AMD 3D V-Cache Comparison

Tests for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2204299-NE-CC771232156&grs.

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel

ASKAP

Test: tConvolve OpenMP - Gridding

ECP-CANDLE

Benchmark: P3B2

ASKAP

Test: tConvolve MT - Gridding

LeelaChessZero

Backend: BLAS

LeelaChessZero

Backend: Eigen

oneDNN

Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU

ECP-CANDLE

Benchmark: P3B1

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

ASKAP

Test: tConvolve MT - Degridding

OpenFOAM

Input: Motorbike 60M

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

ASKAP

Test: tConvolve OpenMP - Degridding

oneDNN

Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

ASKAP

Test: Hogbom Clean OpenMP

Mobile Neural Network

Model: mobilenet-v1-1.0

ONNX Runtime

Model: yolov4 - Device: CPU - Executor: Parallel

OpenFOAM

Input: Motorbike 30M

Mobile Neural Network

Model: mobilenetV3

ASKAP

Test: tConvolve MPI - Gridding

WebP2 Image Encode

Encode Settings: Quality 100, Lossless Compression

Mlpack Benchmark

Benchmark: scikit_qda

WebP2 Image Encode

Encode Settings: Quality 100, Compression Effort 5

TNN

Target: CPU - Model: SqueezeNet v1.1

WebP2 Image Encode

Encode Settings: Quality 75, Compression Effort 7

WebP2 Image Encode

Encode Settings: Quality 95, Compression Effort 7

ASKAP

Test: tConvolve MPI - Degridding

Mlpack Benchmark

Benchmark: scikit_svm

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Parallel

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

Mobile Neural Network

Model: MobileNetV2_224

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

WebP2 Image Encode

Encode Settings: Default

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

oneDNN

Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU

TNN

Target: CPU - Model: DenseNet

ECP-CANDLE

Benchmark: P1B2

Mobile Neural Network

Model: squeezenetv1.1

ONNX Runtime

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

TNN

Target: CPU - Model: SqueezeNet v2

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Standard

TNN

Target: CPU - Model: MobileNet v2

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Parallel

NCNN

Target: CPU - Model: alexnet

oneDNN

Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Parallel

NCNN

Target: CPU - Model: resnet50

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 200

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 8

Open Porous Media Git

OPM Benchmark: Flow MPI Norne-4C MSW - Threads: 8

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 100

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 100

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 200

Numpy Benchmark

NCNN

Target: CPU - Model: squeezenet_ssd

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

oneDNN

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

oneDNN

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

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 8

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 4

Open Porous Media Git

OPM Benchmark: Flow MPI Norne-4C MSW - Threads: 4

Mlpack Benchmark

Benchmark: scikit_ica

Open Porous Media Git

OPM Benchmark: Flow MPI Norne-4C MSW - Threads: 2

Open Porous Media Git

OPM Benchmark: Flow MPI Norne-4C MSW - Threads: 1

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 1

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 4

Open Porous Media Git

OPM Benchmark: Flow MPI Norne - Threads: 2

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 2

Open Porous Media Git

OPM Benchmark: Flow MPI Extra - Threads: 1

oneDNN

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

oneDNN

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

oneDNN

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

Mobile Neural Network

Model: inception-v3

WebP2 Image Encode

CPU Peak Freq (Highest CPU Core Frequency) Monitor

WebP2 Image Encode

CPU Peak Freq (Highest CPU Core Frequency) Monitor

WebP2 Image Encode

CPU Peak Freq (Highest CPU Core Frequency) Monitor

WebP2 Image Encode

CPU Peak Freq (Highest CPU Core Frequency) Monitor

WebP2 Image Encode

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Open Porous Media Git

CPU Peak Freq (Highest CPU Core Frequency) Monitor

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Phoronix Test Suite System Monitoring

Xcompact3d Incompact3d

CPU Peak Freq (Highest CPU Core Frequency) Monitor