Exploring scheduling algorithms for parallel task graphs: a modern game engine case study - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Exploring scheduling algorithms for parallel task graphs: a modern game engine case study

Mustapha Regragui
  • Function : Author
  • PersonId : 1126325
Baptiste Coye
  • Function : Author
  • PersonId : 1126326
Laércio Lima Pilla
Raymond Namyst
Denis Barthou
  • Function : Author
  • PersonId : 866143

Abstract

Game engines are at the heart of the design of modern video games. One of their functions is to keep a high frame rate by scheduling the tasks required to generate each frame (image). These tasks are organized in a soft real-time, parallel task graph, which is a scenario very few works have focused on, or adapted scheduling algorithms to. In this paper, we study the scheduling problem of game engines. We model the tasks and the scheduling problem by proling a commercial game engine, adapt and compare dierent scheduling algorithms, and propose two additional scheduling optimizations.
Fichier principal
Vignette du fichier
main.pdf (448.47 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03580775 , version 1 (18-02-2022)

Identifiers

Cite

Mustapha Regragui, Baptiste Coye, Laércio Lima Pilla, Raymond Namyst, Denis Barthou. Exploring scheduling algorithms for parallel task graphs: a modern game engine case study. International European Conference on Parallel and Distributed Computing (Euro-Par), Aug 2022, Glasgow, United Kingdom. pp.103-118, ⟨10.1007/978-3-031-12597-3_7⟩. ⟨hal-03580775⟩

Collections

CNRS INRIA INRIA2
340 View
689 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More