Communication Dans Un Congrès Année : 2025

Evaluating Energy Efficiency of Genomics Algorithms on Processing-in-Memory Architectures

Résumé

Processing-in-Memory (PiM) is a novel computing paradigm for reducing data movements between memory and processing units, and thus minimizing energy consumption. PiMs are particularly well-suited to data-intensive applications, where traditional systems are often limited by memory bandwidth. Genomics is a representative example of such a domain, involving massive datasets and repetitive access patterns. In this paper, we evaluate the energy efficiency improvements achieved by running several genomic algorithms on a PiM-based system. Our experiments focus on realistic workloads and highlight the challenges and opportunities of parallelizing genomic tasks for PiM. The most significant gains are observed in large-scale database search applications, which naturally map to the parallel structure of PiM and benefit greatly from reduced data movement.

Fichier principal
Vignette du fichier
PECS_2025_EuroPar.pdf (558.77 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05375465 , version 1 (20-11-2025)

Licence

Identifiants

  • HAL Id : hal-05375465 , version 1

Citer

Meven Mognol, Florestan de Moor, Erwan Drezen, Yann Falevoz, Dominique Lavenier. Evaluating Energy Efficiency of Genomics Algorithms on Processing-in-Memory Architectures. PECS 2025 - International Workshop on Performance and Energy Efficiency in Concurrent and Distributed Systems, Biagio Cosenza, Aug 2025, Dresden, Germany. pp.1-12. ⟨hal-05375465⟩
251 Consultations
139 Téléchargements

Partager

  • More