PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 20808-20815
DOI: 10.1609/aaai.v40i25.39220 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ruogu Ding und 3 weiteren Autor:innen.
Abstract (Originalsprache)
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.
Zitieren
APA
Ding, R., Ning, X., Schlichtmann, U., & Qian, W. (2026). PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 20808-20815. https://doi.org/10.1609/aaai.v40i25.39220
Vancouver
Ding R, Ning X, Schlichtmann U, Qian W. PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):20808-20815. doi:10.1609/aaai.v40i25.39220
BibTeX
@article{Ding2026,
author = {Ding, Ruogu and Ning, Xin and Schlichtmann, Ulf and Qian, Weikang},
title = {PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {25},
pages = {20808--20815},
doi = {10.1609/aaai.v40i25.39220}
}
EUVIMED