HEATS scheduler profiles heterogeneous nodes for performance and energy, migrates container tasks to optimize user trade-offs, and reports up to 8.5% energy savings with at most 7% runtime overhead in synthetic trace evaluation.
Energy-Aware Data Allocation and Task Scheduling on Heterogeneous Multiprocessor Systems With Time Constraints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HEATS: Heterogeneity- and Energy-Aware Task-based Scheduling
HEATS scheduler profiles heterogeneous nodes for performance and energy, migrates container tasks to optimize user trade-offs, and reports up to 8.5% energy savings with at most 7% runtime overhead in synthetic trace evaluation.