Heterogeneous computing at INFN-T1

At INFN-T1 we recently acquired some nodes with ARM and RISC-V CPUs to understand the experiment level of readiness on new hardware solutions and to test our production pipelines. After some initial testing, ARM resources entered the standard farm, since the stability both of the nodes and of the software was production quality ready. On the contrary RISC-V solutions are still to be considered only as testbed, since the software is not ready for general production. In this article we will describe all the activities that were necessary to enable users to run on ARM and RISC-V and will give some figures on performance, compared to x86_64 counterpart. In the end we will try to describe our point of view for the possible mass adoption of this architecture in Tier1 data centers.

Authors

Institutions

Publication Details

Journal
EPJ Web of Conferences
Published
2025-01-01
DOI
https://doi.org/10.1051/epjconf/202533701133
Primary Topic
Parallel Computing and Optimization Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Heterogeneous computing at INFN-T1

A. Pascolini, Andrea Chierici, Diego Michelotto, Giusy Sergi et al.
EPJ Web of Conferences
Parallel Computing and Optimization Techniques
article

Heterogeneous computing at INFN-T1

A. Pascolini, Andrea Chierici, Diego Michelotto, Giusy Sergi, Daniele Lattanzio
article en

Abstract

At INFN-T1 we recently acquired some nodes with ARM and RISC-V CPUs to understand the experiment level of readiness on new hardware solutions and to test our production pipelines. After some initial testing, ARM resources entered the standard farm, since the stability both of the nodes and of the software was production quality ready. On the contrary RISC-V solutions are still to be considered only as testbed, since the software is not ready for general production. In this article we will describe all the activities that were necessary to enable users to run on ARM and RISC-V and will give some figures on performance, compared to x86_64 counterpart. In the end we will try to describe our point of view for the possible mass adoption of this architecture in Tier1 data centers.

EPJ Web of ConferencesVol. 337
Istituto Nazionale di Fisica Nucleare, Centro Nazionale Analisi Fotogrammi (IT)
Openalex Percentile: Top 70%
Parallel Computing and Optimization Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.