一种用于布线性预测的轻量级 Inception 增强 U-Net 神经网络
A Lightweight Inception Boosted U-Net Neural Network for Routability Prediction
AI总结:
本文提出一种由 Inception 嵌入模块增强的轻量级 U-Net 变体模型,用于在 VLSI 后端设计中提前预测布线拥塞与设计规则检查热点,在 CircuitNet 基准上显著降低了误差并提升了结构相似性。
摘要:
随着现代 CPU、GPU 和 NPU 芯片设计复杂度与晶体管数量持续增加,以及半导体工艺节点不断缩小至近 1 纳米,布局与布线已逐渐成为现代超大规模集成(VLSI)电路后端设计中最关键的两个过程。如何提前(在布局与全局布线阶段)高效且准确地评估布线性,已成为人工智能(AI)辅助电子设计自动化(EDA)领域的关键研究方向。本文提出了一种由 Inception 嵌入模块增强的新型 U-Net 变体模型,用于预测布线拥塞(RC)与设计规则检查(DRC)热点。在最新发布的 CircuitNet 数据集基准上的实验结果表明,与经典架构相比,我们提出的方法在 Avg-NRMSE(平均归一化均方根误差)方面实现了高达 5%(RC)和 20%(DRC)的比率降低。此外,我们的方法在 SSIM(结构相似性指数度量)指标上始终优于先前的模型。
英文摘要:
As the modern CPU, GPU, and NPU chip design complexity and transistor counts keep increasing, and with the relentless shrinking of semiconductor technology nodes to nearly 1 nanometer, the placement and routing have gradually become the two most pivotal processes in modern very-large-scale-integrated (VLSI) circuit back-end design. How to evaluate routability efficiently and accurately in advance (at the placement and global routing stages) has grown into a crucial research area in the field of artificial intelligence (AI) assisted electronic design automation (EDA). In this paper, we propose a novel U-Net variant model boosted by an Inception embedded module to predict Routing Congestion (RC) and Design Rule Checking (DRC) hotspots. Experimental results on the recently published CircuitNet dataset benchmark show that our proposed method achieves up to 5% (RC) and 20% (DRC) rate reduction in terms of Avg-NRMSE (Average Normalized Root Mean Square Error) compared to the classic architecture. Furthermore, our approach consistently outperforms the prior model on the SSIM (Structural Similarity Index Measure) metric.
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。