Supporting structured parallel program design, development and tuning in FastFlow

The design and tuning of parallel programs is known to be a hard and error-prone process. Structured parallel programming helps overcoming part of the related problems by properly and carefully ensuring separation of concerns in between application and system programmers. In this work, we describe the design and the implementation of ff-RPL, a shell supporting structured parallel programming development in FastFlow. The shell provides ways to explore the space of functionally equivalent, alternative parallel implementations of the same application with different non functional properties. It also provides ways to tune and optimize existing parallel applications standalone or while targeting particular hardware architectures. The tool is entirely written in C++. It has been designed in such a way it can be easily extended to take into account new non functional features, refactoring and optimization rules, as well as different parallel patterns. Experimental results are shown validating the general ff-RPL design as well as its FastFlow code generation features.