An 8.1-to-353 TOPS/W Energy-Aware Deep-Learning Accelerator Supporting Dynamic Neural Networks
Part Of
2024 IEEE Asian Solid-State Circuits Conference, A-SSCC 2024
Start Page
1
End Page
3
ISBN
979-835037632-6
Date Issued
2024-11-18
Author(s)
DOI
10.1109/A-SSCC60305.2024.10849097
Abstract
The demand for edge Al is rapidly increasing in various applications, including image classification, object detection, image segmentation, and key-point detection. Conventionally, deep-learning accelerators are designed for a fixed operating scenario, targeting a high accuracy with affordable energy consumption. However, the operating scenarios and performance requirements may vary. There are cases where low-energy operation is the first priority and a slight accuracy loss is tolerated. Therefore, an energy-aware solution supporting a variety of operating scenarios is required.
Event(s)
2024 IEEE Asian Solid-State Circuits Conference, A-SSCC 2024
SDGs
Publisher
Institute of Electrical and Electronics Engineers Inc.
Type
conference paper