Clo-HDnn: A 4.66 TFLOPS/W and 3.78 TOPS/W Continual On-Device Learning Accelerator with Energy-efficient Hyperdimensional Computing via Progressive Search

2025/07/23 by Song, Chang Eun, Xu, Weihong, Fan, Keming +10
#FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2507.17953

Abstract

Clo-HDnn is an on-device learning (ODL) accelerator designed for emerging continual learning (CL) tasks. Clo-HDnn integrates hyperdimensional computing (HDC) along with low-cost Kronecker HD Encoder and weight clustering feature extraction (WCFE) to optimize accuracy and efficiency. Clo-HDnn adopts gradient-free CL to efficiently update and store the learned knowledge in the form of class hypervectors. Its dual-mode operation enables bypassing costly feature extraction for simpler datasets, while progressive search reduces complexity by up to 61% by encoding and comparing only partial query hypervectors. Achieving 4.66 TFLOPS/W (FE) and 3.78 TOPS/W (classifier), Clo-HDnn delivers 7.77x and 4.85x higher energy efficiency compared to SOTA ODL accelerators.

Related

• FSL-HDnn: A 5.7 TOPS/W End-to-end Few-shot Learning Classifier Accelerator with Feature Extraction and Hyperdimensional Computing
• FSL-HDnn: A 40-nm Few-Shot On-Device Learning Accelerator With Integrated Feature Extraction and Hyperdimensional Computing
• Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
• HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning
• cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCL