extra tests

benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2309060-NE-EXTRATEST87&sro&grs.

Stress-NG

Test: Semaphores

Stress-NG

Test: Pipe

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

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

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

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

Neural Magic DeepSparse

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

Neural Magic DeepSparse

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

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

Stress-NG

Test: x86_64 RdRand

Stress-NG

Test: Hash

Stress-NG

Test: Context Switching

Stress-NG

Test: Vector Shuffle

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream

NCNN

Target: CPU - Model: regnety_400m

Stress-NG

Test: Floating Point

Stress-NG

Test: CPU Stress

Stress-NG

Test: Function Call

Stress-NG

Test: Matrix Math

Stress-NG

Test: Vector Floating Point

Stress-NG

Test: Fused Multiply-Add

Stress-NG

Test: Zlib

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

Blender

Blend File: Classroom - Compute: CPU-Only

Stress-NG

Test: Vector Math

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

Stress-NG

Test: AVX-512 VNNI

Stress-NG

Test: Memory Copying

Stress-NG

Test: Wide Vector Math

Stress-NG

Test: Glibc Qsort Data Sorting

Stress-NG

Test: Malloc

Stress-NG

Test: Glibc C String Functions

Blender

Blend File: Barbershop - Compute: CPU-Only

Blender

Blend File: BMW27 - Compute: CPU-Only

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

Embree

Binary: Pathtracer - Model: Asian Dragon

Embree

Binary: Pathtracer - Model: Asian Dragon Obj

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

Neural Magic DeepSparse

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

Embree

Binary: Pathtracer - Model: Crown

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

Embree

Binary: Pathtracer ISPC - Model: Crown

Stress-NG

Test: Poll

Blender

Blend File: Fishy Cat - Compute: CPU-Only

NCNN

Target: CPU - Model: blazeface

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

Stress-NG

Test: SENDFILE

OSPRay

Benchmark: particle_volume/ao/real_time

OSPRay

Benchmark: particle_volume/scivis/real_time

Stress-NG

Test: Crypto

NCNN

Target: CPU - Model: shufflenet-v2

Stress-NG

Test: Forking

Stress-NG

Test: AVL Tree

Stress-NG

Test: CPU Cache

Stress-NG

Test: MMAP

NCNN

Target: CPU - Model: efficientnet-b0

NCNN

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

Stress-NG

Test: NUMA

NCNN

Target: CPU - Model: mnasnet

NCNN

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

NCNN

Target: CPU - Model: FastestDet

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream

Intel Open Image Denoise

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

Intel Open Image Denoise

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

NCNN

Target: CPU - Model: squeezenet_ssd

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

Intel Open Image Denoise

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

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream

Dragonflydb

Clients Per Thread: 20 - Set To Get Ratio: 1:100

Dragonflydb

Clients Per Thread: 10 - Set To Get Ratio: 1:100

NCNN

Target: CPU - Model: resnet18

NCNN

Target: CPU - Model: alexnet

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream

Dragonflydb

Clients Per Thread: 10 - Set To Get Ratio: 1:10

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream

NCNN

Target: CPU - Model: vgg16

NCNN

Target: CPU - Model: resnet50

Dragonflydb

Clients Per Thread: 20 - Set To Get Ratio: 1:10

NCNN

Target: CPU - Model: mobilenet

NCNN

Target: CPU - Model: vision_transformer

Stress-NG

Test: Socket Activity

BRL-CAD

VGR Performance Metric

Stress-NG

Test: MEMFD

NCNN

Target: CPU - Model: googlenet

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream

SPECFEM3D

Model: Layered Halfspace

SPECFEM3D

Model: Mount St. Helens

Neural Magic DeepSparse

Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream

Neural Magic DeepSparse

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

SPECFEM3D

Model: Water-layered Halfspace

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream

Stress-NG

Test: Futex

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream

Neural Magic DeepSparse

Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream