This thesis is about the development of RPL-Shell, a DSL-based tool aiming to facilitate the design process of structured parallel application development. The tool, written in C++ and intended to be delivered along with the parallel programming framework FastFlow, provides to the designer the possibility to explore a space of functionally equivalent, alternative parallel solutions for structured parallel applications. Starting from a simple parallel expression the user can generate a list of functionally equivalent expressions, change their non-functional parameters by hand or by applying optimizers, modify global environment variables and ask for approximate evaluations of performance measures. Finally the user can pick the "best" solutio...
Languages and tools currently available for the development of parallel applications are difficult t...
Structured parallel programming is recognised as a viable and effective means of tackling parallel p...
Writing applications for high performance computers is a challenging task. Although writing code by ...
The design and tuning of parallel programs is known to be a hard and error-prone process. Structured...
We describe the implementation of ff-RPL, a shell to support structured parallel programming develop...
We describe the implementation of ff-RPL, a shell to support structured parallel programming develop...
AbstractWe introduce a DSL based toolchain supporting the design of parallel applications where para...
We introduce a DSL based toolchain supporting the design of parallel applications where parallelism ...
<p>Parallelising sequential applications is usually a very hard job, due to many different ways in w...
Parallelising sequential applications is usually a very hard job, due to many different ways in whic...
Parallelising sequential applications is usually a very hard job, due to many different ways in whic...
The paper gives an overview on the DSPL programming environment, an integrated approach to automate ...
Abstract. Designing parallel applications is generally experienced as a tedious and diffi-cult task,...
An important challenge in parallel computing is the mapping of parallel algorithms to parallel compu...
Developing complex scientific applications on high performance systems requires both domain knowledg...
Languages and tools currently available for the development of parallel applications are difficult t...
Structured parallel programming is recognised as a viable and effective means of tackling parallel p...
Writing applications for high performance computers is a challenging task. Although writing code by ...
The design and tuning of parallel programs is known to be a hard and error-prone process. Structured...
We describe the implementation of ff-RPL, a shell to support structured parallel programming develop...
We describe the implementation of ff-RPL, a shell to support structured parallel programming develop...
AbstractWe introduce a DSL based toolchain supporting the design of parallel applications where para...
We introduce a DSL based toolchain supporting the design of parallel applications where parallelism ...
<p>Parallelising sequential applications is usually a very hard job, due to many different ways in w...
Parallelising sequential applications is usually a very hard job, due to many different ways in whic...
Parallelising sequential applications is usually a very hard job, due to many different ways in whic...
The paper gives an overview on the DSPL programming environment, an integrated approach to automate ...
Abstract. Designing parallel applications is generally experienced as a tedious and diffi-cult task,...
An important challenge in parallel computing is the mapping of parallel algorithms to parallel compu...
Developing complex scientific applications on high performance systems requires both domain knowledg...
Languages and tools currently available for the development of parallel applications are difficult t...
Structured parallel programming is recognised as a viable and effective means of tackling parallel p...
Writing applications for high performance computers is a challenging task. Although writing code by ...