异步感知的异构高性能计算机性能预测方法  

Efficient Asynchronous Performance Prediction for Heterogeneous Systems

作　　者：金煜阳 马子轩 翟季冬[1] JIN Yuyang;MA Zixuan;ZHAI Jidong(Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)

机构地区：[1]清华大学计算机科学与技术系,北京100084

出　　处：《计算物理》2024年第1期40-51,共12页Chinese Journal of Computational Physics

基　　金：国家自然科学基金(U20A20226);国家重点研发计划项目(2022YFB4500402)资助。

摘　　要：针对异步策略设计难的问题,提出面向异构超级计算机的高效异步性能预测方法,解耦异步与同步执行的性能,通过层次化建模等技术实现快速精确的性能预测,指导异步策略设计与性能优化。在国产神威异构高性能计算机上,以高性能计算领域典型应用为例,验证所提出建模方法的准确性和高效性。实验结果表明:本方法平均预测精度达到96.61%,预测效率在毫秒级。An efficient asynchronous performance prediction method is proposed to guide the design of asynchronous strategies.This method decomposes the performance behavior of synchronous and asynchronous execution and achieves fast and accurate prediction through hierarchical modeling,graph-based simulation and other techniques.Based on this method,the performance of HPL on the Sunway TaihuLight supercomputer is predicted.The experimental results show that the method achieves an accuracy of 96.61%on average for 4 million cores,with a prediction cost as low as milliseconds.

关 键 词：异构高性能计算机 性能预测 异步策略 

分 类 号：TP302.7[自动化与计算机技术—计算机系统结构]