The use of feedback in scheduling parallel computations

This paper discusses the use of run-time feedback for optimizing the execution of parallel computations. Four levels of feedback are distinguished, and the applicability and limitations of each are discussed. A two-part scheduling paradigm known as SEDIA (Static Exploration/Dynamic Instantiation and Activation) that addresses these limitations to perform robust scheduling in the presence of variant run-time behavior is introduced. A key component of this scheduling paradigm is an abstract model of run-rime information fidelity which has evolved from our previous work in the area of Trace Recovery, employing control-theoretic concepts.