Details

Autor(en) / Beteiligte

• Paul, S
• Majumder, T
• Augustine, C
• Malavasi, A. F
• Usirikayala, S
• Kumar, R
• Kollikunnel, J
• Chhabra, S
• Yada, S
• Barajas, M. L
• Ornelas, C
• Lake, D
• Khellah, M. M
• Tschanz, J
• De, V

Titel

A 0.05pJ/Pixel 70fps FHD 1Meps Event-Driven Visual Data Processing Unit

Ist Teil von

• 2020 IEEE Symposium on VLSI Circuits, 2020, p.1-2

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• An Event-driven visual data Processing Unit (EPU) exploits temporal redundancy in stationary camera video streams to localize motion-based Regions-of-Interest (RoI), saving compute FLOPs and memory bandwidth (BW) for Deep Learning (DL) based object detection. The proposed EPU supports FHD frames at 70fps and can be time-multiplexed across multiple video streams. The EPU pipeline consists of event detection, event clustering, event cluster dilation and RoI extraction and occupies 0.34mm 2 in 10nm CMOS. Frame-based, inter- and intra-frame event-driven power management schemes minimize normalized energy/pixel to 0.05pJ at 0.65V. RoI filtering with an EPU frontend improves the end-to-end (E2E) energy-efficiency of a deep-learning (DL) based vision pipeline by 5X, while improving its throughput by 4.3X.