Using Polyhedral Techniques to Tighten WCET Estimates of Optimized Code: A Case Study with Array Contraction

Thomas Lefeuvre (1) , Emin Koray Kasnakli (2) , Imen Fassi (1, 3) , Isabelle Puaut (1, 3) , Christoph Cullmann (4) , Steven Derrien (1, 5) , Gernot Gebhard (4)

1 UR - Université de Rennes
2 Fraunhofer IIS - Fraunhofer Institute for Integrated Circuits
3 PACAP - Pushing Architecture and Compilation for Application Performance
4 Angewandte Informatik - AbsInt GmbH
5 CAIRN - Energy Efficient Computing ArchItectures with Embedded Reconfigurable Resources

The ARGO H2020 European project aims at developing a Worst-Case Execution Time (WCET)-aware parallelizing compilation toolchain. This toolchain operates on Scilab and XCoS inputs, and targets ScratchPad memory (SPM)-based multi-cores. Data-layout and loop transformations play a key role in this flow as they improve SPM efficiency and reduce the number of accesses to shared main memory. In this paper, we study how these transformations impact WCET estimates of sequential codes. We demonstrate that they can bring significant improvements of WCET estimates (up to 2.7×) provided that the WCET analysis process is guided with automatically generated flow annotations obtained using polyhedral counting techniques.

Domaines: Architectures Matérielles [cs.AR]; Systèmes embarqués

Thomas Lefeuvre, Emin Koray Kasnakli, Imen Fassi, Isabelle Puaut, Christoph Cullmann, et al.. Using Polyhedral Techniques to Tighten WCET Estimates of Optimized Code: A Case Study with Array Contraction. DATE 2018 - Design Automation and Test Europe, Mar 2018, Dresden, Germany. pp.925-930, ⟨10.23919/DATE.2018.8342142⟩. ⟨hal-01815499⟩