MEMHD: Memory-Efficient Multi-Centroid Hyperdimensional Computing for Fully-Utilized In-Memory Computing Architectures

TL;DR

MEMHD is a novel framework that enhances memory efficiency and accuracy of hyperdimensional computing on in-memory architectures by using clustering and quantization techniques, enabling better resource utilization and faster computation.

Contribution

MEMHD introduces a clustering-based initialization and quantization-aware learning for multi-centroid HDC, achieving full array utilization and significant improvements in memory and computational efficiency.

Findings

Up to 13.69% higher accuracy over state-of-the-art models.

13.25x more memory efficiency at the same accuracy.

80x reduction in computation cycles and 71x in array usage.

Abstract

The implementation of Hyperdimensional Computing (HDC) on In-Memory Computing (IMC) architectures faces significant challenges due to the mismatch between highdimensional vectors and IMC array sizes, leading to inefficient memory utilization and increased computation cycles. This paper presents MEMHD, a Memory-Efficient Multi-centroid HDC framework designed to address these challenges. MEMHD introduces a clustering-based initialization method and quantization aware iterative learning for multi-centroid associative memory. Through these approaches and its overall architecture, MEMHD achieves a significant reduction in memory requirements while maintaining or improving classification accuracy. Our approach achieves full utilization of IMC arrays and enables one-shot (or few-shot) associative search. Experimental results demonstrate that MEMHD outperforms state-of-the-art binary HDC models, achieving up to 13.69% higher accuracy with the same memory usage, or 13.25x more memory efficiency at the same accuracy level. Moreover, MEMHD reduces computation cycles by up to 80x and array usage by up to 71x compared to baseline IMC mapping methods when mapped to 128x128 IMC arrays, while significantly improving energy and computation cycle efficiency.