EMO-CIM: An Input/Stationary-Data Similarity-Aware Computing-In-Memory Design for Variable Vector-Wise Computation in Edge Multi-Operator AI Acceleration https://sscs.ieee.org/wp-content/themes/movedo/images/empty/thumbnail.jpg 150 150 https://secure.gravatar.com/avatar/8fcdccb598784519a6037b6f80b02dee03caa773fc8d223c13bfce179d70f915?s=96&d=mm&r=g
Abstract:
We propose an edge multi-operator computing-in-memory design (EMO-CIM) that supports variable vector-wise multiply-and-accumulate (MAC) in CNN, Depthwise-Convolution (DW), and Attention operators. It features: (1) A single EMO-CIM bank excels in variable vector-wise MAC for multi-operators; (2) Merging local input-shared compute units with a decode-unit & adder-tree facilitates input/stationary-data similarity-aware computing to improve …