High performance manycore solvers for reservoir simulation

H. Sudan, H. Klie, R. Li, Y. Saad

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

13 Scopus citations

Abstract

The forthcoming generation of many-core architectures compels a paradigm shift in algorithmic design to effectively unlock its full potential for maximum performance. In this paper, we discuss a novel approach for solving large sparse linear systems arising in realistic black oil and compositional flow simulations. A flexible variant of GMRES (FGMRES) is implemented using the CUDA programming model on the GPU platform using the Single Instruction Multiple Threads (SIMT) paradigm by taking advantage of thousands of threads simultaneously executing instructions. The implementation on the GPU is optimized to reduce memory overhead per floating point operations, given the sparsity of the linear system. FGMRES relies on a suite of different preconditioners such as BILU, BILUT and multicoloring SSOR. Additionally, the solver strategy relies on reordering/partitioning strategies algorithms to exploit further performance. Computational experiments on a wide range of realistic reservoir cases show a competitive edge when compared to conventional CPU implementations. The encouraging results demonstrate the potential that many-core solvers have to offer in improving the performance of near future reservoir simulations.

Original languageEnglish (US)
Title of host publicationECMOR 2010 - 12th European Conference on the Mathematics of Oil Recovery
PublisherEuropean Association of Geoscientists and Engineers, EAGE
StatePublished - Jan 1 2010
Event12th European Conference on the Mathematics of Oil Recovery, ECMOR 2010 - Oxford, United Kingdom
Duration: Sep 6 2010Sep 9 2010

Other

Other12th European Conference on the Mathematics of Oil Recovery, ECMOR 2010
CountryUnited Kingdom
CityOxford
Period9/6/109/9/10

Fingerprint Dive into the research topics of 'High performance manycore solvers for reservoir simulation'. Together they form a unique fingerprint.

Cite this