A Deep Dive into Task-Based Parallelism in Python

Modern Python programs in high-performance computing call into compiled libraries and kernels for performance-critical tasks. However, effectively parallelizing these finer-grained, and often dynamic, kernels across modern heterogeneous platforms remains a challenge. First, we perform an experimenta...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2024 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) S. 1147 - 1149
Hauptverfasser:	Ruys, William, Lee, Hochan, You, Bozhi, Talati, Shreya, Park, Jaeyoung, Almgren-Bell, James, Yan, Yineng, Fernando, Milinda, Biros, George, Erez, Mattan, Burtscher, Martin, Rossbach, Christopher J., Pingali, Keshav, Gligoric, Milos
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 27.05.2024
Schlagworte:	heterogeneous computing High performance computing Libraries Parallel processing parallel programming Performance evaluation Processor scheduling Programming Python Runtime task runtime
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!