Iterative Methods for MPC on Graphical Processing Units

Publication: Research - peer-reviewConference abstract in proceedings – Annual report year: 2012

Standard

Iterative Methods for MPC on Graphical Processing Units. / Gade-Nielsen, Nicolai Fog; Jørgensen, John Bagterp; Dammann, Bernd.

Proceedings of the 17th Nordic Process Control Workshop. ed. / John Bagterp Jørgensen; Jakob Kjøbsted Huusom; Gürkan Sin. Kogens Lyngby : Technical University of Denmark, 2012. p. 161.

Publication: Research - peer-reviewConference abstract in proceedings – Annual report year: 2012

Harvard

Gade-Nielsen, NF, Jørgensen, JB & Dammann, B 2012, 'Iterative Methods for MPC on Graphical Processing Units'. in JB Jørgensen, JK Huusom & G Sin (eds), Proceedings of the 17th Nordic Process Control Workshop. Technical University of Denmark, Kogens Lyngby, pp. 161.

APA

Gade-Nielsen, N. F., Jørgensen, J. B., & Dammann, B. (2012). Iterative Methods for MPC on Graphical Processing Units. In J. B. Jørgensen, J. K. Huusom, & G. Sin (Eds.), Proceedings of the 17th Nordic Process Control Workshop. (pp. 161). Kogens Lyngby: Technical University of Denmark.

CBE

Gade-Nielsen NF, Jørgensen JB, Dammann B. 2012. Iterative Methods for MPC on Graphical Processing Units. Jørgensen JB, Huusom JK, Sin G, editors. In Proceedings of the 17th Nordic Process Control Workshop. Kogens Lyngby: Technical University of Denmark. pp. 161.

MLA

Gade-Nielsen, Nicolai Fog, John Bagterp Jørgensen, and Bernd Dammann "Iterative Methods for MPC on Graphical Processing Units"., Jørgensen, John Bagterp Huusom, Jakob Kjøbsted Sin, Gürkan (ed.). Proceedings of the 17th Nordic Process Control Workshop. Kogens Lyngby: Technical University of Denmark. 2012. 161.

Vancouver

Gade-Nielsen NF, Jørgensen JB, Dammann B. Iterative Methods for MPC on Graphical Processing Units. In Jørgensen JB, Huusom JK, Sin G, editors, Proceedings of the 17th Nordic Process Control Workshop. Kogens Lyngby: Technical University of Denmark. 2012. p. 161.

Author

Gade-Nielsen, Nicolai Fog; Jørgensen, John Bagterp; Dammann, Bernd / Iterative Methods for MPC on Graphical Processing Units.

Proceedings of the 17th Nordic Process Control Workshop. ed. / John Bagterp Jørgensen; Jakob Kjøbsted Huusom; Gürkan Sin. Kogens Lyngby : Technical University of Denmark, 2012. p. 161.

Publication: Research - peer-reviewConference abstract in proceedings – Annual report year: 2012

Bibtex

@inbook{ad1425d697054c00b1a7a4a54343b9fb,
title = "Iterative Methods for MPC on Graphical Processing Units",
keywords = "Graphical Processing Unit, Model based control, Iterative methods, Predictive control, Optimization",
publisher = "Technical University of Denmark",
author = "Gade-Nielsen, {Nicolai Fog} and Jørgensen, {John Bagterp} and Bernd Dammann",
year = "2012",
editor = "Jørgensen, {John Bagterp} and Huusom, {Jakob Kjøbsted} and Gürkan Sin",
isbn = "978-87-643-0946-1",
pages = "161",
booktitle = "Proceedings of the 17th Nordic Process Control Workshop",

}

RIS

TY - ABST

T1 - Iterative Methods for MPC on Graphical Processing Units

A1 - Gade-Nielsen,Nicolai Fog

A1 - Jørgensen,John Bagterp

A1 - Dammann,Bernd

AU - Gade-Nielsen,Nicolai Fog

AU - Jørgensen,John Bagterp

AU - Dammann,Bernd

PB - Technical University of Denmark

CY - Kogens Lyngby

PY - 2012

Y1 - 2012

N2 - The high oating point performance and memory bandwidth of Graphical Processing Units (GPUs) makes them ideal for a large number of computations which often arises in scientic computing, such as matrix operations. GPUs achieve this performance by utilizing massive par- allelism, which requires reevaluating existing algorithms with respect to this new architecture. This is of particular interest to large-scale constrained optimization problems with real-time requirements. The aim of this study is to investigate dierent methods for solving large-scale optimization problems with focus on their applicability for GPUs. We examine published techniques for iterative methods in interior points methods (IPMs) by applying them to simple test cases, such as a system of masses connected by springs. Iterative methods allows us deal with the ill-conditioning occurring in the later iterations of the IPM as well as to avoid the use of dense matrices, which may be too large for the limited memory capacity of current graphics cards.

AB - The high oating point performance and memory bandwidth of Graphical Processing Units (GPUs) makes them ideal for a large number of computations which often arises in scientic computing, such as matrix operations. GPUs achieve this performance by utilizing massive par- allelism, which requires reevaluating existing algorithms with respect to this new architecture. This is of particular interest to large-scale constrained optimization problems with real-time requirements. The aim of this study is to investigate dierent methods for solving large-scale optimization problems with focus on their applicability for GPUs. We examine published techniques for iterative methods in interior points methods (IPMs) by applying them to simple test cases, such as a system of masses connected by springs. Iterative methods allows us deal with the ill-conditioning occurring in the later iterations of the IPM as well as to avoid the use of dense matrices, which may be too large for the limited memory capacity of current graphics cards.

KW - Graphical Processing Unit

KW - Model based control

KW - Iterative methods

KW - Predictive control

KW - Optimization

UR - http://npcw17.imm.dtu.dk/

SN - 978-87-643-0946-1

BT - Proceedings of the 17th Nordic Process Control Workshop

T2 - Proceedings of the 17th Nordic Process Control Workshop

A2 - Sin,Gürkan

ED - Sin,Gürkan

SP - 161

ER -