Sparse matrix solvers on the GPU: conjugate gradients and multigrid

By J. Bolz, Ian Farmer, Eitan Grinspun, Peter Schröder. ACM Transactions on Graphics, 2003

711 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design

View Paper: https://www.semanticscholar.org/paper/81c3e6b8e678d75954197afe25dfdaf3975549c5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

Citations in the corpus

Brook for GPUs: Stream Computing on Graphics Hardware (2004, background): “OpenGL Pbu(cid:11)ers provide this functionality, however, as Bolz et al.[2003] discovered, switching between render targets with Pbu(cid:11)ers can have signi(cid:12)cant performance penalties.”
GPGPU: general purpose computation on graphics hardware (2004, methodology): “For details and examples of more sophisticated solvers, see Bolz et al. 2003, Goodnight et al. 2003, and Krüger and Westermann 2003.”
Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow (2007, background): “Although some applications can achieve speedups of 20 to 50 times over their CPU equivalent [15], other applications, while successfully parallelized on different hardware platforms, show little improvement when mapped to a GPU [4].”
GPU Cluster for High Performance Computing (2004, methodology): “[3] have implemented iterative methods for solving sparse linear systems such as conjugate gradient and Gauss-Seidel on the GPU.”
Data‐driven projection method in fluid simulation (2016, methodology): “It will cost a large amount of computing resource [4] and make it inconvenient when tiny adjustments occurred in ﬂuid simulation.”
Model reduction for real-time fluids (2006, methodology): “…have been mapped to the GPU as a stream processor including a Lattice Boltzman Method [Li et al. 2003], Coupled Map Lattice [Harris et al. 2002], semi- Lagrangian solver with boundaries [Wu et al. 2005], and a Poisson solver [Krüger and Westermann 2003; Bolz et al. 2003; Goodnight et al. 2003].”
Model-driven autotuning of sparse matrix-vector multiply on GPUs (2010, background): “These implementations, which include variants on classical blocked compressed sparse row (BCSR) and blocked ELLPACK (BELLPACK) storage formats, match or exceed state-of-the-art implementations.”
Quantum Chemistry on Graphical Processing Units. 1. Strategies for Two-Electron Integral Evaluation. (2008, background): “The “bra-” and “ket-” rectangles on the top left of the thread block represent the pairwise quantities precalculated on the CPU. A )R 1 +R 2; B )R 3 +R 4 ( 6 )”
Random Walks for Interactive Organ Segmentation in Two and Three Dimensions: Implementation and Validation (2005, neutral): “[8] and Krüger et al.”
To appear in the ACM SIGGRAPH conference proceedings Modular Bases for Fluid Dynamics (neutral): “Recent work has mapped a number of Eulerian methods to the GPU, including stable advection [Wu et al. 2005], pressure projection [Krüger and Westermann 2003; Bolz et al. 2003; Goodnight et al. 2003], Lattice Boltzmann methods [Li et al. 2003], and the coupled map lattice [Harris et al. 2002].”
Linear algebra operators for GPU implementation of numerical algorithms (2003, methodology): “Recent examples include GPU implementations of matrix multiplications [Thompson et al. 2002], multi-grid simulation techniques [Bolz et al. 2003] and numerical solution techniques to least squares problems [Hillesland et al. 2003].”