Parallel Breadth First Search on GPU clusters

Fast, scalable, low-cost, and low-power execution of parallel graph algorithms is important for a wide variety of commercial and public sector applications. Breadth First Search (BFS) imposes an extreme burden on memory bandwidth and network communications and has been proposed as a benchmark that m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2014 IEEE International Conference on Big Data (Big Data) S. 110 - 118
Hauptverfasser: Zhisong Fu, Dasari, Harish Kumar, Bebee, Bradley, Berzins, Martin, Thompson, Bryan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2014
Schlagworte:
Bandwidth
BFS
Clustering algorithms
Generators
GPU cluster
graph
Graphics processing units
MPI
parallel graph algorithm
Partitioning algorithms
Scalability
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Fast, scalable, low-cost, and low-power execution of parallel graph algorithms is important for a wide variety of commercial and public sector applications. Breadth First Search (BFS) imposes an extreme burden on memory bandwidth and network communications and has been proposed as a benchmark that may be used to evaluate current and future parallel computers. Hardware trends and manufacturing limits strongly imply that many-core devices, such as NVIDIA® GPUs and the Intel® Xeon Phi®, will become central components of such future systems. GPUs are well known to deliver the highest FLOPS/watt and enjoy a very significant memory bandwidth advantage over CPU architectures. Recent work has demonstrated that GPUs can deliver high performance for parallel graph algorithms and, further, that it is possible to encapsulate that capability in a manner that hides the low level details of the GPU architecture and the CUDA language but preserves the high throughput of the GPU. We extend previous research on GPUs and on scalable graph processing on supercomputers and demonstrate that a high-performance parallel graph machine can be created using commodity GPUs and networking hardware.
DOI:10.1109/BigData.2014.7004219