A new series-parallel decomposition algorithm for general DAGs enables task mapping in heterogeneous systems that improves makespan over HEFT variants while running orders of magnitude faster than genetic algorithms or ILPs.
Benchmarking dag scheduling algorithms on scientific workflow instances
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Static task mapping for heterogeneous systems based on series-parallel decompositions
A new series-parallel decomposition algorithm for general DAGs enables task mapping in heterogeneous systems that improves makespan over HEFT variants while running orders of magnitude faster than genetic algorithms or ILPs.