Paper ID: 2407.12749

HDLCopilot: Hardware Design Library Querying with Natural Language

Manar Abdelatty, Sherief Reda

Hardware design engineers routinely work with multiple Process Design Kits (PDKs) from various fabrication labs, each containing several standard cell libraries, optimized for specific metric such as speed, power, or density. These libraries include multiple views such as liberty files for timing information, LEF files for abstract layout details, and technology LEF for process design rules. Navigating this complex landscape to retrieve specific information about gates or design rules is often time-consuming and error-prone. To address this, we present HDLCopilot, an LLM-powered PDK query system that allows engineers to streamline interactions with PDKs in natural language format, making information retrieval accurate and more efficient. HDLCopilot achieves an accuracy of 94.23\% on an evaluation set comprised of diverse and complex natural language queries. HDLCopilot positions itself as a powerful assistant in the hardware design process, enhancing productivity and reducing potential human errors.

Submitted: Jul 17, 2024