Title :
Cyclo-static multiprocessing model and simulation results
Author_Institution :
Lockheed Eng. & Sci. Co., Hampton, VA
Abstract :
The Algorithm To Architecture Mapping Model (ATAMM) is a scheduling strategy for predictable performance in real-time multiprocessor dataflow architectures. The architecture under consideration consists of either heterogeneous or homogeneous processors and implements dataflow models of real-time applications with a cyclo-static assignment scheme. Terminology is developed for graph partitioning, heterogeneous computing, and assignment classifications. A design methodology is described for partitioning dataflow graphs into blocks of nodes (operations) for the purpose of cyclo-static node-to-processor assignment while satisfying a design objective. A theorem is developed and proved to provide cyclo-static assignment of node blocks and illustrated by simulation results
Keywords :
multiprocessing systems; parallel processing; real-time systems; scheduling; virtual machines; Algorithm To Architecture Mapping Model; assignment classifications; cycle-static assignment scheme; cyclo-static assignment; cyclo-static multiprocessing model; cyclo-static node-to-processor assignment; dataflow graph partitioning; dataflow models; design methodology; graph partitioning; heterogeneous computing; heterogeneous processors; homogeneous processor; node blocks; predictable performance; real-time applications; real-time multiprocessor dataflow architecture; scheduling strategy; simulation; Computer architecture; Data engineering; NASA; Partitioning algorithms; Predictive models; Processor scheduling; Scheduling algorithm; Steady-state; Terminology; Very high speed integrated circuits;
Conference_Titel :
Simulation Symposium, 1994., 27th Annual
Conference_Location :
La Jolla, CA
Print_ISBN :
0-8186-5620-4
DOI :
10.1109/SIMSYM.1994.283107
