%0 Journal Article
%@ 1572-8102
%A Tung, Vu Xuan
%A To, Van Khanh
%A Ogawa, Mizuhito
%D 2017
%F SisLab:2543
%I Springer
%J Formal Methods in System Design
%P 1-38
%T raSAT: an SMT solver for polynomial constraints
%U https://eprints.uet.vnu.edu.vn/eprints/id/eprint/2543/
%X This paper presents raSAT SMT solver, which is aimed to handle polynomial constraints over both reals and integers with simple unified methodologies. Its three main features are (1) a raSAT loop for inequalities, which adds testing to interval constraint propagation to accelerate SAT detection, (2) a non-constructive reasoning for equations over reals based on the generalized intermediate value theorem, and (3) soundness of floating-point arithmetic that is guaranteed by (a) rounding up/down over-approximations of intervals, and (b) confirmation of a satisfying instance detected by testing using the iRRAM package, which guarantees error bounds.