Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Shang, Liu, Shuai, Randall, Owen, Taylor, Matthew E.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.18806
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908981228732416
author Wang, Shang
Liu, Shuai
Randall, Owen
Taylor, Matthew E.
author_facet Wang, Shang
Liu, Shuai
Randall, Owen
Taylor, Matthew E.
contents 3D-IC netlist partitioning is commonly optimized using proxy objectives, while final PPA is treated as a costly evaluation rather than an optimization signal. This proxy-driven paradigm makes it difficult to reliably translate additional PPA evaluations into better PPA outcomes. To bridge this gap, we present DOPP (D-Optimal PPA-driven partitioning selection), an approach that bridges the gap between proxies and true PPA metrics. Across eight 3D-IC designs, our framework improves PPA over Open3DBench (average relative improvements of 9.99% congestion, 7.87% routed wirelength, 7.75% WNS, 21.85% TNS, and 1.18% power). Compared with exhaustive evaluation over the full candidate set, DOPP achieves comparable best-found PPA while evaluating only a small fraction of candidates, substantially reducing evaluation cost. By parallelizing evaluations, our method delivers these gains while maintaining wall-clock runtime comparable to traditional baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A PPA-Driven 3D-IC Partitioning Selection Framework with Surrogate Models
Wang, Shang
Liu, Shuai
Randall, Owen
Taylor, Matthew E.
Machine Learning
Hardware Architecture
3D-IC netlist partitioning is commonly optimized using proxy objectives, while final PPA is treated as a costly evaluation rather than an optimization signal. This proxy-driven paradigm makes it difficult to reliably translate additional PPA evaluations into better PPA outcomes. To bridge this gap, we present DOPP (D-Optimal PPA-driven partitioning selection), an approach that bridges the gap between proxies and true PPA metrics. Across eight 3D-IC designs, our framework improves PPA over Open3DBench (average relative improvements of 9.99% congestion, 7.87% routed wirelength, 7.75% WNS, 21.85% TNS, and 1.18% power). Compared with exhaustive evaluation over the full candidate set, DOPP achieves comparable best-found PPA while evaluating only a small fraction of candidates, substantially reducing evaluation cost. By parallelizing evaluations, our method delivers these gains while maintaining wall-clock runtime comparable to traditional baselines.
title A PPA-Driven 3D-IC Partitioning Selection Framework with Surrogate Models
topic Machine Learning
Hardware Architecture
url https://arxiv.org/abs/2604.18806