Efficient All-to-All Collective Communication Schedules for Direct-Connect Topologies

The all-to-all collective communications primitive is widely used in machine learning (ML) and high performance computing (HPC) workloads, and optimizing its performance is of interest to both ML and HPC communities. All-to-all is a particularly challenging workload that can severely strain the unde...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Basu, Prithwish, Zhao, Liangyu, Fantl, Jason, Pal, Siddharth, Krishnamurthy, Arvind, Khoury, Joud
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!