Xeon EPYC Tests

Tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2002018-VE-XEONEPYCT45&sor&grr.

Timed GCC Compilation

Time To Compile

QMCPACK

MariaDB

Clients: 256

MKL-DNN DNNL

Harness: Convolution Batch conv_all - Data Type: f32

Blender

Blend File: Barbershop - Compute: CPU-Only

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

MariaDB

Clients: 128

High Performance Conjugate Gradient

Blender

Blend File: Classroom - Compute: CPU-Only

MKL-DNN DNNL

Harness: Deconvolution Batch deconv_all - Data Type: f32

dav1d

Video Input: Chimera 1080p 10-bit

Polyhedron Fortran Benchmarks

Benchmark: tfft2

OSPray

Demo: San Miguel - Renderer: Path Tracer

POV-Ray

Trace Time

Numpy Benchmark

Appleseed

Scene: Emily

asmFish

1024 Hash Memory, 26 Depth

GROMACS

Water Benchmark

Timed MrBayes Analysis

Primate Phylogeny Analysis

OSPray

Demo: NASA Streamlines - Renderer: Path Tracer

Parboil

Test: OpenMP MRI Gridding

OSPray

Demo: San Miguel - Renderer: SciVis

Polyhedron Fortran Benchmarks

Benchmark: test_fpu2

AOM AV1

Encoder Mode: Speed 4 Realtime

MKL-DNN DNNL

Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32

Appleseed

Scene: Disney Material

Appleseed

Scene: Material Tester

NAMD

ATPase Simulation - 327,506 Atoms

GEGL

Operation: Cartoon

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Write

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

NAS Parallel Benchmarks

Test / Class: EP.D

DeepSpeech

Acceleration: CPU

Stockfish

Total Time

Parboil

Test: OpenMP LBM

NAS Parallel Benchmarks

Test / Class: BT.C

PyPerformance

Benchmark: raytrace

Timed LLVM Compilation

Time To Compile

rav1e

Speed: 6

Build2

Time To Compile

librsvg

Operation: SVG Files To PNG

rav1e

Speed: 9

GEGL

Operation: Wavelet Blur

Apache Siege

Concurrent Users: 200

VP9 libvpx Encoding

Speed: Speed 5

GEGL

Operation: Color Enhance

SQLite Speedtest

Timed Time - Size 1,000

Polyhedron Fortran Benchmarks

Benchmark: protein

NAS Parallel Benchmarks

Test / Class: LU.C

AOM AV1

Encoder Mode: Speed 6 Realtime

Chaos Group V-RAY

Mode: CPU

Chaos Group V-RAY

Mode: CPU

ASKAP

Test: tConvolve MPI - Degridding

ASKAP

Test: tConvolve MPI - Gridding

Polyhedron Fortran Benchmarks

Benchmark: rnflow

GraphicsMagick

Operation: Rotate

IndigoBench

Scene: Bedroom

IndigoBench

Scene: Supercar

C-Ray

Total Time - 4K, 16 Rays Per Pixel

Timed Linux Kernel Compilation

Time To Compile

GraphicsMagick

Operation: Sharpen

GraphicsMagick

Operation: Noise-Gaussian

GraphicsMagick

Operation: Enhanced

Facebook RocksDB

Test: Read While Writing

GraphicsMagick

Operation: Swirl

Facebook RocksDB

Test: Random Read

GraphicsMagick

Operation: HWB Color Space

7-Zip Compression

Compress Speed Test

NGINX Benchmark

Static Web Page Serving

AOM AV1

Encoder Mode: Speed 5 Two-Pass

OSPray

Demo: NASA Streamlines - Renderer: SciVis

miniFE

Problem Size: Small

GEGL

Operation: Rotate 90 Degrees

GEGL

Operation: Antialias

NAS Parallel Benchmarks

Test / Class: IS.D

Embree

Binary: Pathtracer - Model: Crown

Embree

Binary: Pathtracer ISPC - Model: Crown

Himeno Benchmark

Poisson Pressure Solver

ACES DGEMM

Sustained Floating-Point Rate

MKL-DNN DNNL

Harness: IP Batch All - Data Type: f32

Apache Benchmark

Static Web Page Serving

Rodinia

Test: OpenMP Streamcluster

PyPerformance

Benchmark: regex_compile

Embree

Binary: Pathtracer - Model: Asian Dragon

NAS Parallel Benchmarks

Test / Class: SP.B

GEGL

Operation: Reflect

OSPray

Demo: Magnetic Reconnection - Renderer: SciVis

GEGL

Operation: Tile Glass

MKL-DNN DNNL

Harness: Convolution Batch conv_3d - Data Type: f32

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

MKL-DNN DNNL

Harness: Recurrent Neural Network Training - Data Type: f32

Inkscape

Operation: SVG Files To PNG

Scikit-Learn

PyPerformance

Benchmark: django_template

Coremark

CoreMark Size 666 - Iterations Per Second

John The Ripper

Test: Blowfish

Tungsten Renderer

Scene: Water Caustic

dav1d

Video Input: Summer Nature 4K

XZ Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9

NAS Parallel Benchmarks

Test / Class: FT.C

AOM AV1

Encoder Mode: Speed 8 Realtime

SVT-AV1

Encoder Mode: Enc Mode 4 - Input: 1080p

Facebook RocksDB

Test: Sequential Fill

NAS Parallel Benchmarks

Test / Class: CG.C

Mlpack Benchmark

Benchmark: scikit_svm

Tungsten Renderer

Scene: Non-Exponential

Rodinia

Test: OpenMP LavaMD

Apache Siege

Concurrent Users: 250

Memcached mcperf

Method: Set

Tungsten Renderer

Scene: Hair

PyPerformance

Benchmark: crypto_pyaes

MKL-DNN DNNL

Harness: Deconvolution Batch deconv_1d - Data Type: f32

Polyhedron Fortran Benchmarks

Benchmark: linpk

x265

H.265 1080p Video Encoding

GIMP

Test: unsharp-mask

rays1bench

Large Scene

MKL-DNN DNNL

Harness: IP Batch 1D - Data Type: f32

MKL-DNN DNNL

Harness: Convolution Batch conv_alexnet - Data Type: f32

Memcached mcperf

Method: Delete

GIMP

Test: rotate

Memcached mcperf

Method: Get

Rodinia

Test: OpenMP CFD Solver

NAS Parallel Benchmarks

Test / Class: MG.C

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

GNU Octave Benchmark

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

Darktable

Test: Boat - Acceleration: CPU-only

GIMP

Test: auto-levels

GEGL

Operation: Crop

Parboil

Test: OpenMP Stencil

Tungsten Renderer

Scene: Volumetric Caustic

Intel Open Image Denoise

Scene: Memorial

Smallpt

Global Illumination Renderer; 128 Samples

GIMP

Test: resize

libjpeg-turbo tjbench

Test: Decompression Throughput

GEGL

Operation: Scale

Darktable

Test: Masskrug - Acceleration: CPU-only

Darktable

Test: Server Room - Acceleration: CPU-only

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p