Schedulability Analysis of Conditional Parallel Task Graphs in Multicore Systems

Alessandra Melani,Vincenzo Bonifaci,Marko Bertogna,Giorgio Buttazzo,Alberto Marchetti-Spaccamela

doi:10.1109/tc.2016.2584064

Abstract

Several task models have been introduced in the literature to describe the intrinsic parallelism of real-time activities, including fork/join, synchronous parallel, DAG-based, etc. Although schedulability tests and resource augmentation bounds have been derived for these task models in the context of multicore systems, they are still too pessimistic to describe the execution flow of parallel tasks characterized by multiple (and nested) conditional statements, where it is hard to decide which execution path to select for modeling the worst-case scenario. To overcome this problem, this paper proposes a task model that integrates control flow information by considering conditional parallel tasks (cp-tasks) represented by DAGs with both precedence and conditional edges. For this task model, a set of meaningful parameters are identified and computed by efficient algorithms and a response-time analysis is presented for different scheduling policies. Experimental results are finally reported to evaluate the efficiency of the proposed schedulability tests and their performance with respect to classic tests based on both conditional and non-conditional existing approaches.

Highlights

T He availability of multi-/many-core platforms in the embedded market [1], [2], [3], caused an increasing interest for applications with both high-performance and real-time requirements
Examples of the task models proposed to capture the parallel structure of an application include the fork/join model [21], the synchronous parallel task model [30], and the directed acyclic graph (DAG)-based task model [11]
As noted by Fonseca et al [20], the problem introduced by conditional statements is significant in the schedulability analysis of parallel tasks running on a multicore system, explicitly modeling branching structures has been proven useful for single-core systems to tighten the response time of the tasks [5], [8], [17]

Summary

Introduction

T He availability of multi-/many-core platforms in the embedded market [1], [2], [3], caused an increasing interest for applications with both high-performance and real-time requirements. Examples of the task models proposed to capture the parallel structure of an application include the fork/join model [21], the synchronous parallel task model [30], and the DAG-based task model [11] Each of these models divides a task into smaller computational units, called subtasks, which can run simultaneously on different cores. As noted by Fonseca et al [20], the problem introduced by conditional statements is significant in the schedulability analysis of parallel tasks running on a multicore system, explicitly modeling branching structures has been proven useful for single-core systems to tighten the response time of the tasks [5], [8], [17]. Identifying the worst-case scenario that affects system schedulability the most is a challenging issue

Objectives

Results

Conclusion