Metraipolis › archive › dc_0096abb67f6e

DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design — arXiv:2608.16080

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16080
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:22.733Z
SHA-256 of the archived text
a65cec08f4ac7d13f58be12c9244ea60123053b2e740e46928d10f94911c73ab
Stable URL of this page
https://metraipolis.com/documento/dc_0096abb67f6e

How to cite

DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design — arXiv:2608.16080 — arXiv (en), https://arxiv.org/abs/2608.16080 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0096abb67f6e (Metraipolis archive dc_0096abb67f6e, sha256 a65cec08f4ac7d13f58be12c9244ea60123053b2e740e46928d10f94911c73ab)
BibTeX
@misc{dc0096abb67f6e,
  title = {DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design — arXiv:2608.16080},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16080},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0096abb67f6e; sha256 a65cec08f4ac7d13f58be12c9244ea60123053b2e740e46928d10f94911c73ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16080. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Thermal-aware optimization of multi-die 3D integrated circuits evaluates many designs, each a costly heat-equation solve. Operator-learning surrogates replace this solve with a fast forward pass, ideally trained from physics alone, without labeled data. DeepOHeat-v1 made such surrogates fast and trustworthy, but only on low-contrast geometries. High-contrast multi-die stacks break it in two ways: discontinuous conductivities make the continuous physics loss ill-defined at material interfaces, and ill-conditioning ($\kappa_2(A_h) \approx 6 \times 10^4$) puts the discretized strong-form loss beyond first-order optimization. We propose DeepOHeat-v2 to overcome both. First, we train on a discretized physics loss that handles the discontinuities natively; its energy form reduces the prediction-space loss-Hessian conditioning from $\kappa^2$ to $\kappa$, and a matrix-preconditioned optimizer cuts the mean peak temperature error from over 30 K to 0.55 K. Second, because optimization leaves the training distribution, we propose a self-improving framework: a hotspot trust gate sends flagged placements to a reference solver, and the surrogate incrementally retrains on the refined solutions, keeping an update only when it improves held-out validation error. On a multi-die benchmark, the surrogate-true peak gap on the returned design falls from 1.12 K to 0.11 K, matching a solve-at-every-step optimizer while running $56\times$ faster.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Data Analysis, Statistics and Probability (physics.data-an).
Pagina del lavoro: https://arxiv.org/abs/2608.16080 — 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 2026-10-18T19:02:44.148Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).