@inproceedings{d405eaa8ed5e47209312cffb8a289780,
title = "Use of multiple GPUs on shared memory multiprocessors for ultrasound propagation simulations",
abstract = "This paper outlines our effort to migrate a compute intensive application of ultrasound propagation being developed in Matlab to a cluster computer where each node has seven GPUs. Our goal is to perform realistic simulations in hours and minutes instead of weeks and days. In order to reach this goal we investigate architecture characteristics of the target system focusing on the PCI-Express subsystem and new features proposed in CUDA version 4.0, especially simultaneous host to device, device to host and peer-to-peer transfers that the application is going to highly benefit from. We also present the results from a CPU based implementation and discuss future directions to exploit multiple GPUs.",
keywords = "7-GPU system, Bandwidth, CUDA, FFT, Matlab, Multi-core, PCI-Express, Ultrasound simulation",
author = "Jiri Jaros and Treeby, {Bradley E} and Rendell, {Alistair P.}",
year = "2012",
month = nov,
day = "20",
language = "English",
isbn = "9781921770081",
series = "Conferences in Research and Practice in Information Technology Series",
pages = "43--52",
booktitle = "Parallel and Distributed Computing 2012",
note = "10th Australasian Symposium on Parallel and Distributed Computing, AusPDC 2012 ; Conference date: 31-01-2012 Through 03-02-2012",
}