Welcome! We are the Parallel Programming Laboratory.

Our goal is to develop technology that improves performance of parallel applications while also improving programmer productivity. We aim to reach a point where, with our freely distributed software base, complex irregular and dynamic applications can (a) be developed quickly and (b) perform scalably on machines with thousands of processors.

Processor virtualization is one of our core techniques: the programmer divides the computation into a large number of entities, which are mapped to the available processors by an intelligent runtime system. This separation of concerns between programmers and the system is key to attaining both our goals together.

Charm++ Case Study: Shared Memory Programming
Modern processors are fast reaching the limits of CPU frequency scaling. In their continued bid to increase performance, chip vendors have now made multicore processors commonplace. However, the means to program these increasingly powerful processors have not yet matured. Traditional languages and frameworks for programming multicore systems either provide very low-level constructs, or a performance model that is not well-matched with the underlying hardware.

In recent work we have explored an alternative to these approaches, namely...