EGPGV20: Eurographics Symposium on Parallel Graphics and Visualization

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632899

Browse

Browsing EGPGV20: Eurographics Symposium on Parallel Graphics and Visualization by Subject "Software and its engineering"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Alternative Parameters for On-The-Fly Simplification of MergeTrees
    (The Eurographics Association, 2020) Werner, Kilian; Garth, Christoph; Frey, Steffen and Huang, Jian and Sadlo, Filip
    Topological simplification of merge trees requires a user specified persistence threshold. As this threshold is based on prior domain knowledge and has an unpredictable relation to output size, its use faces challenges in large-data situations like online, distributed or out-of-core scenarios. We propose two alternative parameters, a targeted percentile size reduction and a total output size limit, to increase flexibility in those scenarios.
  • Thumbnail Image
    Item
    Improving Performance of M-to-N Processing and Data Redistribution in In Transit Analysis and Visualization
    (The Eurographics Association, 2020) Loring, Burlen; Wolf, Mathew; Kress, James; Shudler, Sergei; Gu, Junmin; Rizzi, Silvio; Logan, Jeremy; Ferrier, Nicola; Bethel, E. Wes; Frey, Steffen and Huang, Jian and Sadlo, Filip
    In an in transit setting, a parallel data producer, such as a numerical simulation, runs on one set of ranks M, while a data consumer, such as a parallel visualization application, runs on a different set of ranks N: One of the central challenges in this in transit setting is to determine the mapping of data from the set of M producer ranks to the set of N consumer ranks. This is a challenging problem for several reasons, such as the producer and consumer codes potentially having different scaling characteristics and different data models. The resulting mapping from M to N ranks can have a significant impact on aggregate application performance. In this work, we present an approach for performing this M-to-N mapping in a way that has broad applicability across a diversity of data producer and consumer applications. We evaluate its design and performance with a study that runs at high concurrency on a modern HPC platform. By leveraging design characteristics, which facilitate an ''intelligent'' mapping from M-to-N, we observe significant performance gains are possible in terms of several different metrics, including time-to-solution and amount of data moved.