Caffeine: Toward Uniformed Representation and Acceleration for Deep Convolutional Neural Networks

• Published in: IEEE transactions on computer-aided design of integrated circuits and systems Vol. 38; no. 11; pp. 2072 - 2085
• Main Authors: Zhang, Chen, Sun, Guangyu, Fang, Zhenman, Zhou, Peipei, Pan, Peichen, Cong, Jason
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Accelerators; Artificial neural networks; Bandwidth; Caffe; Caffeine; CNN FPGA engine; Computer architecture; convolutional neural network (CNN); Deep learning; Energy efficiency; Engines; Evaluation; Field programmable gate arrays; Graphics processing units; hardware/software co-design; High level networks; Kernel; Machine learning; Multilayers; Multiplication; Neural networks; Performance enhancement; Power efficiency; Representations; Resource utilization; Software

With the recent advancement of multilayer convolutional neural networks (CNNs) and fully connected networks (FCNs), deep learning has achieved amazing success in many areas, especially in visual content understanding and classification. To improve the performance and energy efficiency of the computa...