Using execution logs for improving pseudo-Boolean propagation
Among all procedures that CDCL-based SAT solvers implement, unit propagation dominates the total running time. Hence, it is not a surprise that large research efforts have been invested on improving it. As a result, the two-watched-literal scheme, enhanced with implementation details boosting its pe...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2026 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/450565 |
| Acceso en línea: | https://hdl.handle.net/2117/450565 https://dx.doi.org/10.1016/j.artint.2025.104470 |
| Access Level: | acceso abierto |
| Palabra clave: | SAT Pseudo-Boolean solving Implementation-level details Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial Àrees temàtiques de la UPC::Informàtica::Informàtica teòrica |
| Sumario: | Among all procedures that CDCL-based SAT solvers implement, unit propagation dominates the total running time. Hence, it is not a surprise that large research efforts have been invested on improving it. As a result, the two-watched-literal scheme, enhanced with implementation details boosting its performance, emerged as the dominant method. The importance of unit propagation in pseudo-Boolean solvers is similar. However, no dominant method exists: counter and watch-based propagation are well-suited for different types of constraints, opening the door to hybrid methods. The higher complexity of implementing pseudo-Boolean solvers has shifted the research focus to higher-level aspects of other procedures, considering implementation details of unit propagation not a priority. In this paper, we first present execution logs: a novel methodology that allows us to precisely evaluate the performance of different propagation procedures. Secondly, we show how both counter and watch-based propagation routines in the RoundingSat solver can be largely improved thanks to a careful analysis of various implementation issues. Thirdly, a detailed analysis shows that hybrid methods outperform the ones based on a single technique. Finally, our experiments reveal that improvements in propagation lead to a clearly better overall performance of the solver. |
|---|