Issue No. 02 - March (1992 vol. 3)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/71.127258
Presents the hierarchical task graph (HTG) as an intermediate parallel program representation which encapsulates minimal data and control dependences, and which can be used for the extraction and exploitation of functional, or task-level parallelism. The hierarchical nature of the HTG facilitates efficient task-granularity control during codegeneration, and thus applicability to a variety of parallel architectures. The construction of the HTG at a given hierarchy level, the derivation of the execution conditions of tasks which maximizes task-level parallelism, and the optimization of these conditions which results in reducing synchronization overhead imposed by data and control dependences are emphasized. Algorithms for the formation of tasks and their execution conditions based on data and control dependence constraints are presented. The issue ofoptimization of such conditions is discussed, and optimization algorithms are proposed. The HTG is used as the intermediate representation of parallel Fortran and C programs for generating parallel source as well as parallel machine code.
Index Termsoverhead messages; acyclic systems; closed queuing networks; open cyclic queuingnetworks; distributed simulation algorithms; digital simulation; distributed processing;performance evaluation; programming theory; queueing theory
C. Polychronopoulos and M. Girkar, "Automatic Extraction of Functional Parallelism from Ordinary Programs," in IEEE Transactions on Parallel & Distributed Systems, vol. 3, no. , pp. 166-178, 1992.