Computer Science – Distributed – Parallel – and Cluster Computing
Scientific paper
2010-12-30
Computer Science
Distributed, Parallel, and Cluster Computing
9 pages, 4 figures
Scientific paper
Task parallelism as employed by the OpenMP task construct or some Intel Threading Building Blocks (TBB) components, although ideal for tackling irregular problems or typical producer/consumer schemes, bears some potential for performance bottlenecks if locality of data access is important, which is typically the case for memory-bound code on ccNUMA systems. We present a thin software layer ameliorates adverse effects of dynamic task distribution by sorting tasks into locality queues, each of which is preferably processed by threads that belong to the same locality domain. Dynamic scheduling is fully preserved inside each domain, and is preferred over possible load imbalance even if nonlocal access is required, making this strategy well-suited for typical multicore-mutisocket systems. The effectiveness of the approach is demonstrated by using a blocked six-point stencil solver as a toy model.
Hager Georg
Wittmann Markus
No associations
LandOfFree
Optimizing ccNUMA locality for task-parallel execution under OpenMP and TBB on multicore-based systems does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Optimizing ccNUMA locality for task-parallel execution under OpenMP and TBB on multicore-based systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimizing ccNUMA locality for task-parallel execution under OpenMP and TBB on multicore-based systems will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-401095