HYDRA: A Resource-Efficient Hybrid Data-Multiplexed, Run-time Layer-Reconfigurable Compute Engine for DNN Acceleration

Deep neural networks (DNNs) offer plenty of challenges in executing efficient computation at edge nodes, primarily due to the huge hardware resource demands. The article proposes HYDRA, hybrid data multiplexing and runtime layer configurable DNN accelerators to overcome the drawbacks. The work proposes a layer-multiplexed approach, which further reuses a single activation function (AF) within the execution of a single layer with improved Fused-Multiply-Accumulate (FMA). The proposed approach works in iterative mode to reuse the same hardware and execute different layers in a configurable fashion. The proposed architectures achieve reductions over 90% of power consumption and resource utilization improvements from state-of-the-art (SOTA) works, with an energy efficiency of 7.04 GOPS/w. The proposed architecture reduces the area-overhead (N-1) times required in bandwidth, AF and layer architecture. The proposed HYDRA architecture supports optimal DNN computations while improving performance on resource-constrained edge devices.