You are here: Home ParaPhrase Tools

ParaPhrase Tools

Here is the list of Tools generated in Paraphrase. Deliverable D7-3 provides an overview of all the user manuals and other useful references for downloading, installing, configuring and the ParaPhrase technologies.
FastFlow skeleton framework
FastFlow is a C++, open-source, structured parallel programming framework originally conceived to support highly efficient stream parallel computation while targeting shared memory multi-core. It chiefly supports streaming and data parallelism, targeting heterogeneous platforms composed of clusters of shared-memory platforms, possibly equipped with computing accelerators such as NVidia GPGPUs, Xeon Phi, Tilera TILE64.
Streaming Parallel Skeleton library for Erlang
The Skel library is a collection of algorithmic skeletons that may be used and customised aiming at assisting the programmer in the introduction of parallelism for Erlang programs.
ParaPhrase Refactoring Tool for Erlang (PaRTE)
The ParaPhrase Refactoring Tool for Erlang (PaRTE) [2] is a source-level code refactoring tool from sequential source programs to parallel programs written using the Skel skeleton library. PaRTE is an inter-operable framework that supports the discovery of parallel pattern candidates in Erlang, and provides program shaping refactorings and parallelization refactorings. It makes use of high-level cost models, which allow to predict with reasonable accuracy the parallel performance of the refactored program, enabling programmers to make informed decisions about which refactorings to apply.
FastFlow Performance Enhancement Infrastructure (PEI)
The Performance Enhancement Infrastructure(PEI) is a hardware/software abstraction layer built on FastFlow framework to deliver both static and dynamic mapping, scheduling and load-balancing over heterogeneous multi-core architecture. It produces required system software that can dynamically remap heterogeneous software components to the available CPU/GPU devices based on information provided by the high-level virtualisation interfaces about the extra-functional properties of the software components, on the hardware performance characteristics, and on information that is obtained by monitoring the dynamic system load. The provided system is capable of dealing with components from multiple applications and remapping them to the best available hardware, so ensuring optimal use of the available hardware resources.
Agent-based ParaPhrase platform
The goal of the Agent-based ParaPhrase platform is to help creating highly-concurrent multi-agent systems targeted at massively multicore hardware. Multi-agent system can be designed as patterns, which abstracts of the actual execution model. Then, such high level multi-agent patterns could be mapped to match a specific hardware by using the most adequate execution model for that hardware. In consequence, multi-agent simulations and computations could be easily designed and tested and the same design could then be scaled out along with additional resources to solve harder problems or run bigger simulations.
Machine Learning with Parallel Patterns
Machine Learning with Parallel Patterns
Lapedo Framework for Hybrid Skeletons in Erlang