Delay-aware DNN inference throughput maximization in edge computing via jointly exploring partitioning and parallelism

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Fingerprint

???publication_fingerprints_help???

Computer Science

100
Parallelism Computer Science
100
Partitioning Computer Science
100
Throughput Computer Science
100
Network Inference Computer Science
100
Edge Computing Computer Science
100
Deep Neural Network Computer Science
40
Multi-Access Edge C... Computer Science
20
Algorithms Computer Science
20
Cloudlet Computer Science
10
User Computer Science
10
Experimental Result Computer Science
10
Approximation Algor... Computer Science
10
Service Computer Science
10
Neural Network Mode... Computer Science
10
Mobile Application Computer Science
10
Network Service Computer Science
10
Maximization Proble... Computer Science
10
Intensive Task Computer Science
10
Multiple Thread Computer Science
10
Service Request Computer Science
10
Inference Model Computer Science
10
Internet of Things ... Computer Science
10
Thread Parallelism Computer Science
10
Edge Intelligence Computer Science
10
Deep Learning Metho... Computer Science
10
Internet-Of-Things Computer Science

Keyphrases

100
Parallelization Keyphrases
100
Throughput Maximiza... Keyphrases
100
Edge Computing Keyphrases
100
Delay-aware Keyphrases
100
Deep Neural Network... Keyphrases
37
Mobile Edge Computi... Keyphrases
25
Deep Neural Network Keyphrases
25
Cloudlet Keyphrases
12
NP-hard Keyphrases
12
Experimental Simula... Keyphrases
12
One-part Keyphrases
12
Mobile Application Keyphrases
12
Catering Keyphrases
12
Maximization Proble... Keyphrases
12
Network Services Keyphrases
12
Constant-factor App... Keyphrases
12
Deep Learning Keyphrases
12
Multiple Threads Keyphrases
12
Mobile Edge Computi... Keyphrases
12
Compute-intensive Keyphrases
12
Service Request Keyphrases
12
Internet of Things ... Keyphrases
12
Model Partition Keyphrases
12
Thread-level Parall... Keyphrases
12
Multi-thread Keyphrases
12
Inference Model Keyphrases
12
Artificial Intellig... Keyphrases
12
Inference Service Keyphrases
12
Real-time Deep Neur... Keyphrases
12
Edge Intelligence Keyphrases

INIS

100
neural networks INIS
30
algorithms INIS
20
processing INIS
20
internet INIS
10
learning INIS
10
shape INIS
10
approximations INIS
10
performance INIS
10
applications INIS
10
simulation INIS
10
devices INIS
10
explosions INIS
Research OutputsResearch Output authored by Delay-aware DNN inference throughput maximization in edge computing via jointly exploring partitioning and parallelism is tagged with the concept