PetClaw: A scalable parallel nonlinear wave propagation solver for Python

Amal Alghamdi, Aron Ahmadia, David I. Ketcheson, Matthew Knepley, Kyle Mandli, Lisandro Dalcin

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We present PetClaw, a scalable distributed-memory solver for time-dependent nonlinear wave propagation. PetClaw unifies two well-known scientific computing packages, Clawpack and PETSc, using Python interfaces into both. We rely on Clawpack to provide the infrastructure and kernels for time-dependent nonlinear wave propagation. Similarly, we rely on PETSc to manage distributed data arrays and the communication between them.We describe both the implementation and performance of PetClaw as well as our challenges and accomplishments in scaling a Python-based code to tens of thousands of cores on the BlueGene/P architecture. The capabilities of PetClaw are demonstrated through application to a novel problem involving elastic waves in a heterogeneous medium. Very finely resolved simulations are used to demonstrate the suppression of shock formation in this system.
    Original languageEnglish (US)
    Title of host publicationProceedings of the High Performance Computing Symposium 2011
    Publisher19th High Performance Computing Symposium (HPC 2011)
    StatePublished - 2011

    Bibliographical note

    KAUST Repository Item: Exported on 2020-10-01

    Fingerprint Dive into the research topics of 'PetClaw: A scalable parallel nonlinear wave propagation solver for Python'. Together they form a unique fingerprint.

    Cite this