LIMCA: LLM for Automating Analog In-Memory Computing Architecture Design Exploration

In this paper, we introduce LIMCA, a novel fine-tuning-free Large Language Model (LLM)-driven framework for automating the design and evaluation of In-Memory Computing (IMC) crossbar architectures. Unlike traditional approaches, where the manual, knowledge-intensive design process and the lack of high-quality circuit netlists have significantly constrained Design Space Exploration (DSE) and optimization to behavioral system-level tools, LIMCA employs a No-Human-In-Loop (NHIL) automated pipeline to generate and validate circuit netlists for SPICE simulations, eliminating manual intervention. LIMCA systematically explores the IMC design space by leveraging a structured dataset and LLM-based performance evaluation. Our experimental results on MNIST classification demonstrate that LIMCA successfully generates crossbar designs achieving ≥96% accuracy while maintaining a power consumption ≤3W, making this the first work in LLM-assisted IMC DSE. Compared to existing frameworks, LIMCA provides an automated, scalable, and hardware-aware solution, reducing design exploration time while ensuring user-constrained performance trade-offs. Artifacts are open-sourced at https://github.com/ACADLab/LIMCA.