Browse

ftp://ftp.netlib.org (178)

	ftp://ftp.netlib.org/tennessee/ut-cs-91-136.ps, 19911216 - 13 - integer mynum, hostnum, bytes, msgtype, ... double precision result, data(100), ... character*16 host, ... c Enroll this program in PVM call fenroll( "nodeprogram0", mynum ) c ------- Begin user program -------- c Receive data from host msgtype = 1 call frcv( msgtype ) call fgetndfloat( data,
	ftp://ftp.netlib.org/tennessee/ut-cs-91-130.ps, 19911216 s ntroduction In this paper, we are concerned with the parallel implementation on distributed memory MIMD parallel computers of the LAPACK routines for performing the reduction to Hessenberg form and the reduction to tridiagonal form. These reductions are an important first step in the computation of
	ftp://ftp.netlib.org/tennessee/ut-cs-91-131.ps, 19911216 The Generalized QR Decomposition 22 References J. L. Barlow, N. K. Nichols, and R. J. Plemmons, Iterative methods for equality constrained least squares problems, SIAM J. Sci. and Stat. Comp. 9, pp.892-906, 1988. C. H. Bischof and P. C. Hansen Structure-Perserving and Rank-Revealing QR-
	ftp://ftp.netlib.org/tennessee/old.ut-cs-89-85.ps, 19911216 December 13, 1991 25 Table 3 (cont): Massively Parallel Computing Computer Number of rmax nmax n1=2 rpeak Processors Gflops order order Gflops Intel iPSC/860 (40 MHz) 2 .044 1000 400 .08 nCUBE 2 (20 MHz) 16 .0320 5580 342 .038 Mieko Computing Surface (40 MHz) 1 .031 1250 .04 Intel iPSC/860 (40 MHz) 1
	ftp://ftp.netlib.org/tennessee/dundee.ps, 19911216 u orte the via rants , an . u orte the via rant . u orte the via rants an . 1 1 ntroduction The original goal of the LAPACK project was to modernize the widely used LIN- PACK and EISPACK numerical linear algebra libraries to make them run efficiently on shared memory vector and
	ftp://ftp.netlib.org/tennessee/lawn19.ps, 19911216 Evaluating Block Algorithm Variants in LAPACK * * This work was supported by the National Science Foundation under Grant No. ASC-8715728. This paper was submitted to the proceedings of the Fourth SIAM Conference on Paral lel Processing for Scientific Computing, held in Chicago, Illinois, December 1989.
	ftp://ftp.netlib.org/tennessee/sr.v4.9.ps, 19911216 and climate modeling. 4 Current Status and Availibility PVM was originally developed at Oat Ridge National Laboratory two years ago and was made publically available in March of this year. The current version, Version 2.2, is available through netlib. To obtain a description of what is available, such
	ftp://ftp.netlib.org/tennessee/ut-cs-91-146.ps, 19911216 A- eric An sis Computer Science Department University of Tennessee Knoxville, TN 37996-1301 and Mathematical Sciences Section Oak Ridge National Laboratory Oak Ridge, TN 37831 September 30, 1991 R The NA-NET is a mail facility created to allow numerical analysts (na) an easy method of communicating with
	ftp://ftp.netlib.org/tennessee/sc91.ps, 19911216 editor, Proceedings of Fifth SIAM Conference on Parallel Processing, Philadelphia, 1991. SIAM. A. Beguelin, J. J. Dongarra, G. A. Geist, R. Manchek, and V. S. Sunderam. A users' guide to PVM parallel virtual machine. Technical Report ORNL/TM-11826, Oak Ridge National Laboratory, July 1991. A.
	ftp://ftp.netlib.org/tennessee/ornl-tm-11850.ps, 19920205 ORNL/TM-11850 Engineering Physics and Mathematics Division Mathematical Sciences Section ON FINDING MINIMUM-DIAMETER CLIQUE TREES Jean R. S. Blair y Barry W. Peyton z y Department of Computer Science University of Tennessee Knoxville, TN 37996-1301 z Mathematical Sciences Section Oak Ridge National
	ftp://ftp.netlib.org/tennessee/nipt91-panel.ps, 19920205 The Emergence of Symbolic Processes From the Subsymbolic Substrate Bruce MacLennan Computer Science Department University of Tennessee, Knoxville March 13, 1991
	ftp://ftp.netlib.org/tennessee/icci91.ps, 19920205 Practical Parallel Algorithms for Chordal Graphs Extended Abstract Eric S. Kirsch Jean R. S. Blairy Department of Computer Science Department of Computer Science University of Tennessee University of Tennessee Knoxville, TN 37996 Knoxville, TN 37996 kirsch@cs.utk.edu blair@cs.utk.edu
	ftp://ftp.netlib.org/tennessee/uist91.ps, 19920205 The Importance of Pointer Variables in Constraint Models Brad Vander Zanden Brad A. Myers Pedro Szekely Dario Giuse Computer Science Department School of Computer Science USC/Information Sciences Institute University of Tennessee Carnegie Mellon University 4676 Admiralty Way Knoxville, TN 37996
	ftp://ftp.netlib.org/tennessee/ut-cs-91-147.ps, 19920205 Characteristics of Connectionist Knowledge Representation Technical Report CS-91-147 Bruce MacLennan Computer Science Department University of Tennessee, Knoxville November 26, 1991
	ftp://ftp.netlib.org/tennessee/ut-cs-91-145.ps, 19920205 Continuous Symbol Systems The Logic of Connectionism Technical Report CS-91-145 Bruce MacLennan Computer Science Department University of Tennessee, Knoxville October 7, 1991
	ftp://ftp.netlib.org/tennessee/ut-cs-91-137.ps, 19920207 CS - 91 - 137 Computer Science Department University of Tennessee Knoxville, TN 37996-1301 and Mathematical Sciences Section Oak Ridge National Laboratory Oak Ridge, TN 37831 CS - 91 - 137 September 13, 1991 Electronic mail address: dongarra cs.utk.edu and sidani cs.utk.edu. This work was supported in
	ftp://ftp.netlib.org/tennessee/vector.ps, 19920215 A Comparative Study of Automatic Vectorizing Compilers David Levine David Callahan y Jack Dongarra z
	ftp://ftp.netlib.org/tennessee/pc.v17.10.ps, 19920303 Parallel Loops A Test Suite for Parallelizing Compilers: Description and Example Results Jack Dongarra Mark Furtney Steve Reinhardt Jerry Russell Cray Research, Inc. 655-F Lone Oak Drive Eagan, MN 55121 Computer Science Department University of Tennessee Knoxville, TN 37996-1301 and Mathematical
	ftp://ftp.netlib.org/tennessee/ut-cs-92-168.ps, 19921221 y ntroduction and otivation The LINPAC benchmark has become popular in the past few years as a means of measuring floating-point performance on computers. The benchmark shows in a simple and direct way the performance to be expected for a range of machines when doing dense matrix computations. Many
	ftp://ftp.netlib.org/tennessee/siampvm.ps, 19921221 Fig. 2. Drawing the graph using the HeNCE graphical interface. Fig. 3. Trace mode of the HeNCE graphical interface. computers together to achieve the computational power necessary to solve Computational Grand Challenge Problems. REFERENCES B. Ginatempo, J. B. Staunton, The electronic structure of
	ftp://ftp.netlib.org/tennessee/ut-cs-92-154.ps, 19930215 Lp-Circular Functions Bruce MacLennan Computer Science Department University of Tennessee, Knoxville May 1, 1992
	ftp://ftp.netlib.org/tennessee/oopsla.ps, 19930215 DECLARATIVE PROGRAMMING IN A PROTOTYPE-INSTANCE SYSTEM: OBJECT-ORIENTED PROGRAMMING WITHOUT WRITING METHODS Brad A. Myers Dario A. Giuse Brad Vander Zanden School of Computer Science School of Computer Science Computer Science Department Carnegie Mellon University Carnegie Mellon University University
	ftp://ftp.netlib.org/tennessee/ut-cs-92-152.ps, 19930215 A Constraint Satisfaction Model for Perception of Ambiguous Stimuli Marc D. VanHeyningen Bruce J. MacLennany April 14, 1992
	ftp://ftp.netlib.org/tennessee/ut-cs-92-174.ps, 19930215 Field Computation in the Brain Bruce MacLennany CS-92-174
	ftp://ftp.netlib.org/tennessee/ut-cs-93-195.ps, 19930612 THE DEVELOPMENT AND IMPLEMENTATION OF A PERFORMANCE DATABASE SERVER Brian Howard LaRose Computer Science Department CS-93-195 August 1993 The evelopment and Implementation of a erformance atabase Server A Thesis Presented for the Master of Science Degree The University of Tennessee, Knoxville Brian
	ftp://ftp.netlib.org/tennessee/ornl-tm-12318.ps, 19930812 - 15 - 161. Anthony Skjellum, Lawrence Livermore National Laboratory, 7000 East Ave., L- 316, P.O. Box 808 Livermore, CA 94551 162. Danny C. Sorensen, Department of Mathematical Sciences, Rice University, P.O. Box 1892, Houston, TX 77251 163. G. W. Stewart, Computer Science Department, University of
	ftp://ftp.netlib.org/tennessee/ut-cs-92-157.ps, 19930818 a a arra a a a a ra r a r a a a a ra r r a r a r a r r a ra r r r. . r . r ar , s ntroduction HeNCE is a tool that greatly simplifies the writing of parallel programs. In HeNCE, the programmer explicitly specifies parallelism between subroutines by drawing a graph where nodes in the graph are
	ftp://ftp.netlib.org/tennessee/ut-cs-93-191.ps, 19930818 SOFTWARE DISTRIBUTION USING XNETLIB 12 LaRose, Sharon Lewis, Keith Moore, Andrew Pearson, Jon Richardson, Bill Rosener, and Andrea Van Hull all made valuable contributions to the design, development, and testing of various versions of xnetlib. We also thank the many users of early versions of xnetlib
	ftp://ftp.netlib.org/tennessee/ut-cs-93-194.ps, 19931006 SVDPACKC (Version 1.0) USER'S GUIDE Michael Berry, Theresa Do, Gavin O'Brien Vijay Krishna, and Sowmini Varadhan Computer Science Department CS-93-194 April 1993 (Revised October 1993) SVDPACKC (Version 1.0) User's Guide1 Michael Berry 2 Theresa Do2 Gavin O'Brien2 Vijay Krishna2 Sowmini Varadhan2
	ftp://ftp.netlib.org/tennessee/ornl-tm-11669.ps, 19931008 Algorithm XXX: Fortran Subroutines for Computing the Eigenvalues and Eigenvectors of a General Matrix by Reduction to General Tridiagonal Form J. J. Dongarra G. A. Geist C. H. Rominey October 7, 1993
	ftp://ftp.netlib.org/tennessee/ut-cs-89-90.ps, 19931013 1 Contents 2 Advanced Architecture Computers* Jack J. Dongarra and Iain S. Duff (dongarra@cs.utk.edu and na.duff@na-net.stanford.edu) Computer Science Department University of Tennessee Knoxville, Tennessee 37996-1301 Computer Science and Systems Division Building 8.9 Harwell Laboratory Oxfordshire OX11
	ftp://ftp.netlib.org/tennessee/ut-cs-93-213.ps, 19931108 PUBLIC INTERNATIONAL BENCHMARKS FOR PARALLEL COMPUTERS PARKBENCH Committee: Report-1 assembled by Roger Hockney (chairman) and Michael Berry (secretary) Computer Science Department University of Tennessee CS-93-213 November 1993 Public International Benchmarks for Parallel Computers PARKBENCH Committee:
	ftp://ftp.netlib.org/fortran-m/reports/determinism.ps.Z, 19940206 A Deterministic Notation for Cooperating Processes K. Mani Chandy California Institute of Technology, 256-80 Pasadena, California 91125 mani@vlsi.cs.caltech.edu Ian T. Fostery Mathematics and Computer Science Division Argonne National Laboratory 9700 South Cass Avenue Argonne, Illinois 60439
	ftp://ftp.netlib.org/fortran-m/reports/definition.ps.Z, 19940206 Contents
	ftp://ftp.netlib.org/fortran-m/reports/shpcc94.ps.Z, 19940206 A Compilation System that Integrates High Performance Fortran and Fortran M Ian Foster, Bhaven Avalani,yAlok Choudhary,zand Ming Xu 1 Introduction We describe a Fortran compilation system that provides integrated support for data parallelism (in the form of High Performance Fortran: HPF ) and task
	ftp://ftp.netlib.org/fortran-m/reports/ijsa.ps.Z, 19940206 Integrated Support for Task and Data Parallelism Mani Chandy Center for Research on Parallel Computation California Institute of Technology Pasadena, CA 91125 Ian Foster Argonne National Laboratory Argonne, IL 60439 Ken Kennedy Charles Koelbel Chau-Wen Tseng Center for Research on Parallel Computation
	ftp://ftp.netlib.org/tennessee/ut-cs-93-205.ps, 19940210 HeNCE: A Heterogeneous Network Computing Environment Adam Beguelin, Jack Dongarra, Al Geist, Robert Manchek, and Keith Moore Computer Science Department CS-93-205 August 1993 1 HeNCE: A Heterogeneous Network Computing Environment Adam Louis Beguelin (adamb@cs.cmu.edu) School of Computer Science and
	ftp://ftp.netlib.org/tennessee/ut-cs-93-186.ps, 19940210 ORNL TM-12231 Engineering Physics and Mathematics Division Mathematical Sciences Section A PROPOSAL FOR A USER-LEVEL, MESSAGE-PASSING INTERFACE IN A DISTRIBUTED MEMORY ENVIRONMENT Jack J. Dongarra zx Rolf Hempel Anthony J. G. Hey David W. Walker x z Department of Computer Science 107 Ayres Hall
	ftp://ftp.netlib.org/tennessee/ut-cs-93-209.ps, 19940216 Efficient Communication Operations in Reconfigurable Parallel Computers F. Desprez , A. Ferreiray CNRS - Laboratoire LIP, CNRS-URA 1398 ENS Lyon 46, All ee d'Italie 69364 LYON Cedex 07 France email: @lip.ens-lyon.fr B. Tourancheau zx The University of Tennessee Computer Science
	ftp://ftp.netlib.org/tennessee/ut-cs-93-208.ps, 19940218 Trace2au Audio Monitoring Tools for Parallel Programs Jean-Yves Peterschmitt LIP Unit e de Recherche Associ ee 1398 du CNRS Ecole Normale Sup erieure de Lyon 46, all ee d'Italie 69364 Lyon Cedex 07 France Bernard Tourancheau yz University of Tennessee Computer Science Department Knoxville, TN 37996-1301
	ftp://ftp.netlib.org/tennessee/ut-cs-93-204.ps, 19940218 Monitoring of Distributed Memory Multicomputer Programs Maurice van Riek Laboratoire de l'Informatique du Parall elisme, CNRS-URA 1398 Ecole Normale Sup erieure de Lyon, 69364 Lyon Cedex 07, France. Bernard Tourancheau Department of Computer Science, University of Tennessee 107 Ayres Hall, Knoxville, TN
	ftp://ftp.netlib.org/tennessee/ut-cs-93-214.ps, 19940309 D R A F T Document for a Standard Message-Passing Interface Message Passing Interface Forum November 2, 1993 This work was supported in part by ARPA and NSF under grant ASC-9310330, the National Science Foundation Science and Technology Center Cooperative Agreement No. CCR-8809615, and by the Commission
	ftp://ftp.netlib.org/tennessee/ut-cs-93-210.ps, 19940309 Successive Broadcasts on Hypercube Fr ed eric Desprez , Pierre Fraigniaudy LIP, CNRS URA 1398 Ecole Normale Sup erieure de Lyon 69364 Lyon Cedex 07, France and Bernard Tourancheau zx The University of Tennessee Computer Science Department 107, Ayres Hall Knoxville, TN 37996-1301 USA e-mail:
	ftp://ftp.netlib.org/tennessee/cckr.ps, 19940319 Characteristics of Connectionist Knowledge Representation Bruce MacLennan Computer Science Department University of Tennessee, Knoxville January 13, 1994
	ftp://ftp.netlib.org/tennessee/vp.ps, 19940319 Visualizing the possibilities Bruce J. MacLennan Computer Science Department, University of Tennessee, Knoxville TN 37996 Electronic mail: maclennan@cs.utk.edu Since I am in general agreement with Johnson-Laird & Byrne (JL&B)'s approach and find their experiments convincing, my commentary will be
	ftp://ftp.netlib.org/tennessee/ipdn.ps, 19940319 Information Processing in the Dendritic Net Bruce MacLennany CS-92-180
	ftp://ftp.netlib.org/tennessee/fcb.ps, 19940319 Field Computation in the Brain Bruce MacLennany CS-92-174
	ftp://ftp.netlib.org/tennessee/kohl-91-comp.ps, 19940324 Visual Techniques for Parallel Processing Preliminary Written Ph.D. Comprehensive Examination for James Arthur Kohl July 25, 1991 Ph.D. Committee: Thomas L. Casavant - Chair Jon Kuhl Michael Lyu John P. Robinson Teodor Rus - 2 - Outline I. Introduction & Problem Statement II. Broad Literature Survey
	ftp://ftp.netlib.org/tennessee/kohl-93-mascots.ps, 19940324 The IMPROV Meta-Tool Design Methodology for Visualization of Parallel Programs* Thomas L. Casavant: tomc@eng.uiowa.edu and James Arthur Kohl: kohl@eng.uiowa.edu Parallel Processing Laboratory, Department of Electrical and Computer Engineering University of Iowa, Iowa City, IA 52242
	ftp://ftp.netlib.org/tennessee/kohl-92-prop.ps, 19940324 The Construction of Meta-Tools for Program Visualization of Parallel Software Ph.D. Thesis Proposal James Arthur Kohl February 4, 1992 Ph.D. Committee: Thomas L. Casavant - Chair Jon G. Kuhl Michael R. Lyu John P. Robinson Teodor Rus
	ftp://ftp.netlib.org/tennessee/kohl-91-santafe.ps, 19940324 Methodologies for Rapid Prototyping of Tools for Visualizing Performance of Parallel Systems James Arthur Kohl Thomas L. Casavant Parallel Processing Laboratory Department of Electrical and Computer Engineering University of Iowa Iowa City, IA 52242 OUTLINE: I. Introduction & Motivation II. Overview of
	ftp://ftp.netlib.org/tennessee/ut-cs-94-230.ps, 19940425 MPI: A Message-Passing Interface Standard Message Passing Interface Forum April 21, 1994 This work was supported in part by ARPA and NSF under grant ASC-9310330, the National Science Foundation Science and Technology Center Cooperative Agreement No. CCR-8809615, and by the Commission of the European
	ftp://ftp.netlib.org/tennessee/ut-cs-94-232.ps, 19940429 To the Graduate Council: I am submitting herewith a thesis written by Robert J. Manchek entitled Design and Implementation of PVM Version 3." I have examined the final copy of this thesis for form and content and recommend that it be accepted in partial fulfillment of the requirements for the degree of
	ftp://ftp.netlib.org/lapack/lawns/lawn26.ps, 19941008 CS - 90 - 118 omputer cience epartment ni ersity of ennessee nox ille, - an at ematical ciences ection a i ge ational Laboratory a i ge, eptember , This work was supported in part by the National Science Foundation, under grant ASC-8715728 and the National Science Foundation Science and Technology
	ftp://ftp.netlib.org/lapack/lawns/lawn20.ps, 19941008 LAPACK: A Portable Linear Algebra Library for High-Performance Computers E. Anderson, Z. Bai, C. Bischof, J. Demmel, J. Dongarra, J. DuCroz, A. Greenbaum, S. Hammarling, A. McKenney, D. Sorensen
	ftp://ftp.netlib.org/lapack/lawns/lawn13.ps, 19941008 1 Contents 1 ntroduction 3 2 Spectral ro ectors and the Separation of o atrices 3 An pper Bound on k k for lobal rror Bounds onditioning of igenvalues 4.1 Conditioning of Simple Eigenvalues : : : : : : : : : : : : : : : : : : : : : : : 9 4.2 Conditioning of Clustered Eigenvalues : : : : : : : : : : : :
	ftp://ftp.netlib.org/lapack/lawns/lawn31.ps, 19941008 LAPACK Working Note Generalized QR Factorization and its Applications (Work in Progress) E. Anderson, Z. Bai and J. Dongarra December 9, 1991 August 9, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn75.ps, 19941008 LAPACK{Style Algorithms and Software for Solving the Generalized Sylvester Equation and Estimating the Separation between Regular Matrix Pairs Bo K agstrom and Peter Poromaa December, 1993 Revised April, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn64.ps, 19941008 LAPACK WORKING NOTE 64 (UT CS-93-203) DISTRIBUTED SPARSE GAUSSIAN ELIMINATION AND ORTHOGONAL FACTORIZATION PADMA RAGHAVAN
	ftp://ftp.netlib.org/lapack/lawns/lawn66.ps, 19941008 LAPACK working note 66 A Characterization of Polynomial Iterative Methods Victor Eijkhout University of Tennessee Department of Computer Science 107 Ayres Hall, Knoxville, TN 37996-1301 eijkhout@cs.utk.edu February 10, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn14.ps, 19941008 LAPACK Working Note 14 On Floating Point Errors in Cholesky James Demmel Courant Institute New York, NY 10012 October 1989
	ftp://ftp.netlib.org/lapack/lawns/lawn42.ps, 19941008 UNIVERSITY OF MANCHESTER Perturbation Theory and Backward Error for AX XB = C N.J. Higham Numerical Analysis Report No. 211 April 1992 University of Manchester/UMIST Joint Numerical Analysis Reports DEPARTMENT OF MATHEMATICS Department of Mathematics University of Manchester Manchester M13 9PL England
	ftp://ftp.netlib.org/lapack/lawns/lawn47.ps, 19941008 e r e s er c e r e r . . e e o uter e e s o t e t s e rt e t ers t o or er e e , s ntrod ction The University of Tennessee, the Courant Institute for Mathematical Sciences, the Numerical Algorithms Group, Ltd., Rice University, Argonne National Laboratory, Oak Ridge National Laboratory, and the
	ftp://ftp.netlib.org/lapack/lawns/lawn11.ps, 19941008 The Bidiagonal Singular Value Decomposition and Hamiltonian Mechanics Percy Deift James Demmel1 Courant Institute New York, NY 10012 Chau Li Mathematics Department The Pennsylvania State University University Park, PA 16802 Carlos Tomei PUC Rio de Janeiro, Brazil (visiting Yale University)
	ftp://ftp.netlib.org/lapack/lawns/lawnxx.ps, 19941008 Computing Eigenspaces with Specified Eigenvalues of a Regular Matrix Pair (A; B) and Condition Estimation: Theory, Algorithms and Software Bo K agstrom and Peter Poromaa April, 1994 UMINF-94.04 ISSN-0348-0542 Contents 1 Introduction 4 1.1 Notation : : : : : : : : : : : : : : : : : : : : : : : : : : : :
	ftp://ftp.netlib.org/lapack/lawns/lawn36.ps, 19941008 Robust Triangular Solves for Use in Condition Estimation Edward Anderson Cray Research Inc. 655F Lone Oak Drive Eagan, MN 55121 August 16, 1991
	ftp://ftp.netlib.org/lapack/lawns/lawn05.ps, 19941008 ARGONNE NATIONAL LABORATORY 9700 South Cass Avenue Argonne, Illinois 60439 LAPACK orking Note 5 Provisional Contents ris isc o , ames emmel, ac ongarra, eremy u roz, nne reenbaum, ven ammarling, and anny orensen Mathematics and Computer Science Division ANL-88-38 March 16, 1992 Work supported in part by
	ftp://ftp.netlib.org/lapack/lawns/lawn29.ps, 19941008 LAPACK Working Note 29 On Global Combine Operations Robert A. van de Geijn Department of Computer Science University of Tennessee Knoxville, Tennessee 37996-1301 and Department of Computer Sciences University of Texas at Austin Austin, Texas 78712 na.vandegeijn@na-net.ornl.gov
	ftp://ftp.netlib.org/lapack/lawns/lawn34.ps, 19941008 CS - 1 - 134 This wor was supported in part by the ational Science Foundation, under grant ASC-8715728 and the ational Science Foundation Science and Technology Center Cooperative Agreement o. CCR-880 615. 1 n r c n This is an informal report of a wor shop on the BLACS held in ouston on March 28, 1 1.
	ftp://ftp.netlib.org/lapack/lawns/lawn17.ps, 19941008 . ree . rr e er , s r r r r r r r . r r r r r r r r r . , r r r - r r r , r r r , r r r r . r r r r r r r rr r . ntro uction Numerical experiments with variants of the QR/QL algorithm for the symmetric tridiagonal eigenproblem are reported. Accuracy and timing comparisons are made between root-free and
	ftp://ftp.netlib.org/lapack/lawns/lawn53.ps, 19941008 LAPACK Working Note: 52 University of Tennessee Tech Report CS-92-179 J. W. DEMMEL Computer Science ivision and Mathematics epartment University of California Berkeley, CA 9 720 demmel cs.berkeley.edu
	ftp://ftp.netlib.org/lapack/lawns/lawn33.ps, 19941008 Robust Incremental Condition Estimation Christian H. Bischof bischof@mcs.anl.gov Ping Tak Peter Tang tang@mcs.anl.gov Mathematics and Computer Science Division Argonne National Laboratory Argonne, IL 60439-4801 December 16, 1991
	ftp://ftp.netlib.org/lapack/lawns/lawn09.ps, 19941008 LAPACK Working Note 9 A Test Matrix Generation Suite James Demmel Alan McKenney Courant Institute 251 Mercer St. New York, NY 10012, USA March 1989
	ftp://ftp.netlib.org/lapack/lawns/lawn78.ps, 19941008 Computational variants of the CGS and BiCGstab methods Victor Eijkhout University of Tennessee Department of Computer Science 107 Ayres Hall, Knoxville, TN 37996-1301 eijkhout@cs.utk.edu August 4, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn55.ps, 19941008 References E. Anderson, Z. Bai, C. Bischof, J. Demmel, J. Dongarra, J. DuCroz, A. Greenbaum, S. Hammarling, A. McKenney, and D. Sorensen. Lapack: A portable linear algebra library for highperformance computers. In Proceedings of Supercomputing '90, pages 10. IEEE Press, 1990. E. Anderson, Z.
	ftp://ftp.netlib.org/lapack/lawns/lawn57.ps, 19941008 ORNL/TM-12252 Engineering Physics and Mathematics Division Mathematical Sciences Section PUMMA : PARALLEL UNI ERSAL MATRIX MULTIPLICATION ALGORITHMS ON DISTRIBUTED MEMOR CONCURRENT COMPUTERS Jaeyoung Choi Jack J. Dongarra David W. Walker Mathematical Sciences Section Oak Ridge National Laboratory P.O.
	ftp://ftp.netlib.org/lapack/lawns/lawn10.ps, 19941008 ARGONNE NATIONAL LABORATORY 9700 South Cass Avenue Argonne, Illinois 60439 LAPACK Working Note #10 Installing and Testing the Initial Release of LAPACK Unix and Non-Unix Versions Edward Anderson and Jack Dongarra Mathematics and Computer Science Division Technical Memorandum No. MCS-TM-130 May 1989 __
	ftp://ftp.netlib.org/lapack/lawns/lawn58.ps, 19941008 LAPACK Working Note 58 The Design of Linear Algebra Libraries for High Performance Computers Jack Dongarra yz and David Walker z yDepartment of Computer Science University of Tennessee Knoxville, TN 37996 zMathematical Sciences Section Oak Ridge National Laboratory Oak Ridge, TN 37831
	ftp://ftp.netlib.org/lapack/lawns/lawn86.ps, 19941008 The Performance of Finding Eigenvalues and Eigenvectors of Dense Symmetric Matrices on Distributed Memory Computers J. Demmel K. Stanleyy
	ftp://ftp.netlib.org/lapack/lawns/lawn48.ps, 19941008 a s . s a a a a s s a a , a a a a a a a s a a s a a , a a s ntroduction In it was shown that small relative perturbations in the entries of a bidiagonal matrix B only cause small relative perturbations in its singular values. This is true independent of the values of the nonzero entries of B. This
	ftp://ftp.netlib.org/lapack/lawns/lawn44.ps, 19941008 LAPACK orking Note: 44 Performance of LAPACK: A Portable Library of Numerical Linear Algebra Routines (University of Tennessee Tech Report CS-92-156, ay 1992) Edward Anderson Mathematical Software Group Cray Research Inc. Eagan, MN 55121 Jack Dongarra Department of Computer Science University of
	ftp://ftp.netlib.org/lapack/lawns/lawn39.ps, 19941008 1 ntroduction The original goal of the LAPACK project was to modernize the widely used LINPACK and EISPACK numerical linear algebra libraries to make them run efficiently on shared memory vector and parallel processors. On these machines, LINPACK and EISPACK are inefficient because
	ftp://ftp.netlib.org/lapack/lawns/lawn73.ps, 19941008 LAPACK Working Note 73 Basic Linear Algebra Communication Subprograms: Analysis and Implementation Across Multiple Parallel Architectures. R. Clint Whaley y June 10, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn06.ps, 19941008 ARGONNE NATIONAL LABORATORY 9700 South Cass Avenue Argonne, Illinois 60439 O. Brewer, J. Dongarra, and D. Sorensen Tools to Aid in the Analysis of Memory Access Patterns for Fortran Programs Mathematics and Computer Science Division Technical Memorandum No. June 1988 Tools to Aid in the Analysis of
	ftp://ftp.netlib.org/lapack/lawns/lawn49.ps, 19941008 eci c i r l i i r llel re Ja es e el at e atics e art ent an o uter cience ivision niversit of alifornia er ele , Jul , 1 s r e re s se er r r s e r e r er s, c - s s s e s e s e e e es s e r c r r . e er, e s es e e s r e re r e er s sc r sc r re ee s e ese r r e s. s s ec se e re s sce e er er , ec se
	ftp://ftp.netlib.org/lapack/lawns/lawn50.ps, 19941008 LAPACK working note 50 Distributed Sparse Data Structures for Linear Algebra Operations Victor Eijkhout Department of Computer Science University of Tennessee, Knoxville eijkhout@cs.utk.edu September 15, 1992
	ftp://ftp.netlib.org/lapack/lawns/lawn69.ps, 19941008 A Serial Implementation of Cuppen's Divide and Conquer Algorithm for the Symmetric Eigenvalue Problem J. Rutter Report No. UCB/CSD 94/799 February 1994 Computer Science Division (EECS) University of California Berkeley, California 94720 A Serial Implementation of Cuppen's Divide and Conquer Algorithm
	ftp://ftp.netlib.org/lapack/lawns/lawn87.ps, 19941008 Computing Eigenspaces with Specified Eigenvalues of a Regular Matrix Pair (A; B) and Condition Estimation: Theory, Algorithms and Software Bo K agstrom and Peter Poromaa April, 1994 Revised September, 1994 UMINF-94.04,ISSN-0348-0542 (Also published as LAPACK Working Note xx)
	ftp://ftp.netlib.org/lapack/lawns/lawn25.ps, 19941008 umerical Considerations in Computing Invariant Subspaces Jack J. ongarra1 Department of Computer Science University of Tennessee Knoxville, TN 37996-1301 and Mathematical Sciences Section Oak Ridge National Laboratory Oak Ridge, TN 37831-8083 Sven ammarling Numerical Algorithms Group Ltd. Wilkinson
	ftp://ftp.netlib.org/lapack/lawns/lawn04.ps, 19941008 r n e ui elines for the esign of ymmetric igenroutines, an Iterative e nement for inear ystems James Demmel, Jeremy Du Croz, Sven Hammarling and Dan Sorensen March 1988 stract This note summarizes the numerical and software issues which arise in designing the LAPACK subroutines for the symmetric
	ftp://ftp.netlib.org/lapack/lawns/lawn01.ps, 19941008 YARGONNE NATIONAL LABORATOR 9700 South Cass Avenue P Argonne, Illinois 60439 rospectus for the Development of a Linear Algebra Library J for High-Performance Computers ames Demmel, Jack J. Dongarra, Jeremy Du Croz, Anne Greenbaum, Sven Hammarling, and Danny Sorensen Mathematics and Computer Science
	ftp://ftp.netlib.org/lapack/lawns/lawn59.ps, 19941008 (To appear at 11th IEEE Symposium on Computer Arithmetic) ntroduction A widely accepted design paradigm for computer hardware is to execute the most common instructions as quickly as possible, and replace rarer instructions by sequences of more common ones. In this paper we explore the use of this
	ftp://ftp.netlib.org/lapack/lawns/lawn15.ps, 19941008 Jacobi's method is more accurate than QR James Demmel1 Courant Institute New York, NY 10012 Kre<=simir Veseli c Lehrgebiet Mathematische Physik Fernuniversitat Hagen D-5800 Hagen, West Germany
	ftp://ftp.netlib.org/lapack/lawns/lawn46.ps, 19941008 The GSVD Algorithm 22 F. T. Luk and H. T. Park, On parallel Jacobi orderings, SIAM J. Sci. Stat. Comput. 10:1826(1989). C. C. Paige and M. A. Saunders, Towards a generalized singular value decomposition, SIAM J. Numer. Anal. 18:39805(1981). C. C. Paige, A note on a result of Sun
	ftp://ftp.netlib.org/lapack/lawns/lawn76.ps, 19941008 Algorithmic Bombardment for the Iterative Solution of Linear Systems: A Poly-Iterative Approach Richard Barretty, Michael Berryz, Jack Dongarrazx, Victor Eijkhoutz, and Charles Rominex. July 27, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn71.ps, 19941008 LAPACK Working Note 71 IBM RS/6000-550 & -590 Performance for Selected Routines in ESSL /LAPACK /NAGy/IMSLzx Jack Dongarra and Michael Kolatis Department of Computer Science University of Tennessee Knoxville, Tennessee 37996-1301 May 3, 1994 1 Overview This document contains performance results for
	ftp://ftp.netlib.org/lapack/lawns/lawn62.ps, 19941008 LAPACK WORKING NOTE 62 (UT CS-93-201) DISTRIBUTED SOLUTION OF SPARSE LINEAR SYSTEMS MICHAEL T. HEATH y AND PADMA RAGHAVAN z
	ftp://ftp.netlib.org/lapack/lawns/lawn43.ps, 19941008 or i o oo c l l s i r l r i r ri s a arra y r a a a r y . r rs ss a a a s a a a a ra r a , ar r s rs as s , a , s 1 1 Introduction Advanced parallelizing compilers may one day be capable of generating efficient parallel code for MIMD distributed memory concurrent computers (or multicomputers) from
	ftp://ftp.netlib.org/lapack/lawns/lawn74.ps, 19941008 A Sparse Matrix Library in C++ for High Performance Architectures Jack Dongarraxz, Andrew Lumsdaine , Xinhiu Niu Roldan Pozoz, Karin Remingtonx xOak Ridge National Laboratory zUniversity of Tennessee University of Notre Dame Mathematical Sciences Section Dept. of Computer Science Dept. of Computer
	ftp://ftp.netlib.org/lapack/lawns/lawn67.ps, 19941008 Performance Complexity of LU Factorization with Efficient Pipelining and Overlap on a Multiprocessor F. Desprez and B. Tourancheau yz LIP - ENS Lyon The University of Tennessee URA 1398 du CNRS Computer Science Department 46, All ee d'Italie 107, Ayres Hall 69364 Lyon Cedex 07 Knoxville, TN 37996-1301
	ftp://ftp.netlib.org/lapack/lawns/lawn03.ps, 19941008 d d Accurate Singular Values of Bidiagonal Matrices Appeared in the SIAM J. Sci. Stat . Comput., v. 11, n . 5, pp. 873-912, 1990) C James Demmel W. Kahan ouran t Inst itute Computer Science D ivision N 251 Mercer Str. University of California ew York, NY 10012 Berkeley, CA 94720 C
	ftp://ftp.netlib.org/lapack/lawns/lawn40.ps, 19941008 Block LU Factorization James W. Demmely Nicholas J. Highamz Robert S. Schreiberx February 16, 1992
	ftp://ftp.netlib.org/lapack/lawns/lawn22.ps, 19941008 s r 1 e or s: , , , , s e ss o s. , , . ntroduction A loc al orit m in matrix computations is one that is defined in terms of operations on submatrices rather than matrix elements. Such algorithms are well-suited to many high-performance computers because their data locality properties lead to efficient
	ftp://ftp.netlib.org/lapack/lawns/lawn38.ps, 19941008 Swapping Algorithm 18 C. Davis and W. Kahan, The Rotation of Eigenvectors by a Perturbation III, SIAM J. Num. Anal. 7:1-46(1970) J. Dongarra, S. Hammarling and J. Wilkinson, Numerical considerations in computing invariant subspaces, LAPACK working note 25, University of Tennessee, CS-90-117,
	ftp://ftp.netlib.org/lapack/lawns/lawn52.ps, 19941008 A A T A A A T T A T MICHAE T. HEATH PA MA RAGHAVAN This paper is concerned with the distri uted parallel computation of an ordering for a symmetric positive de nite sparse matrix. The purpose of the ordering is to limit ll and enhance concurrency in the su se uent computation of the Cholesky factori
	ftp://ftp.netlib.org/lapack/lawns/lawn02.ps, 19941008 ARGONNE NATIONAL LABORATORY 9700 South Cass Avenue Argonne, Illinois 60439 LAPACK Working Note #2 Block Reduction of Matrices to Condensed Forms for Eigenvalue Computations Jack J. Dongarra, Sven J. Hammarling, and Danny C. Sorensen Mathematics and Computer Science Division Technical Memorandum No. 99
	ftp://ftp.netlib.org/lapack/lawns/lawn79.ps, 19941008 PARALLELIZING THE QR ALGORITHM FOR THE UNSYMMETRIC ALGEBRAIC EIGENVALUE PROBLEM: MYTHS AND REALITY GREG HENRY AND ROBERT VAN DE GEIJNy
	ftp://ftp.netlib.org/lapack/lawns/lawn54.ps, 19941008 Swapping Algorithm 15 Z. Bai, J. Demmel and A. Mckenney, On Computing Conition Numbers for the Nonsymmetric Eigenproblem, to appear in ACM TOMS. S. Batterson, Convergence of the QR algorithm on 3 3 normal matrices, Num. Math. 58:341352 (1990). C. Bavely and G. W. Stewart, An algorithm for
	ftp://ftp.netlib.org/lapack/lawns/lawn63.ps, 19941008 LAPACK WORKING NOTE 63 (UT CS-93-202) LINE AND PLANE SEPARATORS PADMA RAGHAVAN y
	ftp://ftp.netlib.org/lapack/lawns/lawn16.ps, 19941008 LAPACK Working Note #16 Results from the Initial Release of LAPACK * * This work was supported in part by the National Science Foundation under grant no. NSF ASC-8715728. Edward Anderson and Jack Dongarra
	ftp://ftp.netlib.org/lapack/lawns/lawn08.ps, 19941008 Block Multishift QR Algorithm 19 G. H. Golub and C. Van Loan, Matrix Computations, The Johns Hopkins University Press, Baltimore, 1983. C. C. Paige, The Gatlinburg X Meeting talk, October 1987. W. Kahan, private communication, April,1988. B. T. Smith, J. M. Boyle, Y. Ikebe, V. C.
	ftp://ftp.netlib.org/lapack/lawns/lawn32.ps, 19941008 Generalizing Incremental Condition Estimation Christian H. Bischof bischof@mcs.anl.gov Ping Tak Peter Tang tang@mcs.anl.gov Mathematics and Computer Science Division Argonne National Laboratory Argonne, IL 60439-4801
	ftp://ftp.netlib.org/lapack/lawns/lawn45.ps, 19941008 The inherent inaccuracy of implicit tridiagonal QR James W. Demmel University of California Berkeley, California 94720
	ftp://ftp.netlib.org/lapack/lawns/lawn07.ps, 19941008 d d o Computing Accurate Eigensystems f Scaled D iagonally Dominant Matrices )( Appeared in SIAM J. Numer. Anal., v. 27, n . 3, pp. 762-791, 1990 Jesse Barlow James Demmel e T Department of Computer Science Couran t Inst itut he Pennsylvania State University 251 Mercer Str. 2U niversity Park, PA 16802
	ftp://ftp.netlib.org/lapack/lawns/lawn65.ps, 19941008 ORNL/TM-12309 Engineering Physics and Mathematics Division Mathematical Sciences Section PARALLEL MATRIX TRANSPOSE ALGORITHMS ON DISTRIBUTED MEMORY CONCURRENT COMPUTERS Jaeyoung Choi x Jack J. Dongarra xy David W. Walker x x Mathematical Sciences Section Oak Ridge National Laboratory P.O. Box 2008,
	ftp://ftp.netlib.org/lapack/lawns/lawn35.ps, 19941008 Intro uction LAPACK is planned to be a linear algebra library for high-performance computers. The library will include Fortran 77 subroutines for the analysis and solution of systems of simultaneous linear algebraic equations, linear least-squares problems, and matrix eigenvalue problems. Our approach
	ftp://ftp.netlib.org/lapack/lawns/lawn18.ps, 19941008 1 , ntroduction LAPACK is planned to be a linear algebra library for high-performance computers. The library will include Fortran 77 subroutines for the analysis and solution of systems of simultaneous linear algebraic equations, linear least-squares problems, and matrix eigenvalue problems. Our
	ftp://ftp.netlib.org/lapack/lawns/lawn56.ps, 19941008 LAPACK WORKING NOTE 56 REDUCING COMMUNICATION COSTS IN THE CONJUGATE GRADIENT ALGORITHM ON DISTRIBUTED MEMORY MULTIPROCESSORS EDUARDO D'AZEVEDOy , VICTOR EIJKHOUTz AND CHARLES ROMINE y
	ftp://ftp.netlib.org/lapack/lawns/lawn24.ps, 19941008 L orking ote 24 L lock actorization lgorit s on t e Intel i Jack ongarra and Susan strouchov epartment of omputer Science niversity of ennessee noxville, ennessee 3 99 -13 1 cto er 1, 199 bstract e s r ec s e e e s c c r z r - es r s e r s s e s e s e s s res r e s r \| e , e c e ers s r - , , es s r e -
	ftp://ftp.netlib.org/lapack/lawns/lawn28.ps, 19941008 January 17, 1991 Electronic mail addresses: dongarra cs.utk.edu, na.mayes na-net.ornl.gov, and RADICATI IECSEC.EARN This work was supported in part by IBM and the National Science Foundation Science and Technology Center Cooperative Agreement No. CCR-8809615. 1 1 The IBM RISC System 000 and Linear Alge
	ftp://ftp.netlib.org/lapack/lawns/lawn68.ps, 19941008 A Highly Parallel Algorithm for the Reduction of a Nonsymmetric Matrix to Block Upper-Hessenberg Form Michael W. Berryy Jack J. Dongarra y Youngbae Kimy February 6, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn60.ps, 19941008 LAPACK Working Note 60, UT CS-93-192 Parallel numerical linear algebra James W. Demmel Computer Science Division and Mathematics Department University of California at Berkeley Berkeley, CA 94720 USA E-mail: demmel@cs.berkeley.edu Michael T. Heathy Department of Computer Science and National Center for
	ftp://ftp.netlib.org/lapack/lawns/lawn82.ps, 19941012 LAPACK Working Note 82 Call Conversion Interface (CCI) for LAPACK/ESSL y Jack Dongarra and Michael Kolatis Department of Computer Science University of Tennessee Knoxville, Tennessee 37996-1301 October 3, 1994 1 Overview This document reviews the initial version of the Call Conversion Interface (CCI)
	ftp://ftp.netlib.org/lapack/lawns/lawn88.ps, 19941027 Efficient Computation of the Singular Value Decomposition with Applications to Least Squares Problems Ming Gu James Demmely Inderjit Dhillonz September 29, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn89.ps, 19941104 Solving Secular Equations Stably and Efficiently Ren-Cang Li Department of Mathematics University of California at Berkeley Berkeley, California 94720 April, 1993 Dedicated to B. N. Parlett and W. Kahan on the occasion of their 60th birthdays
	ftp://ftp.netlib.org/lapack/lawns/lawn90.ps, 19941230 Algorithm-Based Diskless Checkpointing for Fault Tolerant Matrix Operations James S. Planky Youngbae Kimy Jack J. Dongarrayz yDepartment of Computer Science, University of Tennessee zMathematical Science Section, Oak Ridge National Laboratory
	ftp://ftp.netlib.org/lapack/lawns/lawn91.ps, 19950113 The Spectral Decomposition of Nonsymmetric Matrices on Distributed Memory Parallel Computers Z. Bai , J. Demmely, J. Dongarraz, A. Petitetx, H. Robinson{, K. Stanleyk January 9, 1995
	ftp://ftp.netlib.org/tennessee/ut-cs-95-277.ps, 19950215 Possibilities for Active Messaging in PVM Philip J. Mucci mucci@cs.utk.edu and Jack Dongarra dongarra@cs.utk.edu December 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn92.ps, 19950227 ORNL/TM-12472 Engineering Physics and Mathematics Division Mathematical Sciences Section THE DESIGN OF A PARALLEL DENSE LINEAR ALGEBRA SOFTWARE LIBRARY: REDUCTION TO HESSENBERG, TRIDIAGONAL, AND BIDIAGONAL FORM Jaeyoung Choi x Jack J. Dongarra xy David W. Walker y x Department of Computer Science
	ftp://ftp.netlib.org/tennessee/ut-cs-95-279.ps, 19950228 Digital Software and Data Repositories for Support of Scientific Computing Ronald Boisvert National Institute of Standards and Technology Shirley Browney University of Tennessee Jack Dongarra University of Tennessee and Oak Ridge National Lab Eric Grosse AT&T Bell Laboratories
	ftp://ftp.netlib.org/tennessee/ut-cs-95-278.ps, 19950303 Location-Independent Naming for Virtual Distributed Software Repositories Shirley Browney, Jack Dongarra, Stan Green, Keith Moore Theresa Pepin, Tom Rowan, and Reed Wade University of Tennessee Eric Grosse AT&T Bell Laboratories
	ftp://ftp.netlib.org/lapack/lawns/lawn41.ps, 19950306 LAPACK Working Note 41 Installation Guide for LAPACK1 Edward Anderson2, Jack Dongarra, and Susan Ostrouchov Department of Computer Science University of Tennessee Knoxville, Tennessee 37996-1301 REVISED: VERSION 2.0, September 30, 1994 Date: October, 1994
	ftp://ftp.netlib.org/lapack/lawns/lawn95.ps, 19950331 LAPACK Working Note 95 ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers - Design Issues and Performance J. Choiy, J. Demmelz, I. Dhillonz, J. Dongarrax, S. Ostrouchovy, A. Petitety, K. Stanleyz, D. Walker{, and R. C. Whaleyy
	ftp://ftp.netlib.org/lapack/lawns/lawn80.ps, 19950428 ORNL/TM-12470 Engineering Physics and Mathematics Division Mathematical Sciences Section THE DESIGN AND IMPLEMENTATION OF THE SCALAPACK LU, QR, AND CHOLESKY FACTORIZATION ROUTINES Jaeyoung Choi x Jack J. Dongarra xy L. Susan Ostrouchov x Antoine P. Petitet x David W. Walker y R. Clint Whaley x x
	ftp://ftp.netlib.org/tennessee/ut-cs-95-274.ps, 19950501 An Introduction to the MPI Standard Jack J. Dongarra University of Tennessee and Oak Ridge National Laboratory Steve W. Otto Oregon Graduate Institute of Science & Technology Marc Snir IBM, T.J. Watson Research Center David Walker Oak Ridge National Laboratory April 29, 1995 1 Contents 1 Introduction 3
	ftp://ftp.netlib.org/lapack/lawns/lawn97.ps, 19950512 Modeling the Benefits of Mixed Data and Task Parallelism Soumen Chakrabarti James Demmely Katherine Yelick
	ftp://ftp.netlib.org/lapack/lawns/lawn98.ps, 19950512 LAPACK++ V. 1.0 High Performance Linear Algebra Users' Guide April 1994 Jack Dongarra Roldan Pozo David Walker Oak Ridge National Laboratory University of Tennessee, Knoxville Contents 1 Introduction 3 2 Overview 5 2.1 Contents of LAPACK++ : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : :
	ftp://ftp.netlib.org/lapack/lawns/lawn96.ps, 19950512 SUMMA: Scalable Universal Matrix Multiplication Algorithm Robert A. van de Geijn Department of Computer Sciences The University of Texas at Austin Austin, Texas 78712 rvdg@cs.utexas.edu Jerrell Watts Scalable Concurrent Programming Laboratory California Institute of Technology Pasadena, California 91125
	ftp://ftp.netlib.org/tennessee/ut-cs-95-276.ps, 19950622 A Test Suite for PVM Henri Casanova (casanova@cs.utk.edu) Jack Dongarra (dongarra@cs.utk.edu) Philip J. Mucci (mucci@cs.utk.edu) March, 1995
	ftp://ftp.netlib.org/lapack/lawns/lawn94.ps, 19950630 LAPACK Working Note 94 A User's Guide to the BLACS v1.0 Jack J. Dongarra, y R. Clint Whaley z June 7, 1995
	ftp://ftp.netlib.org/tennessee/ut-cs-95-294.ps, 19950720 Chebyshev tau - QZ Algorithm Methods for Calculating Spectra of Hydrodynamic Stability Problems* J.J. Dongarra(1), B. Straughan(2) ** & D.W. Walker(2) (1)Department of Computer Science, University of Tennessee, Knoxville, Tennessee 37996- 1301, U.S.A., and Mathematical Sciences Section, Computer Science
	ftp://ftp.netlib.org/tennessee/ut-cs-95-301.ps, 19950810 The Performance of PVM on MPP Systems Henri Casanova Jack Dongarra y Weicheng Jiang August 9, 1995
	ftp://ftp.netlib.org/tennessee/ut-cs-95-299.ps, 19950810 Message-Passing Performance of Various Computers y Jack J. Dongarraz Tom Dunigan x
	ftp://ftp.netlib.org/lapack/lawns/lawn106.ps, 19951116 1 Templates for Linear Algebra Problems Zhaojun Bai University of Kentucky David Day University of Kentucky James Demmel University of California - Berkeley Jack Dongarra University of Tennessee and Oak Ridge National Laboratory Ming Gu University of California - Berkeley Axel Ruhe Chalmers University
	ftp://ftp.netlib.org/tennessee/ut-cs-95-312.ps, 19951116 Assessment of the NHSE Software Submission and Review Process Shirley Browne Tom Rowan October 23, 1995
	ftp://ftp.netlib.org/lapack/lawns/lawn108.ps, 19951127 GEMM{Based Level 3 BLAS: Installation, Tuning and Use of the Model Implemen- tations and the Performance Evaluation Benchmark Bo K agstrom Per Ling Charles Van Loan y October 1995
	ftp://ftp.netlib.org/lapack/lawns/lawn107.ps, 19951127 GEMM{Based Level 3 BLAS: High-Performance Model Implementations and Performance Evaluation Benchmark Bo K agstrom Per Ling Charles Van Loan y October 1995
	ftp://ftp.netlib.org/tennessee/ut-cs-95-313.ps, 19951130 NetSolve: A Network Server for Solving Computational Science Problems Henri Casanova Jack Dongarra y November 27, 1995
	ftp://ftp.netlib.org/lapack/lawns/lawn101.ps, 19951209 LAPACK Working Note 101 A Proposal for a Fortran 90 Interface for LAPACK Jack J. Dongarra Jeremy Du Crozy Sven Hammarlingy Jerzy Wa sniewskiz Adam Zem lax December 7, 1995 1 Introduction The purpose of this paper is to initiate discussion of the design of a Fortran 90 interface to LAPACK . Our
	ftp://ftp.netlib.org/lapack/lawns/lawn72.ps, 19960111 The Computation of Elementary Unitary Matrices R.B. Lehoucq August 28, 1995
	ftp://ftp.netlib.org/tennessee/ut-cs-96-318.ps, 19960119 High Performance Computing in the U.S. in 1995 { An Analysis on the Basis of the TOP500 List Jack J. Dongarra Computer Science Department University of Tennessee Knoxville, TN 37996-1301 and Mathematical Science Section Oak Ridge National Laboratory Oak Ridge, TN 37831-6367 dongarra@cs.utk.edu and Horst
	ftp://ftp.netlib.org/lapack/lawns/lawn83.ps, 19960215 Relative Perturbation Bounds for the Unitary Polar Factor Ren-Cang Li Mathematical Science Section Oak Ridge National Laboratory P.O. Box 2008, Bldg 6012 Oak Ridge, TN 37831-6367 (li@msr.epm.ornl.gov) LAPACK working notes # 83 (first published July, 1994, revised January, 1996)
	ftp://ftp.netlib.org/lapack/lawns/lawn85.ps, 19960215 Relative Perturbation Theory: (II) Eigenspace and Singular Subspace Variations Ren-Cang Li Mathematical Science Section Oak Ridge National Laboratory P.O. Box 2008, Bldg 6012 Oak Ridge, TN 37831-6367 (li@msr.epm.ornl.gov) LAPACK working notes # 85 (first published July, 1994, revised January, 1996)
	ftp://ftp.netlib.org/lapack/lawns/lawn84.ps, 19960215 Relative Perturbation Theory: (I) Eigenvalue and Singular Value Variations Ren-Cang Li Mathematical Science Section Oak Ridge National Laboratory P.O. Box 2008, Bldg 6012 Oak Ridge, TN 37831-6367 (li@msr.epm.ornl.gov) LAPACK working notes # 84 (first published July, 1994, revised January, 1996)
	ftp://ftp.netlib.org/tennessee/hetero.ps, 19960318 The Dangers of Heterogeneous Network Computing: Heterogeneous Networks Considered Harmful Jim Demmel Jack Dongarray Sven Hammarlingz Susan Ostrouchovx Ken Stanley{
	ftp://ftp.netlib.org/lapack/lawns/lawns27.ps, 19960410 Stability of Methods for Matrix Inversion Jeremy J. Du Croz Nicholas J. Higham y May 7, 1991 In IMA J. Numer. Anal., 12 (January 1992).
	ftp://ftp.netlib.org/tennessee/ut-cs-96-325.ps, 19960425 Overview of Recent Supercomputers Aad J. van der Steen and Jack J. Dongarra y
	ftp://ftp.netlib.org/tennessee/ut-cs-95-310.ps, 19960624 Array Redistribution in ScaLAPACK using PVM Jack Dongarra The University of Tennessee and Oak Ridge National Laboratory Loic Prylli, Cyril Randriamaro and Bernard Tourancheauy LIP, Ecole Normale Sup rieure de Lyon, France
	ftp://ftp.netlib.org/tennessee/ut-cs-96-329.ps, 19960718 Software Repository Interoperability Shirley Browne Jack Dongarra University of Tennessee Kay Hohn ASSET Tim Niesen Raytheon Technical Report UT-CS-96-329 July 1996
	ftp://ftp.netlib.org/lapack/lawns/lawn115.ps, 19961025 On the Error Analysis and Implementation of Some Eigenvalue Decomposition and Singular Value Decomposition Algorithms by Huan Ren B.S. (Peking University, P.R.China) 1991 A dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Applied Mathematics in
	ftp://ftp.netlib.org/lapack/lawns/lawn116.ps, 19961114 LAPACK Working Note 116 Parallel Matrix Distributions: Have we been doing it all right Majed Sidani and Bill Harrod Applications Division Cray Research, A Silicon Graphics Company November 14, 1996 * Electronic mail address: sidani@cray.com, harrod@cray.com 1 Parallel Matrix Distributions: Have we been
	ftp://ftp.netlib.org/tennessee/ut-cs-96-343.ps, 19961210 Client User's Guide to NetSolve Henri Casanova Jack Dongarra y Keith Seymour December 6, 1996
	ftp://ftp.netlib.org/lapack/lawns/lawn118.ps, 19970202 LAPACK Working Note 118 Department of Computer Science Technical Report CS-97-347 The Design and Implementation of the Parallel Out-of-core ScaLAPACK LU, QR and Cholesky Factorization Routines 1 E. F. D'Azevedo Mathematical Sciences Section Oak Ridge National Laboratory P.O. Box 2008, Bldg. 6012 Oak
	ftp://ftp.netlib.org/lapack/lawns/lawn119.ps, 19970211 Computing the Singular Value Decomposition with High Relative Accuracy LAPACK Working Note 119, CS-97-348 James Demmel , Ming Guy, Stanley Eisenstatz, Ivan Slapni<=carx, Kre<=simir Veseli c{, Zlatko Drma<=ck February 11, 1997
	ftp://ftp.netlib.org/lapack/lawns/lawn123.ps, 19970326 A Test Matrix Collection for Non-Hermitian Eigenvalue Problems (Release 1.0) Zhaojun Baiy and David Dayz and James Demmelx and Jack Dongarra{ October 6, 1996 1 Introduction The primary purpose of this collection is to provide a testbed for the development of numerical algorithms for solving nonsymmetric
	ftp://ftp.netlib.org/lapack/lawns/lawn122.ps, 19970327 A New Deflation Criterion for the QR Algorithm Mario Ahues Fran coise Tisseury January 14, 1997
	ftp://ftp.netlib.org/lapack/lawns/lawn124.ps, 19970416 An Asynchronous Parallel Supernodal Algorithm for Sparse Gaussian Elimination James W. Demmel John R. Gilberty Xiaoye S. Liz February 27, 1997
	ftp://ftp.netlib.org/lapack/lawns/lawn126.ps, 19970422 Performance Improvements to LAPACK for the Cray Scientific Library Edward Anderson Cray Research 655F Lone Oak Drive Eagan, MN 55121 Mark Fahey y Department of Mathematics University of Kentucky Lexington, KY 40506 April 22, 1997
	ftp://ftp.netlib.org/tennessee/ut-cs-96-342.ps, 19970502 TOP500 Report 1996 Jack J. Dongarra Computer Science Department University of Tennessee Knoxville, TN 37996-1301 and Mathematical Science Section Oak Ridge National Laboratory Oak Ridge, TN 37831-6367 dongarra@cs.utk.edu Hans W. Meuer Computing Center University of Mannheim D-68131 Mannheim Germany
	ftp://ftp.netlib.org/tennessee/ut-cs-97-354.ps, 19970502 Statistical Performance Modeling: Case Study of the NPB 2.1 Results Erich Strohmaier Computer Science Department, University of Tennessee, Knoxville, TN 37996 UTK-CS-97-354, March 1997
	ftp://ftp.netlib.org/lapack/lawns/lawn125.ps, 19970506 Implementation in ScaLAPACK of Divide-and-Conquer Algorithms for Banded and Tridiagonal Linear Systems A. Cleary Department of Computer Science University of Tennessee J. Dongarra Department of Computer Science University of Tennessee Mathematical Sciences Section Oak Ridge National Laboratory
	ftp://ftp.netlib.org/tennessee/ut-cs-97-360.ps, 19970507 Determining the Idle Time of a Tiling: New Results Fr ed eric Desprez1, Jack Dongarra2;3, Fabrice Rastello1, and Yves Robert2 1 LIP, Ecole Normale Sup erieure de Lyon, 69364 Lyon Cedex 07, France 2 Department of Computer Science, University of Tennessee, Knoxville, TN 37996-1301, USA 3 Mathematical
	ftp://ftp.netlib.org/lapack/lawns/lawn127.ps, 19970630 Sparse Gaussian Elimination on High Performance Computers by Xiaoye S. Li B.S. (Tsinghua University) 1986 M.S., M.A. (Penn State University) 1990 A dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy in Computer Science in the GRADUATE DIVISION of
	ftp://ftp.netlib.org/tennessee/ut-cs-97-371.ps, 19970711 ALGORITHMIC REDISTRIBUTION METHODS FOR BLOCK CYCLIC DECOMPOSITIONS A Dissertation Presented for the Doctor of Philosophy Degree The University of Tennessee, Knoxville Antoine Petitet December 1996 Copyright c 1996 by Antoine Petitet All rights reserved ii To my parents iii Acknowledgments The writer
	ftp://ftp.netlib.org/lapack/lawns/lawn128.ps, 19970805 ALGORITHMIC REDISTRIBUTION METHODS FOR BLOCK CYCLIC DECOMPOSITIONS A Dissertation Presented for the Doctor of Philosophy Degree The University of Tennessee, Knoxville Antoine Petitet December 1996 Copyright c 1996 by Antoine Petitet All rights reserved ii To my parents iii Acknowledgments The writer
	ftp://ftp.netlib.org/lapack/lawns/lawn129.ps, 19970912 A New Parallel Matrix Multiplication Algorithm on Distributed-Memory Concurrent Computers Jaeyoung Choi School of Computing Soongsil University 1-1, Sangdo-Dong, Dongjak-Ku Seoul 156-743, KOREA
	ftp://ftp.netlib.org/lapack/lawns/lawn130.ps, 19971010 Accurate SVDs of Structured Matrices James Demmel October 9, 1997
	ftp://ftp.netlib.org/lapack/lawns/lawn131.ps, 19980111 Automatically Tuned Linear Algebra Software R. Clint Whaley Jack J. Dongarra Computer Science Department University of Tennessee Knoxville, TN 37996-1301 and Mathematical Sciences Section Oak Ridge National Laboratory Oak Ridge, TN 37831