Winston: Revisiting iterative compilation for WCET minimization
| Autor: | Pasquale, Valentin, Puaut, Isabelle |
|---|---|
| Přispěvatelé: | École normale supérieure de Lyon (ENS de Lyon), Pushing Architecture and Compilation for Application Performance (PACAP), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-ARCHITECTURE (IRISA-D3), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), ARCHITECTURE (IRISA-D3) |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | RTNS 2022-30th International Conference on Real-Time Networks and Systems RTNS 2022-30th International Conference on Real-Time Networks and Systems, Jun 2022, Paris, France. pp.1-11, ⟨10.1145/3534879.3534899⟩ |
| DOI: | 10.1145/3534879.3534899⟩ |
| Popis: | International audience; Static Worst-Case Execution Time (WCET) estimation techniques take as input the binary code of a program and output a conservative estimate of its execution time. While compilers, and iterative compilation, usually optimize for the average-case, previous work such as [7, 23] has shown that it is also possible to use existing optimization and iterative compilation techniques to lower the WCET estimates drastically. In this paper, we revisit the use of iterative compilation for WCET minimization and show that previous work can be improved both in terms of complexity and reduction of WCET estimates. In particular, we found that the use of long chains of compilation flags, from a few hundred to a few thousand, allows a significant reduction of WCET estimates, of 35% on average, and up to 70% on some benchmarks, compared to the best compilation level (-O0 ..-O3) applicable. These gains are significantly better than the reductions of WCET estimates obtained by [7], which, on the same benchmarks and experimental conditions, reduce the WCET estimates by 20% on average. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|