Integration of Code-Level and System-Level Timing Analysis for Early Architecture Exploration and Reliable Timing Verification

Developers of safety-critical real-time systems have to ensure that their systems react within given time bounds. Sophisticated tools for timing analysis at the code-level, controller-level and networked system-level are becoming state-of- the-art for efficient timing verification in light of ever increasing system complexity. This trend is exemplified by two tools: AbsInt's timing analyzer aiT, which can determine safe upper bounds for the execution times (WCETs) of non-interrupted tasks, and Symtavision's SymTA/S tool, which computes the worst-case response times (WCRTs) (7, 11, 16). of an entire system from the task WCETs and in- formation about possible interrupts and their pri- orities. The two tools thus complement each other in an ideal way. They have recently been coupled to further increase their utility. Starting from a system model, a designer can now seamlessly per- form timing budgeting, performance optimization and timing verification, considering both the code of individual functions, as well as function and sub- system integration. The paper explains and exem- plifies various use cases and tool flows.

[1]  Patrick Cousot,et al.  Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints , 1977, POPL.

[2]  Kai Richter Compositional scheduling analysis using standard event models: the SymTA/S approach , 2005 .

[3]  Ken Tindell,et al.  ADDING TIME-OFFSETS TO SCHEDULABILITY ANALYSIS , 1994 .

[4]  Henrik Theiling,et al.  Combining abstract interpretation and ILP for microarchitecture modelling and program path analysis , 1998, Proceedings 19th IEEE Real-Time Systems Symposium (Cat. No.98CB36279).

[5]  Reinhold Heckmann,et al.  Worst-Case Execution Time - A Tool Provider's Perspective , 2008, 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC).

[6]  Daniel Kästner,et al.  Architecture exploration and timing estimation during early design phases , 2012, International Journal on Software Tools for Technology Transfer.

[7]  Jörn Schneider,et al.  Pipeline behavior prediction for superscalar processors by abstract interpretation , 1999, LCTES '99.

[8]  Jakob Engblom,et al.  The worst-case execution-time problem—overview of methods and survey of tools , 2008, TECS.

[9]  Jan Gustafsson,et al.  ALL-TIMES - A European Project on Integrating Timing Technology , 2008, ISoLA.

[10]  Stephan Thesing,et al.  Pipeline Modeling for Timing Analysis , 2002, SAS.

[11]  Rolf Ernst,et al.  System level performance analysis - the SymTA/S approach , 2005 .

[12]  Sharad Malik,et al.  Performance Analysis of Embedded Software Using Implicit Path Enumeration , 1995, 32nd Design Automation Conference.

[13]  Mathai Joseph,et al.  Finding Response Times in a Real-Time System , 1986, Comput. J..

[14]  Rolf Ernst,et al.  Learning early-stage platform dimensioning from late-stage timing verification , 2009, 2009 Design, Automation & Test in Europe Conference & Exhibition.