Impact on Delay, Power and Area of Machine Learning-based Approximate Logic Synthesis

Created by W.Langdon from gp-bibliography.bib Revision:1.8344

@InProceedings{Prats-Ramos:2024:SBCCI,

• author = "Joao Carlos {Prats Ramos} and Naiara Sachetti and Augusto Berndt and Jonata T. Carvalho and Cristina Meinhardt",
• title = "Impact on Delay, Power and Area of Machine Learning-based Approximate Logic Synthesis",
• booktitle = "2024 37th SBC/SBMicro/IEEE Symposium on Integrated Circuits and Systems Design (SBCCI)",
• year = "2024",
• month = sep,
• keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, Integrated circuits, Measurement, Accuracy, Libraries, Energy efficiency, Delays, Logic, Optimisation, Standards, Logical Synthesis, Physical Synthesis",
• DOI = "doi:10.1109/SBCCI62366.2024.10703989",
• abstract = "Logical optimisation is a crucial step in circuit synthesis, directly impacting the design's area, power, and delay metrics. Machine Learning techniques are particularly suitable for approximate logic synthesis and optimisation in error-resilient scenarios. This work investigates the impact of using ML techniques for logic optimisation and enhancing energy efficiency in approximate circuit synthesis. We consider three state-of-the-art approximate logic optimisation approaches based on mixed-ML, Decision Trees (DT), and Cartesian Genetic Programming (CGP). This work presents a comparative analysis of physical synthesis results for a set of approximate circuit benchmarks, using an open synthesis flow and a 45 nm technology standard cell library. From the techniques evaluated, CGP-based logical optimisation shows a reduction in area, power, and delay of more than 50percent on average compared to the mixed-ML approach. However, this improvement was accompanied by an average accuracy loss of about 5percent. These findings highlight the substantial potential of the CGP approach in optimising approximate circuits.",
• notes = "Also known as \cite{10703989}",

}

Genetic Programming entries for Joao Carlos Prats Ramos Naiara Sachetti Augusto Andre Souza Berndt Jonata Tyska Carvalho Cristina Meinhardt

Citations