首页 | 本学科首页   官方微博 | 高级检索  
     

面向多核程序确定性重演的内存竞争记录机制研究
引用本文:朱素霞,季振洲,刘涛,王庆,张浩.面向多核程序确定性重演的内存竞争记录机制研究[J].电子学报,2011,39(12):2748-2754.
作者姓名:朱素霞  季振洲  刘涛  王庆  张浩
作者单位:1. 哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨 150001;2. 中国科学院计算技术研究所,北京 100190
摘    要:内存竞争记录是实现多核程序确定性重演的关键技术.针对现有内存竞争记录算法存在消耗资源多、记录日志大、重演速度受限等问题,本文提出了一种硬件结构支持的、基于分段技术的、高效的点对点内存竞争记录算法,该算法用一种更严格的间接发生序表示内存竞争,采用分段的可推导约减算法减少记录内存竞争的次数,同时使用最大近似时戳法近似已被替...

关 键 词:多核程序  确定性重演  内存竞争记录
收稿时间:2010-12-15

Study on Memory Race Recording Mechanism in Deterministic Multi-Core Replay
ZHU Su-xia,JI Zhen-zhou,LIU Tao,WANG Qing,ZHANG Hao.Study on Memory Race Recording Mechanism in Deterministic Multi-Core Replay[J].Acta Electronica Sinica,2011,39(12):2748-2754.
Authors:ZHU Su-xia  JI Zhen-zhou  LIU Tao  WANG Qing  ZHANG Hao
Affiliation:1. School of Computer,Harbin Institute of Technology,Harbin,Heilongjiang 150001,China;2. Institute of Computing Technology Chinese Academy of Sciences,Beijing 100190,China
Abstract:Memory race recording is a key technology in deterministic multi-core replay.High hardware consumption,large log size and slow replay speed limited the application of previous memory race recording algorithms.This paper proposes a new efficient hardware memory race recording algorithm,which is implemented in chunks and logs the outcomes of memory races in a point-to-point approach.In this recording mechanism,memory race is presented in a new stricter indirect dependency,a chunk-based transitive reduction algorithm is introduced to reduce the number of memory races logged,a maximum timestamp approximation method is proposed to deal with those races evicted from cache.This new memory race recording algorithm can replay a program at production run speed,and log a smaller memory race log using smaller hardware than previous point-to-point approaches.
Keywords:multi-core program  deterministic replay  memory race recording
本文献已被 万方数据 等数据库收录!
点击此处可从《电子学报》浏览原始摘要信息
点击此处可从《电子学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号