AMD EPYC Genoa Memory Scaling

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2212240-NE-AMDEPYCGE62&sor&grs.

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

RELION

Test: Basic - Device: CPU

WRF

Input: conus 2.5km

NAS Parallel Benchmarks

Test / Class: MG.C

NAS Parallel Benchmarks

Test / Class: SP.C

Graph500

Scale: 26

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

nekRS

Input: TurboPipe Periodic

OpenVINO

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

OpenVINO

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

TensorFlow

Device: CPU - Batch Size: 256 - Model: ResNet-50

GPAW

Input: Carbon Nanotube

NAS Parallel Benchmarks

Test / Class: CG.C

7-Zip Compression

Test: Compression Rating

OpenVKL

Benchmark: vklBenchmark ISPC

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

NAS Parallel Benchmarks

Test / Class: LU.C

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096

Intel Open Image Denoise

Run: RT.hdr_alb_nrm.3840x2160

Rodinia

Test: OpenMP Streamcluster

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

Apache Cassandra

Test: Writes

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenVINO

Model: Person Detection FP32 - Device: CPU

Xmrig

Variant: Monero - Hash Count: 1M

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP16 - Device: CPU

Timed GDB GNU Debugger Compilation

Time To Compile

Timed Gem5 Compilation

Time To Compile

CockroachDB

Workload: KV, 50% Reads - Concurrency: 512

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

CockroachDB

Workload: KV, 10% Reads - Concurrency: 512

OpenVINO

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

Timed Linux Kernel Compilation

Build: defconfig

OpenVINO

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

Rodinia

Test: OpenMP CFD Solver

Blender

Blend File: BMW27 - Compute: CPU-Only

CockroachDB

Workload: KV, 10% Reads - Concurrency: 1024

Embree

Binary: Pathtracer ISPC - Model: Crown

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OSPRay

Benchmark: particle_volume/scivis/real_time

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

CockroachDB

Workload: KV, 60% Reads - Concurrency: 512

libavif avifenc

Encoder Speed: 10, Lossless

OSPRay

Benchmark: particle_volume/ao/real_time

nginx

Connections: 500

DaCapo Benchmark

Java Test: H2

CockroachDB

Workload: KV, 50% Reads - Concurrency: 1024

libavif avifenc

Encoder Speed: 6

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Medium

7-Zip Compression

Test: Decompression Rating

OpenVINO

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

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

Timed LLVM Compilation

Build System: Ninja

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

Timed Node.js Compilation

Time To Compile

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

simdjson

Throughput Test: TopTweet

DaCapo Benchmark

Java Test: Jython

Blender

Blend File: Barbershop - Compute: CPU-Only

Timed Linux Kernel Compilation

Build: allmodconfig

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

libavif avifenc

Encoder Speed: 0

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

CockroachDB

Workload: KV, 60% Reads - Concurrency: 1024

Timed Apache Compilation

Time To Compile

NWChem

Input: C240 Buckyball

CockroachDB

Workload: MoVR - Concurrency: 512

Timed Godot Game Engine Compilation

Time To Compile

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenRadioss

Model: Bird Strike on Windshield

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

Blender

Blend File: Classroom - Compute: CPU-Only

libavif avifenc

Encoder Speed: 6, Lossless

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenVINO

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

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

Xmrig

Variant: Wownero - Hash Count: 1M

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenVINO

Model: Face Detection FP16 - Device: CPU

ACES DGEMM

Sustained Floating-Point Rate

OpenRadioss

Model: Bumper Beam

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

ASTC Encoder

Preset: Exhaustive

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 1024

OSPRay

Benchmark: particle_volume/pathtracer/real_time

simdjson

Throughput Test: LargeRandom

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenVINO

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

CockroachDB

Workload: MoVR - Concurrency: 1024

simdjson

Throughput Test: PartialTweets

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

Timed MPlayer Compilation

Time To Compile

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

libavif avifenc

Encoder Speed: 2

OpenVINO

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

miniBUDE

Implementation: OpenMP - Input Deck: BM2

miniBUDE

Implementation: OpenMP - Input Deck: BM2

Build2

Time To Compile

ASTC Encoder

Preset: Thorough

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

Timed Mesa Compilation

Time To Compile

NAMD

ATPase Simulation - 327,506 Atoms

simdjson

Throughput Test: DistinctUserID

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 1024

Timed PHP Compilation

Time To Compile

Liquid-DSP

Threads: 256 - Buffer Length: 256 - Filter Length: 57

Liquid-DSP

Threads: 384 - Buffer Length: 256 - Filter Length: 57

simdjson

Throughput Test: Kostya