Response time analysis of memory-bandwidth-regulated multiframe mixed-criticality systems

• Type: Article in International Scientific Journal
• Date: 2022-02

Authors

Pedro Souto (Author) FEUP; Ishfaq Hussain (Author) Other; Muhammad Ali Awan (Author) Other; Konstantinos Bletsas (Author) Other; Eduardo Tovar (Author) Other

Journal

Title: Journal of Systems Architecture

Vol. 123

ISSN: 1383-7621

Publisher: Elsevier

Indexing

ISI Web of Knowledge - 0 Citations

Other information

Authenticus ID: P-00V-ZWN

DOI: 10.1016/j.sysarc.2021.102346

Abstract (EN): The multiframe mixed-criticality task model eliminates the pessimism in many systems where the worst-case execution times (WCETs) of successive jobs vary greatly by design, in a known pattern. Existing feasibility analysis techniques for multiframe mixed-criticality tasks are shared-resource-oblivious, hence unsafe for commercial-off-the-shelf (COTS) multicore platforms with a memory controller shared among all cores. Conversely, the feasibility analyses that account for the interference on shared resource(s) in COTS platforms do not leverage the WCET variation in multiframe tasks. This paper extends the state-of-the-art by presenting an analysis that incorporates the memory access stall in memory-bandwidth-regulated multiframe mixed-criticality multicore systems. An exhaustive enumeration approach is proposed for this analysis to further enhance the schedulability success ratio. The running time of the exhaustive analysis is improved by proposing a pruning mechanism that eliminates the combinations of interfering job sequences that subsume others. Experimental evaluation, using synthetic task sets, demonstrates up to 72% improvement in terms of schedulability success ratio, compared to frame-agnostic analysis.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 11