PULP-HD: Accelerating Brain-Inspired High-Dimensional Computing on a Parallel Ultra-Low Power Platform

TL;DR

This paper presents PULP-HD, a highly efficient, brain-inspired high-dimensional computing accelerator on ultra-low-power hardware, achieving significant speed and energy improvements while maintaining high classification accuracy.

Contribution

It introduces an optimized hardware implementation of HD computing on PULPv3 and its scalable extension, demonstrating substantial speed-up and energy savings over previous approaches.

Findings

Achieved 3.7× speed-up and 2× energy savings on PULPv3 platform.

Surpassed state-of-the-art classification accuracy with 92.4%.

Scalability to 18.4× speed-up with multi-core extensions.

Abstract

Computing with high-dimensional (HD) vectors, also referred to as $\textit{hypervectors}$, is a brain-inspired alternative to computing with scalars. Key properties of HD computing include a well-defined set of arithmetic operations on hypervectors, generality, scalability, robustness, fast learning, and ubiquitous parallel operations. HD computing is about manipulating and comparing large patterns-binary hypervectors with 10,000 dimensions-making its efficient realization on minimalistic ultra-low-power platforms challenging. This paper describes HD computing's acceleration and its optimization of memory accesses and operations on a silicon prototype of the PULPv3 4-core platform (1.5mm$^2$, 2mW), surpassing the state-of-the-art classification accuracy (on average 92.4%) with simultaneous 3.7$\times$ end-to-end speed-up and 2$\times$ energy saving compared to its single-core execution. We further explore the scalability of our accelerator by increasing the number of inputs and classification window on a new generation of the PULP architecture featuring bit-manipulation instruction extensions and larger number of 8 cores. These together enable a near ideal speed-up of 18.4$\times$ compared to the single-core PULPv3.