A Runtime Approach to Dynamic Resource Allocation for Sparse Direct Solvers

To face the advent of multicore processors and the ever increasing complexity of hardware architectures, programming models based on DAG-of-tasks parallelism regained popularity in the high performance, scientific computing community. In this context, enabling HPC applications to perform efficiently...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the International Conference on Parallel Processing s. 481 - 490
Hlavní autoři: Hugo, Andra-Ecaterina, Guermouche, Abdou, Wacrenier, Pierre-Andre, Namyst, Raymond
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2014
Témata:
Composability
Context
Dynamic scheduling
Processor scheduling
Program processors
Ressource allocation
Runtime
Sparse direct solver
Sparse matrices
Virtual machine monitors
ISSN:0190-3918
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To face the advent of multicore processors and the ever increasing complexity of hardware architectures, programming models based on DAG-of-tasks parallelism regained popularity in the high performance, scientific computing community. In this context, enabling HPC applications to perform efficiently when dealing with graphs of parallel tasks that could potentially run simultaneously is a great challenge. Even if a uniform runtime system is used underneath, scheduling multiple parallel tasks over the same set of hardware resources introduces many issues, such as undesirable cache flushes or memory bus contention. In this paper, we show how runtime system-based scheduling contexts can be used to dynamically enforce locality of parallel tasks on multicore machines. We extend an existing generic sparse direct solver to use our mechanism and introduce a new decomposition method based on proportional mapping that is used to build the scheduling contexts. We propose a runtime-level dynamic context management policy to cope with the very irregular behaviour of the application. A detailed performance analysis shows significant performance improvements of the solver over various multicore hardware.
ISSN:0190-3918
DOI:10.1109/ICPP.2014.57