Our paper “Robust Dynamic Resource Allocation via Probabilistic Task Pruning in Heterogeneous Computing Systems“, that has been accepted in 33rd IEEE International Parallel & Distributed Processing Symposium (IPDPS ’19), in Rio de Janeiro, Brazil, has got nominated for the Best Paper Award in this prestigious conference. The paper is the result of a Master’s thesis done by “James Gentry” at University of Louisiana, Lafayette in 2018. Chavit Denninnart, PhD student at HPCC lab, is another coauthor of the paper.
The paper presents a way to maximize robustness of heterogeneous computing systems via pruning (i.e., defer or drop) tasks with low probability of meeting their deadlines to increase the probability of other tasks meeting their deadlines. In this paper, we first
provide a mathematical model to estimate a task’s probability of meeting its deadline in the presence of task dropping. We then investigate methods for engaging probabilistic dropping and we find thresholds for dropping and deferring. Next, we develop a pruning-aware mapping heuristic and extend it to engender fairness across various task types. We show the cost benefit of using probabilistic pruning in an heterogeneous computing system.
You can find the pre-print of the paper here.