AMD EPYC Genoa Linux Distro Benchmarks

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2301039-NE-2301028NE28&rdt&grs.

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

Zstd Compression

Compression Level: 8, Long Mode - Compression Speed

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

Renaissance

Test: ALS Movie Lens

PHPBench

PHP Benchmark Suite

Renaissance

Test: Apache Spark ALS

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP32 - Device: CPU

MariaDB

Clients: 256

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenVINO

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

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenVINO

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

7-Zip Compression

Test: Compression Rating

OpenVINO

Model: Face Detection FP16 - Device: CPU

Renaissance

Test: Apache Spark Bayes

OpenVINO

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

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

PyPerformance

Benchmark: raytrace

PyPerformance

Benchmark: go

Renaissance

Test: Genetic Algorithm Using Jenetics + Futures

PyPerformance

Benchmark: chaos

PyPerformance

Benchmark: float

CockroachDB

Workload: MoVR - Concurrency: 512

CockroachDB

Workload: MoVR - Concurrency: 1024

CockroachDB

Workload: MoVR - Concurrency: 128

OpenVINO

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

PyPerformance

Benchmark: pickle_pure_python

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

PyPerformance

Benchmark: crypto_pyaes

PyPerformance

Benchmark: nbody

PyPerformance

Benchmark: django_template

Numenta Anomaly Benchmark

Detector: Contextual Anomaly Detector OSE

CockroachDB

Workload: KV, 10% Reads - Concurrency: 128

PyPerformance

Benchmark: regex_compile

OpenVINO

Model: Person Detection FP32 - Device: CPU

WireGuard + Linux Networking Stack Stress Test

OpenVINO

Model: Person Detection FP16 - Device: CPU

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

PostgreSQL

Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency

OpenVINO

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

PostgreSQL

Scaling Factor: 100 - Clients: 250 - Mode: Read Only

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

Renaissance

Test: Random Forest

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

Timed Linux Kernel Compilation

Build: defconfig

PyPerformance

Benchmark: python_startup

CockroachDB

Workload: KV, 10% Reads - Concurrency: 512

PyPerformance

Benchmark: 2to3

CockroachDB

Workload: KV, 60% Reads - Concurrency: 128

CockroachDB

Workload: KV, 50% Reads - Concurrency: 128

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

PyPerformance

Benchmark: pathlib

CockroachDB

Workload: KV, 50% Reads - Concurrency: 512

OSPRay

Benchmark: particle_volume/pathtracer/real_time

Renaissance

Test: Apache Spark PageRank

CockroachDB

Workload: KV, 95% Reads - Concurrency: 128

Timed Node.js Compilation

Time To Compile

PyBench

Total For Average Test Times

CockroachDB

Workload: KV, 10% Reads - Concurrency: 1024

Timed Linux Kernel Compilation

Build: allmodconfig

Numenta Anomaly Benchmark

Detector: KNN CAD

CockroachDB

Workload: KV, 60% Reads - Concurrency: 512

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

CockroachDB

Workload: KV, 50% Reads - Concurrency: 1024

Renaissance

Test: Finagle HTTP Requests

Zstd Compression

Compression Level: 8 - Compression Speed

OpenVKL

Benchmark: vklBenchmark ISPC

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096

CockroachDB

Workload: KV, 60% Reads - Concurrency: 1024

Intel Open Image Denoise

Run: RT.hdr_alb_nrm.3840x2160

PyPerformance

Benchmark: json_loads

OpenVINO

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

PostgreSQL

Scaling Factor: 100 - Clients: 500 - Mode: Read Only

PostgreSQL

Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency

DaCapo Benchmark

Java Test: Jython

Zstd Compression

Compression Level: 8, Long Mode - Decompression Speed

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

OpenVINO

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

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

Zstd Compression

Compression Level: 19 - Decompression Speed

Zstd Compression

Compression Level: 8 - Decompression Speed

7-Zip Compression

Test: Decompression Rating

Numenta Anomaly Benchmark

Detector: Relative Entropy

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenVINO

Model: Face Detection FP16 - Device: CPU

Blender

Blend File: Classroom - Compute: CPU-Only

OpenVINO

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