%0 Generic
%D 2016
%T 2016 Dense Linear Algebra Software Packages Survey
%A Jack Dongarra
%A Jim Demmel
%A Julien Langou
%A Julie Langou
%X The 2016 Dense Linear Algebra Software Packages Survey was administered from January 1st 2016 to April 12 2016. 234 respondents answered the survey. The survey was advertised directly to the Linear Algebra community via our LAPACK/ScaLAPACK forum, NA Digest and we also directly contacted vendors and linear algebra experts. The breakdown of respondents was: 74% researchers or scientists, 25% were Principal Investigators and 25% Software maintainers or System administrators. The goal of the survey was to get the Linear Algebra community opinion and provide input on dense linear algebra software packages, in particular LAPACK, ScaLAPACK, PLASMA and MAGMA. The ultimate purpose of the survey was to improve these libraries to benefit our user community. The survey would allow the team to prioritize the many possible improvements that could be done. We also asked input from users accessing these libraries via 3rd party interfaces, for example MATLAB, Intel’s MKL, Python’s NumPy, AMD's ACML, and many others.
%B University of Tennessee Computer Science Technical Report
%I University of Tennessee
%8 2016-09
%G eng
%0 Journal Article
%J Computer Physics Communications
%D 1996
%T ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers - Design Issues and Performance
%A Jaeyoung Choi
%A Jim Demmel
%A Inderjit Dhillon
%A Jack Dongarra
%A Susan Ostrouchov
%A Antoine Petitet
%A Kendall Stanley
%A David Walker
%A Clint Whaley
%X This paper outlines the content and performance of ScaLAPACK, a collection of mathematical software for linear algebra computations on distributed memory computers. The importance of developing standards for computational and message passing interfaces is discussed. We present the different components and building blocks of ScaLAPACK. This paper outlines the difficulties inherent in producing correct codes for networks of heterogeneous processors. We define a theoretical model of parallel computers dedicated to linear algebra applications: the Distributed Linear Algebra Machine (DLAM). This model provides a convenient framework for developing parallel algorithms and investigating their scalability, performance and programmability. Extensive performance results on various platforms are presented and analyzed with the help of the DLAM. Finally, this paper briefly describes future directions for the ScaLAPACK library and concludes by suggesting alternative approaches to mathematical libraries, explaining how ScaLAPACK could be integrated into efficient and user-friendly distributed systems.
%B Computer Physics Communications
%V 97
%P 1-15
%8 1996-08
%G eng
%N 1-2
%R https://doi.org/10.1016/0010-4655(96)00017-3