Hardware-Algorithm Co-Design for Hyperdimensional Computing Based on Memristive System-on-Chip

Yi Huang, Alireza Jaberi Rad, Qiangfei Xia

Keywords: in-memory computing, hardware-algorithm co-design, hyperdimensional computing, memristor

TL;DR: A hardware algorithm co-design approach for implementing hyperdimensional computing (HDC) on a memristive System on-Chip (SoC), achieving experimental 90.71% accuracy in a language classification task.

Abstract: Hyperdimensional computing (HDC), utilizing a parallel computing paradigm and efficient learning algorithm, is well-suited for resource-constrained artificial intelligence (AI) applications, such as in edge devices. In-memory computing (IMC) systems based on memristive devices complement this by offering energy-efficient hardware solutions. To harness the advantages of both memristive IMC hardware and HDC algorithms, we propose a hardware-algorithm co-design approach for implementing HDC on a memristive System-on-Chip (SoC). On the hardware side, we utilize the inherent randomness of memristive crossbar arrays for encoding and employ analog IMC for classification. At the algorithm level, we develop hardwareaware encoding techniques that map data features into hyperdimensional vectors, optimizing the classification process within the memristive SoC. Experimental results in hardware demonstrate 90.71% accuracy in the language classification task, highlighting the potential of our approach for achieving energy-efficient AI deployments on edge devices.

Submission Number: 27