Accelerating the Conjugate Gradient Algorithm with GPUs in CFD Simulations

被引：1

作者：

Anzt, Hartwig ^{[1
]}

Baboulin, Marc ^{[2
]}

Dongarra, Jack ^{[1
]}

Fournier, Yvan ^{[3
]}

Hulsemann, Frank ^{[3
]}

Khabou, Amal ^{[2
]}

Wang, Yushan ^{[2
]}

机构：

[1] Univ Tennessee, Innovat Comp Lab, Knoxville, TN USA

[2] Univ Paris 11, Lab Rech Informat, Orsay, France

[3] EDF R&D, Clamart, France

来源：

HIGH PERFORMANCE COMPUTING FOR COMPUTATIONAL SCIENCE - VECPAR 2016 | 2017年 / 10150卷

关键词：

D O I：

10.1007/978-3-319-61982-8_5

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper illustrates how GPU computing can be used to accelerate computational fluid dynamics (CFD) simulations. For sparse linear systems arising from finite volume discretization, we evaluate and optimize the performance of Conjugate Gradient (CG) routines designed for manycore accelerators and compare against an industrial CPU-based implementation. We also investigate how the recent advances in preconditioning, such as iterative Incomplete Cholesky (IC, as symmetric case of ILU) preconditioning, match the requirements for solving real world problems.

引用

页码：35 / 43

页数：9

共 50 条

[1] Accelerating numerical simulations of supernovae with GPUs
Matsufuru, Hideo
Sumiyoshi, Kohsuke
2018 SIXTH INTERNATIONAL SYMPOSIUM ON COMPUTING AND NETWORKING WORKSHOPS (CANDARW 2018), 2018, : 263 - 266
[2] Using GPUs for Accelerating Electromagnetic Simulations
Ujaldon, Manuel
APPLIED COMPUTATIONAL ELECTROMAGNETICS SOCIETY JOURNAL, 2010, 25 (04): : 294 - 302
[3] Accelerating SystemC Simulations using GPUs
Nanjundappa, Mahesh
Kaushik, Anirudh
Patel, Hiren D.
Shukla, Sandeep K.
2012 IEEE INTERNATIONAL HIGH LEVEL DESIGN VALIDATION AND TEST WORKSHOP (HLDVT), 2012, : 132 - 139
[4] Overheads in Accelerating Molecular Dynamics Simulations with GPUs
Narumi, Tetsu
Sakamaki, Ryuji
Kameoka, Shun
Yasuoka, Kenji
PDCAT 2008: NINTH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED COMPUTING, APPLICATIONS AND TECHNOLOGIES, PROCEEDINGS, 2008, : 143 - 150
[5] Accelerating Stochastic Simulations on GPUs Using OpenCL
Kang, Pilsung
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2019, E102D (11): : 2253 - 2256
[6] Accelerating micromagnetic and atomistic simulations using multiple GPUs
Lepadatu, Serban
JOURNAL OF APPLIED PHYSICS, 2023, 134 (16)
[7] Accelerating Shor's factorization algorithm on GPUs
Savran, I.
Demirci, M.
Yilmaz, A. H.
CANADIAN JOURNAL OF PHYSICS, 2018, 96 (07) : 759 - 761
[8] A parallel multigrid preconditioned conjugate gradient algorithm for groundwater flow simulations
Ashby, SF
Falgout, RD
NUCLEAR SCIENCE AND ENGINEERING, 1996, 124 (01) : 145 - 159
[9] Parallel multigrid preconditioned conjugate gradient algorithm for groundwater flow simulations
Lawrence Livermore Natl Lab, Livermore, United States
Nucl Sci Eng, 1 (145-159):
[10] Accelerating unstructured-grid CFD algorithms on NVIDIA and AMD GPUs
Stone, Christopher P.
Walden, Aaron
Zubair, Mohammad
Nielsen, Eric J.
PROCEEDINGS OF IA3 2021: 2021 IEEE/ACM 11TH WORKSHOP ON IRREGULAR APPLICATIONS: ARCHITECTURES AND ALGORITHMS, 2021, : 19 - 26

← 1 2 3 4 5 →