Dongarra, Jack - Department of Electrical and Computer Engineering, University of Tennessee

• The PlayStation 3 for High Performance Scientific Computing Jakub Kurzak
• Bi-objective Scheduling Algorithms for Optimizing Makespan and Reliability on Heterogeneous Systems
• Templates for Linear Algebra Problems Zhaojun Bai
• MPI Collective Algorithm Selection and Quadtree Encoding Jelena PjesivacGrbovic, Graham E. Fagg,
• ForPeerReview Trace-based Performance Analysis for the Petascale
• Heterogeneous MPI Application Interoperation and Process Management under PVMPI ?
• Review of Performance Analysis Tools for MPI Parallel Programs
• Vita for Jack Dongarra April 1, 1999
• X. Parallel and Distributed Scientific A Numerical Linear Algebra Problem Solving Environment
• Self Adapting Numerical Software (SANS) Effort George Bosilca, Zizhong Chen, Jack Dongarra, Victor Eijkhout, Graham E. Fagg,
• THE DESIGN AND IMPLEMENTATION OF THE PARALLEL OUT-OF-CORE SCALAPACK LU, QR AND CHOLESKY
• Fully Dynamic Scheduler for Numerical Computing on Multicore Processors
• Exploiting Mixed Precision Floating Point Hardware in Scientific
• Two-Stage Tridiagonal Reduction for Dense Symmetric Matrices using Tile Algorithms on Multicore Architectures
• Implementing Linear Algebra Routines on Multi-Core Processors
• Providing Access to High Performance Computing Technologies
• JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 1, 22-31 (1984) Multiprocessing Linear Algebra Algorithms on the
• HARNESS: Heterogeneous Adaptable Reconfigurable NEtworked SystemS
• CS 89 85 Performance of Various Computers Using Standard
• The LINPACK Benchmark: Past, Present, and Future Jack J. Dongarra, Piotr Luszczek, and Antoine Petitet
• A Parallel Implementation of the Nonsymmetric QR Algorithm for Distributed Memory Architectures
• Evaluation of HighPerformance Computing Software Shirley Browne \Lambda Jack Dongarra y Tom Rowan z
• LAPACK Working Notes LAPACK Working Note #1
• LocationIndependent Naming for Virtual Distributed Software Repositories \Lambda
• Management of the NHSE a Virtual Distributed Digital Library
• Algorithm-Based Diskless Checkpointing for Fault Tolerant Matrix Operations
• Application Runtime Support System (RSS) stop_application
• Network-Enabled Solvers and the NetSolve H. Casanova
• Changing Technologies of HPC Jack J. Dongarra \Lambda
• ORNL/TM12472 Engineering Physics and Mathematics Division
• Overview of PVM and MPI Jack Dongarra
• Performance Complexity of LU Factorization with Efficient Pipelining and Overlap on a Multiprocessor
• Dense Linear Algebra Solvers for Multicore with GPU Accelerators Stanimire Tomov, Rajib Nath, Hatem Ltaief, and Jack Dongarra
• LAPACK++ V. 1.0 High Performance Linear Algebra
• AlgorithmBased Diskless Checkpointing for Fault Tolerant Matrix Operations
• HighPerformance Computing in Industry Erich Strohmaier \Lambda ,
• Standardized Numerical Linear Algebra Software Jack J. Dongarra
• LAPACK Working Note 95 ScaLAPACK: A Portable Linear Algebra Library for Distributed
• THE DESIGN AND IMPLEMENTATION OF THE PARALLEL OUTOFCORE SCALAPACK LU, QR AND CHOLESKY
• CS 89 85 Performance of Various Computers Using Standard
• Scalable Networked Information Processing Environment (SNIPE) Graham Fagg 1
• Solving Linear Systems on Vector and Shared Memory Computers Jack J. Dongarra Iain S. Duff Danny C. Sorensen Henk A. Van der Vorst
• A Scalable Approach to MPI Application Performance Analysis
• TOP500 Supercomputer Sites Jack J. Dongarra
• NetSolve: A Network Server for Solving Computational Science Problems
• On the Convergence of Computational and Data Grids Dorian C. Arnold Sathish S. Vadhiyar Jack Dongarra
• Chapter in Wiley Encyclopedia of Electrical and Electronics Engineering
• ORNL TM-12470 Engineering Physics and Mathematics Division
• The Design and Implementation of the Parallel Out-of-core ScaLAPACK LU, QR and Cholesky
• National HPCC Software Exchange Shirley Browne, Jack Dongarra, Stan Green,
• MessagePassing Performance of Various Computers \Lambday Jack J. Dongarra z Tom Dunigan x
• LAPACK FOR FORTRAN90 Jack J. Dongarra Jeremy Du Croz y Sven Hammarling y
• Tools for Heterogeneous Network Computing \Lambda Adam Beguelin y , Jack Dongarra z , Al Geist x , Robert Manchek --,
• Evolving Software Repositories http://www.netlib.org/utk/projects/esr/
• Algorithmic Redistribution Methods for Block Cyclic Decompositions \Lambda
• ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers Design Issues and Performance \Lambda
• The Spectral Decomposition of Nonsymmetric Matrices on Distributed Memory Parallel Computers
• The International Exascale Software Project: A Call to Cooperative Action by the Global High Performance
• NetSolve's Network Enabled Server: Examples and Applications
• Some Issues in Dense Linear Algebra for Multicore and Special Purpose Architectures
• An Effective Empirical Search Method for Automatic Software Tuning
• SOFTWARE LIBRARIES FOR LINEAR ALGEBRA COMPUTATIONS ON HIGH PERFORMANCE COMPUTERS
• Hash functions for datatype signatures in MPI Julien Langou, George Bosilca, Graham Fagg, and Jack Dongarra
• Automated Empirical Optimizations of Software and the ATLAS project
• Enhancing Parallelism of Tile QR Factorization for Multicore Architectures
• The LAPACK for Clusters Project: an Example of Self Adapting Numerical Software
• 161. Anthony Skjell um, Lawrence Livermore Nati onal Laboratory, 7000 East Ave. , L-316, P. O. Box 808 Li vermore, CA94551
• and candor rarely encountered in a sin-gle work, the authors describe an evo-
• Using Mixed Precision for Sparse Matrix Computations to Enhance the
• Software Reuse in High Performance Computing Shirley Browne
• SOFTWARE LIBRARIES FOR LINEAR ALGEBRA COMPUTATIONS ON HIGH PERFORMANCE COMPUTERS
• Using Agentbased Software for Scientific Computing
• Software Standards and Tools for Concurrent Computing
• Message-Passing Performance of Various Computers y
• MARCH/APRIL 2005 Copublished by the IEEE CS and the AIP 1521-9615/05/$20.00 2005 IEEE 51 PERSPECTIVESP E R S P E C T I V E S I N C O M P U TAT I O N A L S C I E N C E
• ALGORITHM 589 SlCEDR: A FORTRAN Subroutine
• Recent Trends in the Marketplace of High Performance Computing
• Access 02 Summer 2005 Access 03 Summer 2005
• IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 1 Solving Systems of Linear Equations on the CELL
• Interior state computation of nano structures Andrew Canning1
• Scheduling Block-Cyclic Array Redistribution Fr ed eric Desprez1, Jack Dongarra2;3, Antoine Petitet2, Cyril Randriamaro1 and Yves Robert2
• Dense Linear Algebra Solvers for Multicore with GPU Accelerators Stanimire Tomov1
• Reliability Analysis of Self-Healing Network using Discrete-Event Simulation Thara Angskun 1
• This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research
• Decision Trees and MPI Collective Algorithm Selection Problem
• Level-3 Cholesky Kernel Subroutine of a Fully Portable High Performance Minimal Storage Hybrid
• X. Parallel and Distributed Scientific A Numerical Linear Algebra Problem Solving Environment
• A COMPARISON OF PARALLEL SOLVERS FOR DIAGONALLY DOMINANT AND GENERAL NARROWBANDED LINEAR
• High Performance Computing in the U.S. in An Analysis on the Basis of the TOP500 List
• [1] E. Anderson, Z. Bai, C. Bischof, J. Demmel, J. Dongarra, J. DuCroz, A. Greenbaum, S. Ham
• Numerical Linear Algebra Algorithms and Software Jack J. Dongarra
• The Impact of RISC and Parallel RISC Systems
• Advanced Architecture Computers* Jack J. Dongarra and Iain S. Duff
• Constructing Resiliant Communication Infrastructure for Runtime Environments
• Changing Technologies of HPC Jack J. Dongarra
• Message-Passing Performance of Various Computers y Jack J. Dongarraz
• Performance Instrumentation and Compiler Optimizations for MPI/OpenMP Applications
• SUPERCOMPUTING '96 ScaLAPACK: A Portable Linear Algebra Library
• Dynamic Reconfiguration and Virtual Machine Management in the Harness Metacomputing System
• Netlib, NHSE and other Sources Jack Dongarra
• [1] 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
• Algorithmic Issues on Heterogeneous Computing Platforms Pierre Boulet 1 , Jack Dongarra 2;3 , Fabrice Rastello 4 , Yves Robert 4 and Fr ed eric Vivien 5
• NetworkEnabled Solvers and the NetSolve H. Casanova
• Fault Tolerant Matrix Operations for Networks of Workstations Using Multiple Checkpointing
• MPI Collective Algorithm Selection and Quadtree Encoding
• Improving Time to Solution with Automated Performance Analysis Shirley Moore, Felix Wolf, and Jack Dongarra
• Performance Analysis of MPI Collective Operations Jelena PjesivacGrbovic, Thara Angskun, George Bosilca,
• Implementation in ScaLAPACK of Divide-and-Conquer Algorithms for Banded and Tridiagonal Linear Systems
• Performance Instrumentation and Measurement for Terascale Systems
• NetSolve: A Network Server for Solving Computational Science Problems
• A Sparse Matrix Library in C++ for High Performance Architectures \Lambda
• IML++ v. 1.2 Iterative Methods Library
• Methodology, Relations and Results
• 161. Anthony Skjellum, Lawrence Livermore National Laboratory, 7000 East Ave., L 316, P.O. Box 808 Livermore, CA 94551
• The Spectral Decomposition of Nonsymmetric Matrices on Distributed Memory Parallel Computers
• A Rough Guide to Scientific Computing On the PlayStation 3 Technical Report UT-CS-07-595
• Numerical Libraries And The Grid Antoine Petitet
• High Performance Computing in the U.S. in An Analysis on the Basis of the TOP500 List
• Self Adapting Linear Algebra Algorithms and , Jack Dongarra
• 1 Disaster Survival Guide in Petascale Computing: An Algo-rithmic Approach 3
• ScaLAPACK: A Linear Algebra Library for MessagePassing Computers \Lambda
• A Test Suite for PVM Henri Casanova (casanova@cs.utk.edu)
• LAPACK Working Note 43 A Look at Scalable Dense Linear Algebra Libraries #
• [32] D. Sorensen and P. Tang. On the orthogonality of eigenvectors computed by divide andconquer techniques. Mathematics and Computer Science Division MCSP152
• Software Standards and Tools for Concurrent Computing
• National HPCC Software Exchange \Lambda Shirley Browne, Jack Dongarra, Stan Green,
• Determining the Idle Time of a Tiling: New Results \Lambda Fr'ed'eric Desprez 1 , Jack Dongarra 2;3 , Fabrice Rastello 1 and Yves Robert 2
• [11] R. van de Geijn, On global combine operations, LAPACK Working Note 29, Technical Report CS91129, University of Tennessee, 1991.
• NetSolve: A Network Server for Solving Computational Science Problems
• High Performance Computing Technologies Jack Dongarra
• Key Concepts For Parallel OutOfCore LU Factorization
• The Generalized QR Decomposition 22 [1] J. L. Barlow, N. K. Nichols, and R. J. Plemmons, Iterative methods for equality con
• Problem Solving Environments for Parallel Scientific Computation
• NetSolve's Network Enabled Server: Examples and Applications
• TOP500 Supercomputer Sites 13th Edition
• Optimal Routing in Binomial Graph Networks Thara Angskun 1
• Software Reuse in High Performance Computing Shirley Browne
• Building and using an Fault Tolerant MPI implementation Graham E Fagg +*
• Overview of PVM and MPI Jack Dongarra
• Taskers and General Resource Managers : PVM supporting DCE Process Management
• Static Tiling for Heterogeneous Computing Platforms Pierre Boulet 1 , Jack Dongarra 2;3 , Yves Robert 4 and Fr ed eric Vivien 5
• Document for a Standard MessagePassing Interface Message Passing Interface Forum
• Overview of ScaLAPACK Jack Dongarra
• [4] J. Dongarra, J. Du Croz, S. Hammarling, and R. Hanson. An extended set of fortran basic linear algebra subroutines. ACM Transactions on Mathematical Software, 14(1):1--17,
• Netlib, NHSE and other Sources Jack Dongarra
• Heterogeneous MPI Application Interoperation and Process Management under PVMPI ?
• Developing numerical libraries in Java RONALD F. BOISVERT 1 , JACK J. DONGARRA 2 , ROLDAN POZO 1 ,
• An Introduction to the MPI Standard Jack J. Dongarra
• Implementation in ScaLAPACK of DivideandConquer Algorithms for Banded and Tridiagonal Linear Systems
• TOP500 Supercomputer Sites Jack J. Dongarra
• Parallel Tiled QR Factorization for Multicore Architectures
• The Dangers of Heterogeneous Network Computing: Heterogeneous Networks Considered Harmful
• C H A P T E R F O U R T E E N How Elegant Code Evolves with
• Adaptive Scheduling for Task Farming with Grid Middleware
• JLAPACK---Compiling LAPACK Fortran to Java, Phase 1 Technical Report cs97367
• An Object Oriented Design for High Performance Linear Algebra on Distributed Memory Architectures
• LAPACK Working Note 41 Installation Guide for LAPACK 1
• Chebyshev tau QZ Algorithm Methods for Calculating Spectra
• A Parallel Implementation of the Nonsymmetric QR Algorithm for Distributed Memory Architectures
• Evaluating Block Algorithm Variants in LAPACK * * This work was supported by the National Science Foundation
• Hybrid Multicore Cholesky Factorization with Multiple GPU Accelerators
• An Updated Set of Basic Linear Algebra Subprograms BLAS
• An Introduction to the MPI Standard Jack J. Dongarra
• ne petaflop per second is a rate of computation corresponding to 1015
• Automatic Optimisation of Parallel Linear Algebra Routines in Systems with Variable Load*
• Available online at www.sciencedirect.com Procedia ScienceProcedia Computer Science 00 (2009) 000000
• From CUDA to OpenCL: Towards a Performance-portable Solution for Multi-platform GPU Programming$,$$
• Current software releases and reports regarding HeNCE can be obtained from netlib by sending electronic mail to netlib@ornl.gov containing the line ``send index from hence''. Instructions on how to receive the
• ScaLAPACK Tutorial ? Jack Dongarra 1;2 and L. Susan Blackford ??1
• Integrated PVM Framework Supports Heterogeneous Network Computing
• Jack Dongarra Pete Beckman
• Accelerating TIME-TO-SOLUTION for Computational
• Rectangular Full Packed Format for Cholesky's Algorithm: Factorization,
• Scheduling Two-sided Transformations using Tile Algorithms on Multicore Architectures
• QR Factorization for the CELL Processor LAPACK Working Note 201
• Trace-based Performance Analysis for the Petascale Simulation Code FLASH
• Elsevier Editorial System(tm) for Future Generation Computer Systems Manuscript Draft
• This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research
• Rectangular Full Packed Format for Cholesky's Algorithm: Factorization, Solution and Inversion
• Cloud Computing and Software Services: Theory and Technique April 30, 2009
• Cloud Service Reliability: Modeling and Analysis Yuan-Shun Dai * a c
• Parallel Two-Sided Matrix Reduction to Band Bidiagonal Form on Multicore Architectures
• The Problem with the Linpack Benchmark Matrix Generator June 28, 2008
• Analytical Modeling and Optimization for Affinity Based Thread Scheduling on Multicore Systems
• Dynamic Task Scheduling for Linear Algebra Algorithms on Distributed-Memory Multicore Systems
• A Note on Auto-tuning GEMM for GPUs , Jack Dongarra1,2,3
• Scheduling Linear Algebra Operations on Multicore Processors LAPACK Working Note 213
• Scheduling Two-sided Transformations using Algorithms-by-Tiles on Multicore Architectures
• Comparative Study of One-Sided Factorizations with Multiple Software Packages on Multi-Core Hardware
• Accelerating the reduction to upper Hessenberg form through hybrid GPU-based computing
• Accelerating Scientific Computations with Mixed Precision Algorithms
• Algorithmic Based Fault Tolerance Applied to High Performance Computing May 23, 2008
• Parallel Block Hessenberg Reduction using Algorithms-By-Tiles for Multicore Architectures
• Request Sequencing: Enabling Workflow for Efficient Problem Solving in , Jack Dongarra 2
• CTWatch Quarterly Creating Software Tools and Libraries for Leaders... http://www.ctwatch.org/quarterly/print.php?p=92 1 of 5 12/13/2007 12:22 PM
• Fast and Small Short Vector SIMD Matrix Multiplication Kernels for the Synergistic Processing Element of the CELL Processor
• Matrix Product on Heterogeneous Master-Worker Platforms Jack Dongarra1
• COMPUTING THE CONDITIONING OF THE COMPONENTS OF A LINEAR LEAST SQUARES SOLUTION
• K EN KE NNE DY 51S C I D A C R E V I E W F A L L 2 0 0 7 W W W . S C I D A C R E V I E W . O R G
• A Class of Parallel Tiled Linear Algebra Algorithms for Multicore Architectures
• Self Adaptive Application Level Fault Tolerance for Parallel and Distributed Computing
• Mixed Precision Iterative Refinement Techniques for the Solution of Dense Linear Systems
• International Journal of Foundations of Computer Science c World Scientific Publishing Company
• High Performance Development for High End Computing with Python Language Wrapper (PLW)
• This article was originally published in a journal published by Elsevier, and the attached copy is provided by Elsevier for the
• Int. J. Computational Science and Engineering, Vol. 2, Nos. 3/4, 2006 205 Conjugate-gradient eigenvalue solvers in
• Parallel Processing Letters fc World Scientific Publishing Company
• Solving Systems of Linear Equations on the CELL Processor Using Cholesky Factorization LAPACK Working Note 184
• O'Reilly Media, Inc. 4/17/2007 How Elegant Code Evolves with
• The Impact of Multicore on Math Software Alfredo Buttari1
• Parallel Linear Algebra Victor Eijkhout, Julien Langou, and Jack Dongarra
• Using Mixed Precision for Sparse Matrix Computations to Enhance the
• University of California/Davis University of California/Berkeley
• Summary of Software for Linear Algebra
• Twenty-Plus Years of Netlib and NA-Net Jack Dongarra, Gene Golub, Eric Grosse, Cleve Moler, Keith Moore
• Biological Sequence Alignment On The Computational Grid Using The Grads Framework
• NanoPSE: Nanoscience Problem Solving Environment for atomistic electronic structure of
• Performance Analysis of MPI Collective Operations Jelena Pjesivac-Grbovic1, Thara Angskun1, George Bosilca1,
• An Asynchronous Algorithm on NetSolve Global Computing System
• Conjugate-Gradient Eigenvalue Solvers in Computing Electronic Properties of
• NetSolve: Grid Enabling Scientific Computing Environments
• UncorrectedProof DOI: 10.1007/s10766-005-3584-4
• A Scalable Approach to MPI Application Performance Analysis
• Recovery Patterns for Iterative Methods in a Parallel Unstable Environment
• Automatic Experimental Analysis of Communication Patterns in Virtual Topologies
• Introduction to the HPCChallenge Benchmark Suite Jack J. Dongarra Piotr Luszczek
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2004; 00:126 Prepared using cpeauth.cls [Version: 2002/09/19
• Active Logistical State Management in GridSolve/L Micah Beck, Jack Dongarra, Jian Huang, Terry Moore and James S. Plank
• An Algebra for Cross-Experiment Performance Analysis Fengguang Song, Felix Wolf, Nikhil Bhatia, Jack Dongarra, and Shirley Moore
• AN OVERVIEW OF HETEROGENEOUS HIGH PERFORMANCE AND GRID COMPUTING
• Efficient Pattern Search in Large Traces through Successive Refinement
• %&'() 0(1)2345 0)(6(7 %8 9(''5 (@& A(BC A8 DE@'())( F@@EG(H2G3 IE7PQH2@' R(1E)(HE)S5 IE7PQH3) TB23@B3 D3P()H373@H5
• A Fault-Tolerant Communication Library for Grid Environments
• Applying Aspect-Orient Programming Concepts to a Component-based Programming Model
• Energy Minimization of Protein Tertiary Structure by Parallel Simulated Annealing using Genetic Crossover
• Fault Tolerant Communication Library and Applications for High Performance Graham E. Fagg, Edgar Gabriel, Zizhon Chen,
• GrADSolve -a Grid-based RPC system for Parallel Computing with Application-Level
• NetSolve: past, present, and future; a look at a Grid enabled server1
• Optimization Problem Solving System using Grid RPC Tomoyuki HIROYASU Mitsunori MIKI Hisashi SHIMOSAKA
• SCALABLE, TRUSTWORTHY NETWORK COMPUTING USING UNTRUSTED INTERMEDIARIES
• SCHEDULING IN THE GRID APPLICATION DEVELOPMENT SOFTWARE PROJECT
• Self-adapting Numerical Software and Automatic Tuning of Jack Dongarra, Victor Eijkhout
• Hamparsum Bozdogan Statistical Data Mining, and
• 0 100 200 300 400 500 600 700 800 900 1000 Vector dimension
• A Metascheduler For The Grid Sathish S. Vadhiyar and Jack J. Dongarra
• A Performance Oriented Migration Framework For The Grid Sathish S. Vadhiyar and Jack J. Dongarra
• Network File System Sun's NFS (RPC/UDP)
• NetBuild: Transparent Cross-Platform Access to Computational Software Libraries Keith Moore
• Lecture Notes in Computer Science 1 Parallel IO support for Meta-Computing Applications
• Performance Modeling for Self Adapting Collective Communications for MPI
• The GrADS Project: Software Support for High-Level Grid Application Development
• Using PAPI for hardware performance monitoring on Linux Jack Dongarra, Kevin London, Shirley Moore, Phil Mucci, and Dan Terpstra
• A Scalable Cross-Platform Infrastructure for Application Performance Tuning Using Hardware Counters
• Automatically Tuned Collective Communications Sathish S. Vadhiyar+
• Lecture Notes in Computer Science 1 FT-MPI: Fault Tolerant MPI, supporting dynamic
• Telescoping Languages: A Strategy for Automatic Generation of Scientific Problem-Solving Systems from Annotated Libraries
• JLAPACK|Compiling LAPACK Fortran to Java David M. Doolin
• This paper describes an approach for the automatic generation and optimization of numer-ical software for processors with deep memory hierarchies and pipelined functional units.
• Determining the Idle Time of a Tiling: New Results Fr ed eric Desprez1, Jack Dongarra2;3, Fabrice Rastello1 and Yves Robert2
• Using Agent-based Software for Scienti c Computing
• Case Studies on The Development of ScaLAPACK and the NAG
• Java Access to Numerical Libraries Henri Casanova
• JLAPACK|Compiling LAPACK Fortran to Java, Phase 1 Technical Report cs-97-367
• Key Concepts For Parallel Out-Of-Core LU Factorization
• Scheduling Block-Cyclic Array Redistribution Fr ed eric Desprez1, Jack Dongarra2;3, Antoine Petitet2, Cyril Randriamaro1 and Yves Robert2
• A Test Matrix Collection for Non-Hermitian Eigenvalue Problems
• Matrix Market : A Web Resource for Test Matrix Collections
• NetSolve: A Network Server for Solving Computational Science Problems
• Practical Experience in the Dangers of Heterogeneous L. S. Blackford, A. Clearyy, J. Demmelz, I. Dhillonz, J. Dongarrax,
• The Spectral Decomposition of Nonsymmetric Matrices on Distributed Memory Parallel Computers
• The use of Java in the NetSolve project
• Algorithmic Bombardment for the Iterative Solution of Linear Systems
• Future Linear Algebra Libraries Jack Dongarra
• Key Concepts For Parallel Out-Of-Core LU Factorization
• PVMPI: An Integration of the PVM and MPI Systems Graham E. Fagg
• ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers -Design Issues and Performance
• Templates for Linear Algebra Problems Zhaojun Bai
• TOP500 Supercomputer Sites Jack J. Dongarra
• A Highly Parallel Algorithm for the Reduction of a Nonsymmetric Matrix to Block Upper-Hessenberg Form
• Digital Software and Data Repositories for Support of Scienti c Computing
• Toward a Proposal for a set of Parallel Basic Linear Algebra Subprograms
• IML++ v. 1.2 Iterative Methods Library
• Location-Independent Naming for Virtual Distributed Software Repositories
• Overview of VPE: A Visual Environment for Message-Passing Peter Newton
• A Sparse Matrix Library in C++ for High Performance Architectures
• SIAM J. ScI. COMPUT. Vol. 14, No. 3, pp. 542-569, May 1993
• Tools for Heterogeneous Network Computing Adam Begueliny
• SUPERCOMPUTING '96 ScaLAPACK: A Portable Linear Algebra Library
• High Performance Computing Technologies Jack Dongarra
• Problem Solving Environments for Parallel Scienti c Computation
• Evolving Software Repositories http: www.netlib.org utk projects esr
• A Framework For Migrating Applications Under Changing Load Conditions In The Grid
• Reliability and Performance Models for Grid Computing Yuan-Shun Dai 1,2
• Performance Analysis of MPI Collective Jelena Pjesivac-Grbovic1
• Parallel Band Two-Sided Matrix Bidiagonalization for Multicore Architectures
• An Implementation of the Tile QR Factorization for a GPU and Multiple CPUs
• Enabling Workflows in GridSolve: Request Sequencing and Service Trading
• ITW2004, San Antonio, Texas, October 24 29, 2004 Numerically Stable Real-Number Codes Based on Random Matrices
• A Comparison of Search Heuristics for Empirical Code Optimization
• ScaLAPACK Tutorial ? Jack Dongarra1;2 and L. Susan Blackford??1
• Practical Experience in the Dangers of Heterogeneous L. S. Blackford \Lambda , A. Cleary y , J. Demmel z , I. Dhillon z , J. Dongarra x ,
• MPI: A MessagePassing Interface Standard Message Passing Interface Forum
• Sparse Matrix Libraries in C++ for High Performance Architectures
• Overview of Templates Jack Dongarra
• Overview of ScaLAPACK Jack Dongarra
• A Parallel Implementation of the Nonsymmetric QR Algorithm for Distributed Memory Architectures
• The Performance of PVM on MPP Systems
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. (2010)
• Predicting the electronic properties of 3D, million-atom semiconductor nanostructure architectures
• LAPACK Working Note #224 QR Factorization of Tall and Skinny Matrices in a
• More on Scheduling BlockCyclic Array Redistribution \Lambda Fr'ed'eric Desprez 1 , St'ephane Domas 1 , Jack Dongarra 2;3 ,
• MPI WALL Determine elapsed wallclock time in seconds. double precision function MPI WALL ( )
• Providing Infrastructure and Interface to HighPerformance Applications in a Distributed Setting. (Extended Abstract)
• A Fully Parallel Algorithm for the Symmetric Eigenvalue Problem J.J. Dongarra and D. C. Sorensen
• A Test Matrix Collection for NonHermitian Eigenvalue Problems \Lambda
• Values of N Subroutine 100 200 300 400 500
• Chebyshev tau -QZ Algorithm Methods for Calculating Spectra
• Optimization Problem Solving System using GridRPC
• ATLAS on the BlueGene/L Preliminary Results Keith Seymour Haihang You Jack Dongarra
• Extending the MPI Specification for Process Fault Tolerance on High Performance Computing Systems
• Reliability and Performance Modeling and Analysis for Grid Computing
• Netlib and NA-Net: building a scientific computing community Jack Dongarra, Gene Golub, Eric Grosse, Cleve Moler, Keith Moore
• Parallel Computing 3 (1986) 25-34 25 North-Holland
• Comparative Study of One-Sided Factorizations with Multiple Software Packages on Multi-Core Hardware
• EXPERIMENTS WITH STRASSEN'S ALGORITHM: FROM SEQUENTIAL TO PARALLEL
• Static tiling for heterogeneous computing platforms 1
• Deploying Fault-tolerance and Task Migration with NetSolve James S. Plank
• Algorithm-Based Checkpoint-Free Fault Tolerance for Parallel Matrix Computations on Volatile Resources
• Methodology, Relations and Results
• Developing numerical libraries in Java RONALD F. BOISVERT1, JACK J. DONGARRA2, ROLDAN POZO1,
• Parallelizing the Divide and Conquer Algorithm
• 144. Andrew B. White, Los Alamos National Laboratory, P. O. Box 1663, MS265, Los Alamos, 145. David L. Williamson, National Center for Atmospheric Research, P. O. Box 3000, Boulder,
• Java Access to Numerical Libraries Henri Casanova \Lambda Jack Dongarra \Lambda y David M. Doolin \Lambda
• The Spectral Decomposition of Nonsymmetric Matrices on Distributed Memory Parallel Computers
• Possibilities for Active Messaging in PVM Philip J. Mucci
• Fast and Small Short Vector SIMD Matrix Multiplication Kernels for the Synergistic Processing Element of the CELL Processor
• Interactive and Dynamic Content in Software Repositories
• Scanning the Issue Special Issue on Program Generation, Optimization, and
• [10] H. J. Symm and J. H. Wilkinson. Realistic error bounds for a simple eigenvalue and its associated eigenvector. Num. Math., 35:113--, 1980.
• Fault Tolerant MPI for the HARNESS MetaComputing system
• The Dangers of Heterogeneous Network Computing: Heterogeneous Networks Considered Harmful
• Key Concepts For Parallel OutOfCore LU Factorization
• Algorithmic Bombardment for the Iterative Solution of Linear Systems
• PVMPI: An Integration of the PVM and MPI Systems Graham E. Fagg \Lambda Jack J. Dongarra y
• CTWatch Quarterly Enabling Advanced Scientific Computing Software http://www.ctwatch.org/quarterly/print.php?p=91 1 of 5 12/13/2007 12:21 PM
• LAPACK Working Note 95 ScaLAPACK: A Portable Linear Algebra Library for Distributed
• This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research
• ST-HEC: Reliable and Scalable Software for Linear Algebra Computations on High End James Demmel (U California, Berkeley) and Jack Dongarra (U Tennessee, Knoxville)
• Logistical Computing and Internetworking: Middleware for the Use of Storage in Communication
• LAPACK++ V. 1.0 High Performance Linear Algebra
• UT-CS-01-460 April 28, 2001
• Dynamic Recon guration and Virtual Machine Management in the Harness Metacomputing
• Integrated Tool Capabilities for Performance Instrumentation and Measurement
• Vita for Jack Dongarra April 1, 1999
• Overview of recent supercomputers Aad J. van der Steen
• Revisiting Matrix Product on Master-Worker Platforms Jack Dongarra2
• CTWatch Quarterly The Impact of Multicore on Computational Scienc... http://www.ctwatch.org/quarterly/print.php?p=67 1 of 8 2/28/2007 4:31 PM
• Providing Access to High Performance Computing Technologies
• Overview of VPE: A Visual Environment for MessagePassing Peter Newton
• This paper describes an approach for the automatic generation and optimization of numer ical software for processors with deep memory hierarchies and pipelined functional units.
• 0 100 200 300 400 500 600 Order of vectors/matrices
• UNCORRECTEDPROOF 2 HARNESS and fault tolerant MPI
• Integrated PVM Framework Supports Heterogeneous Network Computing
• Scalability Analysis of the SPEC OpenMP Benchmarks on Large-Scale Shared Memory
• Automatic search for patterns of inefficient
• Process Fault-Tolerance: Semantics, Design and Applications for High Performance Computing
• visPerf: Monitoring Tool for Grid Computing DongWoo Lee1
• Another Architecture: PVM on Windows 95 NT Markus Fischer
• DOI: 10.1007/s10766-005-3577-3 International Journal of Parallel Programming, Vol. 33, No. 2, June 2005 ( 2005)
• Binomial Graph: A Scalable and Fault-Tolerant Logical Network Topology
• Analysis of Preparation
• The Performance of PVM on MPP Systems
• Experiences and Lessons Learned with a Portable Interface to Hardware Performance Counters
• UsersApplications Fault Tolerance
• A PARALLEL IMPLEMENTATION OF THE NONSYMMETRIC QR ALGORITHM FOR DISTRIBUTED MEMORY ARCHITECTURES
• from SIAM News, Volume 32, Number 6 Atlanta Organizers Put Mathematics to Work
• Feedback-Directed Thread Scheduling with Memory Considerations
• SIAM J. ScI. STAT. COMPUT. Vol. 7, No. 1, January 1986
• Automatic Blocking of Nested Loops Robert Schreiber
• Design of Interactive Environment for Numerically Intensive Parallel Linear Algebra Calculations
• The Impact of RISC and Parallel RISC Systems
• Fault Tolerant Matrix Operations for Networks of Workstations Using Multiple Checkpointing
• Case Studies on The Development of ScaLAPACK and the NAG
• HARNESS: A Next Generation Distributed Virtual Machine
• Sparse Matrix Libraries in C++ for High Performance Architectures \Lambda
• LAPACK Working Note #16 Results from the Initial Release of LAPACK *
• Last name: Rosener First name: Bill
• subroutine prec3s( x, px, a2, a3, a4, nx, ny, nz, rkr ) implicit double precision (ah,oz)
• GridSolve: The Evolution of A Network Enabled Solver
• Fault Tolerant MPI for the HARNESS MetaComputing system
• Scalable Fault Tolerant Protocol for Parallel Runtime Environments
• EXPERIENCES WITH WINDOWS 95 NT AS A CLUSTER COMPUTING PLATFORM FOR PARALLEL COMPUTING.
• Flexible collective communication tuning architecture applied to Open MPI
• Optimizing Matrix Multiplication for a Short-Vector SIMD Architecture CELL
• HIGH PERFORMANCE COMPUTING TODAY Jack Dongarra
• LAPACK Working Note 139 A Numerical Linear Algebra Problem Solving Environment
• An Asynchronous Algorithm on NetSolve Global Computing System
• ORNL/TM-2004/13 Cray X1 Evaluation Status Report
• End-user Tools for Application Performance Analysis Using Hardware Counters
• Overview of Templates Jack Dongarra
• MessagePassing Performance of Various Computers \Lambday
• Another Architecture: PVM on Windows 95/NT Markus Fischer \Lambday Jack Dongarra \Lambda z
• LAPACK Working Notes: LAPACK Working Note #1: J. Demmel and J. Dongarra and J. Du Croz and A. Greenbaum
• Interactive and Dynamic Content in Software Repositories \Lambda
• Users' Guidei Vincent A. Barker 1 L. Susan Blackford 2
• Matrix Market : A Web Resource for Test Matrix Collections
• Benchmarking Performance
• ORNL/TM12470 Engineering Physics and Mathematics Division
• LAPACK Working Note 58 The Design of Linear Algebra Libraries for High Performance Computers \Lambda
• ORNL/TM12309 Engineering Physics and Mathematics Division
• Management of the NHSE --a Virtual Distributed Digital Library \Lambda
• An Introduction to the MPI Standard Jack J. Dongarra
• Revisiting Matrix Product on Master-Worker Platforms Jack Dongarra2
• Numerical Libraries and Tools for Scalable Parallel Cluster Computing Shirley Browne, Jack Dongarra, and Anne Trefethen*
• CS -89 -85 Performance of Various Computers Using Standard
• Packages of Subroutines
• Optimizing Performance and Reliability in Distributed Computing Systems Through Wide Spectrum Storage
• Middleware for the Use of Storage in Communication , Dorian Arnold
• Toward a Proposal for a set of Parallel Basic Linear Algebra Subprograms
• Table 4: Timings for Wilkinson Shift and Perfect Shift Algorithms n = 100 n = 200
• [1] E. Anderson and J. Dongarra, LAPACK Working Note 16: Results from the Initial Release of LAPACK, University of Tennessee, CS8989, November 1989.
• Stochastic Performance Prediction for Iterative Algorithms in Distributed Environments
• CS 89 85 Performance of Various Computers Using Standard
• Scheduling BlockCyclic Array Redistribution \Lambda Fr'ed'eric Desprez 1 , Jack Dongarra 2;3 , Antoine Petitet 2 , Cyril Randriamaro 1 and Yves Robert 2
• Chapter in Wiley Encyclopedia of Electrical and Electronics Engineering
• [13] T.Y. Li, Zhonggang Zeng, and Luan Cong. Solving eigenvalue problems of real nonsym metric matrices with real homotopies. Preprint, Michigan State University, E. Lansing, MI
• Taskers and General Resource Managers : PVM supporting DCE Process Management
• The Marketplace of High Performance Erich Strohmaiera 1 , Jack J. Dongarraa;b 2 , Hans W. Meuerc 3
• Scalable Fault Tolerant MPI: Extending the recovery algorithm
• Toward a Framework for Preparing and Executing Adaptive Grid Programs
• ScaLAPACK: A Linear Algebra Library for Message-Passing L. S. Blackford,yJ. Choi,zA. Cleary,y E. D'Azevedo,xJ. Demmel, I. Dhillon, J. Dongarra,k
• DOI: 10.1007/s10766-005-3584-4 International Journal of Parallel Programming, Vol. 33, Nos. 2/3, June 2005 ( 2005)
• Overview of HPC Jack Dongarra
• [9] T.H. Dunigan. Performance of the Intel iPSC/860 and NCUBE 6400 hypercubes. Technical Report ORNL/TM11790, Oak Ridge National Laboratory, Oak Ridge, Tennessee, 1991.
• ARGONNE NATIONAL LABORATORY 9700 South Cass Avenue
• ARGONNE NATIONAL LABORATOR 9700 South Cass Avenue
• LAPACK Working Note ? LAPACK Block Factorization Algorithms
• Implementation of a Mixed-Precision in Solving Systems of Linear Equations
• Self-adapting Numerical Software for Next Generation Applications
• DARPA's HPCS Program: History, Models, Tools, Languages Jack Dongarra, University of Tennessee and Oak Ridge National Lab
• High-Performance Computing in Industry Erich Strohmaier
• HARNESS Fault Tolerant MPI design, usage and performance issues
• Algorithmic Redistribution Methods for Block Cyclic Decompositions
• Review of Performance Analysis Tools for MPI Parallel Programs Shirley Moore, David Cronk, Kevin London, and Jack Dongarra
• SELF-HEALING NETWORK FOR SCALABLE FAULT TOLERANT
• Evaluation of High-Performance Computing Software Shirley Browne Jack Dongarray Tom Rowanz
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2008; 20:15731590
• National HPCC Software Exchange Shirley Browne, Jack Dongarra, Stan Green,
• Parallelizing the Divide and Conquer Algorithm
• Prospectus for the Next LAPACK and ScaLAPACK Libraries
• The use of Java in the NetSolve project
• Tiling on Systems with Communication/Computation Overlap \Lambda
• integer mynum, hostnum, bytes, msgtype, ... double precision result, data(100), ...
• Scalable Networked Information Processing Environment (SNIPE)
• Automatic Blocking of Nested Loops Robert Schreiber \Lambda
• Future Linear Algebra Libraries Jack Dongarra
• Distributed Probabilistic Model-Building Genetic Algorithm
• Creating Software Technology to Harness the Power of Leadership-class Computing Systems
• Overview of HPC Jack Dongarra
• Self-Healing in Binomial Graph Networks Thara Angskun1
• Exploiting the Performance of 32 bit Floating Point Arithmetic in Obtaining
• Self-adapting software for numerical linear algebra and LAPACK for clusters q
• Future Generation Computer Systems 15 (1999) 595605 Scalable networked information processing environment (SNIPE)
• The use of bulk states to accelerate the band edge state calculation of a semiconductor quantum dot q
• Noname manuscript No. (will be inserted by the editor)
• SIAM J. MATRIX ANAL. APPL. c 2005 Society for Industrial and Applied Mathematics Vol. 27, No. 3, pp. 603620
• Predicting the electronic properties of 3D, million-atom semiconductor nanostructure architectures
• Applying Netsolve's Network-Enabled Server
• An iterative solver benchmark1 Jack Dongarra, Victor Eijkhout and
• CONCURRENCY: PRACTICE AND EXPERIENCE Concurrency: Pract. Exper. 2000; 12:14811493
• T h e F i r s t W o r d Copublished by the IEEE CS and the AIP 1521-9615/08/$25.00 2008 IEEE Computing in SCienCe & engineering
• Solving Systems of Linear Equations on the CELL Processor Using Cholesky Factorization
• Future Generation Computer Systems 22 (2006) 279290 An asynchronous algorithm on the NetSolve global
• http://hpc.sagepub.com/ Computing Applications
• Recent trends in the marketplace of high performance computing
• Scientific Programming 18 (2010) 3550 35 DOI 10.3233/SPR-2010-0297
• HARNESS and fault tolerant MPI Graham E. Fagg *, Antonin Bukovsky, Jack J. Dongarra
• TOP500 Supercomputer Sites 10th Edition
• SIAM J. ScI. STAT. COMPUT. Vol. 4, No. 4, December 1983
• Future Generation Computer Systems 22 (2006) 665675 www.elsevier.com/locate/fgcs
• Highly Scalable Self-Healing Algorithms for High Performance Scientific Computing
• http://hpc.sagepub.com/ Computing Applications
• The TOP500 and Computational Science A not-so-simple matter of software
• NanoPSE: Nanoscience Problem Solving Environment for atomistic electronic structure of semiconductor nanostructures
• A Proposal [or an ExLcndcd Set of IrorLran Basic Linear Algebra Subprograms
• PERFORMANCE STUDY OF LU FACTORIZATION WITH LOW COMMUNICATION OVERHEAD ON MULTIPROCESSORS
• Future Generation Computer Systems 18 (2002) 11271142 HARNESS fault tolerant MPI design, usage
• Optimizing Symmetric Dense Matrix-Vector Multiplication Computer Science and
• Future Generation Computer Systems 15 (1999) 745755 Deploying fault tolerance and taks migration with NetSolve
• CONCURRENCY: PRACTICE AND EXPERIENCE Concurrency: Pract. Exper., Vol. 11(3), 139153 (1999)
• ELSEVIER Parallel Computing 23 (1997) 49-70 Key concepts for parallel out-of-core LU
• A Parallel Divide and Conquer Algorithm for the Symmetric Eigenvalue
• ParallelComputingI (1984)223-235 223 North-Holland
• An Updated Set of Basic Linear Algebra Subprograms (BLAS)
• The Eigenvalue Problem for Hermitian Matrices with Time Reversal Symmetry
• Future Generation Computer Systems 27 (2011) 357369 Contents lists available at ScienceDirect
• CONCURRENCY: PRACTICE AND EXPERIENCE, VOL. 9(10), 915926 (OCTOBER 1997) Message-passing performance of various
• Parallel Two-Sided Matrix Reduction to Band Bidiagonal Form on Multicore Architectures
• http://hpc.sagepub.com/ Computing Applications
• CONCURRENCY: PRACTICE AND EXPERIENCE Concurrency: Pract. Exper., Vol. 10(1113), 11171129 (1998)
• Future Generation Computer Systems 21 (2005) 980986 Biological sequence alignment on the computational
• Jack Dongarra Universityof Tennessee,Knoxville
• Automated empirical optimizations of software and the ATLAS project q
• Future Generation Computer Systems 15 (1999) 571582 HARNESS: a next generation distributed virtual machine
• Using Mixed Precision for Sparse Matrix Computations to Enhance the Performance
• ELSEVIER Parallel Computing 210995) 1189-1211 A parallel algorithm for the reduction of a nonsymmetric
• Practical Experience in the Numerical Dangers of Heterogeneous Computing
• ne petaflop per second is a rate of computation corresponding to 1015
• Journal of Parallel and Distributed Computing 58, 68 91 (1999) Stochastic Performance Prediction for Iterative
• An Improved Magma Gemm For Fermi Graphics Processing Units
• DOI: 10.1007/s10766-005-3577-3 International Journal of Parallel Programming, Vol. 33, Nos. 2/3, June 2005 ( 2005)
• SIAM REVIEW Vol. 26, No. 1, January, 1984
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2003; 15:803820 (DOI: 10.1002/cpe.728)
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2010; 22:24672487
• The marketplace of high-performance computing Erich Strohmaiera,*, Jack J. Dongarraa,b
• A COMPARISON OF PARALLEL SOLVERS FOR DIAGONALLY DOMINANT AND GENERAL NARROW-BANDED LINEAR
• from SIAM News, Volume 34, Number 9 Biannual Top-500 Computer Lists Track Changing Environments
• Algorithm-Based Fault Tolerance for Fail-Stop Failures
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2007; 19:13711385
• TOP500 Supercomputer Sites Jack J. Dongarra
• http://hpc.sagepub.com/ Computing Applications
• THE SPECTRAL DECOMPOSITION OF NONSYMMETRIC MATRICES ON DISTRIBUTED MEMORY PARALLEL COMPUTERS
• Journal of Computational and Applied Mathematics 123 (2000) 489514 www.elsevier.nl/locate/cam
• JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 43, 125138 (1997) ARTICLE NO. PC971336
• Cluster Comput (2009) 12: 101122 DOI 10.1007/s10586-009-0080-4
• Network-enabled Solvers: A Step Toward Grid-based December 13, 2001
• SOFTWARE-PRACTICE AND EXPERIENCE, VOL. 9, 219-226 (1979) Unrolling Loops in FORTRAN*
• Netlib and NA-Net: Building A Scientific Computing Community Jack Dongarra
• Middleware for the use of storage in communication q
• http://hpc.sagepub.com/ Computing Applications
• D-Lib Magazine ISSN 1082-9873
• Squeezing the Most out of an Algorithm in CRAY FORTRAN
• When we try to assess how much progress we have made in computational modeling and simulation, recalling some history
• Scientific Programming 17 (2009) 3142 31 DOI 10.3233/SPR-2009-0268
• http://hpc.sagepub.com/ Computing Applications
• http://hpc.sagepub.com/ Computing Applications
• The Netlib Mathematical Software Repository
• Parallel Processing Letters, Vol. 17, No. 1 (2007) 47-59 %%k. ... _, ~ ** ,, ,, , ., ,, . x.c ,, ,.. .. ,, v
• ELSEVIER Parallel Computing 21(1995) 1387-1405 Parallel matrix transpose algorithms
• Optimizing matrix multiplication for a short-vector SIMD architecture CELL processor
• ParallelComputingI (1984) 133-142 133 North-Holland
• 192 IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, VOL. 9, NO. 2, FEBRUARY 1998 Scheduling Block-Cyclic Array Redistribution
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2010; 22:21962211
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2003; 15:207222 (DOI: 10.1002/cpe.657)
• Software Distribution Using Xnetlib JACK DONGARRA
• Review: [untitled] Author(s): Jack Dongarra
• http://hpc.sagepub.com/ Computing Applications
• COMPUTATIONAL AND APPLIEDMATHEMATICS
• Supporting Heterogeneous Network Computing: Jack J. Dongarra
• JOURNAL OF COMPUTATIONAL PHYSICS 54, 278-288 (1984) Solving the Secular Equation Including Spin Orbit Coupling
• 84 July 1996/Vol. 39, No. 7 COMMUNICATIONS OF THE ACM HE Message Passing Interface
• Self-Adapting Linear Algebra Algorithms and Software
• Using agent-based software for scientic computing in the NetSolve system
• http://hpc.sagepub.com/ Computing Applications
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2010; 22:1544
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2007; 19:14811496
• Algorithmic Redistribution Methods for Block-Cyclic Decompositions
• Future Generation Computer Systems 26 (2010) 479485 Contents lists available at ScienceDirect
• Squeezing the Most out of Eigenvalue Solvers on High-Performance Computers
• Numerical Algorithms 10(1995)379-399 379 of a parallel dense linear algebra software
• Journal of Parallel and Distributed Computing 61, 1803 1826 (2001) Telescoping Languages: A Strategy for Automatic
• CONCURRENCY: PRACTICE AND EXPERIENCE, VOL. 9(11), 12791291 (NOVEMBER 1997) Java access to numerical libraries
• http://hpc.sagepub.com/ Computing Applications
• EL`SVIER Future Generation Computer Systems 12 (1997) 461-474 Changing technologies of HPC
• http://hpc.sagepub.com/ Computing Applications
• State-of-the-art eigensolvers for electronic structure calculations of large scale nano-systems q
• Editor: Michael A. Gray, gray@american.edu 84 Copublished by the IEEE CS and the AIP 1521-9615/08/$25.00 2008 IEEE Computing in SCienCe & engineering
• http://hpc.sagepub.com/ Computing Applications
• Implementation of the HPC Challenge
• Towards dense linear algebra for hybrid GPU accelerated manycore systems Stanimire Tomov a,*, Jack Dongarra a,b,c
• MPI: A Message-Passing Interface Standard Message Passing Interface Forum
• A Comparison of Parallel Solvers for Diagonally Dominant and General Narrow-Banded Linear
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2002; 14:14571479 (DOI: 10.1002/cpe.678)
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2002; 14:14451456 (DOI: 10.1002/cpe.670)
• Exploiting Fine-Grain Parallelism in Recursive LU Factorization1
• Process FaultTolerance: Semantics, Design and Applications for High Performance Computing
• Fault Tolerant Communication Library and Applications for High Performance Graham E. Fagg, Edgar Gabriel, Zizhon Chen,
• CONCURRENCYPRACTICE AND EXPERIENCE, VOL.8(7), 517-535 (SEPTEMBER 1996) PB-BLAS: A set of parallel block basic linear
• JLAPACK compiling LAPACK FORTRAN David M. Doolin a, Jack Dongarra b,c,
• Jack Dongarra A Historical Overview and
• INTERACTIVE GRID-ACCESS USING GRIDSOLVE AND K. Seymour,1
• Logistical quality of service in NetSolve , H. Casanovaa
• http://hpc.sagepub.com/ Computing Applications
• SIAM J. NUMER. ANAL. Vol. 20, No. 1, February 1983
• ~" NUMERICAL MATHEMATICS
• Recursive approach in sparse matrix LU factorization
• Parallel Processing Letters, Vol. 11, Nos. 2 & 3 (2001) 187-202 World Scientific Publishing Company
• Linear Algebra on High Performance Computers JJ. Dongarra and D.C. Sorensen
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2005; 17:235257
• A Software Tool for Accurate Estimation of Parameters of
• Performance of Various bompuacrs U~,~ ~~c.~ Linear Equations So/tv:ar'ein a Fortre.n [i]nvironm ant
• Computer Physics Communications 180 (2009) 25262533 Contents lists available at ScienceDirect
• J. Parallel Distrib. Comput. 69 (2009) 410416 Contents lists available at ScienceDirect
• Visual Programming and Debugging for Parallel .
• J. Parallel Distrib. Comput. 64 (2004) 774783 GrADSolve--a grid-based RPC system for parallel computing with
• NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS Numer. Linear Algebra Appl. (2008)
• A Class of Hybrid LAPACK Algorithms for Multicore and GPU Architectures Mitch Horton, Stanimire Tomov and Jack Dongarra
• Dynamic Reconfiguration and Virtual Machine Management in the Harness Metacomputing System
• Static Tiling for Heterogeneous Computing Platforms Pierre Boulet 1 , Jack Dongarra 2;3 , Yves Robert 4 and Fr ed eric Vivien 5
• Software Reuse in High Performance Computing Shirley Browne
• Parallelizing the Divide and Conquer Algorithm
• Parallel Processing Letters, Vol. 17, No. 1 (2007) 47-59 %%k. ... _, ~ ** ,, ,, , ., ,, . x.c ,, ,.. .. ,, v
• A Scalable Approach to MPI Application Performance Analysis
• JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 1, 22-31 (1984) Multiprocessing Linear Algebra Algorithms on the
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2008; 20:15731590
• Impact of Kernel-Assisted MPI Communication over Scientific Applications: CPMD and FFTW
• Network-enabled Solvers: A Step Toward Grid-based December 13, 2001
• Optimizing matrix multiplication for a short-vector SIMD architecture CELL processor
• Recursive approach in sparse matrix LU factorization
• From CUDA to OpenCL: Towards a Performance-portable Solution for Multi-platform GPU Programming$,$$
• DOI: 10.1007/s10766-005-3584-4 International Journal of Parallel Programming, Vol. 33, Nos. 2/3, June 2005 ( 2005)
• Implementing Matrix Factorizations on the Cell B. E.
• The marketplace of high-performance computing Erich Strohmaiera,*, Jack J. Dongarraa,b
• A Comprehensive Study of Task Coalescing for Selecting Parallelism Granularity in a Two-Stage Bidiagonal Reduction
• Achieving Numerical Accuracy and High Performance using Recursive Tile LU Factorization
• Integrated Tool Capabilities for Performance Instrumentation and Measurement
• ELSEVIER Parallel Computing 21(1995) 1387-1405 Parallel matrix transpose algorithms
• Future Generation Computer Systems 22 (2006) 279290 An asynchronous algorithm on the NetSolve global
• Hybrid Multicore Cholesky Factorization with Multiple GPU Accelerators
• OMPIO: A Modular Software Architecture for Mohamad Chaarawi1
• Acta Numerica (2012), pp. 001 c Cambridge University Press, 2012 doi:10.1017/S09624929 Printed in the United Kingdom
• JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 43, 125138 (1997) ARTICLE NO. PC971336
• Self-adapting Numerical Software and Automatic Tuning of Jack Dongarra, Victor Eijkhout
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2007; 19:13711385
• An Implementation of the Tile QR Factorization for a GPU and Multiple CPUs
• April 20, 2011 17:0 9in x 6in b1189-ch11 Solving the Schrodinger Equation 1st Reading Chapter 111
• DAGuE: A generic distributed DAG engine for high performance computing
• Dense Linear Algebra for Hybrid GPU-Based Systems
• Overlapping Computation and Communication for Advection on
• LU Factorization for Accelerator-based Systems Emmanuel Agullo, Cedric Augonnet, Jack Dongarra, Mathieu Faverge,
• Redesigning the Message Logging Model for High Performance Aurelien Bouteiller, George Bosilca, Jack Dongarra
• NanoPSE: Nanoscience Problem Solving Environment for atomistic electronic structure of semiconductor nanostructures
• Computer Physics Communications 180 (2009) 25262533 Contents lists available at ScienceDirect
• COMPUTATIONAL AND APPLIEDMATHEMATICS
• High Performance Dense Linear System Solver with Soft Error Resilience
• ALGORITHM 589 SlCEDR: A FORTRAN Subroutine
• The Netlib Mathematical Software Repository
• and candor rarely encountered in a sin-gle work, the authors describe an evo-
• Self-adapting software for numerical linear algebra and LAPACK for clusters q
• Scientific Programming 17 (2009) 3142 31 DOI 10.3233/SPR-2009-0268
• CONCURRENCY: PRACTICE AND EXPERIENCE Concurrency: Pract. Exper., Vol. 10(1113), 11171129 (1998)
• Hash functions for datatype signatures in MPI Julien Langou, George Bosilca, Graham Fagg, and Jack Dongarra
• Parallel Computing 3 (1986) 25-34 25 North-Holland
• from SIAM News, Volume 34, Number 9 Biannual Top-500 Computer Lists Track Changing Environments
• Evaluation of the HPC Challenge Benchmarks in Virtualized Environments
• Correlated Set Coordination in Fault Tolerant Message Logging Protocols
• Future Generation Computer Systems 15 (1999) 745755 Deploying fault tolerance and taks migration with NetSolve
• J. Parallel Distrib. Comput. 64 (2004) 774783 GrADSolve--a grid-based RPC system for parallel computing with
• Software Distribution Using Xnetlib JACK DONGARRA
• ne petaflop per second is a rate of computation corresponding to 1015
• An iterative solver benchmark1 Jack Dongarra, Victor Eijkhout and
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2005; 17:235257
• Trace-based performance analysis for the petascale simulation code
• High Performance Development for High End Computing with Python Language Wrapper (PLW)
• Scheduling Linear Algebra Operations on Multicore Processors LAPACK Working Note 213
• http://hpc.sagepub.com/ Computing Applications
• Journal of Parallel and Distributed Computing 58, 68 91 (1999) Stochastic Performance Prediction for Iterative
• Recent trends in the marketplace of high performance computing
• Implementing Matrix Multiplication on the Cell B. E.
• A Proposal [or an ExLcndcd Set of IrorLran Basic Linear Algebra Subprograms
• A Software Tool for Accurate Estimation of Parameters of
• CONCURRENCYPRACTICE AND EXPERIENCE, VOL.8(7), 517-535 (SEPTEMBER 1996) PB-BLAS: A set of parallel block basic linear
• High Performance Bidiagonal Reduction using Tile Algorithms on Homogeneous Multicore Architectures
• Optimizing Symmetric Dense Matrix-Vector Multiplication Computer Science and
• ELSEVIER Parallel Computing 23 (1997) 49-70 Key concepts for parallel out-of-core LU
• Centre de recherche INRIA Bordeaux Sud Ouest Domaine Universitaire -351, cours de la Libration 33405 Talence Cedex
• HierKNEM: An Adaptive Framework for Kernel-Assisted and Topology-Aware Collective Communications on Many-core Clusters
• Hierarchical QR factorization algorithms for multi-core cluster systems
• DAGuE: A generic distributed DAG engine for high performance computing
• List of Figures 1.1 The software stack of PLASMA, Version 2.3. . . . . . . . . . 4
• Middleware for the use of storage in communication q
• Scalability Analysis of the SPEC OpenMP Benchmarks on Large-Scale Shared Memory
• Rectangular Full Packed Format for Cholesky's Algorithm: Factorization,
• Creating Software Technology to Harness the Power of Leadership-class Computing Systems
• Linear Algebra on High Performance Computers JJ. Dongarra and D.C. Sorensen
• Visual Programming and Debugging for Parallel .
• http://hpc.sagepub.com/ Computing Applications
• Performance of Various bompuacrs U~,~ ~~c.~ Linear Equations So/tv:ar'ein a Fortre.n [i]nvironm ant
• TransparentCross-PlatformAccessto
• SIAM J. ScI. STAT. COMPUT. Vol. 4, No. 4, December 1983
• INTERACTIVE GRID-ACCESS USING GRIDSOLVE AND K. Seymour,1
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2002; 14:14451456 (DOI: 10.1002/cpe.670)
• An Improved Magma Gemm For Fermi Graphics Processing Units
• Faster, Cheaper, Better a Hybridization Methodology to Develop Linear Algebra Software
• http://hpc.sagepub.com/ Computing Applications
• Numerical Algorithms 10(1995)379-399 379 of a parallel dense linear algebra software
• JOURNAL OF COMPUTATIONAL PHYSICS 54, 278-288 (1984) Solving the Secular Equation Including Spin Orbit Coupling
• A Comparison of Search Heuristics for Empirical Code Optimization
• Parallel Processing Letters, Vol. 11, Nos. 2 & 3 (2001) 187-202 World Scientific Publishing Company
• Journal of Computational and Applied Mathematics 123 (2000) 489514 www.elsevier.nl/locate/cam
• SIAM J. NUMER. ANAL. Vol. 20, No. 1, February 1983
• Reducing the Amount of Pivoting in Symmetric Indefinite Systems
• Algorithm-Based Fault Tolerance for Fail-Stop Failures
• http://hpc.sagepub.com/ Computing Applications
• Scientific Programming 18 (2010) 3550 35 DOI 10.3233/SPR-2010-0297
• Highly Scalable Self-Healing Algorithms for High Performance Scientific Computing
• SOFTWARE-PRACTICE AND EXPERIENCE, VOL. 9, 219-226 (1979) Unrolling Loops in FORTRAN*
• http://hpc.sagepub.com/ Computing Applications
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2010; 22:21962211
• Cluster Comput (2009) 12: 101122 DOI 10.1007/s10586-009-0080-4
• Jack Dongarra A Historical Overview and
• Automated empirical optimizations of software and the ATLAS project q
• http://hpc.sagepub.com/ Computing Applications
• THE SPECTRAL DECOMPOSITION OF NONSYMMETRIC MATRICES ON DISTRIBUTED MEMORY PARALLEL COMPUTERS
• Reliability and Performance Modeling and Analysis for Grid Computing
• The Eigenvalue Problem for Hermitian Matrices with Time Reversal Symmetry
• ParallelComputingI (1984) 133-142 133 North-Holland
• http://hpc.sagepub.com/ Computing Applications
• Review: [untitled] Author(s): Jack Dongarra
• A COMPARISON OF PARALLEL SOLVERS FOR DIAGONALLY DOMINANT AND GENERAL NARROW-BANDED LINEAR
• National HPCC Software Exchange Shirley Browne, Jack Dongarra, Stan Green,
• Solving Systems of Linear Equations on the CELL Processor Using Cholesky Factorization
• SOFTWARE LIBRARIES FOR LINEAR ALGEBRA COMPUTATIONS ON HIGH PERFORMANCE COMPUTERS
• Future Generation Computer Systems 18 (2002) 11271142 HARNESS fault tolerant MPI design, usage
• On Scalability for MPI Runtime Systems George Bosilca
• SIAM REVIEW Vol. 26, No. 1, January, 1984
• Accelerating linear system solutions using randomization techniques
• When we try to assess how much progress we have made in computational modeling and simulation, recalling some history
• Determining the Idle Time of a Tiling: New Results Fr ed eric Desprez1, Jack Dongarra2;3, Fabrice Rastello1 and Yves Robert2
• Implementation of the HPC Challenge
• Dense Linear Algebra on Distributed Heterogeneous Hardware with a Symbolic DAG
• NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS Numer. Linear Algebra Appl. (2008)
• from SIAM News, Volume 32, Number 6 Atlanta Organizers Put Mathematics to Work
• Static tiling for heterogeneous computing platforms 1
• Block-asynchronous Multigrid Smoothers for GPU-accelerated Systems
• Self Adapting Numerical Software (SANS) Effort George Bosilca, Zizhong Chen, Jack Dongarra, Victor Eijkhout, Graham E. Fagg,
• The TOP500 and Computational Science A not-so-simple matter of software
• ~" NUMERICAL MATHEMATICS
• Programming the LU Factorization for a Multicore System with Accelerators
• Using agent-based software for scientic computing in the NetSolve system
• TOP500 Supercomputer Sites Jack J. Dongarra
• 192 IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, VOL. 9, NO. 2, FEBRUARY 1998 Scheduling Block-Cyclic Array Redistribution
• Parallel Reduction to Condensed Forms for Symmetric Eigenvalue Problems using Aggregated Fine-Grained and
• A Parallel Divide and Conquer Algorithm for the Symmetric Eigenvalue
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2010; 22:24672487
• High-performance high-resolution semi-Lagrangian tracer transport on a sphere
• A PARALLEL IMPLEMENTATION OF THE NONSYMMETRIC QR ALGORITHM FOR DISTRIBUTED MEMORY ARCHITECTURES
• http://hpc.sagepub.com/ Computing Applications
• Conjugate-Gradient Eigenvalue Solvers in Computing Electronic Properties of
• CTWatch Quarterly The Impact of Multicore on Computational Scienc... http://www.ctwatch.org/quarterly/print.php?p=67 1 of 8 2/28/2007 4:31 PM
• Applying Netsolve's Network-Enabled Server
• Future Generation Computer Systems 21 (2005) 980986 Biological sequence alignment on the computational
• Self-Adapting Linear Algebra Algorithms and Software
• Revisiting Matrix Product on Master-Worker Platforms Jack Dongarra2
• Squeezing the Most out of Eigenvalue Solvers on High-Performance Computers
• MARCH/APRIL 2005 Copublished by the IEEE CS and the AIP 1521-9615/05/$20.00 2005 IEEE 51 PERSPECTIVESP E R S P E C T I V E S I N C O M P U TAT I O N A L S C I E N C E
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2010; 22:1544
• Predicting the electronic properties of 3D, million-atom semiconductor nanostructure architectures
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2003; 15:207222 (DOI: 10.1002/cpe.657)
• CONCURRENCY: PRACTICE AND EXPERIENCE Concurrency: Pract. Exper. 2000; 12:14811493
• CONCURRENCY: PRACTICE AND EXPERIENCE, VOL. 9(10), 915926 (OCTOBER 1997) Message-passing performance of various
• PERFORMANCE STUDY OF LU FACTORIZATION WITH LOW COMMUNICATION OVERHEAD ON MULTIPROCESSORS
• Logistical quality of service in NetSolve , H. Casanovaa
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2002; 14:14571479 (DOI: 10.1002/cpe.678)
• MPI: A Message-Passing Interface Standard Message Passing Interface Forum
• http://hpc.sagepub.com/ Computing Applications
• Future Generation Computer Systems 26 (2010) 479485 Contents lists available at ScienceDirect
• Practical Experience in the Numerical Dangers of Heterogeneous Computing
• http://hpc.sagepub.com/ Computing Applications
• EL`SVIER Future Generation Computer Systems 12 (1997) 461-474 Changing technologies of HPC
• JLAPACK compiling LAPACK FORTRAN David M. Doolin a, Jack Dongarra b,c,
• UT-CS-01-460 April 28, 2001
• Exploiting Fine-Grain Parallelism in Recursive LU Factorization1
• 3 Empirical Performance Tuning of Dense Linear Algebra Soft-Jack Dongarra and Shirley Moore
• Automated Empirical Optimizations of Software and the ATLAS project
• Scanning the Issue Special Issue on Program Generation, Optimization, and
• High Performance Matrix Inversion Based on LU Factorization for Multicore Architectures
• 84 July 1996/Vol. 39, No. 7 COMMUNICATIONS OF THE ACM HE Message Passing Interface
• Performance Portability of a GPU Enabled Factorization with the DAGuE George Bosilca, Aurelien Bouteiller, Thomas Herault, Pierre Lemarinier,
• Enhancing Parallelism of Tile Bidiagonal Transformation on Multicore Architectures using Tree
• BLAS for GPUs Department of Electrical Engineering and Computer Science, University of
• Jack Dongarra Universityof Tennessee,Knoxville
• An Updated Set of Basic Linear Algebra Subprograms (BLAS)
• Flexible Development of Dense Linear Algebra Algorithms on Massively Parallel Architectures with DPLASMA
• Future Generation Computer Systems 22 (2006) 665675 www.elsevier.com/locate/fgcs
• Towards Dense Linear Algebra for Hybrid GPU Accelerated Manycore Systems
• Solving the Generalized Symmetric Eigenvalue Problem using Tile
• Editor: Michael A. Gray, gray@american.edu 84 Copublished by the IEEE CS and the AIP 1521-9615/08/$25.00 2008 IEEE Computing in SCienCe & engineering
• Self-adapting Numerical Software for Next Generation Applications
• Scalable Runtime for MPI: Efficiently Building the Communication Infrastructure
• ELSEVIER Parallel Computing 210995) 1189-1211 A parallel algorithm for the reduction of a nonsymmetric
• PVMPI: An Integration of the PVM and MPI Systems Graham E. Fagg
• Automatic Experimental Analysis of Communication Patterns in Virtual Topologies
• http://hpc.sagepub.com/ Computing Applications
• Autotuning GEMMs for Fermi Jakub Kurzak
• Future Generation Computer Systems 27 (2011) 357369 Contents lists available at ScienceDirect
• SIAM J. MATRIX ANAL. APPL. c 2005 Society for Industrial and Applied Mathematics Vol. 27, No. 3, pp. 603620
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2003; 15:803820 (DOI: 10.1002/cpe.728)
• http://hpc.sagepub.com/ Computing Applications
• Using Mixed Precision for Sparse Matrix Computations to Enhance the Performance
• http://hpc.sagepub.com/ Computing Applications
• A Comparison of Parallel Solvers for Diagonally Dominant and General Narrow-Banded Linear
• HARNESS Fault Tolerant MPI design, usage and performance issues
• QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators Emmanuel Agullo, Cedric Augonnet, Jack Dongarra, Mathieu Faverge,
• DOI: 10.1007/s10766-005-3577-3 International Journal of Parallel Programming, Vol. 33, No. 2, June 2005 ( 2005)
• Two-Stage Tridiagonal Reduction for Dense Symmetric Matrices using Tile Algorithms on Multicore Architectures
• TOWARD HIGH PERFORMANCE DIVIDE AND CONQUER EIGENSOLVER FOR DENSE SYMMETRIC MATRICES
• CONCURRENCY: PRACTICE AND EXPERIENCE, VOL. 9(11), 12791291 (NOVEMBER 1997) Java access to numerical libraries
• State-of-the-art eigensolvers for electronic structure calculations of large scale nano-systems q
• banner above paper title From Serial Loops to Parallel Execution
• ParallelComputingI (1984)223-235 223 North-Holland
• Supporting Heterogeneous Network Computing: Jack J. Dongarra
• Algorithmic Redistribution Methods for Block-Cyclic Decompositions
• SIAM J. ScI. COMPUT. Vol. 14, No. 3, pp. 542-569, May 1993
• Towards dense linear algebra for hybrid GPU accelerated manycore systems Stanimire Tomov a,*, Jack Dongarra a,b,c
• Algorithm-based Fault Tolerance for Dense Matrix Factorizations
• Soft Error Resilient QR Factorization for Hybrid System with GPGPU
• CONCURRENCY: PRACTICE AND EXPERIENCE Concurrency: Pract. Exper., Vol. 11(3), 139153 (1999)
• J. Parallel Distrib. Comput. 69 (2009) 410416 Contents lists available at ScienceDirect
• SIAM J. ScI. STAT. COMPUT. Vol. 7, No. 1, January 1986
• Noname manuscript No. (will be inserted by the editor)
• Twenty-Plus Years of Netlib and NA-Net Jack Dongarra, Gene Golub, Eric Grosse, Cleve Moler, Keith Moore
• http://hpc.sagepub.com/ Computing Applications
• Netlib and NA-Net: Building A Scientific Computing Community Jack Dongarra
• T h e F i r s t W o r d Copublished by the IEEE CS and the AIP 1521-9615/08/$25.00 2008 IEEE Computing in SCienCe & engineering
• A Class of Hybrid LAPACK Algorithms for Multicore and GPU Architectures Mitch Horton, Stanimire Tomov and Jack Dongarra
• Level-3 Cholesky Factorization Routines as Part of Many Cholesky Algorithms
• Integrated PVM Framework Supports Heterogeneous Network Computing
• Fast and Small Short Vector SIMD Matrix Multiplication Kernels for the Synergistic Processing Element of the CELL Processor
• Access 02 Summer 2005 Access 03 Summer 2005
• Hamparsum Bozdogan Statistical Data Mining, and
• The use of bulk states to accelerate the band edge state calculation of a semiconductor quantum dot q
• CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2007; 19:14811496
• DOI: 10.1007/s10766-005-3577-3 International Journal of Parallel Programming, Vol. 33, Nos. 2/3, June 2005 ( 2005)
• 90 Copublished by the IEEE CS and the AIP 1521-9615/11/$26.00 2011 IEEE Computing in SCienCe & engineering N o v E l A r C h I t E C t u r E S
• Squeezing the Most out of an Algorithm in CRAY FORTRAN
• Parallel Two-Sided Matrix Reduction to Band Bidiagonal Form on Multicore Architectures
• Journal of Parallel and Distributed Computing 61, 1803 1826 (2001) Telescoping Languages: A Strategy for Automatic
• HARNESS and fault tolerant MPI Graham E. Fagg *, Antonin Bukovsky, Jack J. Dongarra
• http://hpc.sagepub.com/ Computing Applications
• Scalable Fault Tolerant MPI: Extending the recovery algorithm
• EXPERIENCES WITH WINDOWS 95 NT AS A CLUSTER COMPUTING PLATFORM FOR PARALLEL COMPUTING.
• A Class of Parallel Tiled Linear Algebra Algorithms for Multicore Architectures
• ATLAS on the BlueGene/L Preliminary Results Keith Seymour Haihang You Jack Dongarra
• Recovery Patterns for Iterative Methods in a Parallel Unstable Environment
• Future Generation Computer Systems 15 (1999) 595605 Scalable networked information processing environment (SNIPE)
• A parallel tiled solver for dense symmetric indefinite systems on multicore architectures
• TOP500 Supercomputer Sites 10th Edition
• D-Lib Magazine ISSN 1082-9873
• Accelerating the reduction to upper Hessenberg form through hybrid GPU-based computing
• Future Generation Computer Systems 15 (1999) 571582 HARNESS: a next generation distributed virtual machine
• Accelerating TIME-TO-SOLUTION for Computational