5 papers
SEGA-DCIM: Design Space Exploration-Guided Automatic Digital CIM Compiler with Multiple Precision Support
Haikang Diao, Haoyi Zhang, Jiahao Song +5
Digital computing-in-memory (DCIM) has been a popular solution for addressing the memory wall problem in recent years. However, the DCIM design still heavily relies on manual effor…
EasyACIM: An End-to-End Automated Analog CIM with Synthesizable Architecture and Agile Design Space Exploration
Haoyi Zhang, Jiahao Song, Xiaohan Gao +4
Analog Computing-in-Memory (ACIM) is an emerging architecture to perform efficient AI edge computing. However, current ACIM designs usually have unscalable topology and still heavi…
An Energy-Efficient Mixed-Signal Parallel Multiply-Accumulate (MAC) Engine Based on Stochastic Computing
Xinyue Zhang, Jiahao Song, Yuan Wang +4
Convolutional neural networks (CNN) have achieved excellent performance on various tasks, but deploying CNN to edge is constrained by the high energy consumption of convolution ope…
Memory System Designed for Multiply-Accumulate (MAC) Engine Based on Stochastic Computing
Xinyue Zhang, Yuan Wang, Yawen Zhang +5
Convolutional neural network (CNN) achieves excellent performance on fascinating tasks such as image recognition and natural language processing at the cost of high power consumpti…
A Parallel Bitstream Generator for Stochastic Computing
Yawen Zhang, Runsheng Wang, Xinyue Zhang +5
Stochastic computing (SC) presents high error tolerance and low hardware cost, and has great potential in applications such as neural networks and image processing. However, the bi…