Dynamic and Adaptive Calling Context Encoding

Calling context has been widely used in many software development processes such as testing, event logging, and program analysis. It plays an even more important role in data race detection and performance bottleneck analysis for multi-threaded programs. This paper presents DACCE (Dynamic and Adaptive Calling Context Encoding), an efficient runtime encoding/decoding mechanism for single-threaded and multi-threaded programs that captures dynamic calling contexts. It can dynamically encode all call paths invoked at runtime, and adjust the encodings according to program's execution behavior. In contrast to existing context encoding method, DACCE can work on incomplete call graph, and it does not require source code analysis and offline profiling to conduct context encoding. DACCE has significantly expanded the functionality and applicability of calling context with even lower runtime overhead. DACCE is very efficient based on experiments with SPEC CPU2006 and Parsec 2.1 (with about 2% of runtime overhead) and effective for all tested benchmarks.

[1]  Xiangyu Zhang,et al.  Alchemist: A Transparent Dependence Distance Profiling Infrastructure , 2009, 2009 International Symposium on Code Generation and Optimization.

[2]  Michael D. Bond,et al.  Practical path profiling for dynamic optimizers , 2005, International Symposium on Code Generation and Optimization.

[3]  Jong-Deok Choi,et al.  Accurate, efficient, and adaptive calling context profiling , 2006, PLDI '06.

[4]  Kai Li,et al.  The PARSEC benchmark suite: Characterization and architectural implications , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).

[5]  Weibo Gong,et al.  Anomaly detection using call stack information , 2003, 2003 Symposium on Security and Privacy, 2003..

[6]  Xiangyu Zhang,et al.  Precise Calling Context Encoding , 2012, IEEE Trans. Software Eng..

[7]  Harish Patil,et al.  Pin: building customized program analysis tools with dynamic instrumentation , 2005, PLDI '05.

[8]  Nicholas Nethercote,et al.  Using Valgrind to Detect Undefined Value Errors with Bit-Precision , 2005, USENIX Annual Technical Conference, General Track.

[9]  James R. Larus,et al.  Efficient path profiling , 1996, Proceedings of the 29th Annual IEEE/ACM International Symposium on Microarchitecture. MICRO 29.

[10]  Donald E. Porter,et al.  Improved error reporting for software that uses black-box components , 2007, PLDI '07.

[11]  Nathan R. Tallent,et al.  Binary analysis for measurement and attribution of program performance , 2009, PLDI '09.

[12]  Michael D. Bond,et al.  Probabilistic calling context , 2007, OOPSLA.

[13]  James R. Larus,et al.  Exploiting hardware performance counters with flow and context sensitive profiling , 1997, PLDI '97.

[14]  Camil Demetrescu,et al.  Mining hot calling contexts in small space , 2011, PLDI '11.

[15]  Bixin Li,et al.  Profiling all paths: A new profiling technique for both cyclic and acyclic paths , 2012, J. Syst. Softw..

[16]  Michael D. Bond,et al.  Breadcrumbs: efficient context sensitivity for dynamic bug detection analyses , 2010, PLDI '10.

[17]  Xiangyu Zhang,et al.  Dynamic slicing long running programs through execution fast forwarding , 2006, SIGSOFT '06/FSE-14.

[18]  J. Michael Spivey,et al.  Fast, accurate call graph profiling , 2004, Softw. Pract. Exp..

[19]  Koushik Sen.  DART: Directed Automated Random Testing , 2009, Haifa Verification Conference.

[20]  Nicholas Nethercote,et al.  Valgrind: a framework for heavyweight dynamic binary instrumentation , 2007, PLDI '07.

[21]  Amer Diwan,et al.  Inferred call path profiling , 2009, OOPSLA 2009.