Parallel Sn Sweeps on Unstructured Grids: Algorithms for Prioritization, Grid Partitioning, and Cycle Detection

The method of discrete ordinates is commonly used to solve the Boltzmann transport equation. The solution in each ordinate direction is most efficiently computed by sweeping the radiation flux across the computational grid. For unstructured grids this poses many challenges, particularly when impleme...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Nuclear science and engineering Ročník 150; číslo 3; s. 267 - 283
Hlavní autoři:	Plimpton, Steven J., Hendrickson, Bruce, Burns, Shawn P., McLendon, William, Rauchwerger, Lawrence
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Taylor & Francis 01.07.2005
ISSN:	0029-5639, 1943-748X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	The method of discrete ordinates is commonly used to solve the Boltzmann transport equation. The solution in each ordinate direction is most efficiently computed by sweeping the radiation flux across the computational grid. For unstructured grids this poses many challenges, particularly when implemented on distributed-memory parallel machines where the grid geometry is spread across processors. We present several algorithms relevant to this approach: (a) an asynchronous message-passing algorithm that performs sweeps simultaneously in multiple ordinate directions, (b) a simple geometric heuristic to prioritize the computational tasks that a processor works on, (c) a partitioning algorithm that creates columnar-style decompositions for unstructured grids, and (d) an algorithm for detecting and eliminating cycles that sometimes exist in unstructured grids and can prevent sweeps from successfully completing. Algorithms (a) and (d) are fully parallel; algorithms (b) and (c) can be used in conjunction with (a) to achieve higher parallel efficiencies. We describe our message-passing implementations of these algorithms within a radiation transport package. Performance and scalability results are given for unstructured grids with up to 3 million elements (500 million unknowns) running on thousands of processors of Sandia National Laboratories' Intel Tflops machine and DEC-Alpha CPlant cluster.
ISSN:	0029-5639 1943-748X
DOI:	10.13182/NSE150-267