Cross-architecture benchmarking and performance evaluation of HPC systems

This thesis presents a comprehensive evaluation of the New Generation General Pur- pose Partition of the MareNostrum 5 supercomputer, deployed at the Barcelona Su- percomputing Center, and built on the NVIDIA Grace CPU architecture. The anal- ysis is conducted at three levels: micro-benchmarks targe...

Descripción completa

Detalles Bibliográficos
Autor: Trimmel, Majesa
Tipo de recurso: tesis de maestría
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/448968
Acceso en línea:https://hdl.handle.net/2117/448968
Access Level:acceso abierto
Palabra clave:High performance computing
HPC systems
Performance analysis
NVIDIA Grace CPU
Energy efficiency
Micro-architecture
Scientific application
Càlcul intensiu (Informàtica)
Àrees temàtiques de la UPC::Informàtica::Impacte ambiental
id ES_dddae2c29dc0d1ffd8ea9e6f50a01e34
oai_identifier_str oai:upcommons.upc.edu:2117/448968
network_acronym_str ES
network_name_str España
repository_id_str
spelling Cross-architecture benchmarking and performance evaluation of HPC systemsTrimmel, MajesaHigh performance computingHPC systemsPerformance analysisNVIDIA Grace CPUEnergy efficiencyMicro-architectureScientific applicationCàlcul intensiu (Informàtica)Àrees temàtiques de la UPC::Informàtica::Impacte ambientalThis thesis presents a comprehensive evaluation of the New Generation General Pur- pose Partition of the MareNostrum 5 supercomputer, deployed at the Barcelona Su- percomputing Center, and built on the NVIDIA Grace CPU architecture. The anal- ysis is conducted at three levels: micro-benchmarks targeting specific system compo- nents, High Performance Computing benchmarks for system-to-system comparisons, and a performance study using a scientific application that simulates a real-world workload. Additionally, this work compares the new cluster to the two existing oper- ational partitions of MareNostrum 5, the General Purpose and Accelerated Partition, both of which are based on Intel's Sapphire Rapids micro-architecture. This com- parison aims to assess the maturity and competitiveness of the NVIDIA Grace-based system relative to established technologies. The study also explores the performance variability introduced by using different compilers and runtimes on the new cluster. The findings indicate that the NVIDIA Grace-based system is largely mature, de- livering strong out-of-the-box performance with minimal tuning, notably for memory- bound workloads. This was particularly evident, as its memory bandwidth reached the advertised 1 TB/s and showed an improvement of more than twice that of the Intel- based clusters. However, some hardware characteristics remain opaque due to limited documentation, and the choice of compiler and runtime has a measurable impact on performance. In terms of scalability, the system demonstrates efficient node utiliza- tion and improved energy efficiency in standard HPC benchmarks. Although the CPU is not floating-point centric, as evidenced by achieving only 5.50 TFlop/s per node in HPL compared to 6.61 TFlop/s on the General Purpose Partition, it still demon- strates notable energy efficiency. Specifically, it reaches around 9.10 GFlop/(s × W) for a single node, outperforming the 7.59 GFlop/(s × W) observed on the General Purpose Partition. For real-life workloads, the new architecture outperforms x86 sys- tems in smaller-scale runs, but performance diminishes at larger scales, likely due to load-balancing issues.Universitat Politècnica de CatalunyaVicente Dorca, DavidBanchelli Gracia, Fabio20252025-07-0220252025-12-10master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/448968reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4489682026-05-27T15:37:01Z
dc.title.none.fl_str_mv Cross-architecture benchmarking and performance evaluation of HPC systems
title Cross-architecture benchmarking and performance evaluation of HPC systems
spellingShingle Cross-architecture benchmarking and performance evaluation of HPC systems
Trimmel, Majesa
High performance computing
HPC systems
Performance analysis
NVIDIA Grace CPU
Energy efficiency
Micro-architecture
Scientific application
Càlcul intensiu (Informàtica)
Àrees temàtiques de la UPC::Informàtica::Impacte ambiental
title_short Cross-architecture benchmarking and performance evaluation of HPC systems
title_full Cross-architecture benchmarking and performance evaluation of HPC systems
title_fullStr Cross-architecture benchmarking and performance evaluation of HPC systems
title_full_unstemmed Cross-architecture benchmarking and performance evaluation of HPC systems
title_sort Cross-architecture benchmarking and performance evaluation of HPC systems
dc.creator.none.fl_str_mv Trimmel, Majesa
author Trimmel, Majesa
author_facet Trimmel, Majesa
author_role author
dc.contributor.none.fl_str_mv Vicente Dorca, David
Banchelli Gracia, Fabio
dc.subject.none.fl_str_mv High performance computing
HPC systems
Performance analysis
NVIDIA Grace CPU
Energy efficiency
Micro-architecture
Scientific application
Càlcul intensiu (Informàtica)
Àrees temàtiques de la UPC::Informàtica::Impacte ambiental
topic High performance computing
HPC systems
Performance analysis
NVIDIA Grace CPU
Energy efficiency
Micro-architecture
Scientific application
Càlcul intensiu (Informàtica)
Àrees temàtiques de la UPC::Informàtica::Impacte ambiental
description This thesis presents a comprehensive evaluation of the New Generation General Pur- pose Partition of the MareNostrum 5 supercomputer, deployed at the Barcelona Su- percomputing Center, and built on the NVIDIA Grace CPU architecture. The anal- ysis is conducted at three levels: micro-benchmarks targeting specific system compo- nents, High Performance Computing benchmarks for system-to-system comparisons, and a performance study using a scientific application that simulates a real-world workload. Additionally, this work compares the new cluster to the two existing oper- ational partitions of MareNostrum 5, the General Purpose and Accelerated Partition, both of which are based on Intel's Sapphire Rapids micro-architecture. This com- parison aims to assess the maturity and competitiveness of the NVIDIA Grace-based system relative to established technologies. The study also explores the performance variability introduced by using different compilers and runtimes on the new cluster. The findings indicate that the NVIDIA Grace-based system is largely mature, de- livering strong out-of-the-box performance with minimal tuning, notably for memory- bound workloads. This was particularly evident, as its memory bandwidth reached the advertised 1 TB/s and showed an improvement of more than twice that of the Intel- based clusters. However, some hardware characteristics remain opaque due to limited documentation, and the choice of compiler and runtime has a measurable impact on performance. In terms of scalability, the system demonstrates efficient node utiliza- tion and improved energy efficiency in standard HPC benchmarks. Although the CPU is not floating-point centric, as evidenced by achieving only 5.50 TFlop/s per node in HPL compared to 6.61 TFlop/s on the General Purpose Partition, it still demon- strates notable energy efficiency. Specifically, it reaches around 9.10 GFlop/(s × W) for a single node, outperforming the 7.59 GFlop/(s × W) observed on the General Purpose Partition. For real-life workloads, the new architecture outperforms x86 sys- tems in smaller-scale runs, but performance diminishes at larger scales, likely due to load-balancing issues.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-07-02
2025
2025-12-10
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/448968
url https://hdl.handle.net/2117/448968
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869421921349664768
score 15,81155

Similares en LA Referencia