NPS：使用图神经网络进行准确程序采样的框架（英文版）

英文标题：NPS: A Framework for Accurate Program Sampling Using Graph Neural Network中文摘要：该研究介绍了一种名为神经程序抽样的新框架，它可以学习动态图神经网络的执行嵌入，以提高微处理器设计中程序抽样的表现，实验证明神经程序抽样在准确性和鲁棒性方面较传统方法有优势。英文摘要：With the end of Moore's Law, there is a growing demand for rapidarchitectural innovations in modern processors, such as RISC-V customextensions, to continue performance scaling. Program sampling is a crucial stepin microprocessor design, as it selects representative simulation points forworkload simulation. While SimPoint h