Search papers, labs, and topics across Lattice.
CHICO-Agent is introduced as an LLM-driven framework for optimizing 2.5D/3D chiplet-based systems by navigating the complex design space across application, architecture, chip, and package levels. It uses a persistent knowledge base to learn parameter-outcome relationships and employs a multi-agent workflow for coordinated exploration. Experiments show that CHICO-Agent identifies lower-cost configurations than simulated annealing while also providing an interpretable audit trail.
LLMs can now automate and optimize the notoriously complex design of 2.5D/3D chiplet systems, outperforming traditional simulated annealing.
The rapid growth of large language models (LLMs) and AI workloads has pushed monolithic silicon to its reticle and economic limits, accelerating the adoption of 2.5D/3D chiplet systems. However, these systems increase design complexity by requiring co-design across multiple levels of the computing stack, including application, architecture, chip, and package. The resulting design space is highly combinatorial, with trade-offs among latency, energy, area, and cost. To address this challenge, we propose CHICO-Agent, an LLM-driven optimization framework for 2.5D/3D chiplet-based systems. CHICO-Agent maintains a persistent knowledge base to capture parameter-outcome trends and coordinates exploration through an admin-field multi-agent workflow. Compared with a simulated-annealing baseline, CHICO-Agent finds lower-cost configurations and provides an interpretable audit trail for designers.
