FastTrack: Efficient and Precise Dynamic Race Detection

作     者：Flanagan, Cormac Freund, Stephen N. 

作者机构：Univ Calif Santa Cruz Dept Comp Sci Santa Cruz CA 95064 USA Williams Coll Dept Comp Sci Williamstown MA 01267 USA 

出 版 物：《COMMUNICATIONS OF THE ACM》 (美国计算机学会通讯)

年 卷 期：2010年第53卷第11期

页      面：93-101页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：NSF [0341179, 0341387, 0644130, 0707885] Direct For Computer & Info Scie & Enginr Funding Source: National Science Foundation Direct For Computer & Info Scie & Enginr Division of Computing and Communication Foundations [0341387, 0644130, 0341179] Funding Source: National Science Foundation Division Of Computer and Network Systems Funding Source: National Science Foundation 

主　　题：PARALLEL programs (Computer programs) VECTOR analysis DATA analysis ACQUISITION of data COMPUTER programming ALGORITHM research 

摘      要：Multithreaded programs are notoriously prone to race conditions Prior work developed precise dynamic race detectors that never report false alarms However, these checkers employ expensive data structures, such as vector clocks (VCs), that result in significant performance overhead This paper exploits the insight that the full generality of VCs is not necessary in most cases That is, we can replace VCs with an adaptive lightweight representation that, for almost all operations of the target program, requires constant space and supports constant time operations Experimental results show that the resulting race detection algorithm is over twice as fast as prior precise race detectors, with no loss of precision