Using Software Refactoring to form Parallel Programs: the ParaPhrase Approach


By Erlang Central | Published: May 28, 2012



Despite Moore’s “law”, uniprocessor clock speeds have now stalled. Rather than using single processors running at ever higher clock speeds, it is  common to find dual-, quad- or even hexa-core processors, even in consumer laptops and desktops. Future hardware will not be slightly parallel, however, as in today’s multicore systems, but will be massively parallel, with manycore and perhaps even megacore systems becoming mainstream. This means that programmers need to start thinking parallel from the outset of  their program development rather than treating parallelism as a bolt-on afterthought. This talk introduces the Paraphrase approach to constructing parallel programs, a new approach that uses formally-defined refactoring transformations based around strong parallel patterns and associated skeleton implementations, and directly exploits functional programming concepts. We show how complex parallel programs can be built from primitive Erlang building blocks, and describe some new software refactorings for parallel Erlang programs that capture common parallel abstractions, such as divide-and-conquer and data parallelism, using these building blocks. The ParaPhrase approach is both flexible and scalable, capable of covering both GPU and CPU computations, scaling from multi-core to mega-core processors, and covering a variety of parallel programming paradigms.
Talk Objectives: To give an overview of the ParaPhrase project and to show how we can parallelise Erlang programs using refactoring and skeletons.
Target Audience: Anyone who is interested in refactoring and/or parallelism.
Download Presentation Download

Speakers:

  • Chris Brown

    Research Fellow working on the ParaPhrase project and refactoring guru
    University of St Andrews

    Chris Brown is a Post-Doctoral Research Fellow at the University of St Andrews working in the area of Refactoring and Parallelism. Chris received his Ph.D. from the University of Kent in 2008 under the supervision of Simon Thompson, where he worked on the implementation of the HaRe refactoring tool for Haskell. Chris now works full time on the ParaPhrase project working towards building radically new refactoring techniques and methodologies to exploit parallel skeleton and pattern applications in both the functional and imperative domains. Chris has published at major conferences in the field of functional programming and refactoring. Chris is a keen classical guitarist in his spare time, specialising in early, baroque and classical repertoires.

    Chris Brown
  • Kevin Hammond

    Professor in Computer Science
    University of St Andrews,

    Kevin Hammond is a full professor of Computer Science at the University of St Andrews, where he leads the functional programming research group. His research interests lie in programming language design and implementation, with a focus > on parallelism and real=time properties of functional languages, including modelling and reasoning about extra-functional properties. In total, he has published around 100 research papers, books and articles, and held over 20 national and international > research grants, totalling around £11M of research funding. He was a member of the Haskell design committee, co-designed the Hume real-time functional language, and is co-editor of the main reference text on parallel functional programming. > He currently coordinates the ParaPhrase project, a 3-year EU research project that aims to develop new refactoring technology for Erlang and C++ programs, targeting heterogeneous parallel architectures. > Kevin is a keen hill-walker, whisky connoisseur and enjoys early music. > >

    Kevin Hammond