A Fast Mixed-Precision Strategy for Iterative Gpu-Based Solution of the Laplace Equation

Stefan Lemvig Glimberg; Allan Peter Engsig-Karup

A Fast Mixed-Precision Strategy for Iterative Gpu-Based Solution of the Laplace Equation

Stefan Lemvig Glimberg (Author), Allan Peter Engsig-Karup (Author)

Research output: Non-textual form › Sound/Visual production (digital) › Research

134 Downloads (Pure)

Abstract

Our work is concerned with the development of a generic high-performance library for scientific computing. The library is targeted for assembling flexible-order finite-difference solvers for PDEs. Our goal is to enable fast solution of large PDE systems, fully exploiting the massively parallel architecture of Graphics Processing Units. We will detail a strategy for an iterative mixed-precision p-multigrid solver of the Laplace equation, which appears as a computational bottleneck in applications in coastal and offshore engineering.

Original language	English
Publication date	2011
Publication status	Published - 2011
Event	SIAM Conference on Analysis of Partial Differential Equations - San Diego, California, USA Duration: 1 Jan 2011 → …

Conference

Conference	SIAM Conference on Analysis of Partial Differential Equations
City	San Diego, California, USA
Period	01/01/2011 → …

Access to Document

Sllides glimbergFinal published version, 644 KB

http://www.siam.org/meetings/pd11/

Cite this

@misc{d27639e8962a432da35cd8ef0d2446f8,

title = "A Fast Mixed-Precision Strategy for Iterative Gpu-Based Solution of the Laplace Equation",

abstract = "Our work is concerned with the development of a generic high-performance library for scientific computing. The library is targeted for assembling flexible-order finite-difference solvers for PDEs. Our goal is to enable fast solution of large PDE systems, fully exploiting the massively parallel architecture of Graphics Processing Units. We will detail a strategy for an iterative mixed-precision p-multigrid solver of the Laplace equation, which appears as a computational bottleneck in applications in coastal and offshore engineering.",

author = "Glimberg, {Stefan Lemvig} and Engsig-Karup, {Allan Peter}",

year = "2011",

language = "English",

note = "SIAM Conference on Analysis of Partial Differential Equations ; Conference date: 01-01-2011",

}

TY - ADVS

T1 - A Fast Mixed-Precision Strategy for Iterative Gpu-Based Solution of the Laplace Equation

A2 - Glimberg, Stefan Lemvig

A2 - Engsig-Karup, Allan Peter

PY - 2011

Y1 - 2011

N2 - Our work is concerned with the development of a generic high-performance library for scientific computing. The library is targeted for assembling flexible-order finite-difference solvers for PDEs. Our goal is to enable fast solution of large PDE systems, fully exploiting the massively parallel architecture of Graphics Processing Units. We will detail a strategy for an iterative mixed-precision p-multigrid solver of the Laplace equation, which appears as a computational bottleneck in applications in coastal and offshore engineering.

AB - Our work is concerned with the development of a generic high-performance library for scientific computing. The library is targeted for assembling flexible-order finite-difference solvers for PDEs. Our goal is to enable fast solution of large PDE systems, fully exploiting the massively parallel architecture of Graphics Processing Units. We will detail a strategy for an iterative mixed-precision p-multigrid solver of the Laplace equation, which appears as a computational bottleneck in applications in coastal and offshore engineering.

M3 - Sound/Visual production (digital)

T2 - SIAM Conference on Analysis of Partial Differential Equations

Y2 - 1 January 2011

ER -

A Fast Mixed-Precision Strategy for Iterative Gpu-Based Solution of the Laplace Equation

Abstract

Conference

Access to Document

Fingerprint

Cite this