Projektbeschreibung
Maschinelles Lernen könnte die Gestaltung anspruchsvoller analoger Schaltungen vorantreiben
Das Zeitalter, in dem alles intelligent ist, hat zu einem sprunghaften Anstieg des Bedarfs an fortschrittlichen Halbleitertechnologien und intelligenter Datenverarbeitung geführt. Trotz Fortschritten auf diesem Gebiet hinkt die Entwicklung analoger Schaltungen ihrem digitalen Pendant hinterher: Analoge Schaltungen werden immer noch im Labor hergestellt, was zu fehleranfälligen Zyklen und hohen Entwicklungskosten führt. Das EU-finanzierte Projekt AnalogCreate wird das Potenzial des maschinellen Lernens nutzen, um den Entwurf fortschrittlicher integrierter Schaltungen für vielversprechende Informations- und Kommunikationsanwendungen zu beschleunigen. Die Projektaktivitäten werden erstmals die autonome Erstellung erschwinglicher analoger Schaltungen von der Spezifikation bis zum vollständig verifizierten Layout erlauben, ohne dass menschliches Feedback erforderlich ist.
Ziel
Progress in semiconductor technology and in intelligent data processing are converging today, opening the door to countless smart ICT applications through the Cloud and Internet of Everything, to the people’s benefit in years to come. Applications that interact with the physical world (e.g. environmental sensing, healthcare, autonomous vehicles, etc.), also need analog integrated circuits in the cyber-physical or edge layer. But while digital circuits are largely synthesized automatically through software, the analog circuits are mainly still handcrafted in industry with low design productivity. This results in long and error-prone design cycles, and the high development costs jeopardize many potential new ICT applications from ever being realized (e.g. solutions for rare diseases). It becomes even more problematic when moving to advanced technologies below 16 nm CMOS, that come with way more design and layout rules to be dealt with. The showstopper for state-of-the-art analog synthesis tools is that they require design heuristics and constraints to be entered explicitly by designers in order to handle the humongous solution space and to steer the circuit and layout optimizations towards acceptable solutions. The proposed disruptively new approach is to use the self-learning capabilities of advanced machine learning algorithms to self-learn and then exploit the design expertise and constraints from the many available successfully completed designs. Also a true circuit topology synthesis approach will be developed to create a proper (possibly novel) schematic from the target specifications, as well as an innovative formal analog design verification approach based on Quick Error Detection. These innovations will enable for the first time ever to truly autonomously create analog circuits from specifications to fully verified layout without direct input from any designer in the loop, and therefore enable the affordable implementation of many promising ICT applications.
Wissenschaftliches Gebiet
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineeringautonomous vehicles
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringanalogue electronics
- natural sciencescomputer and information sciencesdata sciencedata processing
Schlüsselbegriffe
Programm/Programme
Thema/Themen
Finanzierungsplan
ERC-ADG - Advanced GrantGastgebende Einrichtung
3000 Leuven
Belgien