Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques (2011)
Galveston, Texas USA
Oct. 10, 2011 to Oct. 14, 2011
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/PACT.2011.44
The popularity of serial execution paradigms in the High Performance Computing (HPC) field greatly hinders the ability of computational scientists to develop and support massively parallel programs. Programmers are left with languages that are inadequate to express parallel constructs, being forced to take decisions that are not directly related to the programs they write. Computer architects are forced to support sequential memory semantics only because serial languages require them and operating system designers are forced to support slow synchronization operations. This poster addresses the development and execution of HPC programs in many-core architectures by introducing the Time Iterated Dependency Flow (Tide Flow) execution model.
Dataflow, Dynamic dataflow, Macro dataflow, Parallel execution model, Parallel Runtime Systems, Task Management, Tasking framework, Manycore, Cyclops-64
Daniel Orozco, "TIDeFlow: A Parallel Execution Model for High Performance Computing Programs", Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques, vol. 00, no. , pp. 211, 2011, doi:10.1109/PACT.2011.44