Impact of GPU memory access patterns on FDTD

Matthew Livesey, James F. Stack, Fumie Costen, Takeshi Nanri, Norimasa Nakashima, Seiji Fujino

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

2 Citations (Scopus)

Abstract

The application of General Purpose computing on a GPU is an effective way to accelerate the FDTD method. This work explores the different domain decomposition techniques from the literature and extends the theoretically best approach with additional flexibility. We examine the performance on both Tesla and Fermi architecture GPUs and identify the best way to determine the GPU parameters for the proposed method.

Original languageEnglish
Title of host publication2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings
DOIs
Publication statusPublished - Dec 10 2012
EventJoint 2012 IEEE International Symposium on Antennas and Propagation and USNC-URSI National Radio Science Meeting, APSURSI 2012 - Chicago, IL, United States
Duration: Jul 8 2012Jul 14 2012

Publication series

NameIEEE Antennas and Propagation Society, AP-S International Symposium (Digest)
ISSN (Print)1522-3965

Other

OtherJoint 2012 IEEE International Symposium on Antennas and Propagation and USNC-URSI National Radio Science Meeting, APSURSI 2012
CountryUnited States
CityChicago, IL
Period7/8/127/14/12

Fingerprint

Data storage equipment
Decomposition
Graphics processing unit

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Livesey, M., Stack, J. F., Costen, F., Nanri, T., Nakashima, N., & Fujino, S. (2012). Impact of GPU memory access patterns on FDTD. In 2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings [6348987] (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)). https://doi.org/10.1109/APS.2012.6348987

Impact of GPU memory access patterns on FDTD. / Livesey, Matthew; Stack, James F.; Costen, Fumie; Nanri, Takeshi; Nakashima, Norimasa; Fujino, Seiji.

2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings. 2012. 6348987 (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)).

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

Livesey, M, Stack, JF, Costen, F, Nanri, T, Nakashima, N & Fujino, S 2012, Impact of GPU memory access patterns on FDTD. in 2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings., 6348987, IEEE Antennas and Propagation Society, AP-S International Symposium (Digest), Joint 2012 IEEE International Symposium on Antennas and Propagation and USNC-URSI National Radio Science Meeting, APSURSI 2012, Chicago, IL, United States, 7/8/12. https://doi.org/10.1109/APS.2012.6348987
Livesey M, Stack JF, Costen F, Nanri T, Nakashima N, Fujino S. Impact of GPU memory access patterns on FDTD. In 2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings. 2012. 6348987. (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)). https://doi.org/10.1109/APS.2012.6348987
Livesey, Matthew ; Stack, James F. ; Costen, Fumie ; Nanri, Takeshi ; Nakashima, Norimasa ; Fujino, Seiji. / Impact of GPU memory access patterns on FDTD. 2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings. 2012. (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)).
@inproceedings{d456c20270f64c4ba66e80b37b41e075,
title = "Impact of GPU memory access patterns on FDTD",
abstract = "The application of General Purpose computing on a GPU is an effective way to accelerate the FDTD method. This work explores the different domain decomposition techniques from the literature and extends the theoretically best approach with additional flexibility. We examine the performance on both Tesla and Fermi architecture GPUs and identify the best way to determine the GPU parameters for the proposed method.",
author = "Matthew Livesey and Stack, {James F.} and Fumie Costen and Takeshi Nanri and Norimasa Nakashima and Seiji Fujino",
year = "2012",
month = "12",
day = "10",
doi = "10.1109/APS.2012.6348987",
language = "English",
isbn = "9781467304627",
series = "IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)",
booktitle = "2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings",

}

TY - GEN

T1 - Impact of GPU memory access patterns on FDTD

AU - Livesey, Matthew

AU - Stack, James F.

AU - Costen, Fumie

AU - Nanri, Takeshi

AU - Nakashima, Norimasa

AU - Fujino, Seiji

PY - 2012/12/10

Y1 - 2012/12/10

N2 - The application of General Purpose computing on a GPU is an effective way to accelerate the FDTD method. This work explores the different domain decomposition techniques from the literature and extends the theoretically best approach with additional flexibility. We examine the performance on both Tesla and Fermi architecture GPUs and identify the best way to determine the GPU parameters for the proposed method.

AB - The application of General Purpose computing on a GPU is an effective way to accelerate the FDTD method. This work explores the different domain decomposition techniques from the literature and extends the theoretically best approach with additional flexibility. We examine the performance on both Tesla and Fermi architecture GPUs and identify the best way to determine the GPU parameters for the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84870517143&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870517143&partnerID=8YFLogxK

U2 - 10.1109/APS.2012.6348987

DO - 10.1109/APS.2012.6348987

M3 - Conference contribution

SN - 9781467304627

T3 - IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)

BT - 2012 IEEE International Symposiumon Antennas and Propagation, APSURSI 2012 - Proceedings

ER -