A PPA-Driven 3D-IC Partitioning Selection Framework with Surrogate Models

TL;DR

This paper introduces DOPP, a surrogate model-based framework for 3D-IC partitioning that improves PPA metrics efficiently by reducing evaluation costs and bridging the gap between proxy objectives and true PPA outcomes.

Contribution

DOPP is a novel surrogate model approach that enhances 3D-IC partitioning by effectively integrating true PPA evaluations into the optimization process.

Findings

DOPP improves PPA metrics across eight 3D-IC designs.

DOPP achieves comparable results to exhaustive evaluation with fewer candidate evaluations.

Parallel evaluation enables DOPP to maintain runtime efficiency.

Abstract

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.