Ubuntu 21.04 LTS To Ubuntu 21.10 AMD EPYC Milan Benchmarks

AMD EPYC 74F3 24-Core testing of Ubuntu Linux versions by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2110138-TJ-UBUNTUMIL38&sgm=1&sro&grs.

LeelaChessZero

Backend: BLAS

Stress-NG

Test: Socket Activity

VP9 libvpx Encoding

Speed: Speed 5 - Input: Bosphorus 4K

MariaDB

Clients: 512

libavif avifenc

Encoder Speed: 10

VP9 libvpx Encoding

Speed: Speed 0 - Input: Bosphorus 4K

Timed LLVM Compilation

Build System: Unix Makefiles

Timed LLVM Compilation

Build System: Ninja

Timed Linux Kernel Compilation

Time To Compile

Timed Godot Game Engine Compilation

Time To Compile

NAS Parallel Benchmarks

Test / Class: IS.D

NCNN

Target: CPU - Model: regnety_400m

Timed Node.js Compilation

Time To Compile

Stress-NG

Test: Vector Math

Rodinia

Test: OpenMP Leukocyte

JPEG XL libjxl

Input: PNG - Encode Speed: 5

Mobile Neural Network

Model: MobileNetV2_224

Stress-NG

Test: CPU Stress

Apache Cassandra

Test: Writes

Mobile Neural Network

Model: SqueezeNetV1.0

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

NCNN

Target: CPU - Model: vgg16

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: CPU

NAS Parallel Benchmarks

Test / Class: CG.C

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

SVT-HEVC

Tuning: 10 - Input: Bosphorus 1080p

Mobile Neural Network

Model: squeezenetv1.1

libavif avifenc

Encoder Speed: 6

NCNN

Target: CPU - Model: efficientnet-b0

NCNN

Target: CPU - Model: resnet18

NCNN

Target: CPU - Model: mnasnet

NCNN

Target: CPU - Model: resnet50

NCNN

Target: CPU - Model: mobilenet

NAS Parallel Benchmarks

Test / Class: FT.C

NCNN

Target: CPU - Model: squeezenet_ssd

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

Stockfish

Total Time

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

simdjson

Throughput Test: LargeRandom

NAS Parallel Benchmarks

Test / Class: MG.C

SVT-HEVC

Tuning: 7 - Input: Bosphorus 1080p

NAS Parallel Benchmarks

Test / Class: LU.C

JPEG XL libjxl

Input: PNG - Encode Speed: 8

ASTC Encoder

Preset: Thorough

OSPray

Demo: NASA Streamlines - Renderer: SciVis

OpenFOAM

Input: Motorbike 30M

Intel Open Image Denoise

Run: RT.ldr_alb_nrm.3840x2160

Chaos Group V-RAY

Mode: CPU

simdjson

Throughput Test: DistinctUserID

AOM AV1

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K

NAS Parallel Benchmarks

Test / Class: SP.C

NAS Parallel Benchmarks

Test / Class: SP.B

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

libavif avifenc

Encoder Speed: 6, Lossless

libavif avifenc

Encoder Speed: 0

Stress-NG

Test: Matrix Math

ONNX Runtime

Model: fcn-resnet101-11 - Device: OpenMP CPU

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

7-Zip Compression

Compress Speed Test

LuxCoreRender

Scene: LuxCore Benchmark - Acceleration: CPU

simdjson

Throughput Test: Kostya

LuxCoreRender

Scene: Danish Mood - Acceleration: CPU

Appleseed

Scene: Material Tester

Natron

Input: Spaceship

OpenFOAM

Input: Motorbike 60M

OSPray

Demo: San Miguel - Renderer: SciVis

Xmrig

Variant: Monero - Hash Count: 1M

Sysbench

Test: RAM / Memory

LuxCoreRender

Scene: Orange Juice - Acceleration: CPU

ASTC Encoder

Preset: Exhaustive

LuxCoreRender

Scene: DLSC - Acceleration: CPU

Xmrig

Variant: Wownero - Hash Count: 1M

Blender

Blend File: Barbershop - Compute: CPU-Only

NAMD

ATPase Simulation - 327,506 Atoms

Sysbench

Test: CPU

Redis

Test: SET

Rodinia

Test: OpenMP Streamcluster

Geometric Mean Of All Test Results

Result Composite - Ubuntu 21.04 LTS To Ubuntu 21.10 AMD EPYC Milan Benchmarks

Phoronix Test Suite v10.8.5