Publication detail

Performance and Accuracy Analysis of Nonlinear k-Wave Simulations Using Local Domain Decomposition with an 8-GPU Server

TREEBY, B. VAVERKA, F. JAROŠ, J.

Original Title

Performance and Accuracy Analysis of Nonlinear k-Wave Simulations Using Local Domain Decomposition with an 8-GPU Server

Type

journal article in Scopus

Language

English

Original Abstract

Large-scale nonlinear ultrasound simulations using the open-source k-Wave toolbox are now routinely performed using the MPI version of k-Wave running on traditional CPU-based clusters. However, the allto-all communications required by the 3D fast Fourier transform (FFT) severely impact performance when scaling to large numbers of compute cores. This can be overcome by using a domain decomposition strategy based on a local Fourier basis. In this work, we analyse the performance and accuracy of using local domain decomposition for running a high-intensity focused ultrasound (HIFU) simulation in the kidney on a single server containing eight NVIDIA P40 graphical processing units (GPUs). Different decompositions and overlap sizes are investigated and compared to a global MPI simulation running on a CPU-based supercomputer using 1280 cores. For a grid size of 960 × 960 × 1280 grid points and an overlap size of 4 grid points, the error in the simulation using local domain decomposition is on the order of 0.1% compared to the global simulation, which is sufficient for most applications. The financial cost for running the simulation is also reduced by more than an order of magnitude.

Keywords

k-Wave, Local domain decomposition, Fourier Basis, pseudospectral methods

Authors

TREEBY, B.; VAVERKA, F.; JAROŠ, J.

Released

22. 10. 2018

ISBN

1939-800X

Periodical

Proceedings of Meetings on Acoustics

Year of study

34

Number

1

State

United States of America

Pages from

1

Pages to

5

Pages count

5

URL

BibTex

@article{BUT155074,
  author="Bradley {Treeby} and Filip {Vaverka} and Jiří {Jaroš}",
  title="Performance and Accuracy Analysis of Nonlinear k-Wave Simulations Using Local Domain Decomposition with an 8-GPU Server",
  journal="Proceedings of Meetings on Acoustics",
  year="2018",
  volume="34",
  number="1",
  pages="1--5",
  doi="10.1121/2.0000883",
  issn="1939-800X",
  url="https://asa.scitation.org/doi/10.1121/2.0000883"
}