October 15, 2009
ReLooper: Refactoring for Loop ParallelismAn Eclipse-based refactoring tool that performs tasks automatically.
In the multicore era, sequential programs need to be refactored for parallelism. The next version of Java provides ParallelArray, an array data structure that supports parallel operations over the array elements. For example, one can "apply" a procedure to each element, or "reduce" all elements to a new element in parallel.
Refactoring an array to a ParallelArray requires: (a) analyzing whether the loop iterations are safe for parallel execution, and (b) replacing loops with the equivalent parallel operations. When done manually, these tasks are non-trivial and time-consuming.
In this presentation, Danny Dig presents ReLooper, an Eclipse-based refactoring tool, that performs these tasks automatically. Experience with refactoring real programs shows that ReLooper is useful: it reduces the burden of analyzing and rewriting parallel loops, and it is fast enough to be used interactively.
This session, entitled "ReLooper: Refactoring for Loop Parallelism," will be presented via live stream at http://media.cs.uiuc.edu/live/upcrc0910/upcrc1015thx1138.asx on Thursday, October 15, 2009 at 4:00 PM (Central Time).
Danny Dig is a PI at the University of Illinois at Urbana-Champaign, where he leads research on refactorings for parallelism. He got a PhD from Illinois, working on upgrading applications to use the newer APIs of software libraries. Before coming to Illinois he built JavaRefactor, the first open-source refactoring engine for Java.
|
 |
|
|||||||||||||||||||||||||||
|
|
|
