Toward an Efficient Column Minimum Degree Code for Symmetric Multiprocessors
نویسندگان
چکیده
Ordering the columns of a nonsymmetric sparse matrix can reduce the fill created in its factorization. Minimum-degree is a popular heuristic for ordering symmetric matrices; a variant that can be used to order nonsymmetric matrices is called column minimum degree. In this paper we describe the design of a multithreaded approximate column minimum degree code. We present a framework for the algorithm, study potential sources of parallel inefficiency, and describe our attempts to circumvent the obstacles. We present experimental results that support our analysis.
منابع مشابه
Automatic parallelization of sequential code for a cluster of multiprocessors
In recent years parallel architectures have rapidly evolved to solve increasingly large problems, mainly because single processor based systems have reached the limit of their physical capacity. The end of 90’s has seen the growth and evolution of parallel architectures towards a cluster of multiprocessors owing to scaling problems with shared memory machines. The efficient use of such parallel...
متن کاملAn Object-Oriented Collection of Minimum Degree Algorithms
The multiple minimum degree (MMD) algorithm and its variants have enjoyed 20+ years of research and progress in generating fill-reducing ordcrings for sparse, symmetric positive definite matrices. Although conceptually simple, efficient implementations of these algorithms are deceptively complex and highly specialized. In this case study, we present an object-oriented library that implements se...
متن کاملAn Object-oriented Collection of Minimum Degree Algorithms: Design, Implementation, and Experiences
The multiple minimum degree (MMD) algorithm and its variants have enjoyed 20+ years of research and progress in generating fill-reducing orderings for sparse, symmetric positive definite matrices. Although conceptually simple, efficient implementations of these algorithms are deceptively complex and highly specialized. In this case study, we present an object-oriented library that implements se...
متن کاملAn Object - Oriented Collection ofMinimum Degree
The multiple minimum degree (MMD) algorithm and its variants have enjoyed 20+ years of research and progress in generating ll-reducing orderings for sparse, symmetric positive deenite matrices. Although conceptually simple, eecient implementations of these algorithms are deceptively complex and highly specialized. In this case study, we present an object-oriented library that implements several...
متن کاملEfficient Adaptive Algorithms for Transposing Small and Large Matrices on Symmetric Multiprocessors
Matrix transpose in parallel systems typically involves costly all-to-all communications. In this paper, we provide a comparative characterization of various efficient algorithms for transposing small and large matrices using the popular symmetric multiprocessors (SMP) architecture, which carries a relatively low communication cost due to its large aggregate bandwidth and lowlatency inter-proce...
متن کامل