Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |