GPU-enabled steady-state solution of large Markov models

Magalhaes, Bruno R. C. and Dingle, Nicholas J. and Knottenbelt, William J. (2010) GPU-enabled steady-state solution of large Markov models. In: 6th International Workshop on the Numerical Solution of Markov Chains (NSMC'10), 16-17 Sep 2010, Williamsburg, Virginia.

[thumbnail of nsmc2010-gpu.pdf] PDF
nsmc2010-gpu.pdf

Download (167kB)

Abstract

We describe a novel parallel steady-state solver that uses NVIDIA's Compute Unified Device Architecture (CUDA) library to perform calculations on a graphics processing unit (GPU). We demonstrate speed-ups of over 8 times compared with a CPU-only solver. We also discuss a parallel implementation which runs on multiple GPUs on separate machines, and explain how we deal with allocating appropriate amounts of work to heterogeneous computing resources.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Parallel and distributed computing, Performance analysis
Subjects: MSC 2010, the AMS's Mathematics Subject Classification > 60 Probability theory and stochastic processes
MSC 2010, the AMS's Mathematics Subject Classification > 65 Numerical analysis
Depositing User: Dr Nicholas Dingle
Date Deposited: 24 Oct 2010
Last Modified: 20 Oct 2017 14:12
URI: https://eprints.maths.manchester.ac.uk/id/eprint/1533

Actions (login required)

View Item View Item