A Low-Power Sparse Convolutional Neural Network Accelerator With Pre-Encoding Radix-4 Booth Multiplier

Working on edging device, convolutional neural network (CNN) inference application demands low-power consumption and high-performance computation. Therefore, exploiting energy-efficient multiply-and-accumulate (MAC) unit and high-throughput sparse CNN accelerator is of great importance. In this brie...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on circuits and systems. II, Express briefs Express briefs, 2023-06, Vol.70 (6), p.2246-2250
Hauptverfasser:	Cheng, Quan, Dai, Liuyao, Huang, Mingqiang, Shen, Ao, Mao, Wei, Hashimoto, Masanori, Yu, Hao
Format:	Artikel
Sprache:	eng
Schlagworte:	Accelerator Adders Algorithms Artificial neural networks CNN Coders Coding Convolutional neural networks Engines Feature extraction Hardware Inference algorithms low-power MAC Modules Multipliers Neural networks Power consumption Power demand Power efficiency Power management radix-4 Booth Sparsity
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!