2022
DOI: 10.29292/jics.v17i1.546
|View full text |Cite
|
Sign up to set email alerts
|

CGP-based Logic Flow: Optimizing Accuracy and Size of Approximate Circuits

Abstract: Logic synthesis tools face tough challenges when providing algorithms for synthesizing circuits with increased inputs and complexity. Machine learning techniques show high performance in solving specific problems, being an attractive option to improve electronic design tools. We explore Cartesian Genetic Programming (CGP) for logic optimization of exact or approximate Boolean functions in our work. The proposed CGP-based flow receives the expected circuit behavior as a truth-table and either performs the synth… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
2
1
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(4 citation statements)
references
References 0 publications
0
2
0
Order By: Relevance
“…Previous work on CGP usually attempts to improve its main drawback: runtime [66]. In Berndt [13], a CGP solution is adopted to improve the accuracy and size of approximate circuits representing a logic function. The implementation has the potential of further improving solutions found by the other techniques, this way bootstrapping the evolutionary process.…”
Section: B Logic Learningmentioning
confidence: 99%
See 1 more Smart Citation
“…Previous work on CGP usually attempts to improve its main drawback: runtime [66]. In Berndt [13], a CGP solution is adopted to improve the accuracy and size of approximate circuits representing a logic function. The implementation has the potential of further improving solutions found by the other techniques, this way bootstrapping the evolutionary process.…”
Section: B Logic Learningmentioning
confidence: 99%
“…Those concepts greatly motivate the exploratory usage of ML algorithms in EDA tools and techniques. The goal of ML in EDA algorithms is based on three concepts: prediction of verification metrics [8] [11], guiding conventional techniques [7] [12], and improving the design space exploration [13] [14].…”
Section: Introductionmentioning
confidence: 99%
“…Um fluxo de otimização lógica baseado em CGP é apresentado em [2] e [3], com resultados promissores para boa parte das funções lógicas consideradas, quando levados em conta simultaneamente acurácia e tamanho dos circuitos gerados. Entretanto, restam situações em que a solução não produz circuitos com uma acurácia satisfatória.…”
Section: Introductionunclassified
“…Neste trabalho, aplicou-se uma estratégia de Curriculum Learning semelhante à utilizada em [4] a um fluxo de otimização lógica baseado em CGP inspirado em [2] e [3]. No presente resumo são apresentados resultados de experimentos preliminares que visam entender se tal abordagem pode ser efetiva para melhorar a acurácia dos circuitos em evolução.…”
Section: Introductionunclassified