Higher Order Flattening

Roman Leshchinskiy, Manuel M. T. Chakravarty and Gabriele Keller

In V. Alexandrov, D. van Albada, P. Sloot, and J. Dongarra, editors, ICCS'06: International Conference on Computational Science (2), pp. 920-928, LNCS 3992. Springer-Verlag, 2006.

Presented at the Third International Workshop on Practical Aspects of High-Level Parallel Programming (PAPP 2006).

Download: gzipped Postscript

We extend the flattening transformation, which turns nested into flat data parallelism, to the full higher-order case, including lambda abstractions and data parallel arrays of functions. Our central observation is that flattening needs to transform the closures used to represent functional values. Thus, we use closure conversion before flattening and introduce array closures to represent arrays of functional values.