AMD EPYC 4th Gen AVX-512 Comparison

AMD EPYC 9654 Genoa AVX-512 benchmark comparison by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2212195-NE-AVXCOMPAR69&sro&grr.

JPEG XL libjxl

Input: JPEG - Quality: 100

NCNN

Target: CPU - Model: FastestDet

NCNN

Target: CPU - Model: vision_transformer

NCNN

Target: CPU - Model: regnety_400m

NCNN

Target: CPU - Model: resnet50

NCNN

Target: CPU - Model: googlenet

NCNN

Target: CPU - Model: blazeface

NCNN

Target: CPU - Model: efficientnet-b0

NCNN

Target: CPU - Model: mnasnet

Mobile Neural Network

Model: inception-v3

Mobile Neural Network

Model: SqueezeNetV1.0

Mobile Neural Network

Model: resnet-v2-50

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

LeelaChessZero

Backend: BLAS

OpenVKL

Benchmark: vklBenchmark ISPC

Darmstadt Automotive Parallel Heterogeneous Suite

Backend: OpenMP - Kernel: Points2Image

CP2K Molecular Dynamics

Input: Fayalite-FIST

LeelaChessZero

Backend: Eigen

AI Benchmark Alpha

Device AI Score

AI Benchmark Alpha

Device Training Score

AI Benchmark Alpha

Device Inference Score

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Standard

oneDNN

Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer

Numpy Benchmark

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Standard

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

TensorFlow

Device: CPU - Batch Size: 16 - Model: ResNet-50

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer

TensorFlow

Device: CPU - Batch Size: 16 - Model: GoogLeNet

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer

OSPRay Studio

Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer

JPEG XL libjxl

Input: JPEG - Quality: 90

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer

JPEG XL libjxl

Input: PNG - Quality: 90

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

simdjson

Throughput Test: TopTweet

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Mesh Time

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

simdjson

Throughput Test: DistinctUserID

simdjson

Throughput Test: PartialTweets

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream

simdjson

Throughput Test: Kostya

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

simdjson

Throughput Test: LargeRandom

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream

TensorFlow

Device: CPU - Batch Size: 16 - Model: AlexNet

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

Cpuminer-Opt

Algorithm: scrypt

Cpuminer-Opt

Algorithm: LBC, LBRY Credits

Cpuminer-Opt

Algorithm: x25x

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

Cpuminer-Opt

Algorithm: Garlicoin

Cpuminer-Opt

Algorithm: Quad SHA-256, Pyrite

Cpuminer-Opt

Algorithm: Skeincoin

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

Darmstadt Automotive Parallel Heterogeneous Suite

Backend: OpenMP - Kernel: NDT Mapping

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

miniBUDE

Implementation: OpenMP - Input Deck: BM2

miniBUDE

Implementation: OpenMP - Input Deck: BM2

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

Numenta Anomaly Benchmark

Detector: Relative Entropy

Intel Open Image Denoise

Run: RT.hdr_alb_nrm.3840x2160

Intel Open Image Denoise

Run: RT.ldr_alb_nrm.3840x2160

SMHasher

Hash: FarmHash32 x86_64 AVX

SMHasher

Hash: FarmHash32 x86_64 AVX

Embree

Binary: Pathtracer ISPC - Model: Crown

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

miniBUDE

Implementation: OpenMP - Input Deck: BM1

miniBUDE

Implementation: OpenMP - Input Deck: BM1

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

CPU Temperature Monitor

Phoronix Test Suite System Monitoring

CPU Power Consumption Monitor

Phoronix Test Suite System Monitoring