AMD Ryzen 7 9800X3D Linux Benchmarks

AMD Ryzen 7 9800X3D Linux performance benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2411063-NE-AMDRYZEN744&sor&grs.

CockroachDB

Workload: KV, 60% Reads - Concurrency: 128

Cpuminer-Opt

Algorithm: Myriad-Groestl

Cpuminer-Opt

Algorithm: Skeincoin

DuckDB

Benchmark: TPC-H Parquet

ASKAP

Test: tConvolve MT - Gridding

simdjson

Throughput Test: TopTweet

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400

simdjson

Throughput Test: DistinctUserID

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Mesh Time

NAS Parallel Benchmarks

Test / Class: CG.C

CockroachDB

Workload: KV, 95% Reads - Concurrency: 128

Radiance Benchmark

Test: SMP Parallel

ScyllaDB

Test: Writes

ASKAP

Test: tConvolve OpenMP - Gridding

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400

OpenSSL

Algorithm: SHA256

ASKAP

Test: tConvolve MT - Degridding

OpenVINO

Model: Person Detection FP16 - Device: CPU

Pennant

Test: leblancbig

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenRadioss

Model: Chrysler Neon 1M

ASKAP

Test: tConvolve MPI - Degridding

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Mesh Time

SPECFEM3D

Model: Layered Halfspace

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

libxsmm

M N K: 64

x265

Video Input: Bosphorus 4K

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Execution Time

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

ClickHouse

100M Rows Hits Dataset, Third Run

eSpeak-NG Speech Engine

Text-To-Speech Synthesis

Speedb

Test: Read While Writing

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400

OpenSSL

Algorithm: AES-256-GCM

Apache IoTDB

Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400

ASKAP

Test: tConvolve MPI - Gridding

NAS Parallel Benchmarks

Test / Class: BT.C

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only

Ngspice

Circuit: C7552

LuxCoreRender

Scene: Danish Mood - Acceleration: CPU

libavif avifenc

Encoder Speed: 6, Lossless

NAS Parallel Benchmarks

Test / Class: SP.B

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency

PostgreSQL

Scaling Factor: 100 - Clients: 1000 - Mode: Read Only

OpenSSL

Algorithm: SHA512

Git

Time To Complete Common Git Commands

Ngspice

Circuit: C2670

Apache HTTP Server

Concurrent Requests: 500

simdjson

Throughput Test: Kostya

TensorFlow

Device: CPU - Batch Size: 64 - Model: ResNet-50

CloverLeaf

Input: clover_bm

7-Zip Compression

Test: Compression Rating

RocksDB

Test: Read While Writing

Whisper.cpp

Model: ggml-small.en - Input: 2016 State of the Union

OpenRadioss

Model: Cell Phone Drop Test

BRL-CAD

VGR Performance Metric

Blender

Blend File: BMW27 - Compute: CPU-Only

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

GEGL

Operation: Scale

GPAW

Input: Carbon Nanotube

GraphicsMagick

Operation: Sharpen

SPECFEM3D

Model: Homogeneous Halfspace

Blender

Blend File: Junkshop - Compute: CPU-Only

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

Coremark

CoreMark Size 666 - Iterations Per Second

Speedb

Test: Update Random

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

NAS Parallel Benchmarks

Test / Class: LU.C

TensorFlow

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

DuckDB

Benchmark: Clickbench

Stockfish

Chess Benchmark

Parallel BZIP2 Compression

FreeBSD-13.0-RELEASE-amd64-memstick.img Compression

Apache HTTP Server

Concurrent Requests: 1000

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

Cpuminer-Opt

Algorithm: Ringcoin

Whisper.cpp

Model: ggml-medium.en - Input: 2016 State of the Union

GraphicsMagick

Operation: Resizing

Speedb

Test: Random Read

PyPerformance

Benchmark: nbody

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

ClickHouse

100M Rows Hits Dataset, First Run / Cold Cache

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenSCAD

Render: Pistol

GIMP

Test: auto-levels

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K

LuxCoreRender

Scene: Rainbow Colors and Prism - Acceleration: CPU

QuantLib

Size: XXS

GIMP

Test: rotate

Selenium

Benchmark: PSPDFKit WASM - Browser: Firefox

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

Liquid-DSP

Threads: 1 - Buffer Length: 256 - Filter Length: 512

DaCapo Benchmark

Java Test: H2 Database Engine

SPECFEM3D

Model: Water-layered Halfspace

GIMP

Test: unsharp-mask

RocksDB

Test: Random Read

OpenVINO

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

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenSCAD

Render: Leonardo Phone Case Slim

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

OpenVINO

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

FFmpeg

Encoder: libx265 - Scenario: Live

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

Zstd Compression

Compression Level: 19 - Compression Speed

ClickHouse

100M Rows Hits Dataset, Second Run

WebP Image Encode

Encode Settings: Quality 100, Lossless, Highest Compression

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 4K

Intel Open Image Denoise

Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only

OpenVINO

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

Cryptsetup

PBKDF2-sha512

Java JMH

Throughput

OpenSSL

Algorithm: AES-128-GCM

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

PyPerformance

Benchmark: regex_compile

ASKAP

Test: tConvolve OpenMP - Degridding

Blender

Blend File: Fishy Cat - Compute: CPU-Only

SVT-HEVC

Tuning: 10 - Input: Bosphorus 4K