Polynomial Scheduling Algorithm for Parallel Applications on Hybrid Platforms

Massinissa Ait Aba (1, 2) , Lilia Zaourar (1) , Alix Munier (2)

1 LECA - Laboratoire Environnement de Conception & Architecture
2 ALSOC - Architecture et Logiciels pour Systèmes Embarqués sur Puce

This work addresses the problem of scheduling parallel applications into hybrid platforms composed of two different types of resources. We focus on finding a generic approach to schedule applications represented by directed acyclic graphs that minimises makespan with performance guarantee. A three-phase algorithm is proposed; the first two phases consist in solving linear formulations to find the type of processor assigned to execute each task. In the third phase, we compute the start execution time of each task to generate a feasible schedule. Finally, we test our algorithm on a large number of instances. These tests demonstrate that the proposed algorithm achieves a close-to-optimal performance.

Domaines: Informatique [cs]

Massinissa Ait Aba, Lilia Zaourar, Alix Munier. Polynomial Scheduling Algorithm for Parallel Applications on Hybrid Platforms. 6th International Symposium, ISCO 2020, May 2020, Montreal, Canada. pp.143-155, ⟨10.1007/978-3-030-53262-8_12⟩. ⟨hal-04443275⟩