pith. sign in

arxiv: 2503.09917 · v1 · pith:D3X2Z6N5new · submitted 2025-03-13 · 💻 cs.DC · cs.PF

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

classification 💻 cs.DC cs.PF
keywords marenostrum5performancememoryworkloadsddr5designedenergypre-exascale
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Constraint-satisfying binary boson star initial data via XCFC

    gr-qc 2026-05 unverdicted novelty 6.0

    Constraint-satisfying scalar-field initial data for boson star binaries is constructed via the XCFC formalism, improving on superposition by ensuring the constraints are met.

  2. PICO: Performance Insights for Collective Operations

    cs.DC 2025-08 unverdicted novelty 6.0

    PICO is a benchmarking framework for collective operations that decouples portable setup from platform execution, supplies reference MPI implementations, and shows default choices can be up to 5x slower with up to 44%...

  3. Mapping the Schedule x Bit-Width Boundary in Sub-100M Quantisation-Aware Training

    cs.LG 2026-05 unverdicted novelty 5.0

    Factorial experiments with over 1300 runs falsify the hypothesis that INT6 QAT needs a different LR schedule from higher precision and identify a 50M-parameter boundary for INT4 schedule sensitivity.