer
OSPray
Demo: NASA Streamlines - Renderer: SciVis
OSPray
Demo: NASA Streamlines - Renderer: Path Tracer
OSPray
Demo: San Miguel - Renderer: SciVis
OSPray
Demo: San Miguel - Renderer: Path Tracer
rays1bench
Large Scene
LuxCoreRender
Scene: DLSC
LuxCoreRender
Scene: Rainbow Colors and Prism
Chaos Group V-RAY
Mode: CPU
IndigoBench
Acceleration: CPU - Scene: Supercar
IndigoBench
Acceleration: CPU - Scene: Bedroom
ACES DGEMM
Sustained Floating-Point Rate
ASKAP
Test: tConvolve MPI - Gridding
ASKAP
Test: tConvolve OpenMP - Degridding
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Euclidean Cluster
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: NDT Mapping
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Points2Image
FFTE
N=256, 3D Complex FFT Routine
High Performance Conjugate Gradient
Himeno Benchmark
Poisson Pressure Solver
Kripke
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
LULESH
miniFE
Problem Size: Small
GROMACS
Water Benchmark
NAS Parallel Benchmarks
Test / Class: EP.C
NAS Parallel Benchmarks
Test / Class: EP.D
NAS Parallel Benchmarks
Test / Class: FT.C
NAS Parallel Benchmarks
Test / Class: LU.C
NAS Parallel Benchmarks
Test / Class: IS.D
NAS Parallel Benchmarks
Test / Class: MG.C
NAS Parallel Benchmarks
Test / Class: CG.C
Numpy Benchmark
AI Benchmark Alpha
Device AI Score
LeelaChessZero
Backend: BLAS
LeelaChessZero
Backend: Eigen
ONNX Runtime
Model: yolov4 - Device: OpenMP CPU
ONNX Runtime
Model: fcn-resnet101-11 - Device: OpenMP CPU
ONNX Runtime
Model: shufflenet-v2-10 - Device: OpenMP CPU
ONNX Runtime
Model: super-resolution-10 - Device: OpenMP CPU
ONNX Runtime
Model: bertsquad-10 - Device: OpenMP CPU
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
Cpuminer-Opt
Algorithm: x25x
Cpuminer-Opt
Algorithm: Garlicoin
Cpuminer-Opt
Algorithm: Deepcoin
Cpuminer-Opt
Algorithm: Skeincoin
John The Ripper
Test: MD5
John The Ripper
Test: Blowfish
dav1d
Video Input: Summer Nature 1080p
dav1d
Video Input: Summer Nature 4K
dav1d
Video Input: Chimera 1080p
dav1d
Video Input: Chimera 1080p 10-bit
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Medium
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Very Fast
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Ultra Fast
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 1080p
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p
x264
H.264 Video Encoding
x265
Video Input: Bosphorus 4K
Aircrack-ng
BRL-CAD
VGR Performance Metric
Apache Cassandra
Test: Writes
KeyDB
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
Redis
Test: SET
Redis
Test: GET
PHPBench
PHP Benchmark Suite
simdjson
Throughput Test: PartialTweets
simdjson
Throughput Test: LargeRandom
simdjson
Throughput Test: Kostya
simdjson
Throughput Test: DistinctUserID
Facebook RocksDB
Test: Random Fill Sync
Facebook RocksDB
Test: Random Read
Facebook RocksDB
Test: Read While Writing
ebizzy
BlogBench
Test: Read
Botan
Test: AES-256
Botan
Test: Blowfish
Botan
Test: CAST-256
Botan
Test: KASUMI
Botan
Test: Twofish
Crypto++
Test: Unkeyed Algorithms
Crypto++
Test: Keyed Algorithms
Crypto++
Test: Integer + Elliptic Curve Public Key Algorithms
C-Blosc
Compressor: blosclz
Zstd Compression
Compression Level: 3
Zstd Compression
Compression Level: 19
7-Zip Compression
Compress Speed Test
LZ4 Compression
Compression Level: 3 - Decompression Speed
LZ4 Compression
Compression Level: 9 - Decompression Speed
Coremark
CoreMark Size 666 - Iterations Per Second
Stress-NG
Test: CPU Stress
Stress-NG
Test: Crypto
Stress-NG
Test: Vector Math
Stress-NG
Test: Matrix Math
Stress-NG
Test: Socket Activity
Stress-NG
Test: Context Switching
Stress-NG
Test: CPU Cache
Stream
Type: Copy
Stream
Type: Add
Tinymembench
Standard Memset
MBW
Test: Memory Copy - Array Size: 8192 MiB
LibRaw
Post-Processing Benchmark
Google SynthMark
Test: VoiceMark_100
Etcpak
Configuration: ETC2
Etcpak
Configuration: DXT1
QuantLib
Swet
Average
Sysbench
Test: CPU
Sysbench
Test: Memory
Crafty
Elapsed Time
TSCP
AI Chess Performance
Stockfish
Total Time
asmFish
1024 Hash Memory, 26 Depth
Hierarchical INTegration
Test: FLOAT
OpenVKL
Benchmark: vklBenchmark
Intel Open Image Denoise
Scene: Memorial
Algebraic Multi-Grid Benchmark
Stream
Type: Triad
Chaos Group V-RAY
Mode: CPU
GROMACS
Input: water_GMX50_bare
JPEG XL
Input: PNG - Encode Speed: 5
JPEG XL
Input: PNG - Encode Speed: 7
JPEG XL
Input: PNG - Encode Speed: 8
JPEG XL
Input: JPEG - Encode Speed: 5
JPEG XL
Input: JPEG - Encode Speed: 7
JPEG XL
Input: JPEG - Encode Speed: 8
JPEG XL Decoding
CPU Threads: 1
JPEG XL Decoding
CPU Threads: All
Stream-Dynamic
- Triad
Phoronix Test Suite v10.8.4