This work describes the development of a Fortran parsing tool, which extracts parallelising information from legacy code. This tool will be used as a front-end parser for an evolutionary algorithm, which evolves sequences of parallel transformations to apply to serial code. As only data dependencies are considered in this process, the parsing tool is required to encapsulate flow dependencies in that information, in a transparent manner, to prevent the evolution of transformations that change the semantic meaning of the original serial code. The techniques employed to handle this constraint, as well as other techniques required for the correct extraction of data dependencies, are described in this work, as well as the choices and practical d...
A significant amount of software research for developing programming environments for distributed--m...
The ParaScope Editor is a new kind of interactive parallel programming tool for developing scientic ...
Abstract: Some approaches to choosing parallel features for computing systems are discusse...
This work describes the development of a Fortran parsing tool, which extracts parallelising informat...
User supplied knowledge and interaction is a vital component of a toolkit for producing high quality...
In recent years, methods for analyzing and parallelizing sequential code using data analysis and loo...
The recent success of vector computers like the Cray-1 and array processors such as those manufactur...
For next generation applications, programmers will be required to adapt to a new style of programmin...
Current parallelizing compilers cannot identify a significant fraction of parallelizable loops becau...
As it is widely known, multi-core computers are broadly used these days, and automatic parallelizati...
Current parallelizing compilers cannot identify a significant fraction of parallelizable loops becau...
The ParaScope Editor is a new kind of interactive parallel programming tool for developing scientifi...
The parallelization of real-world compute intensive Fortran application codes is generally not a tri...
The peak processing performance of highly parallel computers can be achieved only by advanced progra...
Parafrase transforms a FORTRAN code, subroutine by subroutine, into a parallel code for a vector and...
A significant amount of software research for developing programming environments for distributed--m...
The ParaScope Editor is a new kind of interactive parallel programming tool for developing scientic ...
Abstract: Some approaches to choosing parallel features for computing systems are discusse...
This work describes the development of a Fortran parsing tool, which extracts parallelising informat...
User supplied knowledge and interaction is a vital component of a toolkit for producing high quality...
In recent years, methods for analyzing and parallelizing sequential code using data analysis and loo...
The recent success of vector computers like the Cray-1 and array processors such as those manufactur...
For next generation applications, programmers will be required to adapt to a new style of programmin...
Current parallelizing compilers cannot identify a significant fraction of parallelizable loops becau...
As it is widely known, multi-core computers are broadly used these days, and automatic parallelizati...
Current parallelizing compilers cannot identify a significant fraction of parallelizable loops becau...
The ParaScope Editor is a new kind of interactive parallel programming tool for developing scientifi...
The parallelization of real-world compute intensive Fortran application codes is generally not a tri...
The peak processing performance of highly parallel computers can be achieved only by advanced progra...
Parafrase transforms a FORTRAN code, subroutine by subroutine, into a parallel code for a vector and...
A significant amount of software research for developing programming environments for distributed--m...
The ParaScope Editor is a new kind of interactive parallel programming tool for developing scientic ...
Abstract: Some approaches to choosing parallel features for computing systems are discusse...