Parallel Distributed Breadth First Search on the Kepler Architecture
Authors:
- 1 September 2015
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 27 (7) , 2091-2102
Abstract
We present the results obtained by using an evolution of our CUDA-based solution for the exploration, via a breadth first search, of large graphs. This latest version exploits at its best the features of the Kepler architecture and relies on a combination of techniques to reduce both the number of communications among the GPUs and the amount of exchanged data. The final result is a code that can visit more than 800 billion edges in a second by using a cluster equipped with 4,096 Tesla K20X GPUs.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Solutions to the st-connectivity problem using a GPU-based distributed BFSJournal of Parallel and Distributed Computing, 2015
- Traversing Trillions of Edges in Real Time: Graph Exploration on Large-Scale Parallel Machines2014
- Parallel distributed breadth first search on GPU2013
- Efficient breadth first search on multi-GPU systemsJournal of Parallel and Distributed Computing, 2013
- Distributed Memory Breadth-First Search Revisited: Enabling Bottom-Up Search2013
- Atomic-free irregular computations on GPUs2013
- Efficient Hybrid Breadth-First Search on GPUsLecture Notes in Computer Science, 2013
- Highly scalable graph search for the Graph500 benchmark2012
- Accelerating Large Graph Algorithms on the GPU Using CUDA2008
- A Scalable Distributed Parallel Breadth-First Search Algorithm on BlueGene/L2005