Solving Boolean satisfiability problems with resistive content addressable memories
Solving optimization problems is a highly demanding workload requiring high-performance computing systems. Optimization solvers are usually difficult to parallelize in conventional digital architectures, particularly when stochastic decisions are involved. Recently, analog computing architectures for accelerating stochastic optimization solvers have been presented, but they were limited to academic problems in quadratic polynomial format. Here we present KLIMA, a k − Local In-Memory Accelerator with resistive Content Addressable Memories (CAMs) and Dot-Product Engines (DPEs) to accelerate the solution of high-order industry-relevant optimization problems, in particular Boolean Satisfiability. By co-designing the optimization heuristics and circuit architecture we improve the speed and energy to the solution up to 182 × compared to the digital state of the art.
Authors
- E. Valiante (ORCID: https://orcid.org/0000-0003-3820-7851)
- J. W. Moon (ORCID: https://orcid.org/0000-0001-7420-1751)
- Catherine E. Graves (ORCID: https://orcid.org/0000-0002-0907-583X)
- Thomas Van Vaerenbergh (ORCID: https://orcid.org/0000-0002-7301-8610)
- John Paul Strachan (ORCID: https://orcid.org/0000-0002-1382-3677)
- Arne Heittmann
- Dmitri B. Strukov
- Dongseok Kwon (ORCID: https://orcid.org/0000-0001-7676-8938)
- Jim Ignowski (ORCID: https://orcid.org/0000-0001-5091-3674)
- George Hutchinson (ORCID: https://orcid.org/0009-0000-0413-4362)
- Fabian Böhm (ORCID: https://orcid.org/0000-0001-8516-9785)
- Tinish Bhattacharya (ORCID: https://orcid.org/0000-0003-4591-6277)
- Ignacio Rozada
- Mohammad Hizzani (ORCID: https://orcid.org/0000-0002-7734-8473)
- Xiangyi Zhang (ORCID: https://orcid.org/0000-0003-4395-2776)
- Masoud Mohseni (ORCID: https://orcid.org/0000-0003-4065-9400)
- Giacomo Pedretti (ORCID: https://orcid.org/0000-0002-4501-8672)
- Ray Beausoleil
Institutions
- Hewlett-Packard (United States) (US)
- University of California, Santa Barbara (US)
- Forschungszentrum Jülich (DE)
- 1QBit
Publication Details
- Journal
- npj Unconventional Computing
- Published
- 2025-04-02
- DOI
- https://doi.org/10.1038/s44335-025-00020-w
- Citations
- 7
- Primary Topic
- Advanced Memory and Neural Computing
- Type
- article
- Field-Weighted Citation Impact
- 5.11
Funders
- Defense Advanced Research Projects Agency
- Advanced Research Projects Agency
- Defense Sciences Office, DARPA
- Air Force Research Laboratory