Parallelizing Alternating Direction Implicit Solver on GPUs
نویسندگان
چکیده
We present a parallel Alternating Direction Implicit (ADI) solver on GPUs. Our implementation significantly improves existing implementations in two aspects. First, we address the scalability issue of existing Parallel Cyclic Reduction (PCR) implementations by eliminating their hardware resource constraints. As a result, our parallel ADI, which is based on PCR, no longer has the maximum domain size limitation. Second, we optimize inefficient data accesses of parallel ADI solver by leveraging hardware texture memory and matrix transpose techniques. These memory optimizations further make already parallelized ADI solver twice faster, achieving overall more than 100 times speedup over a highly optimized CPU version. We also present the analysis of numerical accuracy of the proposed parallel ADI solver.
منابع مشابه
An Alternating Direction Implicit Method for Modeling of Fluid Flow
This research includes of the numerical modeling of fluids in two-dimensional cavity. The cavity flow is an important theoretical problem. In this research, modeling was carried out based on an alternating direction implicit via Vorticity-Stream function formulation. It evaluates different Reynolds numbers and grid sizes. Therefore, for the flow field analysis and prove of the ability of the sc...
متن کاملSolving Two-Dimensional Fuzzy Partial Dierential Equation by the Alternating Direction Implicit Method
متن کامل
Scalable Implicit Methods for Reaction-diffusion Equations in Two and Three Space Dimensions
This paper describes the implementation of a solver for systems of semi-linear parabolic partial di erential equations in two and three space dimensions. The solver is based on a parallel implementation of a non-linear Alternating Direction Implicit (ADI) scheme which uses a Cartesian grid in space and an implicit time-stepping algorithm. Various reordering strategies for the linearized equatio...
متن کاملAlternating-Direction Line-Relaxation Methods on Multicomputers
We study the multicomputer performance of a three-dimensional Navier-Stokes solver based on alternating-direction line-relaxation methods. We compare several multicomputer implementations, each of which combines a particular line-relaxation method and a particular distributed block-tridiagonal solver. In our experiments, the problem size was determined by resolution requirements of the applicat...
متن کاملFull-Vectorial Beam-Propagation Method Based on the Mckee-Mitchell Scheme with Improved Finite-Diffe - Lightwave Technology, Journal of
The alternating-direction implicit method proposed by McKee–Mitchell is applied to full-vectorial paraxial wave equations. The high computational efficiency of the present method is demonstrated in comparison with an iterative solver. Novel finite-difference formulas that take into account discontinuities of the fields are proposed and employed to ensure second-order accuracy. Calculations rega...
متن کامل