AMSNet: Netlist Dataset for AMS Circuits

TL;DR

This paper introduces AMSNet, a comprehensive dataset of transistor-level schematics and netlists for AMS circuits, enabling the application of multimodal large language models to automate and improve AMS IC design.

Contribution

The paper presents a novel automatic method for converting schematics into netlists and releases AMSNet, the first extensive dataset linking schematic diagrams with SPICE netlists for AMS circuits.

Findings

Created AMSNet dataset with schematic-netlist pairs

Developed an automatic schematic-to-netlist conversion tool

Facilitates MLLM research in AMS circuit design

Abstract

Today's analog/mixed-signal (AMS) integrated circuit (IC) designs demand substantial manual intervention. The advent of multimodal large language models (MLLMs) has unveiled significant potential across various fields, suggesting their applicability in streamlining large-scale AMS IC design as well. A bottleneck in employing MLLMs for automatic AMS circuit generation is the absence of a comprehensive dataset delineating the schematic-netlist relationship. We therefore design an automatic technique for converting schematics into netlists, and create dataset AMSNet, encompassing transistor-level schematics and corresponding SPICE format netlists. With a growing size, AMSNet can significantly facilitate exploration of MLLM applications in AMS circuit design. We have made an initial set of netlists public, and will make both our netlist generation tool and the full dataset available upon publishing of this paper.