PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer

TL;DR

PrefixGPT leverages a generative Transformer model to automatically generate optimized prefix adders, significantly improving design quality and exploration efficiency in hardware design.

Contribution

The paper introduces PrefixGPT, a novel GPT-based framework that directly generates valid and optimized prefix adder designs from scratch, combining design rule learning and optimization.

Findings

Achieved a 7.7% improvement in area-delay product (ADP) over existing designs.

Lowered average ADP by up to 79.1% through superior exploration.

Demonstrated GPT models' potential in complex hardware design optimization.

Abstract

Prefix adders are widely used in compute-intensive applications for their high speed. However, designing optimized prefix adders is challenging due to strict design rules and an exponentially large design space. We introduce PrefixGPT, a generative pre-trained Transformer (GPT) that directly generates optimized prefix adders from scratch. Our approach represents an adder's topology as a two-dimensional coordinate sequence and applies a legality mask during generation, ensuring every design is valid by construction. PrefixGPT features a customized decoder-only Transformer architecture. The model is first pre-trained on a corpus of randomly synthesized valid prefix adders to learn design rules and then fine-tuned to navigate the design space for optimized design quality. Compared with existing works, PrefixGPT not only finds a new optimal design with a 7.7% improved area-delay product (ADP) but exhibits superior exploration quality, lowering the average ADP by up to 79.1%. This demonstrates the potential of GPT-style models to first master complex hardware design principles and then apply them for more efficient design optimization.