AutoMap: Automatic Mapping of Neural Networks to Deep Learning Accelerators for Edge Devices

Emerging deep neural networks (DNNs) have been emerging in applications (object detection, automatic speech recognition, etc.) deployed on edge devices. To improve the energy efficiency of edge devices, domain-specific deep learning accelerators (DLAs) are designed with limited on-chip resources. Th...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on computer-aided design of integrated circuits and systems 2023-09, Vol.42 (9), p.2994-3006
Hauptverfasser:	Wang, Yanhong, Zhao, Zihao, Jin, Xu, Zheng, Haotian, Nie, Maohua, Zou, Qiaosha, Shi, C.-J. Richard
Format:	Artikel
Sprache:	eng
Schlagworte:	Accelerators Artificial neural networks Automatic speech recognition Chips (memory devices) Computational modeling Deep learning Deep learning accelerator (DLA) deep neural network (DNN) extended directed weighted graph (EDWG) Feature extraction Graph representations Graphical representations Hardware Hardware acceleration Interlayers Machine learning mapper Mapping Memory management Neural networks Object recognition Resource scheduling System-on-chip Task analysis Topology
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!