Introducing MareNostrum5: A European pre-exascale energy-efficient system designed to serve a broad spectrum of scientific workloads

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Banchelli, Fabio, Garcia-Gasulla, Marta, Mantovani, Filippo, Vinyals, Joan, Pocurull, Josep, Vicente, David, Eguzkitza, Beatriz, Galeazzo, Flavio C. C., Acosta, Mario C., Girona, Sergi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912272531587072
author Banchelli, Fabio
Garcia-Gasulla, Marta
Mantovani, Filippo
Vinyals, Joan
Pocurull, Josep
Vicente, David
Eguzkitza, Beatriz
Galeazzo, Flavio C. C.
Acosta, Mario C.
Girona, Sergi
author_facet Banchelli, Fabio
Garcia-Gasulla, Marta
Mantovani, Filippo
Vinyals, Joan
Pocurull, Josep
Vicente, David
Eguzkitza, Beatriz
Galeazzo, Flavio C. C.
Acosta, Mario C.
Girona, Sergi
contents MareNostrum5 is a pre-exascale supercomputer at the Barcelona Supercomputing Center (BSC), part of the EuroHPC Joint Undertaking. With a peak performance of 314 petaflops, MareNostrum5 features a hybrid architecture comprising Intel Sapphire Rapids CPUs, NVIDIA Hopper GPUs, and DDR5 and high-bandwidth memory (HBM), organized into four partitions optimized for diverse workloads. This document evaluates MareNostrum5 through micro-benchmarks (floating-point performance, memory bandwidth, interconnect throughput), HPC benchmarks (HPL and HPCG), and application studies using Alya, OpenFOAM, and IFS. It highlights MareNostrum5's scalability, efficiency, and energy performance, utilizing the EAR (Energy Aware Runtime) framework to assess power consumption and the effects of direct liquid cooling. Additionally, HBM and DDR5 configurations are compared to examine memory performance trade-offs. Designed to complement standard technical documentation, this study provides insights to guide both new and experienced users in optimizing their workloads and maximizing MareNostrum5's computational capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09917
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Introducing MareNostrum5: A European pre-exascale energy-efficient system designed to serve a broad spectrum of scientific workloads
Banchelli, Fabio
Garcia-Gasulla, Marta
Mantovani, Filippo
Vinyals, Joan
Pocurull, Josep
Vicente, David
Eguzkitza, Beatriz
Galeazzo, Flavio C. C.
Acosta, Mario C.
Girona, Sergi
Distributed, Parallel, and Cluster Computing
Performance
MareNostrum5 is a pre-exascale supercomputer at the Barcelona Supercomputing Center (BSC), part of the EuroHPC Joint Undertaking. With a peak performance of 314 petaflops, MareNostrum5 features a hybrid architecture comprising Intel Sapphire Rapids CPUs, NVIDIA Hopper GPUs, and DDR5 and high-bandwidth memory (HBM), organized into four partitions optimized for diverse workloads. This document evaluates MareNostrum5 through micro-benchmarks (floating-point performance, memory bandwidth, interconnect throughput), HPC benchmarks (HPL and HPCG), and application studies using Alya, OpenFOAM, and IFS. It highlights MareNostrum5's scalability, efficiency, and energy performance, utilizing the EAR (Energy Aware Runtime) framework to assess power consumption and the effects of direct liquid cooling. Additionally, HBM and DDR5 configurations are compared to examine memory performance trade-offs. Designed to complement standard technical documentation, this study provides insights to guide both new and experienced users in optimizing their workloads and maximizing MareNostrum5's computational capabilities.
title Introducing MareNostrum5: A European pre-exascale energy-efficient system designed to serve a broad spectrum of scientific workloads
topic Distributed, Parallel, and Cluster Computing
Performance
url https://arxiv.org/abs/2503.09917