AMD EPYC 7F52
AMD EPYC 7F52 16-Core testing with a Supermicro H11DSi-NT v2.00 (2.1 BIOS) and llvmpipe on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012294-HA-AMDEPYC7F75&sor&grr.
PlaidML
FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU
OpenVKL
Benchmark: vklBenchmarkUnstructuredVolume
Polyhedron Fortran Benchmarks
Benchmark: tfft2
Numenta Anomaly Benchmark
Detector: EXPoSE
PlaidML
FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU
LAMMPS Molecular Dynamics Simulator
Model: 20k Atoms
PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
Polyhedron Fortran Benchmarks
Benchmark: test_fpu2
Mobile Neural Network
Model: inception-v3
Mobile Neural Network
Model: mobilenet-v1-1.0
Mobile Neural Network
Model: MobileNetV2_224
Mobile Neural Network
Model: resnet-v2-50
Mobile Neural Network
Model: SqueezeNetV1.0
Timed Clash Compilation
Time To Compile
BRL-CAD
VGR Performance Metric
AI Benchmark Alpha
Device AI Score
AI Benchmark Alpha
Device Training Score
AI Benchmark Alpha
Device Inference Score
Open Porous Media
OPM Benchmark: Flow MPI Norne - Threads: 1
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 200
OpenVKL
Benchmark: vklBenchmark
Blender
Blend File: Barbershop - Compute: CPU-Only
Open Porous Media
OPM Benchmark: Flow MPI Norne - Threads: 16
Polyhedron Fortran Benchmarks
Benchmark: gas_dyn2
ECP-CANDLE
Benchmark: P3B2
NCNN
Target: CPU - Model: regnety_400m
NCNN
Target: CPU - Model: squeezenet_ssd
NCNN
Target: CPU - Model: yolov4-tiny
NCNN
Target: CPU - Model: resnet50
NCNN
Target: CPU - Model: alexnet
NCNN
Target: CPU - Model: resnet18
NCNN
Target: CPU - Model: vgg16
NCNN
Target: CPU - Model: googlenet
NCNN
Target: CPU - Model: blazeface
NCNN
Target: CPU - Model: efficientnet-b0
NCNN
Target: CPU - Model: mnasnet
NCNN
Target: CPU - Model: shufflenet-v2
NCNN
Target: CPU-v3-v3 - Model: mobilenet-v3
NCNN
Target: CPU-v2-v2 - Model: mobilenet-v2
NCNN
Target: CPU - Model: mobilenet
WireGuard + Linux Networking Stack Stress Test
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Points2Image
Blender
Blend File: Pabellon Barcelona - Compute: CPU-Only
Numpy Benchmark
Blender
Blend File: Classroom - Compute: CPU-Only
Hierarchical INTegration
Test: FLOAT
PlaidML
FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU
ECP-CANDLE
Benchmark: P3B1
Open Porous Media
OPM Benchmark: Flow MPI Norne - Threads: 8
Open Porous Media
OPM Benchmark: Flow MPI Norne - Threads: 2
Polyhedron Fortran Benchmarks
Benchmark: channel2
Polyhedron Fortran Benchmarks
Benchmark: mp_prop_design
Monte Carlo Simulations of Ionised Nebulae
Input: Dust 2D tau100.0
Caffe
Model: GoogleNet - Acceleration: CPU - Iterations: 100
Polyhedron Fortran Benchmarks
Benchmark: fatigue2
SVT-AV1
Encoder Mode: Enc Mode 0 - Input: 1080p
Open Porous Media
OPM Benchmark: Flow MPI Norne - Threads: 4
asmFish
1024 Hash Memory, 26 Depth
PlaidML
FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 200
Tachyon
Total Time
GPAW
Input: Carbon Nanotube
Stress-NG
Test: CPU Cache
YafaRay
Total Time For Sample Scene
Timed HMMer Search
Pfam Database Search
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 250 - Mode: Read Write
BYTE Unix Benchmark
Computational Test: Dhrystone 2
dav1d
Video Input: Chimera 1080p 10-bit
PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
ASTC Encoder
Preset: Exhaustive
Blender
Blend File: Fishy Cat - Compute: CPU-Only
LZ4 Compression
Compression Level: 3 - Decompression Speed
LZ4 Compression
Compression Level: 3 - Compression Speed
PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
Timed GDB GNU Debugger Compilation
Time To Compile
Node.js V8 Web Tooling Benchmark
Stress-NG
Test: System V Message Passing
InfluxDB
Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000
Mlpack Benchmark
Benchmark: scikit_qda
VP9 libvpx Encoding
Speed: Speed 0
Timed Eigen Compilation
Time To Compile
Blender
Blend File: BMW27 - Compute: CPU-Only
PyPerformance
Benchmark: raytrace
Polyhedron Fortran Benchmarks
Benchmark: induct2
GROMACS
Water Benchmark
oneDNN
Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU
Numenta Anomaly Benchmark
Detector: Earthgecko Skyline
TensorFlow Lite
Model: Inception V4
InfluxDB
Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 50 - Mode: Read Only
Build2
Time To Compile
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU
oneDNN
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU
simdjson
Throughput Test: Kostya
Caffe
Model: AlexNet - Acceleration: CPU - Iterations: 100
PyPerformance
Benchmark: python_startup
KeyDB
Mlpack Benchmark
Benchmark: scikit_linearridgeregression
TensorFlow Lite
Model: Inception ResNet V2
OpenVINO
Model: Person Detection 0106 FP16 - Device: CPU
OpenVINO
Model: Person Detection 0106 FP16 - Device: 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: Person Detection 0106 FP32 - Device: CPU
OpenVINO
Model: Person Detection 0106 FP32 - Device: CPU
Chaos Group V-RAY
Mode: CPU
SQLite Speedtest
Timed Time - Size 1,000
OpenVKL
Benchmark: vklBenchmarkVdbVolume
Mlpack Benchmark
Benchmark: scikit_ica
Polyhedron Fortran Benchmarks
Benchmark: capacita
Polyhedron Fortran Benchmarks
Benchmark: rnflow
NAMD
ATPase Simulation - 327,506 Atoms
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU
LuxCoreRender
Scene: Rainbow Colors and Prism
LuxCoreRender
Scene: DLSC
IndigoBench
Acceleration: CPU - Scene: Supercar
IndigoBench
Acceleration: CPU - Scene: Bedroom
TensorFlow Lite
Model: SqueezeNet
TensorFlow Lite
Model: NASNet Mobile
PyPerformance
Benchmark: 2to3
TensorFlow Lite
Model: Mobilenet Quant
TensorFlow Lite
Model: Mobilenet Float
Timed Linux Kernel Compilation
Time To Compile
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
John The Ripper
Test: MD5
GraphicsMagick
Operation: Sharpen
GraphicsMagick
Operation: Noise-Gaussian
GraphicsMagick
Operation: Enhanced
GraphicsMagick
Operation: Rotate
GraphicsMagick
Operation: Swirl
GraphicsMagick
Operation: Resizing
GraphicsMagick
Operation: HWB Color Space
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Slow
LZ4 Compression
Compression Level: 9 - Decompression Speed
LZ4 Compression
Compression Level: 9 - Compression Speed
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Medium
OpenVKL
Benchmark: vklBenchmarkStructuredVolume
simdjson
Throughput Test: LargeRandom
rav1e
Speed: 5
Redis
Test: SET
rav1e
Speed: 1
simdjson
Throughput Test: PartialTweets
DeepSpeech
Acceleration: CPU
simdjson
Throughput Test: DistinctUserID
Redis
Test: GET
Hugin
Panorama Photo Assistant + Stitching Time
PyPerformance
Benchmark: go
Polyhedron Fortran Benchmarks
Benchmark: protein
Zstd Compression
Compression Level: 19
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon Obj
Embree
Binary: Pathtracer ISPC - Model: Asian Dragon
Embree
Binary: Pathtracer - Model: Asian Dragon Obj
CLOMP
Static OMP Speedup
Stockfish
Total Time
eSpeak-NG Speech Engine
Text-To-Speech Synthesis
rav1e
Speed: 6
PyPerformance
Benchmark: django_template
WebP Image Encode
Encode Settings: Quality 100, Lossless, Highest Compression
PlaidML
FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU
PyPerformance
Benchmark: regex_compile
7-Zip Compression
Compress Speed Test
Timed FFmpeg Compilation
Time To Compile
AOM AV1
Encoder Mode: Speed 0 Two-Pass
Embree
Binary: Pathtracer ISPC - Model: Crown
PHPBench
PHP Benchmark Suite
LibRaw
Post-Processing Benchmark
Redis
Test: LPOP
AOM AV1
Encoder Mode: Speed 6 Realtime
Embree
Binary: Pathtracer - Model: Crown
LZ4 Compression
Compression Level: 1 - Decompression Speed
LZ4 Compression
Compression Level: 1 - Compression Speed
Polyhedron Fortran Benchmarks
Benchmark: aermod
Stress-NG
Test: CPU Stress
John The Ripper
Test: Blowfish
Aircrack-ng
Stress-NG
Test: NUMA
Stress-NG
Test: Malloc
Stress-NG
Test: MEMFD
Stress-NG
Test: Matrix Math
Stress-NG
Test: Crypto
Stress-NG
Test: Glibc C String Functions
Stress-NG
Test: Context Switching
Stress-NG
Test: SENDFILE
Stress-NG
Test: Memory Copying
Stress-NG
Test: Vector Math
Stress-NG
Test: MMAP
Stress-NG
Test: Socket Activity
Stress-NG
Test: Forking
Stress-NG
Test: Atomic
Stress-NG
Test: Glibc Qsort Data Sorting
Stress-NG
Test: Semaphores
Zstd Compression
Compression Level: 3
PyPerformance
Benchmark: pathlib
Embree
Binary: Pathtracer - Model: Asian Dragon
AOM AV1
Encoder Mode: Speed 6 Two-Pass
x265
Video Input: Bosphorus 4K
rav1e
Speed: 10
PyPerformance
Benchmark: pickle_pure_python
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: NDT Mapping
Polyhedron Fortran Benchmarks
Benchmark: doduc
Numenta Anomaly Benchmark
Detector: Bayesian Changepoint
Unpacking Firefox
Extracting: firefox-84.0.source.tar.xz
Mlpack Benchmark
Benchmark: scikit_svm
VP9 libvpx Encoding
Speed: Speed 5
Crafty
Elapsed Time
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 100 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 250 - Mode: Read Only
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 50 - Mode: Read Write
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 100 - Mode: Read Only
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 1 - Mode: Read Only
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency
PostgreSQL pgbench
Scaling Factor: 1 - Clients: 1 - Mode: Read Write
Sunflow Rendering System
Global Illumination + Image Synthesis
librsvg
Operation: SVG Files To PNG
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Very Fast
PyPerformance
Benchmark: json_loads
WavPack Audio Encoding
WAV To WavPack
PyPerformance
Benchmark: chaos
PyPerformance
Benchmark: float
Timed Apache Compilation
Time To Compile
Polyhedron Fortran Benchmarks
Benchmark: linpk
Coremark
CoreMark Size 666 - Iterations Per Second
Polyhedron Fortran Benchmarks
Benchmark: ac
PyPerformance
Benchmark: nbody
oneDNN
Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU
XZ Compression
Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9
PyPerformance
Benchmark: crypto_pyaes
Monkey Audio Encoding
WAV To APE
Ogg Audio Encoding
WAV To Ogg
AOM AV1
Encoder Mode: Speed 4 Two-Pass
Timed MPlayer Compilation
Time To Compile
Darmstadt Automotive Parallel Heterogeneous Suite
Backend: OpenMP - Kernel: Euclidean Cluster
oneDNN
Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU
RNNoise
OpenSSL
RSA 4096-bit Performance
OCRMyPDF
Processing 60 Page PDF Document
dav1d
Video Input: Chimera 1080p
TNN
Target: CPU - Model: MobileNet v2
ASTC Encoder
Preset: Thorough
TNN
Target: CPU - Model: SqueezeNet v1.1
AOM AV1
Encoder Mode: Speed 8 Realtime
WebP Image Encode
Encode Settings: Quality 100, Lossless
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Slow
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Medium
SVT-AV1
Encoder Mode: Enc Mode 4 - Input: 1080p
Redis
Test: LPUSH
dav1d
Video Input: Summer Nature 4K
Polyhedron Fortran Benchmarks
Benchmark: mdbx
oneDNN
Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU
Kvazaar
Video Input: Bosphorus 4K - Video Preset: Ultra Fast
Numenta Anomaly Benchmark
Detector: Relative Entropy
FLAC Audio Encoding
WAV To FLAC
Intel Open Image Denoise
Scene: Memorial
Opus Codec Encoding
WAV To Opus Encode
ECP-CANDLE
Benchmark: P1B2
GNU Octave Benchmark
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU
oneDNN
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU
LibreOffice
Test: 20 Documents To PDF
LAMMPS Molecular Dynamics Simulator
Model: Rhodopsin Protein
Redis
Test: SADD
x265
Video Input: Bosphorus 1080p
SVT-AV1
Encoder Mode: Enc Mode 8 - Input: 1080p
oneDNN
Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU
Timed MAFFT Alignment
Multiple Sequence Alignment - LSU RNA
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Very Fast
WebP Image Encode
Encode Settings: Quality 100, Highest Compression
LAME MP3 Encoding
WAV To MP3
Numenta Anomaly Benchmark
Detector: Windowed Gaussian
Polyhedron Fortran Benchmarks
Benchmark: air
ASTC Encoder
Preset: Medium
dav1d
Video Input: Summer Nature 1080p
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU
oneDNN
Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU
Kvazaar
Video Input: Bosphorus 1080p - Video Preset: Ultra Fast
ASTC Encoder
Preset: Fast
x264
H.264 Video Encoding
SVT-VP9
Tuning: Visual Quality Optimized - Input: Bosphorus 1080p
oneDNN
Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU
SVT-VP9
Tuning: VMAF Optimized - Input: Bosphorus 1080p
SVT-VP9
Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p
WebP Image Encode
Encode Settings: Quality 100
FFTE
N=256, 3D Complex FFT Routine
WebP Image Encode
Encode Settings: Default
Phoronix Test Suite v10.8.4