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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ding, Ruogu, Ning, Xin, Schlichtmann, Ulf, Qian, Weikang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915637835595776
author Ding, Ruogu
Ning, Xin
Schlichtmann, Ulf
Qian, Weikang
author_facet Ding, Ruogu
Ning, Xin
Schlichtmann, Ulf
Qian, Weikang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19472
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer
Ding, Ruogu
Ning, Xin
Schlichtmann, Ulf
Qian, Weikang
Machine Learning
Artificial Intelligence
Hardware Architecture
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.
title PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer
topic Machine Learning
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2511.19472