RTL-Sequencer: Towards Scalable RTL Timing Prediction with the Sequence-based Paradigm

2026/07/17 by Ziyan Guo, Wenji Fang, Wenkai Li +3
#cs.AR #cs.AI #cs.LG

paper · pdf

Abstract

Accurate timing prediction at the register-transfer level (RTL) is a longstanding challenge in design automation. Existing graph-based methods struggle with limited receptive fields, high complexity, and a lack of signal directionality. We present RTL-Sequencer, a novel sequence-based paradigm that enables scalable RTL timing prediction via linearizing logic cones by breadth-first traversal and applying modern linear sequence models. Furthermore, sequence models are customized by four synergistic techniques, including sequence shuffling, bidirectional modeling, differentiable modeling, and a hybrid graph-sequence architecture. Extensive experiments demonstrate significant improvements of RTL-Sequencer over state-of-the-art baselines, advancing early-stage timing optimization.

Citations

• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Attention Is All You Need

Related

• Annotating Slack Directly on Your Verilog: Fine-Grained RTL Timing Evaluation for Early Optimization
• Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
• RTLRewriter: Methodologies for Large Models aided RTL Code Optimization
• MasterRTL: A Pre-Synthesis PPA Estimation Framework for Any RTL Design
• SmaRTLy: RTL Optimization with Logic Inferencing and Structural Rebuilding