Parallel evidence propagation on multicore processors

Authors:
Yinglong Xia;Viktor K. Prasanna
Affiliations:
Computer Science Department, University of Southern California, Los Angeles, USA 90089;Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, USA 90089
Venue:
The Journal of Supercomputing
Year:
2011

Citing 7
Cited 1

Bayesian Networks for Data Mining

Data Mining and Knowledge Discovery
A parallel Lauritzen-Spiegelhalter algorithm for probabilistic inference

Proceedings of the 1994 ACM/IEEE conference on Supercomputing
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach
Cilk: An Efficient Multithreaded Runtime System

Cilk: An Efficient Multithreaded Runtime System
Parallel exact inference on the cell broadband engine processor

Proceedings of the 2008 ACM/IEEE conference on Supercomputing
Variational probabilistic inference and the QMR-DT network

Journal of Artificial Intelligence Research
Logarithmic time parallel Bayesian inference

UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence

Data Parallel Implementation of Belief Propagation in Factor Graphs on Multi-core Platforms

International Journal of Parallel Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a parallel evidence propagation method on general-purpose multicore processors. Evidence propagation is a major step in exact inference, a key problem in exploring probabilistic graphical models. We explore the parallelism in evidence propagation at various levels. First, given an arbitrary junction tree, we construct a directed acyclic graph (DAG) with weighted nodes, each denoting a computation task for evidence propagation. Since the execution time of the tasks varies significantly, we develop a workload-aware scheduler to allocate the tasks to the cores of the processors. The scheduler monitors the workload of each core and dynamically allocates tasks to support load balance across the cores. In addition, we integrate a module in the scheduler to partition the tasks converted from cliques with large potential tables so as to achieve improved load balance. We implemented the proposed method using Pthreads on both AMD and Intel quadcore processors. For a representative set of junction trees, our method achieved almost linear speedup. The execution time of our method was around twice as fast as an OpenMP-based implementation on both the platforms.