Paradigms for Effective Parallelization of Inherently Sequential Graph Algorithms on Multi-Core Architectures

The chapter describes two algorithmic paradigms, dubbed speculation and iteration and approximate update, for parallelizing greedy graph algorithms and vertex ordering algorithms, respectively, on multicore architectures. The common challenge in these two classes of algorithms is that the computations involved are inherently sequential. The efficacy of the paradigms in overcoming this challenge is demonstrated via extensive experimental study on two representative algorithms from each class and two Intel multi-core systems. The algorithms studied are (1) greedy algorithms for distance-k coloring (for k = 1 and k = 2) and (2) algorithms for two degree-based vertex orderings. The experimental results show that the paradigms enable the design of scalable methods that to a large extent preserve the quality of solution obtained by the underlying serial algorithms.

A Novel Ensemble Clustering for Operational Transients Classification with Application to a Nuclear Power Plant Turbine

The objective of the present work is to develop a novel approach for combining in an ensemble multiple base clusterings of operational transients of industrial equipment, when the number of clusters in the final consensus clustering is unknown. A measure of pairwise similarity is used to quantify the co-association matrix that describes the similarity among the different base clusterings. Then, a Spectral Clustering technique of literature, embedding the unsupervised K-Means algorithm, is applied to the coassociation matrix for finding the optimum number of clusters of the final consensus clustering, based on Silhouette validity index calculation. The proposed approach is developed with reference to an artificial casestudy, properly designed to mimic the signal trend behavior of a Nuclear Power Plant (NPP) turbine during shut-down. The results of the artificial case have been compared with those achieved by a state-of-art approach, known as Clusterbased Similarity Partitioning and Serial Graph Partitioning and Fill-reducing Matrix Ordering Algorithms (CSPAMETIS). The comparison shows that the proposed approach is able to identify a final consensus clustering that classifies the transients with better accuracy and robustness compared to the CSPA-METIS approach. The approach is, then, validated on an industrial case concerning 149 shut-down transients of a NPP turbine.

Empirical Study Between Compiled, Interpreted, and Dynamic Programming Languages Applying Stable Ordering Algorithms (Case Study: Java, Python, Jython, Jpype and Py4J)

.

Implementing Sparse Matrix Ordering Using Hypergraph Partitioning

Matrix ordering is a key technique when applying Cholesky factorization method to solving sparse symmetric positive definite system Ax = b. Much effort has been devoted to the development of powerful heuristic ordering algorithms. This paper implements a sparse matrix ordering scheme based on hypergraph partitioning. The novel nested dissection ordering scheme achieve the vertex separator by hypergraph partitioning. Experimental results show that the novel scheme produces results that are substantially better than METIS.