A Column Streaming-Based Convolution Engine and Mapping Algorithm for CNN-based Edge AI Accelerators

Abstract

Edge AI accelerators have been emerging as a solution for near customers' applications in areas such as image recognition sensors, remote sensing satellites, robotics, wearable devices, and drones. These applications require meeting performance targets and strict area and power constraints due to their portable mobility feature and limited power sources. As a result, a column streaming-based convolution engine has been proposed in this paper that includes column sets of processing elements design for flexibility in terms of the applicability for different CNN algorithms in edge AI accelerators. Compared to a commercialized CNN accelerator, the key results reveal that the column streaming-based convolution engine requires similar execution cycles to process a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$227 \times 227$</tex> feature map and avoid zero-padding penalties.