LLM speeds up analog circuit design with fast accurate models
NEMESIS2.0: LLM-Aided Netlist-Driven Performance Equation Modeling for Accelerated Analog Circuit Sizing
Hardware Architecture
Summary
Designing analog circuits usually requires slow and complex simulations to check how well they work. This paper introduces NEMESIS2.0, a tool that uses large language models to create simple math equations that predict circuit performance much faster. The authors tested this on various amplifier and comparator circuits and found their equations matched detailed simulations within 5%. Using these models, they sped up the process of finding the right circuit parts by nearly 200 times while still meeting design requirements most of the time.
What this means in practice
- •For analog circuit designers: Rapidly evaluate circuit performance during transistor sizing to shorten design cycles for amplifiers and comparators.
- •For electronic design automation tool developers: Integrate equation-based performance models generated by LLMs to speed up analog circuit optimization workflows.
Authors
Subhadip Ghosh, Ramesh Harjani, Sachin S. Sapatnekar
Abstract
This work presents NEMESIS2.0, an open-source LLM-aided framework that automatically derives equation-based performance models for analog circuits. The resulting equations provide fast, accurate surrogates for SPICE evaluation. To validate the method, equation-based models are developed for seven circuit test cases in a commercial 65nm CMOS technology, covering 15 metrics on five operational transconductance amplifier topologies, and six metrics on two dynamic comparator topologies. When tested on 1000 unseen variants of these seven designs, each corresponding to a different set of independently sampled transistor sizes, the accuracy is found to be within 5% of SPICE. To demonstrate use cases for NEMESIS2.0, the generated models are used as performance evaluators in multiple transistor sizers based on different population-based stochastic search optimizers. For each of the seven test cases, transistor sizing is performed for 100 different sets of performance specifications, with final SPICE simulation confirming that 83.3% of the resulting designs meet all specifications after a single sizing run. The rest fail to meet the specifications due to discrepancies between the model and SPICE, and require iterative resizing under tightened specifications; all such scenarios meet specifications within five iterations. Within the transistor sizers, this equation-based performance analysis evaluates ~400 design candidates per second, versus 0.14 candidates per second for SPICE-based evaluation, achieving 196-238x sizing runtime speedup, including final SPICE verification.