08.01.2018
Hybrid work stealing of locality-flexible and cancelable tasks for the APGAS library
Erschienen in: The Journal of Supercomputing | Ausgabe 4/2018
EinloggenAktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
asyncAny
construct. These tasks are transparently mapped to any resource in the overall system, so that the load is balanced over both nodes and cores. Unprocessed asyncAny
-tasks can also be cancelled. In performance measurements with up to 144 workers on up to 12 nodes, we observed near linear speedups for four benchmarks and a low overhead for cancellation-related bookkeeping.