RTLRewriter: Methodologies for Large Models aided RTL Code Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Xufeng, Wang, Yiwen, Li, Xing, Lian, Yingzhao, Chen, Ran, Chen, Lei, Yuan, Mingxuan, Xu, Hong, Yu, Bei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916398984331264
author Yao, Xufeng
Wang, Yiwen
Li, Xing
Lian, Yingzhao
Chen, Ran
Chen, Lei
Yuan, Mingxuan
Xu, Hong
Yu, Bei
author_facet Yao, Xufeng
Wang, Yiwen
Li, Xing
Lian, Yingzhao
Chen, Ran
Chen, Lei
Yuan, Mingxuan
Xu, Hong
Yu, Bei
contents Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often requiring multiple iterations based on synthesis feedback. In contrast, existing compiler-based methods fall short in addressing complex designs. This paper introduces RTLRewriter, an innovative framework that leverages large models to optimize RTL code. A circuit partition pipeline is utilized for fast synthesis and efficient rewriting. A multi-modal program analysis is proposed to incorporate vital visual diagram information as optimization cues. A specialized search engine is designed to identify useful optimization guides, algorithms, and code snippets that enhance the model ability to generate optimized RTL. Additionally, we introduce a Cost-aware Monte Carlo Tree Search (C-MCTS) algorithm for efficient rewriting, managing diverse retrieved contents and steering the rewriting results. Furthermore, a fast verification pipeline is proposed to reduce verification cost. To cater to the needs of both industry and academia, we propose two benchmarking suites: the Large Rewriter Benchmark, targeting complex scenarios with extensive circuit partitioning, optimization trade-offs, and verification challenges, and the Small Rewriter Benchmark, designed for a wider range of scenarios and patterns. Our comparative analysis with established compilers such as Yosys and E-graph demonstrates significant improvements, highlighting the benefits of integrating large models into the early stages of circuit design. We provide our benchmarks at https://github.com/yaoxufeng/RTLRewriter-Bench.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11414
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RTLRewriter: Methodologies for Large Models aided RTL Code Optimization
Yao, Xufeng
Wang, Yiwen
Li, Xing
Lian, Yingzhao
Chen, Ran
Chen, Lei
Yuan, Mingxuan
Xu, Hong
Yu, Bei
Hardware Architecture
Artificial Intelligence
Software Engineering
Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often requiring multiple iterations based on synthesis feedback. In contrast, existing compiler-based methods fall short in addressing complex designs. This paper introduces RTLRewriter, an innovative framework that leverages large models to optimize RTL code. A circuit partition pipeline is utilized for fast synthesis and efficient rewriting. A multi-modal program analysis is proposed to incorporate vital visual diagram information as optimization cues. A specialized search engine is designed to identify useful optimization guides, algorithms, and code snippets that enhance the model ability to generate optimized RTL. Additionally, we introduce a Cost-aware Monte Carlo Tree Search (C-MCTS) algorithm for efficient rewriting, managing diverse retrieved contents and steering the rewriting results. Furthermore, a fast verification pipeline is proposed to reduce verification cost. To cater to the needs of both industry and academia, we propose two benchmarking suites: the Large Rewriter Benchmark, targeting complex scenarios with extensive circuit partitioning, optimization trade-offs, and verification challenges, and the Small Rewriter Benchmark, designed for a wider range of scenarios and patterns. Our comparative analysis with established compilers such as Yosys and E-graph demonstrates significant improvements, highlighting the benefits of integrating large models into the early stages of circuit design. We provide our benchmarks at https://github.com/yaoxufeng/RTLRewriter-Bench.
title RTLRewriter: Methodologies for Large Models aided RTL Code Optimization
topic Hardware Architecture
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2409.11414