Intel Core Ultra 9 285K Linux Performance

Intel Core Ultra 9 285K Arrow Lake performance benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2410249-NE-285KARROW75&rdt&grs.

Whisper.cpp

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

ASKAP

Test: tConvolve MT - Degridding

Whisper.cpp

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

Pennant

Test: leblancbig

NAS Parallel Benchmarks

Test / Class: CG.C

Whisper.cpp

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

ASKAP

Test: tConvolve MT - Gridding

libxsmm

M N K: 32

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

libxsmm

M N K: 64

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Execution Time

OpenRadioss

Model: Rubber O-Ring Seal Installation

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

PyTorch

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

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

CloverLeaf

Input: clover_bm

PyTorch

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

GPAW

Input: Carbon Nanotube

NAS Parallel Benchmarks

Test / Class: SP.B

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

RocksDB

Test: Read Random Write Random

OpenRadioss

Model: Bumper Beam

SPECFEM3D

Model: Tomographic Model

OpenRadioss

Model: Bird Strike on Windshield

ASKAP

Test: tConvolve MPI - Gridding

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 512

ASKAP

Test: tConvolve MPI - Degridding

ACES DGEMM

Sustained Floating-Point Rate

OpenRadioss

Model: Cell Phone Drop Test

SPECFEM3D

Model: Mount St. Helens

Xmrig

Variant: GhostRider - Hash Count: 1M

GIMP

Test: rotate

SPECFEM3D

Model: Homogeneous Halfspace

Darktable

Test: Server Rack - Acceleration: CPU-only

NAS Parallel Benchmarks

Test / Class: BT.C

SPECFEM3D

Model: Water-layered Halfspace

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 512

VKMark

Resolution: 3840 x 2160 - Present Mode: Mailbox

NAS Parallel Benchmarks

Test / Class: LU.C

PyPerformance

Benchmark: python_startup

Google Draco

Model: Church Facade

ASTC Encoder

Preset: Exhaustive

SVT-VP9

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

TensorFlow

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

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 4K

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Mesh Time

RawTherapee

Total Benchmark Time

Darktable

Test: Masskrug - Acceleration: CPU-only

TensorFlow

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

ClickHouse

100M Rows Hits Dataset, Second Run

Node.js V8 Web Tooling Benchmark

QuantLib

Size: XXS

Selenium

Benchmark: Speedometer 3.0 - Browser: Google Chrome

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

ASTC Encoder

Preset: Very Thorough

Darktable

Test: Server Room - Acceleration: CPU-only

Stockfish

Chess Benchmark

AOM AV1

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K

LAMMPS Molecular Dynamics Simulator

Model: 20k Atoms

Speedb

Test: Update Random

Ngspice

Circuit: C2670

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

GIMP

Test: unsharp-mask

Xonotic

Resolution: 3840 x 2160 - Effects Quality: Ultra

ClickHouse

100M Rows Hits Dataset, First Run / Cold Cache

GIMP

Test: auto-levels

Apache IoTDB

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

Memcached

Set To Get Ratio: 1:10

DaCapo Benchmark

Java Test: H2 Database Engine

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP16 - Device: CPU

Blender

Blend File: Junkshop - Compute: CPU-Only

NAS Parallel Benchmarks

Test / Class: EP.C

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 1024

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenVINO

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

PJSIP

Method: OPTIONS, Stateful

Z3 Theorem Prover

SMT File: 2.smt2

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

Zstd Compression

Compression Level: 19 - Compression Speed

srsRAN Project

Test: PDSCH Processor Benchmark, Throughput Total

ClickHouse

100M Rows Hits Dataset, Third Run

Speedb

Test: Read Random Write Random

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Medium

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

Ngspice

Circuit: C7552

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenVINO

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

OpenVINO

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

OpenVINO

Model: Noise Suppression Poconet-Like FP16 - Device: CPU

SPECFEM3D

Model: Layered Halfspace

LuxCoreRender

Scene: DLSC - Acceleration: CPU

Timed PHP Compilation

Time To Compile

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

Xonotic

Resolution: 3840 x 2160 - Effects Quality: High

GraphicsMagick

Operation: Enhanced

7-Zip Compression

Test: Compression Rating

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

SVT-HEVC

Tuning: 10 - Input: Bosphorus 4K

OpenVINO

Model: Road Segmentation ADAS FP16-INT8 - Device: CPU

PostgreSQL

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

PostgreSQL

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

Embree

Binary: Pathtracer - Model: Asian Dragon

VVenC

Video Input: Bosphorus 4K - Video Preset: Faster

Google Draco

Model: Lion

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p

Timed FFmpeg Compilation

Time To Compile

ScyllaDB

Test: Writes

NAMD

Input: STMV with 1,066,628 Atoms

OpenVINO

Model: Person Re-Identification Retail FP16 - Device: CPU

OpenSCAD

Render: Pistol

Appleseed

Scene: Disney Material

AOM AV1

Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

Stargate Digital Audio Workstation

Sample Rate: 44100 - Buffer Size: 512

OpenVINO

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

Selenium

Benchmark: PSPDFKit WASM - Browser: Google Chrome

RocksDB

Test: Read While Writing

Z3 Theorem Prover

SMT File: 1.smt2

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Slow

Xonotic

Resolution: 3840 x 2160 - Effects Quality: Ultimate

Kvazaar

Video Input: Bosphorus 1080p - Video Preset: Very Fast

Intel Open Image Denoise

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

Apache IoTDB

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

PyPerformance

Benchmark: async_tree_io

Radiance Benchmark

Test: SMP Parallel

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU

Cpuminer-Opt

Algorithm: Deepcoin

Cpuminer-Opt

Algorithm: Myriad-Groestl

OpenVINO

Model: Handwritten English Recognition FP16-INT8 - Device: CPU