Trinity: One Differentiable Physics for Training, Refining and Scoring Generative Floorplanners

Abstract:Floorplanning arranges the blocks of a chip and decides their shapes under objectives that press blocks together, short wirelength and a small outline, and constraints that hold them apart, non-overlap, clusters, MIB shapes and boundary blocks. Recent diffusion placers train on reference layouts alone and leave this coupled system to guidance, post-hoc loops and a legalizer, reporting only the endpoint, which hides what the generator contributes. We re-implement four of them under one recipe on FloorSet, score raw, refined and legalized layouts on one scale, and propose Trinity, a flow-matching floorplanner whose six differentiable functions for the constraints and objectives are its training loss term, the energy of a closed-form refiner after sampling and the base of a soft cost for every stage. The network thus learns the correction prior placers apply in their samplers, and sampling needs no guidance. Stage by stage, the training term lowers a plain transformer's raw soft cost by 26% and matters most at short budgets, the shared refiner decides more of the final cost than the generator and matches a ported placer's loop in 16 to 660 times fewer steps, Trinity's refined soft cost is 36% below the best ported pipeline, the soft cost ranks settings as the contest's hard cost does, and on the FloorSet val set the pipeline reaches a mean hard cost of 1.014 in 1.63 s per case.

Shih-Ying Yeh and Tzu-Sian Wang contributed equally. 85 pages, 65 figures, 67 tables. Project page: this https URL Code: this https URL Models: this https URL

Machine Learning (cs.LG); Hardware Architecture (cs.AR)

arXiv:2610.04957 [cs.LG]

(or arXiv:2610.04957v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.04957 arXiv-issued DOI via DataCite (pending registration)