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

Ruogu Ding; Xin Ning; Ulf Schlichtmann; Weikang Qian

AAAI 2026technical0 citations

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

Ruogu Ding, Xin Ning, Ulf Schlichtmann, Weikang Qian

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

BibTeX

@inproceedings{aaai2026_prefixgptprefixa,
  title = {PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer},
  author = {Ruogu Ding and Xin Ning and Ulf Schlichtmann and Weikang Qian},
  booktitle = {AAAI 2026},
  year = {2026}
}