Algorithm-Driven On-Chip Integration for High Density and Low Cost

TL;DR

This paper introduces an algorithm-driven on-chip integration approach that significantly reduces area and cost for high-density, multi-project chip tapeouts, enabling scalable research and training platforms.

Contribution

It presents a systematic, automated method for dense on-chip integration of multiple designs, including packing algorithms, shared architecture, and power management techniques.

Findings

Achieves up to 13x area reduction compared to existing methods.

Enables per-project power characterization without low-power ASIC expertise.

Provides a scalable, cost-effective solution for large-scale chip tapeouts.

Abstract

Growing interest in semiconductor workforce development has generated demand for platforms capable of supporting large numbers of independent hardware designs for research and training without imposing high per-project overhead. Traditional multi-project wafer (MPW) services based solely on physical co-placement have historically met this need, yet their scalability breaks down as project counts rise. Recent efforts towards scalable chip tapeouts mitigate these limitations by integrating many small designs within a shared die and attempt to amortize costly resources such as IO pads and memory macros. However, foundational principles for arranging, linking, and validating such densely integrated design sites have received limited systematic investigation. This work presents a new approach with three key techniques to address this gap. First, we establish a structured formulation of the design space that enables automated, algorithm-driven packing of many projects, replacing manual layout practices. Second, we introduce an architecture that exploits only the narrow-area regions between sites to deliver on off-chip communication and other shared needs. Third, we provide a practical approach for on-chip power domains enabling per-project power characterization at a standard laboratory bench and requiring no expertise in low-power ASIC design. Experimental results show that our approach achieves substantial area reductions of up to 13x over state-of-the-art physical-only aggregation methods, offering a scalable and cost-effective path forward for large-scale tapeout environments.