Processor Tagged Descriptors: A Data Structure for Compiling for Distributed-Memory Multicomputers

The computation partitioning, communication analysis, and optimization phases performed during compilation for distributed-memory multicomputers require an eecient way of describing distributed sets of iterations and regions of data. Processor Tagged Descriptors (PTDs) provide these capabilities through a single set representation parameterized by the processor location for each dimension of a virtual mesh. A uniform representation is maintained for every processor in the mesh, whether it is a boundary or an interior node. As a result, operations on the sets are very eecient because the eeect on all processors in a dimension can be captured in a single symbolic operation. In addition, PTDs are easily extended to an arbitrary number of dimensions, necessary for describing iteration sets in multiply nested loops as well as sections of multidimensional arrays. Using the symbolic features of PTDs it is also possible to generate code for variable numbers of processors, thereby allowing a compiled program to run unchanged on varying sized machines. The PARADIGM (PARAllelizing compiler for DIstributed-memory General-purpose Multicomputers) project at the University of Illinois utilizes PTDs to provide an automated means to parallelize serial programs for execution on distributed-memory multicomputers.