9684X EOY2024 AMD Linux

2 x AMD EPYC 9684X 96-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 24.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2412303-NE-9684XEOY253&grs&rdt.

XNNPACK

Model: FP32MobileNetV1

LiteRT

Model: DeepLab V3

LiteRT

Model: Mobilenet Quant

LiteRT

Model: Mobilenet Float

XNNPACK

Model: FP32MobileNetV2

miniFE

Problem Size: Small

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 1080p

XNNPACK

Model: QS8MobileNetV2

XNNPACK

Model: FP16MobileNetV1

LiteRT

Model: SqueezeNet

XNNPACK

Model: FP16MobileNetV3Small

NCNN

Target: CPU - Model: yolov4-tiny

NCNN

Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3

NCNN

Target: CPU - Model: mobilenet

NCNN

Target: CPU - Model: vision_transformer

NCNN

Target: CPU - Model: FastestDet

LiteRT

Model: Quantized COCO SSD MobileNet v1

NCNN

Target: CPU - Model: vgg16

NCNN

Target: CPU - Model: mnasnet

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

NCNN

Target: CPU - Model: squeezenet_ssd

NCNN

Target: CPU - Model: shufflenet-v2

NCNN

Target: CPU - Model: alexnet

NCNN

Target: CPU - Model: googlenet

NCNN

Target: CPU - Model: resnet50

NCNN

Target: CPU - Model: resnet18

Stockfish

Chess Benchmark

LiteRT

Model: Inception V4

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128

NCNN

Target: CPU - Model: blazeface

NCNN

Target: CPU - Model: efficientnet-b0

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

XNNPACK

Model: FP16MobileNetV3Large

LiteRT

Model: Inception ResNet V2

LiteRT

Model: NASNet Mobile

XNNPACK

Model: FP32MobileNetV3Small

XNNPACK

Model: FP32MobileNetV3Large

NCNN

Target: CPU - Model: regnety_400m

Apache Cassandra

Test: Writes

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

C-Ray

Resolution: 1080p - Rays Per Pixel: 16

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024

Llama.cpp

Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048

Primesieve

Length: 1e12

srsRAN Project

Test: PUSCH Processor Benchmark, Throughput Total

OpenVINO GenAI

Model: Gemma-7b-int4-ov - Device: CPU

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512

WarpX

Input: Uniform Plasma

OpenVINO GenAI

Model: Falcon-7b-instruct-int4-ov - Device: CPU

Graph500

Scale: 26

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128

XNNPACK

Model: FP16MobileNetV2

GROMACS

Input: water_GMX50_bare

Graph500

Scale: 26

OpenVINO

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

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

Rustls

Benchmark: handshake-resume - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256

NCNN

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

OpenVINO

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

7-Zip Compression

Test: Decompression Rating

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048

WarpX

Input: Plasma Acceleration

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 1080p

Graph500

Scale: 26

srsRAN Project

Test: PDSCH Processor Benchmark, Throughput Total

Llama.cpp

Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024

x265

Video Input: Bosphorus 1080p

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 4K

OpenVINO

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

Etcpak

Benchmark: Multi-Threaded - Configuration: ETC2

OpenVINO

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

OpenVINO

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

RELION

Test: Basic - Device: CPU

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenVINO GenAI

Model: Phi-3-mini-128k-instruct-int4-ov - Device: CPU

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048

Blender

Blend File: Fishy Cat - Compute: CPU-Only

Graph500

Scale: 26

OpenSSL

Algorithm: RSA4096

Rustls

Benchmark: handshake-ticket - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384

7-Zip Compression

Test: Compression Rating

Rustls

Benchmark: handshake-resume - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384

Intel Open Image Denoise

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

Rustls

Benchmark: handshake-ticket - Suite: TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256

Laghos

Test: Sedov Blast Wave, ube_922_hex.mesh

OpenVINO

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

x265

Video Input: Bosphorus 1080p

OpenVINO GenAI

Model: TinyLlama-1.1B-Chat-v1.0 - Device: CPU

Blender

Blend File: BMW27 - Compute: CPU-Only

C-Ray

Resolution: 4K - Rays Per Pixel: 16

Build2

Time To Compile

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 1080p

7-Zip Compression

Test: Compression Rating

Timed FFmpeg Compilation

Time To Compile

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

Epoch

Epoch3D Deck: Cone

Intel Open Image Denoise

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

OSPRay

Benchmark: particle_volume/pathtracer/real_time

Timed Eigen Compilation

Time To Compile

7-Zip Compression

Test: Decompression Rating

Blender

Blend File: Junkshop - Compute: CPU-Only

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 4K

Timed Linux Kernel Compilation

Build: defconfig

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

Y-Cruncher

Pi Digits To Calculate: 500M

NAMD

Input: STMV with 1,066,628 Atoms

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

Blender

Blend File: Barbershop - Compute: CPU-Only

Laghos

Test: Triple Point Problem

Timed Linux Kernel Compilation

Build: allmodconfig

OpenVINO

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

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

Rustls

Benchmark: handshake - Suite: TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

Palabos

Grid Size: 100

OpenVINO

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

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP16 - Device: CPU

C-Ray

Resolution: 5K - Rays Per Pixel: 16

WebP Image Encode

Encode Settings: Default

Llama.cpp

Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128

OpenVINO

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

OpenVINO

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

x265

Video Input: Bosphorus 4K

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU

OSPRay Studio

Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU

x265

Video Input: Bosphorus 4K

OSPRay Studio

Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU