Ultrafast Hybrid Computing Systems Enabled by Memristor‐Based Quadratic Programming Circuits
Abstract Implementing algorithms purely on digital computing platforms dramatically halts the performance of conventional computing systems. Revolutionary computing systems with extreme energy efficiency and high accuracy are demanded to handle the growing computing tasks. Here, the research on hybrid analog–digital computing platforms enabled by memristor‐based optimization solvers for achieving ultrafast computations is presented. By utilizing tunable memristors as parameters to solve linear programming (LP) and quadratic programming (QP) problems, a real‐time control algorithm for micro air vehicles (MAVs) and a support vector machine (SVM) algorithm for cancer diagnosis are implemented. These experiments demonstrate over 2000x speed‐up compared to conventional digital platforms, with negligible energy consumption, using a memristor‐based system consisting of six memristors. These findings underscore the vast potential of memristor‐based optimization solvers not only in hybrid analog–digital computing platforms but also as a transformative solution for a wide range of modern computing challenges. This approach promises significant advancements in energy efficiency and ultrafast speed, positioning it as a leading contender for next‐generation computing paradigms.
Authors
- Qiaochu Zhang (ORCID: https://orcid.org/0000-0002-6782-8086)
- Ryan M. Bena (ORCID: https://orcid.org/0000-0003-2088-5769)
- Hao Yang (ORCID: https://orcid.org/0000-0002-0992-9161)
- Boxiang Song (ORCID: https://orcid.org/0000-0002-4946-2738)
- Zhexiang Tang (ORCID: https://orcid.org/0000-0001-6693-0735)
- Quan Nguyen (ORCID: https://orcid.org/0000-0001-8620-0561)
- Shiyu Su (ORCID: https://orcid.org/0000-0002-2558-4159)
- Sushmit Hossain (ORCID: https://orcid.org/0009-0000-7562-0659)
- Pan Hu (ORCID: https://orcid.org/0000-0002-8214-6147)
- Stephen B. Cronin (ORCID: https://orcid.org/0000-0001-9153-7687)
- Yudi Shi
- Buyun Chen (ORCID: https://orcid.org/0000-0001-8326-6688)
- Mayank Palaria
- Mark Barnell (ORCID: https://orcid.org/0000-0002-9865-6723)
- Wei Wu (ORCID: https://orcid.org/0000-0001-6404-0317)
- Tse‐Hsien Ou (ORCID: https://orcid.org/0000-0002-0892-908X)
- Deming Meng (ORCID: https://orcid.org/0000-0001-9619-090X)
- Zhi Cai (ORCID: https://orcid.org/0000-0002-3741-5715)
- Hsiang‐Chun Cheng (ORCID: https://orcid.org/0009-0003-9112-6628)
- Zerui Liu (ORCID: https://orcid.org/0000-0002-2575-5851)
- Nishat Tasnim Hiramony (ORCID: https://orcid.org/0000-0002-3191-3801)
- Mike Shuo‐Wei Chen (ORCID: https://orcid.org/0000-0001-7033-272X)
- Hongming Zhang (ORCID: https://orcid.org/0000-0002-6131-2505)
- Ting‐Hao Hsu (ORCID: https://orcid.org/0000-0002-5318-7230)
- Qing Wu (ORCID: https://orcid.org/0000-0001-7248-9755)
- Yunxiang Wang (ORCID: https://orcid.org/0000-0002-9788-074X)
- Jiacheng Ye
- Ce Yang
- Daniel W. Yang
Institutions
- University of Southern California (US)
- United States Air Force Research Laboratory (US)
- University of Waterloo (CA)
- Wuhan National Laboratory for Optoelectronics (CN)
- U.S. Air Force Research Laboratory Information Directorate
- Huazhong University of Science and Technology (CN)
- University of Virginia (US)
Publication Details
- Journal
- Advanced Functional Materials
- Published
- 2024-09-05
- DOI
- https://doi.org/10.1002/adfm.202401600
- Citations
- 5
- Primary Topic
- Advanced Memory and Neural Computing
- Type
- article
- Field-Weighted Citation Impact
- 1.04
Funders
- Office of the Director of National Intelligence
- Intelligence Advanced Research Projects Activity