High rayleigh number mantle convection on GPU

David A. Sanchez, Christopher Gonzalez, David A. Yuen, Grady B. Wright, Gregory A. Barnett

Research output: Chapter in Book/Report/Conference proceedingChapter (Book)Researchpeer-review

Abstract

We implemented two- and three-dimensional Rayleigh–Benard convection on Nvidia GPUs by utilizing a 2nd-order finite difference method. By exploiting the massive parallelism of GPU using both CUDA for C and optimized CUBLAS routines, we have on a single Fermi GPU run simulations of Rayleigh number up to 6 × 1010 (on a mesh of 2000 × 4000 uniform grid points) in two dimensions and up to 107 (on a mesh of 450 × 450 × 225 uniform grid points) for three dimensions. On Nvidia Tesla C2070 GPUs, these implementations enjoy single-precision performance of 535 GFLOP/s and 100 GFLOP/s respectively, and double-precision performance of 230 GFLOP/s and 70 GFLOP/s respectively.

Original languageEnglish
Title of host publicationGPU Solutions to Multi-scale Problems in Science and Engineering
EditorsDavid A Yuen, Long Wang, Xuebin Chi
Place of PublicationHeidelberg Germany
PublisherSpringer
Chapter22
Pages335-352
Number of pages18
ISBN (Electronic)9783642164057
ISBN (Print)9783642164040
DOIs
Publication statusPublished - 1 Jan 2013
Externally publishedYes

Publication series

NameLecture Notes in Earth System Sciences
PublisherSpringer
ISSN (Print)2193-858X
ISSN (Electronic)2193-8571

Cite this

Sanchez, D. A., Gonzalez, C., Yuen, D. A., Wright, G. B., & Barnett, G. A. (2013). High rayleigh number mantle convection on GPU. In D. A. Yuen, L. Wang, & X. Chi (Eds.), GPU Solutions to Multi-scale Problems in Science and Engineering (pp. 335-352). (Lecture Notes in Earth System Sciences). Heidelberg Germany: Springer. https://doi.org/10.1007/978-3-642-16405-7_22
Sanchez, David A. ; Gonzalez, Christopher ; Yuen, David A. ; Wright, Grady B. ; Barnett, Gregory A. / High rayleigh number mantle convection on GPU. GPU Solutions to Multi-scale Problems in Science and Engineering. editor / David A Yuen ; Long Wang ; Xuebin Chi. Heidelberg Germany : Springer, 2013. pp. 335-352 (Lecture Notes in Earth System Sciences).
@inbook{48edc339f202411794fd9497ec1a31f2,
title = "High rayleigh number mantle convection on GPU",
abstract = "We implemented two- and three-dimensional Rayleigh–Benard convection on Nvidia GPUs by utilizing a 2nd-order finite difference method. By exploiting the massive parallelism of GPU using both CUDA for C and optimized CUBLAS routines, we have on a single Fermi GPU run simulations of Rayleigh number up to 6 × 1010 (on a mesh of 2000 × 4000 uniform grid points) in two dimensions and up to 107 (on a mesh of 450 × 450 × 225 uniform grid points) for three dimensions. On Nvidia Tesla C2070 GPUs, these implementations enjoy single-precision performance of 535 GFLOP/s and 100 GFLOP/s respectively, and double-precision performance of 230 GFLOP/s and 70 GFLOP/s respectively.",
author = "Sanchez, {David A.} and Christopher Gonzalez and Yuen, {David A.} and Wright, {Grady B.} and Barnett, {Gregory A.}",
year = "2013",
month = "1",
day = "1",
doi = "10.1007/978-3-642-16405-7_22",
language = "English",
isbn = "9783642164040",
series = "Lecture Notes in Earth System Sciences",
publisher = "Springer",
pages = "335--352",
editor = "Yuen, {David A} and Wang, {Long } and Chi, {Xuebin }",
booktitle = "GPU Solutions to Multi-scale Problems in Science and Engineering",

}

Sanchez, DA, Gonzalez, C, Yuen, DA, Wright, GB & Barnett, GA 2013, High rayleigh number mantle convection on GPU. in DA Yuen, L Wang & X Chi (eds), GPU Solutions to Multi-scale Problems in Science and Engineering. Lecture Notes in Earth System Sciences, Springer, Heidelberg Germany, pp. 335-352. https://doi.org/10.1007/978-3-642-16405-7_22

High rayleigh number mantle convection on GPU. / Sanchez, David A.; Gonzalez, Christopher; Yuen, David A.; Wright, Grady B.; Barnett, Gregory A.

GPU Solutions to Multi-scale Problems in Science and Engineering. ed. / David A Yuen; Long Wang; Xuebin Chi. Heidelberg Germany : Springer, 2013. p. 335-352 (Lecture Notes in Earth System Sciences).

Research output: Chapter in Book/Report/Conference proceedingChapter (Book)Researchpeer-review

TY - CHAP

T1 - High rayleigh number mantle convection on GPU

AU - Sanchez, David A.

AU - Gonzalez, Christopher

AU - Yuen, David A.

AU - Wright, Grady B.

AU - Barnett, Gregory A.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - We implemented two- and three-dimensional Rayleigh–Benard convection on Nvidia GPUs by utilizing a 2nd-order finite difference method. By exploiting the massive parallelism of GPU using both CUDA for C and optimized CUBLAS routines, we have on a single Fermi GPU run simulations of Rayleigh number up to 6 × 1010 (on a mesh of 2000 × 4000 uniform grid points) in two dimensions and up to 107 (on a mesh of 450 × 450 × 225 uniform grid points) for three dimensions. On Nvidia Tesla C2070 GPUs, these implementations enjoy single-precision performance of 535 GFLOP/s and 100 GFLOP/s respectively, and double-precision performance of 230 GFLOP/s and 70 GFLOP/s respectively.

AB - We implemented two- and three-dimensional Rayleigh–Benard convection on Nvidia GPUs by utilizing a 2nd-order finite difference method. By exploiting the massive parallelism of GPU using both CUDA for C and optimized CUBLAS routines, we have on a single Fermi GPU run simulations of Rayleigh number up to 6 × 1010 (on a mesh of 2000 × 4000 uniform grid points) in two dimensions and up to 107 (on a mesh of 450 × 450 × 225 uniform grid points) for three dimensions. On Nvidia Tesla C2070 GPUs, these implementations enjoy single-precision performance of 535 GFLOP/s and 100 GFLOP/s respectively, and double-precision performance of 230 GFLOP/s and 70 GFLOP/s respectively.

UR - http://www.scopus.com/inward/record.url?scp=85038082044&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-16405-7_22

DO - 10.1007/978-3-642-16405-7_22

M3 - Chapter (Book)

SN - 9783642164040

T3 - Lecture Notes in Earth System Sciences

SP - 335

EP - 352

BT - GPU Solutions to Multi-scale Problems in Science and Engineering

A2 - Yuen, David A

A2 - Wang, Long

A2 - Chi, Xuebin

PB - Springer

CY - Heidelberg Germany

ER -

Sanchez DA, Gonzalez C, Yuen DA, Wright GB, Barnett GA. High rayleigh number mantle convection on GPU. In Yuen DA, Wang L, Chi X, editors, GPU Solutions to Multi-scale Problems in Science and Engineering. Heidelberg Germany: Springer. 2013. p. 335-352. (Lecture Notes in Earth System Sciences). https://doi.org/10.1007/978-3-642-16405-7_22