Timing Analysis for DAG-based and GFP Scheduled Tasks

TL;DR

This paper presents a schedulability analysis method for DAG-based real-time tasks on multi-core systems, focusing on response-time bounds and interference management to improve predictability.

Contribution

It introduces a novel response-time analysis that accounts for self-interference and high-priority task interference in DAG-based scheduling.

Findings

The proposed analysis accurately predicts task schedulability.

It effectively bounds self-interference within DAG tasks.

The method improves real-time system predictability.

Abstract

Modern embedded systems have made the transition from single-core to multi-core architectures, providing performance improvement via parallelism rather than higher clock frequencies. DAGs are considered among the most generic task models in the real-time domain and are well suited to exploit this parallelism. In this paper we provide a schedulability test using response-time analysis exploiting exploring and bounding the self interference of a DAG task. Additionally we bound the interference a high priority task has on lower priority ones.