A Unified Tiling Approach for Out-Of-Core Computations

This paper describes a framework by which an out-of-core stencil program written in a data-parallel language can be translated into node programs in a distributed-memory message-passing machine with explicit I/O and communication. We focus on a technique called Data Space Tiling to group data elements into slabs that can t into memories of processors. Methods to choose legal tile shapes under several constraints and deadlock-free scheduling of tiles are investigated. Our approach is uni ed in the sense that it can be applied to both FORALL loops and the loops that involve ow-dependences.