HYDRA: Hybrid Data Multiplexing and Run-time Layer Configurable DNN Accelerator

TL;DR

HYDRA introduces a hybrid data multiplexing and runtime layer configurable DNN accelerator that significantly reduces power and resource usage while maintaining high performance for edge computing.

Contribution

It proposes a novel layer-multiplexed architecture with improved FMA, enabling efficient, configurable DNN execution on resource-constrained edge devices.

Findings

Achieves over 90% power reduction and resource utilization improvements.

Supports 35.21 TOPSW performance in a configurable architecture.

Reduces area overhead for bandwidth, AF, and layer architecture.

Abstract

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 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 of state-of-the-art works, with 35.21 TOPSW. The proposed architecture reduces the area overhead (N-1) times required in bandwidth, AF and layer architecture. This work shows HYDRA architecture supports optimal DNN computations while improving performance on resource-constrained edge devices.