DMCA
Fast GPU Algorithms for Graph Connectivity (2010)
| Venue: | WORKSHOP ON LARGE SACLE PARALLEL PROCESSING |
BibTeX
@MISC{Kothapalli10fastgpu,
author = {Kishore Kothapalli and Jyothish Soman and P J Narayanan},
title = {Fast GPU Algorithms for Graph Connectivity },
year = {2010}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Graphics processing units provide a large computational power at a very low price which position them as an ubiquitous accelerator. General purpose programming on the graphics processing units (GPGPU) is best suited for regular data parallel algorithms. They are not directly amenable for algorithms which have irregular data access patterns such as list ranking, and finding the connected components of a graph, and the like. In this work, we present a GPU-optimized implementation for finding the connected components of a given graph. Our implementation tries to minimize the impact of irregularity, both at the data level and functional level. Our implementation achieves a speed up of 9 to 12 times over the best sequential CPU implementation. For instance, our implementation finds connected components of a graph of 10 million nodes and 60 million edges in about 500 milliseconds on a GPU, given a random edge list. We also draw interesting observations on why PRAM algorithms, such as the Shiloach-Vishkin algorithm may not be a good fit for the GPU and how they should be modified.
Keyphrases
connected component graph connectivity fast gpu algorithm list ranking random edge list data level ubiquitous accelerator sequential cpu implementation low price functional level large computational power gpu-optimized implementation pram algorithm irregular data access pattern interesting observation regular data good fit shiloach-vishkin algorithm
