General Reuse-Centric CNN Accelerator

Nihat Mert Cicek, Lin Ning, Ozcan Ozturk, Xipeng Shen

Abstract: This article introduces the first <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">general reuse-centric accelerator</i> for CNN inferences. Unlike prior work that exploits similarities only across consecutive video frames, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">general reuse-centric accelerator</i> is able to discover similarities among arbitrary patches within an image or across independent images, and translate them into computation time and energy savings. Experiments show that the accelerator complements both prior software-based CNN and various CNN hardware accelerators, producing up to 14.96X speedups for similarity discovery, up to 2.70X speedups for overall inference.