LEAP: A Self-Supervised Per-Cycle Toggle Propagation Model Supports Fast, Transferable, and Early Analysis of Layout Power
2026-08-03 • Hardware Architecture
Hardware Architecture
AI summaryⓘ
The authors developed LEAP, a new method to quickly and accurately predict how signals toggle through electronic circuits in very large scale integration (VLSI) design. This process is important for estimating power use but is usually slow because it tracks changes every cycle. LEAP uses a special graph transformer and training tasks to understand circuit behavior efficiently, achieving much faster speeds while keeping prediction accuracy very high. They also combined LEAP with other models in LEAP-Power to predict power use directly from circuit designs, speeding up runtime significantly compared to previous methods.
VLSI designpower analysistoggle propagationnetlistgraph transformerself-supervised learningPrecision-Recall curvemean absolute percentage errorpost-synthesis netlistpower modeling
Authors
Wenkai Li, Yuchao Wu, Ziyan Guo, Yao Lu, Wenji Fang, Mengming Li, Zhiyao Xie
Abstract
Accurate power analysis is critical in VLSI design, as it directly impacts power optimization strategies. However, traditional approaches are often hindered by the substantial runtime required for per-cycle toggle propagation in the netlist, which propagates register toggle information through combinational logic. To address this, we propose LEAP, the first work to enable per-cycle toggle propagation prediction with both high accuracy and efficiency. This is achieved through a novel, linear-complexity graph transformer capable of simulating toggle propagation, along with specially designed self-supervised pre-training tasks that enable the model to capture circuit structure and functionality. LEAP achieves a 7.6x speedup over the EDA tool in toggle propagation, and attains a near-perfect area under the Precision-Recall curve (PR-AUC) of 0.99 for prediction results. Moreover, LEAP can be seamlessly integrated with other machine learning based power models into LEAP-Power. This integration enables precise per-cycle layout power prediction directly from post-synthesis netlists, achieving a mean absolute percentage error(MAPE) of only 4.55%. By bypassing toggle propagation in the netlist, LEAP-Power delivers substantial runtime gains, running 5.3x faster than the model without LEAP.