PetClaw: A scalable parallel nonlinear wave propagation solver for Python

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

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 proceeding › Conference 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 language	English (US)
Title of host publication	Proceedings of the High Performance Computing Symposium 2011
Publisher	19th High Performance Computing Symposium (HPC 2011)
State	Published - 2011

Access to Document

https://repository.kaust.edu.sa/bitstream/10754/333645/1/petclaw2011.pdf

Cite this

@inproceedings{70906734228946e58a5d0c31f4d81b3c,

title = "PetClaw: A scalable parallel nonlinear wave propagation solver for Python",

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.",

author = "Amal Alghamdi and Aron Ahmadia and Ketcheson, {David I.} and Matthew Knepley and Kyle Mandli and Lisandro Dalcin",

note = "KAUST Repository Item: Exported on 2020-10-01",

year = "2011",

language = "English (US)",

booktitle = "Proceedings of the High Performance Computing Symposium 2011",

publisher = "19th High Performance Computing Symposium (HPC 2011)",

}

TY - GEN

T1 - PetClaw: A scalable parallel nonlinear wave propagation solver for Python

AU - Alghamdi, Amal

AU - Ahmadia, Aron

AU - Ketcheson, David I.

AU - Knepley, Matthew

AU - Mandli, Kyle

AU - Dalcin, Lisandro

N1 - KAUST Repository Item: Exported on 2020-10-01

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

UR - http://hdl.handle.net/10754/333645

UR - http://numerics.kaust.edu.sa/papers/petclaw2011/petclaw2011.html

M3 - Conference contribution

BT - Proceedings of the High Performance Computing Symposium 2011

PB - 19th High Performance Computing Symposium (HPC 2011)

ER -

PetClaw: A scalable parallel nonlinear wave propagation solver for Python

Abstract

Access to Document

Other files and links

Fingerprint

Cite this