Interconnects have always played a cornerstone role In HPC. Since the Inception of the Top500 ranking, Interconnect statistics have been predominantly dominated by two competing technologies: InfiniBand and Ethernet. However, even if Ethernet is very popular due to versatility and cost-effectiveness, InfiniBand used to provide higher bandwidth and continues to feature lower latency. Industry seeks for a further evolution of the Ethernet standards to enable fast and low-latency interconnect for emerging AI workloads by offering competitive, open-standard solutions. This paper analyzes the early results obtained from two systems relying on an HPC Ethernet interconnect, one relying on 100G and the other on 200G Ethernet. Preliminary findings indicate that the Ethernet-based networks exhibit competitive performance, closely aligning with InfiniBand, especially for large message exchanges.

Benchmarking Ethernet Interconnect for HPC/AI workloads / Pichetti, L.; De Sensi, D.; Sivalingam, K.; Nassyr, S.; Cesarini, D.; Turisini, M.; Pleiter, D.; Artigiani, A.; Vella, F.. - (2024), pp. 869-875. ( 2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024 Georgia World Congress Center, usa ) [10.1109/SCW63240.2024.00124].

Benchmarking Ethernet Interconnect for HPC/AI workloads

De Sensi D.;
2024

Abstract

Interconnects have always played a cornerstone role In HPC. Since the Inception of the Top500 ranking, Interconnect statistics have been predominantly dominated by two competing technologies: InfiniBand and Ethernet. However, even if Ethernet is very popular due to versatility and cost-effectiveness, InfiniBand used to provide higher bandwidth and continues to feature lower latency. Industry seeks for a further evolution of the Ethernet standards to enable fast and low-latency interconnect for emerging AI workloads by offering competitive, open-standard solutions. This paper analyzes the early results obtained from two systems relying on an HPC Ethernet interconnect, one relying on 100G and the other on 200G Ethernet. Preliminary findings indicate that the Ethernet-based networks exhibit competitive performance, closely aligning with InfiniBand, especially for large message exchanges.
2024
2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024
ethernet; gigabit ethernet; hpc/ai workloads; infiniband; interconnect
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Benchmarking Ethernet Interconnect for HPC/AI workloads / Pichetti, L.; De Sensi, D.; Sivalingam, K.; Nassyr, S.; Cesarini, D.; Turisini, M.; Pleiter, D.; Artigiani, A.; Vella, F.. - (2024), pp. 869-875. ( 2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024 Georgia World Congress Center, usa ) [10.1109/SCW63240.2024.00124].
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1737590
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact