Hardware Acceleration Implementation of Sparse Coding Algorithm with Spintronic Devices

摘要

In this paper, we explore the possibility of hardware acceleration implementation of sparse coding algorithm with spintronic devices by a series of design optimizations across the architecture, circuit and device. Firstly, a domain wall motion (DWM) based compound spintronic device (CSD) is engineered and modelled, which is envisioned to achieve multiple conductance states. Sequentially, a parallel architecture is presented based on a dense cross-point array of the proposed DWM based CSD, where each dictionary (D) value can be mapped into the conductance of the proposed DWM based CSD at the corresponding cross-point. Benefitting from its massively parallel read and write operation, such proposed parallel architecture can accelerate the selected sparse coding algorithm using a designed dedicated periphery read and write circuit. Experimental results show that the selected sparse coding algorithm can be accelerated by 1400× with the proposed parallel architecture in comparison with software implementation. Moreover, its energy dissipation is 8 orders of magnitude smaller than that with software implementation.