Memory-Efficient Dataflow Inference for Deep CNNs on FPGA

Custom dataflow Convolutional Neural Network (CNN) inference accelerators on FPGA are tailored to a specific CNN topology and store parameters in On-Chip Memory (OCM), creating the potential for high energy efficiency and low inference latency. However, in these accelerators the shapes of parameter memories are dictated by throughput constraints and do not map well to the underlying OCM, which bec...