NeuroSteiner:一种用于线长估计的图Transformer
NeuroSteiner: A Graph Transformer for Wirelength Estimation
AI总结:
NeuroSteiner通过蒸馏最优RSMT求解器GeoSteiner训练图Transformer,在ISPD基准上以更快的速度实现低线长估计误差,并支持可微布局优化。
摘要:
物理设计的一个核心目标是在画布上放置芯片组件时最小化线长(WL)。计算一个布局的最小线长需要求解直线Steiner最小树(RSMTs),这是一个NP难问题。我们提出NeuroSteiner,一个神经模型,它蒸馏最优RSMT求解器GeoSteiner,以在WL估计的成本-精度前沿上进行权衡。NeuroSteiner在由GeoSteiner标注的合成线网上训练,从而无需在真实芯片设计上训练。此外,NeuroSteiner的可微性允许通过梯度下降最小化WL来进行布局。在ISPD 2005和2019上,NeuroSteiner可以获得0.3%的WL误差,同时比GeoSteiner快60%,或者获得0.2%的误差且快30%。
英文摘要:
A core objective of physical design is to minimize wirelength (WL) when placing chip components on a canvas. Computing the minimal WL of a placement requires finding rectilinear Steiner minimum trees (RSMTs), an NP-hard problem. We propose NeuroSteiner, a neural model that distills GeoSteiner, an optimal RSMT solver, to navigate the cost--accuracy frontier of WL estimation. NeuroSteiner is trained on synthesized nets labeled by GeoSteiner, alleviating the need to train on real chip designs. Moreover, NeuroSteiner's differentiability allows to place by minimizing WL through gradient descent. On ISPD 2005 and 2019, NeuroSteiner can obtain 0.3% WL error while being 60% faster than GeoSteiner, or 0.2% and 30%.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。