Preplacement Net Length and Timing Estimation by Customized Graph Neural Network
Preplacement Net Length and Timing Estimation by Customized Graph Neural Network
复制标题
DOI：
10.1109/tcad.2022.3149977
复制
发表时间：
2022-11
影响因子：
2.9
通讯作者：
Zhiyao Xie;Rongjian Liang;Xiaoqing Xu;Jiangkun Hu;Chen-Chia Chang;Jingyu Pan;Yiran Chen
中科院分区：
文献类型：
--
作者：
Zhiyao Xie;Rongjian Liang;Xiaoqing Xu;Jiangkun Hu;Chen-Chia Chang;Jingyu Pan;Yiran Chen
净长度是在标准数字设计流程的各个阶段优化时间和功率的关键代理指标。然而，在单元放置之前，大部分净长度信息是不可获得的，因此，在放置之前的设计阶段明确考虑净长度优化是一个重大挑战，例如逻辑合成。此外，网长信息的缺失使得准确的预置时间估计极其困难。时序可预测性差不仅影响时序优化，而且妨碍对综合解的准确评价。这项工作解决了这些挑战，通过预放置预测流与估算器在净长度和时间。我们提出了一种具有自定义的图注意网络（GAT）方法，称为Net2，用于在单元格放置之前估计单个网络长度。其面向精度的Net2a版本在识别长网和长关键路径方面比之前的几个工作提高了大约15%的精度。其快速版本Net2f比放置速度快1000多倍，同时在各种精度指标方面仍然优于以前的作品和其他神经网络技术。基于净尺寸估计，我们提出了第一个基于机器学习的预放置时间估计器。与商业工具的预放置时间报告相比，该方法将电弧延迟的相关系数提高了0.08，并将松弛、最坏负松弛和总负松弛估计的平均绝对误差降低了50%以上。
Net length is a key proxy metric for optimizing timing and power across various stages of a standard digital design flow. However, the bulk of net length information is not available until cell placement, and hence, it is a significant challenge to explicitly consider net length optimization in design stages prior to placement, such as logic synthesis. In addition, the absence of net length information makes accurate preplacement timing estimation extremely difficult. Poor predictability on the timing not only affects timing optimizations but also hampers the accurate evaluation of synthesis solutions. This work addresses these challenges by a preplacement prediction flow with estimators on both net length and timing. We propose a graph attention network (GAT) method with customization, called Net2, to estimate individual net length before cell placement. Its accuracy-oriented version Net2a achieves about 15% better accuracy than several previous works in identifying both long nets and long critical paths. Its fast version Net2f is more than $1000\times $ faster than placement while still outperforms previous works and other neural network techniques in terms of various accuracy metrics. Based on net size estimations, we propose the first machine learning-based preplacement timing estimator. Compared with the preplacement timing report from commercial tools, it improves the correlation coefficient in arc delays by 0.08, and reduces the mean absolute error in slack, worst negative slack, and total negative slack estimations by more than 50%.