AMD EPYC Turin 8c vs. 12c Memory Channel DDR5 Comparison

AMD EPYC 9655P memory benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2411164-NE-AMDEPYCTU56.

RAMspeed SMP

Type: Add - Benchmark: Integer

RAMspeed SMP

Type: Copy - Benchmark: Integer

RAMspeed SMP

Type: Scale - Benchmark: Integer

RAMspeed SMP

Type: Triad - Benchmark: Integer

RAMspeed SMP

Type: Average - Benchmark: Integer

Stream

Type: Copy

Stream

Type: Scale

Stream

Type: Triad

Stream

Type: Add

MBW

Test: Memory Copy - Array Size: 4096 MiB

MBW

Test: Memory Copy - Array Size: 8192 MiB

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB

High Performance Conjugate Gradient

X Y Z: 104 104 104 - RT: 60

High Performance Conjugate Gradient

X Y Z: 144 144 144 - RT: 60

NAS Parallel Benchmarks

Test / Class: BT.C

NAS Parallel Benchmarks

Test / Class: CG.C

NAS Parallel Benchmarks

Test / Class: EP.C

NAS Parallel Benchmarks

Test / Class: EP.D

NAS Parallel Benchmarks

Test / Class: FT.C

NAS Parallel Benchmarks

Test / Class: IS.D

NAS Parallel Benchmarks

Test / Class: LU.C

NAS Parallel Benchmarks

Test / Class: MG.C

NAS Parallel Benchmarks

Test / Class: SP.B

NAS Parallel Benchmarks

Test / Class: SP.C

miniBUDE

Implementation: OpenMP - Input Deck: BM2

miniBUDE

Implementation: OpenMP - Input Deck: BM2

NAMD

Input: ATPase with 327,506 Atoms

NAMD

Input: STMV with 1,066,628 Atoms

Algebraic Multi-Grid Benchmark

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Mesh Time

OpenFOAM

Input: drivaerFastback, Small Mesh Size - Execution Time

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Mesh Time

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

OpenRadioss

Model: Chrysler Neon 1M

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

SPECFEM3D

Model: Mount St. Helens

SPECFEM3D

Model: Layered Halfspace

SPECFEM3D

Model: Tomographic Model

SPECFEM3D

Model: Homogeneous Halfspace

SPECFEM3D

Model: Water-layered Halfspace

srsRAN Project

Test: PDSCH Processor Benchmark, Throughput Total

srsRAN Project

Test: PUSCH Processor Benchmark, Throughput Total

John The Ripper

Test: bcrypt

John The Ripper

Test: WPA PSK

John The Ripper

Test: Blowfish

John The Ripper

Test: HMAC-SHA512

John The Ripper

Test: MD5

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Slow

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Medium

Kvazaar

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

Kvazaar

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

Kvazaar

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

SVT-AV1

Encoder Mode: Preset 3 - Input: Bosphorus 4K

SVT-AV1

Encoder Mode: Preset 5 - Input: Bosphorus 4K

SVT-AV1

Encoder Mode: Preset 8 - Input: Bosphorus 4K

SVT-AV1

Encoder Mode: Preset 13 - Input: Bosphorus 4K

SVT-AV1

Encoder Mode: Preset 3 - Input: Beauty 4K 10-bit

SVT-AV1

Encoder Mode: Preset 5 - Input: Beauty 4K 10-bit

SVT-AV1

Encoder Mode: Preset 8 - Input: Beauty 4K 10-bit

SVT-AV1

Encoder Mode: Preset 13 - Input: Beauty 4K 10-bit

uvg266

Video Input: Bosphorus 4K - Video Preset: Slow

uvg266

Video Input: Bosphorus 4K - Video Preset: Medium

uvg266

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

uvg266

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

uvg266

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

VVenC

Video Input: Bosphorus 4K - Video Preset: Fast

VVenC

Video Input: Bosphorus 4K - Video Preset: Faster

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 512

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 512

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 1024

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 1024

Timed Godot Game Engine Compilation

Time To Compile

Timed Linux Kernel Compilation

Build: defconfig

Timed Linux Kernel Compilation

Build: allmodconfig

Build2

Time To Compile

oneDNN

Harness: IP Shapes 1D - Engine: CPU

oneDNN

Harness: IP Shapes 3D - Engine: CPU

oneDNN

Harness: Convolution Batch Shapes Auto - Engine: CPU

oneDNN

Harness: Deconvolution Batch shapes_1d - Engine: CPU

oneDNN

Harness: Deconvolution Batch shapes_3d - Engine: CPU

oneDNN

Harness: Recurrent Neural Network Training - Engine: CPU

oneDNN

Harness: Recurrent Neural Network Inference - Engine: CPU

Liquid-DSP

Threads: 64 - Buffer Length: 256 - Filter Length: 57

Liquid-DSP

Threads: 128 - Buffer Length: 256 - Filter Length: 57

Liquid-DSP

Threads: 192 - Buffer Length: 256 - Filter Length: 57

Liquid-DSP

Threads: 64 - Buffer Length: 256 - Filter Length: 512

Liquid-DSP

Threads: 128 - Buffer Length: 256 - Filter Length: 512

Liquid-DSP

Threads: 192 - Buffer Length: 256 - Filter Length: 512

Graph500

Scale: 26

Graph500

Scale: 26

Graph500

Scale: 26

Graph500

Scale: 26

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

PostgreSQL

Scaling Factor: 1000 - Clients: 800 - Mode: Read Only

PostgreSQL

Scaling Factor: 1000 - Clients: 800 - Mode: Read Only - Average Latency

PostgreSQL

Scaling Factor: 1000 - Clients: 800 - Mode: Read Write

PostgreSQL

Scaling Factor: 1000 - Clients: 800 - Mode: Read Write - Average Latency

TensorFlow

Device: CPU - Batch Size: 512 - Model: ResNet-50

RawTherapee

Total Benchmark Time

GPAW

Input: Carbon Nanotube

Blender

Blend File: BMW27 - Compute: CPU-Only

Blender

Blend File: Junkshop - Compute: CPU-Only

Blender

Blend File: Classroom - Compute: CPU-Only

Blender

Blend File: Fishy Cat - Compute: CPU-Only

Blender

Blend File: Barbershop - Compute: CPU-Only

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenVINO

Model: Face Detection Retail FP16-INT8 - Device: CPU

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

OpenVINO

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

nginx

Connections: 500

Apache HTTP Server

Concurrent Requests: 500

Whisperfile

Model Size: Small

Whisperfile

Model Size: Medium

Epoch

Epoch3D Deck: Cone

WarpX

Input: Uniform Plasma

WarpX

Input: Plasma Acceleration

LuxCoreRender

Scene: DLSC - Acceleration: CPU

LuxCoreRender

Scene: Danish Mood - Acceleration: CPU

LuxCoreRender

Scene: Orange Juice - Acceleration: CPU

LuxCoreRender

Scene: LuxCore Benchmark - Acceleration: CPU

LuxCoreRender

Scene: Rainbow Colors and Prism - Acceleration: CPU

OpenVKL

Benchmark: vklBenchmarkCPU ISPC

7-Zip Compression

Test: Compression Rating

7-Zip Compression

Test: Decompression Rating

m-queens