Unlocking approximation for in-memory computing with Cartesian genetic programming and computer algebra for arithmetic circuits
| dc.contributor.author | Froehlich, Saman | |
| dc.contributor.author | Drechsler, Rolf | |
| dc.date.accessioned | 2022-11-22T09:53:17Z | |
| dc.date.available | 2022-11-22T09:53:17Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | With ReRAM being a non-volative memory technology, which features low power consumption, high scalability and allows for in-memory computing, it is a promising candidate for future computer architectures. Approximate computing is a design paradigm, which aims at reducing the complexity of hardware by trading off accuracy for area and/or delay. In this article, we introduce approximate computing techniques to in-memory computing. We extend existing compilation techniques for the Programmable Logic in-Memory (PLiM) computer architecture, by adapting state-of-the-art approximate computing techniques for arithmetic circuits. We use Cartesian Genetic Programming for the generation of approximate circuits and evaluate them using a Symbolic Computer Algebra-based technique with respect to error-metrics. In our experiments, we show that we can outperform state-of-the-art handcrafted approximate adder designs. | en |
| dc.identifier.doi | 10.1515/itit-2021-0042 | |
| dc.identifier.pissn | 2196-7032 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/39759 | |
| dc.language.iso | en | |
| dc.publisher | De Gruyter | |
| dc.relation.ispartof | it - Information Technology: Vol. 64, No. 3 | |
| dc.subject | Approximate Computing | |
| dc.subject | In-Memory Computing | |
| dc.subject | ReRAM | |
| dc.subject | RRAM | |
| dc.subject | Symbolic Computer Algebra | |
| dc.subject | SCA | |
| dc.subject | PLiM | |
| dc.subject | CGP | |
| dc.subject | EA | |
| dc.subject | Cartesian Genetic Programming | |
| dc.title | Unlocking approximation for in-memory computing with Cartesian genetic programming and computer algebra for arithmetic circuits | en |
| dc.type | Text/Journal Article | |
| gi.citation.endPage | 107 | |
| gi.citation.publisherPlace | Berlin | |
| gi.citation.startPage | 99 | |
| gi.conference.sessiontitle | Article |