On deriving data parallel code from a functional program

We discuss a translation methodology for transforming a high level algorithmic speciication written in Alpha to an imperative data parallel language. We informally introduce the Alpha language with the aid of an example and explain how it is adapted for doing static analysis and transformation. An Alpha program can be naively compiled 11] using applicative caching. Our compilation method makes incremen-tal transformations on the abstract syntax tree of an Alpha program in order to make eeciency and performance improvements over the naive code and optimize it for a given architecture. The compilation steps described include scheduling, alignment, partitioning, allocation, loop nest generation, and code generation and they are illustrated with an example.