Titre :

Massively parallel CMA-ES with increasing population

Auteur(s) :

Redon, David [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Optimisation de grande taille et calcul large échelle [BONUS]
Fortin, Pierre [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Optimisation de grande taille et calcul large échelle [BONUS]
Derbel, Bilel [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Optimisation de grande taille et calcul large échelle [BONUS]
Tsuji, Miwako [Auteur]
RIKEN Center for Computational Science [Kobe] [RIKEN CCS]
Sato, Mitsuhisa [Auteur]
RIKEN Center for Computational Science [Kobe] [RIKEN CCS]

Date de publication :

2024-09-16

Mot(s)-clé(s) en anglais :

Parallel Optimization Blackbox Optimization Local Optimization Large-Scale Parallelism BLAS
Parallel Optimization
Blackbox Optimization
Local Optimization
Large-Scale Parallelism
BLAS

Discipline(s) HAL :

Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]

Résumé en anglais : [en]

<div><p>The Increasing Population Covariance Matrix Adaptation Evolution Strategy (IPOP-CMA-ES) algorithm is a reference stochastic optimizer dedicated to blackbox optimization, where no prior knowledge about the underlying ...
Lire la suite ><div><p>The Increasing Population Covariance Matrix Adaptation Evolution Strategy (IPOP-CMA-ES) algorithm is a reference stochastic optimizer dedicated to blackbox optimization, where no prior knowledge about the underlying problem structure is available. This paper aims at accelerating IPOP-CMA-ES thanks to high performance computing and parallelism when solving large optimization problems. We first show how BLAS and LAPACK routines can be introduced in linear algebra operations, and we then propose two strategies for deploying IPOP-CMA-ES efficiently on large-scale parallel architectures with thousands of CPU cores. The first parallel strategy processes the multiple searches in the same ordering as the sequential IPOP-CMA-ES, while the second one processes concurrently these multiple searches. These strategies are implemented in MPI+OpenMP and compared on 6144 cores of the supercomputer Fugaku. We manage to obtain substantial speedups (up to several thousand) and even super-linear ones, and we provide an in-depth analysis of our results to understand precisely the superior performance of our second strategy.</p></div>Lire moins >

Langue :

Anglais

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Date de dépôt :

2024-09-19T02:03:07Z