Esmond G. Ng

Parallel algorithms for sparse linear systems

This paper surveys recent progress in the development of parallel algorithms for solving sparse linear systems on computer architectures having multiple processors. Attention is focused on direct methods for solving sparse symmetric positive definite systems, specifically by Cholesky factorization. Recent progress on parallel algorithms is surveyed for all phases of the solution process, including ordering, symbolic factorization, numeric factorization, and triangular solution.

Block sparse Cholesky algorithms on advanced uniprocessor computers

As with many other linear algebra algorithms, devising a portable implementation of sparse Cholesky factorization that performs well on the broad range of computer architectures currently available is a formidable challenge. Even after limiting the attention to machines with only one processor, as has been done in this paper, there are still several interesting issues to consider. For dense matrices, it is well known that block factorization algorithms are the best means of achieving this goal. This approach is taken for sparse factorization as well.This paper has two primary goals. First, two sparse Cholesky factorization algorithms, the multifrontal method and a blocked left-looking sparse Cholesky method, are examined in a systematic and consistent fashion, both to illustrate the strengths of the blocking techniques in general and to obtain a fair evaluation of the two approaches, Second, the impact of various implementation techniques on time and storage efficiency is assessed, paying particularly clo...

Adaptive mesh, finite volume modeling of marine ice sheets

Continental scale marine ice sheets such as the present day West Antarctic Ice Sheet are strongly affected by highly localized features, presenting a challenge to numerical models. Perhaps the best known phenomenon of this kind is the migration of the grounding line - the division between ice in contact with bedrock and floating ice shelves - which needs to be treated at sub-kilometer resolution. We implement a block-structured finite volume method with adaptive mesh refinement (AMR) for three dimensional ice sheets, which allows us to discretize a narrow region around the grounding line at high resolution and the remainder of the ice sheet at low resolution. We demonstrate AMR simulations that are in agreement with uniform mesh simulations, but are computationally far cheaper, appropriately and efficiently evolving the mesh as the grounding line moves over significant distances. As an example application, we model rapid deglaciation of Pine Island Glacier in West Antarctica caused by melting beneath its ice shelf.

Communication results for parallel sparse Cholesky factorization on a hypercube

Abstract We consider the problem of reducing data traffic among processor nodes during the parallel factorization of a sparse matrix on a hypercube multiprocessor. A task assignment strategy based on the structure of an elimination tree is presented. This assignment is aimed at achieving load balancing among the processors and also reducing the amount of processor-to-processor data communication. An analysis of regular grid problems is presented, providing a bound on communication volume generated by the new strategy, and showing that the allocation scheme is optimal in the asymptotic sense. Some experimental results on the performance of this scheme are presented.

On finding supernodes for sparse matrix computations

A simple characterization of fundamental supernodes is given in terms of the row subtrees of sparse Cholesky factors in the elimination tree. Using this characterization, an efficient algorithm is presented that determines the set of such supernodes in time proportional to the number of nonzeros and equations in the original matrix. Experimental results verify the practical efficiency of this algorithm.

Algorithm 836: COLAMD, a column approximate minimum degree ordering algorithm

Two codes are discussed, COLAMD and SYMAMD, that compute approximate minimum degree orderings for sparse matrices in two contexts: (1) sparse partial pivoting, which requires a sparsity preserving column pre-ordering prior to numerical factorization, and (2) sparse Cholesky factorization, which requires a symmetric permutation of both the rows and columns of the matrix being factorized. These orderings are computed by COLAMD and SYMAMD, respectively. The ordering from COLAMD is also suitable for sparse QR factorization, and the factorization of matrices of the form ATA and AAT, such as those that arise in least-squares problems and interior point methods for linear programming problems. The two routines are available both in MATLAB and C-callable forms. They appear as built-in routines in MATLAB Version 6.0.

Hamiltonian light-front field theory in a basis function approach

Hamiltonian light-front quantum field theory constitutes a framework for the nonperturbative solution of invariant masses and correlated parton amplitudes of self-bound systems. By choosing the light-front gauge and adopting a basis function representation, a large, sparse, Hamiltonian matrix for mass eigenstates of gauge theories is obtained that is solvable by adapting the ab initio no-core methods of nuclear many-body theory. Full covariance is recovered in the continuum limit, the infinite matrix limit. There is considerable freedom in the choice of the orthonormal and complete set of basis functions with convenience and convergence rates providing key considerations. Here we use a two-dimensional harmonic oscillator basis for transverse modes that corresponds with eigensolutions of the soft-wall anti-de Sitter/quantum chromodynamics (AdS/QCD) model obtained from light-front holography. We outline our approach and present illustrative features of some noninteracting systems in a cavity. We illustrate the first steps toward solving quantum electrodynamics (QED) by obtaining the mass eigenstates of an electron in a cavity in small basis spaces and discuss the computational challenges.

Symbolic factorization for sparse Gaussian elimination with partial pivoting

Let

A supernodal Cholesky factorization algorithm for shared-memory multiprocessors

Ax = b

Predicting structure in nonsymmetric sparse matrix factorizations

be a large sparse nonsingular system of linear equations to be solved using Gaussian elimination with partial pivoting. The factorization obtained can be expressed in the form