JavaScript is disabled for your browser. Some features of this site may not work without it.
Browsing Center for Advanced Computing by Issue Date
Now showing items 120 of 150

Stereo Viewing Interface for Workstations
Land, Bruce; Devine, Catherine (Cornell University, 199010)Three dimensional data sets are becoming widespread in scientific simulations and analysis of physical systems. Applications ranging from fluid simulations to medical imaging require understanding of three ... 
Parallel Finite Element Analysis of Biomechanical Structures on the Ncube 6400
Chinchalkar, Shirish; Coleman, Thomas F. (Cornell University, 199108)This paper presents parallel 3D finite element analysis for distributed memory multiprocessors. Traditionally, finite element analysis has been performed on sequential computers. Current research in high ... 
Computing Eigenvalues and Eigenvectors of a Dense Real Symmetric Matrix on the Ncube 6400
Chinchalkar, Shirish (Cornell University, 199109)This report demonstrates parallel versions of the Eispack functions TRED2 and TQL2 for finding all eigenvalues and eigenvectors of a dense, real symmetric matrix on the Ncube 6400. There are several techniques for ... 
Stiffness of ODEs
Higham, Desmond J.; Trefethen, Lloyd N. (Cornell University, 199201)It is argued that even for a linear system of ODEs with constant coefficients, stiffness cannot properly be characterized in terms of the eigenvalues of the Jacobian, because stiffness is a transient phenomenon ... 
BLAS Based on Block Data Structures
Henry, Greg (Cornell University, 199202)The optimization of the BLAS is discussed, with examples given for the IBM superscalar RISC S/6000. The approach suggested is to use block data structures based on storebyblock schemes. We give results and ... 
Block Factorizations on a Cluster of RS/6000s
Henry, Greg; Hoisie, Adolfy (Cornell University, 199202)This paper discusses optimizing computational linear algebra algorithms on a ring cluster of IBM RS/6000s. We offer the results of a block Cholesky factorization and the underlying BLAS to demonstrate the advantage ... 
A Parallel Row Distributed Linear Algebra System (PRDLA Users' Guide)
Wu, Zhijun; Coleman, Thomas (Cornell University, 199204)The purpose of this system is to provide an easytouse et of basic parallel matrix manipulation subroutines, in C, for use on the Intel iPSC/860 hypercube. Most of the subroutines exhibit good performance, but not ... 
GMRES/CR and Arnoldi/Lanczos as Matrix Approximation Problems
Greenbaum, Anne; Trefethen, Lloyd N. (Cornell University, 199206)The GMRES and Arnoldi algorithms, which reduce to the CR and Lanczos algorithms in the symmetric case, both minimize p(A)b over polynomials p of degree n. The difference is that p is nor malized at z=0 for GMRES ... 
A Singular Loop Transformation Framework Based on Nonsingular Matrices
Li, Wei; Pingali, Keshav (Cornell University, 199207)In this paper, we discuss a loop transformation framework that is based on integer nonsingular matrices. The transformations included in this framework are called Atransformations and include permutation, skewing ... 
Access Normalization: Loop Restructuring for NUMA Compilers
Li, Wei; Pingali, Keshav (Cornell University, 199207)A common feature of many scalable parallel machines is nonuniform memory access  a processor can access data in its local memory ten to a thousand times faster than it can access local data. In addition, when a ... 
Increasing Data Reuse in the Unsymmetric QR Algorithm
Henry, Greg (Cornell University, 199207)This paper models data use in the Unsymmetric QR Eigenvalue Algorithm to improve performance on machines with memory hierarchy. Most of the algorithms and strategies presented can be implemented so that they are ... 
Advantages of Differential Dynamic Programming Over Newton's Method for Discretetime Optimal Control Problems
Liao, Lizhi; Shoemaker, Christine A. (Cornell University, 199207)Differential Dynamic Programming (DDP) and stagewise Newton's method are both quadratically convergent algorithms for solving discrete time optimal control problems. Although these two algorithms share many theoretical ... 
Access Normalization: Loop Restructuring for NUMA Compilers
Li, Wei; Pingali, Keshav (Cornell University, 199207)A common feature of many scalable parallel machines is nonuniform memory access  a processor can access data in its local memory ten to a thousand times faster than it can access local data. In addition, when a ... 
Efficient Parallel Solutions of Large Sparse SPD Systems on Distributedmemory Multiprocessors
Sun, Chunguang (Cornell University, 199208)We consider several issues involved in the solution of sparse symmetric positive definite system by multifrontal method on distributedmemory multiprocessors. First, we present a new algorithm for computing the ... 
IPSCMATLAB Reference Manual
Chinchalkar, Shirish (Cornell University, 199209)IPSCMATLAB is a programming environment for running MATLAB programs on the Intel iPSC/860 hypercube. The system is designed such that the user can execute computationally intensive poitions of MATLAB programs on ... 
Quality Mesh Generation in Three Dimensions
Mitchell, Scott A.; Vavasis, Stephen A. (Cornell University, 199209)We show how to triangulate a three dimensional polyhedral region with holes. Our triangulation is optimal in the following two senses. First, our triangulation achieves the best possible aspect ratio up to a constant. ... 
Stable Numerical Algorithms for Equilibrium
Vavasis, Stephen A. (Cornell University, 199209)An equilibrium system (also known as a KKT system, a saddle point system, or a sparse tableau) is a square linear system with a certain structure. G. Strang has observed that equilibrium systems arise in optimization, ... 
Case Study in KSR Programming: Finding Outliers by the Minimum Volume Ellipsoid Method
Bergmark, Donna; Crovella, Mark (Cornell University, 199209)This case study describes the enablement of a parallel application on Cornell Theory Center's KSR1, a highly parallel machine from Kendall Square Research. The application is from statistics, and exposes some interesting ... 
Isotropic Effective Energy Simulated Annealing Searches for Low Energy Molecular Cluster States
Coleman, Thomas F.; Shalloway, David; Wu, Zhijun (Cornell University, 199211)The search for low energy states of molecular clusters is associated with the study of molecular conformation and especially protein folding. This paper describes a new global minimization algorithm which is effective ... 
On the Convergence of Reflective Newton Methods for Largescale Nonlinear Minimization Subject to Bounds
Coleman, Thomas F.; Li, Yuying (Cornell University, 199211)We consider a new algorithm, a reflective Newton method, for the problem of minimizing a smooth nonlinear function of many variables, subject to upper and/or lower bounds on some of the variables. This approach ...