Saved in:
Bibliographic Details
Main Authors: Yoshioka, Kanta, Hirayae, Soshi, Tanaka, Yuichiro, Katori, Yuichi, Morie, Takashi, Tamukoh, Hakaru
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.06808
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915923684753408
author Yoshioka, Kanta
Hirayae, Soshi
Tanaka, Yuichiro
Katori, Yuichi
Morie, Takashi
Tamukoh, Hakaru
author_facet Yoshioka, Kanta
Hirayae, Soshi
Tanaka, Yuichiro
Katori, Yuichi
Morie, Takashi
Tamukoh, Hakaru
contents This paper presents CBM-Dual, the first silicon-proven digital chaotic dynamics processor (CDP) supporting both simulated annealing (SA) and reservoir computing (RC). CBM-Dual enables real-time decision-making and lightweight adaptation for autonomous Edge AI, employing the largest-scale fully connected 1024-neuron chaotic Boltzmann machine (CBM). To address the high computational and area costs of digital CDPs, we propose: 1) a CBM-specific scheduler that exploits an inherently low neuron flip rate to reduce multiply-accumulate operations by 99%, and 2) an efficient multiply splitting scheme that reduces the area by 59%. Fabricated in 65nm (12mm$^2$), CBM-Dual achieves simultaneous heterogeneous task execution and state-of-the-art energy efficiency, delivering $\times$25-54 and $\times$4.5 improvements in the SA and RC fields, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06808
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CBM-Dual: A 65-nm Fully Connected Chaotic Boltzmann Machine Processor for Dual Function Simulated Annealing and Reservoir Computing
Yoshioka, Kanta
Hirayae, Soshi
Tanaka, Yuichiro
Katori, Yuichi
Morie, Takashi
Tamukoh, Hakaru
Hardware Architecture
Machine Learning
This paper presents CBM-Dual, the first silicon-proven digital chaotic dynamics processor (CDP) supporting both simulated annealing (SA) and reservoir computing (RC). CBM-Dual enables real-time decision-making and lightweight adaptation for autonomous Edge AI, employing the largest-scale fully connected 1024-neuron chaotic Boltzmann machine (CBM). To address the high computational and area costs of digital CDPs, we propose: 1) a CBM-specific scheduler that exploits an inherently low neuron flip rate to reduce multiply-accumulate operations by 99%, and 2) an efficient multiply splitting scheme that reduces the area by 59%. Fabricated in 65nm (12mm$^2$), CBM-Dual achieves simultaneous heterogeneous task execution and state-of-the-art energy efficiency, delivering $\times$25-54 and $\times$4.5 improvements in the SA and RC fields, respectively.
title CBM-Dual: A 65-nm Fully Connected Chaotic Boltzmann Machine Processor for Dual Function Simulated Annealing and Reservoir Computing
topic Hardware Architecture
Machine Learning
url https://arxiv.org/abs/2604.06808