Extending the Task Dataflow Model with Speculative Data Accesses - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Extending the Task Dataflow Model with Speculative Data Accesses

Abstract

In this paper, we describe a data-centric version-based approach to extending the task dataflow model with new access types that provide speculation capabilities to applications. We further describe the performance benefits of such a model using two scenarios that model realistic applications ; the parallelization of a finite-state machine and Monte-Carlo simulations.
Fichier principal
Vignette du fichier
SpecX__Task_Model_with_Speculative_Accesses.pdf (858.94 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04156383 , version 1 (08-07-2023)

Licence

Identifiers

  • HAL Id : hal-04156383 , version 1

Cite

Anastasios Souris, Bérenger Bramas, Philippe Clauss. Extending the Task Dataflow Model with Speculative Data Accesses. COMPAS 2023 - Conférence francophone d'informatique en Parallélisme, Architecture et Système, Jul 2023, Annecy (France), France. ⟨hal-04156383⟩
35 View
25 Download

Share

Gmail Mastodon Facebook X LinkedIn More