Repository for "Evaluating LLMs for Hardware Design and Test"

Data Repository for "Evaluating LLMs for Hardware Design and Test"

This repository contains the conversations and related scripts for the paper "Evaluating LLMs for Hardware Design and Test", submitted to ISLAD 2024.

The repository is organized as follows:

•  `scripted-benchmarks` - this contains additional data used in the paper, which examines a more rigid process when exploring the potential applications for LLMs in hardware design. Here, each model chats are separated by subdirectory.
• `scripted-benchmarks-gpt4-tt03` - this contains just the benchmarks used in the paper, made by the first run of GPT-4, which were used for tapeout in Tiny Tapeout 3.

The tt03 directory contains the GitHub action scripts required to invoke OpenLane and produce synthesis files, as well as used to perform simulation tests.