Metraipolis › archive › dc_991bcd45c20b

PRISM: Preference-based Reward and Uncertainty-Integrated Synthesis Minimization for RTL PPA Optimization — arXiv:2611.11051

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11051
License (as archived)
CC0-1.0
Archived
2026-11-10T18:46:15.445Z
SHA-256 of the archived text
e6466e5dc5fca91fbf099b454278f8079468c724ab9563f3932b8653514a808c
Stable URL of this page
https://metraipolis.com/documento/dc_991bcd45c20b

How to cite

PRISM: Preference-based Reward and Uncertainty-Integrated Synthesis Minimization for RTL PPA Optimization — arXiv:2611.11051 — arXiv (en), https://arxiv.org/abs/2611.11051 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_991bcd45c20b (Metraipolis archive dc_991bcd45c20b, sha256 e6466e5dc5fca91fbf099b454278f8079468c724ab9563f3932b8653514a808c)
BibTeX
@misc{dc991bcd45c20b,
  title = {PRISM: Preference-based Reward and Uncertainty-Integrated Synthesis Minimization for RTL PPA Optimization — arXiv:2611.11051},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11051},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_991bcd45c20b; sha256 e6466e5dc5fca91fbf099b454278f8079468c724ab9563f3932b8653514a808c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11051. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper introduces a budget-aware, multi-objective framework (called PRISM) for RTL optimization that improves power, performance, and area (PPA) while sharply limiting expensive commercial synthesis tool calls. Starting from a synthesizable baseline and functional testbench, the method iterates through LLM-driven rewrite generation, fast compile/simulation equivalence filtering, low-cost proxy feature extraction, and selective commercial synthesis tool (Synopsys Design Compiler (DC)) evaluation. To prioritize which candidates deserve high-quality synthesis, we train a preference-based reward model using pairwise ranking supervision derived from commercial synthesis tool outcomes, and combine ensemble uncertainty with a diversity-aware acquisition rule to avoid early bias and redundant evaluations. A key advantage is that PRISM maintains a best-tradeoff set G of non-dominated designs throughout the run: G preserves the best solutions found so far, is fed back into generation and refinement, and enables consistent, cumulative improvements rather than repeatedly restarting from the baseline. Across RTLLM v2.0 modules, the approach consistently yields post-synthesis gains under fixed commercial synthesis tool call budgets, and ablations confirm that reward-guided selection and candidate dropping are central to sample-efficient progress. PRISM efficacy is evaluated across multiple technology nodes (7 nm, 15 nm, and 45 nm) using identical pipelines without retraining.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno).
Categorie arXiv: Hardware Architecture (cs.AR) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.11051 — 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 2026-11-10T18:38:22.451Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).