The aim of this project is to design and develop PEAK, a multi-layer, multi-target, intelligent programming environment for the efficient solution of numerical problems on a variety of parallel machines. At the highest level, a numerical problem may be formulated in a problem-oriented specification language, using familiar mathematical concepts such as PDEs or ODEs. The system provides a rich set of automatic tools which transform specifications step by step into machine specific Fortran dialects that exploit the inherent parallelism of the given machine. Fortran 90, the new Fortran standard, plays a central role in the environment by serving as a target as well as a source language. We strive to make the program development process as auto...
To formulate data structures suited to numerical problems like selfadapting multilevel algorithms fo...
User supplied knowledge and interaction is a vital component of a toolkit for producing high quality...
It has become common knowledge that parallel programming is needed for scientific applications, part...
To date, programming language research has made several major contributions to the support of high s...
Although it has many flaws by comparison with more modern programming languages, Fortran remains the...
In this paper, we present the first, preliminary results of HPF/Fortran-D language analysis based on...
The peak processing performance of highly parallel computers can be achieved only by advanced progra...
Parallel compilers and programming environments need a high degree of intelligence to cope with the ...
Abstract: Some approaches to choosing parallel features for computing systems are discusse...
78 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2000.In the past decades, the use o...
The definition of High Performance Fortran (HPF) is a significant event in the maturation of paralle...
We present an overview of research at the Center for Research on Parallel Computation designed to pr...
Many programming models for massively parallel machines exist, and each has its advantages and disad...
We present the top-down design of a new system which performs automatic parallelization of numerical...
Over the past few decades, scientific research has grown to rely increasingly on simulation and othe...
To formulate data structures suited to numerical problems like selfadapting multilevel algorithms fo...
User supplied knowledge and interaction is a vital component of a toolkit for producing high quality...
It has become common knowledge that parallel programming is needed for scientific applications, part...
To date, programming language research has made several major contributions to the support of high s...
Although it has many flaws by comparison with more modern programming languages, Fortran remains the...
In this paper, we present the first, preliminary results of HPF/Fortran-D language analysis based on...
The peak processing performance of highly parallel computers can be achieved only by advanced progra...
Parallel compilers and programming environments need a high degree of intelligence to cope with the ...
Abstract: Some approaches to choosing parallel features for computing systems are discusse...
78 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2000.In the past decades, the use o...
The definition of High Performance Fortran (HPF) is a significant event in the maturation of paralle...
We present an overview of research at the Center for Research on Parallel Computation designed to pr...
Many programming models for massively parallel machines exist, and each has its advantages and disad...
We present the top-down design of a new system which performs automatic parallelization of numerical...
Over the past few decades, scientific research has grown to rely increasingly on simulation and othe...
To formulate data structures suited to numerical problems like selfadapting multilevel algorithms fo...
User supplied knowledge and interaction is a vital component of a toolkit for producing high quality...
It has become common knowledge that parallel programming is needed for scientific applications, part...