A Multi-Stage CUDA Kernel for Floyd-Warshall

A Multi-Stage CUDA Kernel for Floyd-Warshall

We present a new implementation of the Floyd-Warshall All-Pairs Shortest Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than the previously best reported algorithm. In order to achieve this speedup, we applied a new technique to reduce usage of on-chip shared memory and all...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lund, Ben, Smith, Justin W
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Distributed, Parallel, and Cluster Computing
Computer Science - Performance
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present a new implementation of the Floyd-Warshall All-Pairs Shortest Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than the previously best reported algorithm. In order to achieve this speedup, we applied a new technique to reduce usage of on-chip shared memory and allow the CUDA scheduler to more effectively hide instruction latency.
DOI:10.48550/arxiv.1001.4108