Metraipolis › archive › dc_714404a2bf0b
Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration — arXiv:2609.02988
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02988
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:52:56.058Z
- SHA-256 of the archived text
749167f133d9f8f86926ab98a50b1f746a31f519deb205077b82ebedcbf6e047- Stable URL of this page
https://metraipolis.com/documento/dc_714404a2bf0b
How to cite
Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration — arXiv:2609.02988 — arXiv (en), https://arxiv.org/abs/2609.02988 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_714404a2bf0b (Metraipolis archive dc_714404a2bf0b, sha256 749167f133d9f8f86926ab98a50b1f746a31f519deb205077b82ebedcbf6e047)
BibTeX
@misc{dc714404a2bf0b,
title = {Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration — arXiv:2609.02988},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02988},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_714404a2bf0b; sha256 749167f133d9f8f86926ab98a50b1f746a31f519deb205077b82ebedcbf6e047},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02988. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-fidelity TCAD simulation of drift-diffusion transport remains the workhorse of emerging FinFET device design, but it is computationally expensive, especially for 3D structures where runtime escalates steeply with mesh complexity. This sharply limits multi-objective design space exploration. Existing machine-learning surrogates map a fixed set of design parameters to a few scalar device metrics, discarding the underlying physics and losing transferability across device geometries and families. A physics-informed graph attention network (GAT) surrogate is proposed. It operates directly on the tetrahedral TCAD mesh and predicts, at every mesh node, the electrostatic potential together with the electron and hole quasi-Fermi levels, the fundamental unknowns of the drift-diffusion system. Training combines a data loss with finite-volume current-continuity residuals, embedding carrier-transport physics into the objective. Operating on the mesh as a graph, the surrogate inherits size generalization: a model trained on few-fin meshes applies unchanged to substantially larger arrays, bounded at inference only by GPU memory. Per-node uncertainty from a deep ensemble drives an active-learning loop that screens large candidate pools in seconds and forwards only the most informative designs for full simulation. Benchmarked against Sentaurus Device on multi-fin tri-gate FinFETs, the surrogate reproduces the three drift-diffusion fields with sub-volt per-field RMSE and reaches a per-design throughput orders of magnitude higher than the full simulator. The advantage grows with device size: on large multi-fin arrays that are prohibitively slow to simulate directly, inference still completes in under a second per device, enabling Pareto-front exploration across device scales infeasible for direct TCAD sweeps. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AR). Categorie arXiv: Machine Learning (cs.LG) ; Hardware Architecture (cs.AR); Computational Engineering, Finance, and Science (cs.CE). Pagina del lavoro: https://arxiv.org/abs/2609.02988 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T01:12:15.695Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).