STYLIANOS VENIERIS

To drive the experimentation and development of novel deep learning models, both industrial and academic institutions have released software frameworks, optimised for training and deploying deep learning models with high compute performance. Currently, frameworks such as Caffe2, PyTorch and CNTK achieve high processing speed by primarily targeting power-hungry CPUs and GPUs. Recently, FPGAs have emerged as a potential alternative platform that can reduce significantly power consumption cost while meeting the compute requirements of modern deep learning systems. In this project, we survey the landscape of toolflows which automate the mapping of the CNN inference stage to FPGA-based platforms. From a deep learning scientist perspective, we conduct a study over the supported deep learning models, including DNNs, CNNs and LSTMs, the achieved processing speed and the applicability of each toolflow on specific deep learning applications, from latency-critical mobile systems to high-..