Efficient sparse matrix-vector multiplication on cache-based GPUs

TL;DR: ACSR is presented, an adaptive SpMV algorithm that uses the standard CSR format but reduces thread divergence by combining rows into groups which have a similar number of non-zero elements, and thus avoids significant preprocessing overheads.

TL;DR: This paper performs extensive characterization of pertinent sparsity features of around 700 sparse matrices and their SpMV performance with a number of sparse representations implemented in the NVIDIA CUSP and cuSPARSE libraries, and builds a decision model using machine learning to automatically select the best representation to use for a given sparse matrix on a given target platform.

TL;DR: This article provides a review of the techniques for implementing the SpMV kernel on GPGPUs that have appeared in the literature of the last few years, and discusses the issues and tradeoffs that have been encountered by the various researchers.

TL;DR: In this paper, a compressed sparse row (CSR) format based SpMV algorithm utilizing both types of cores in a CPU-GPU heterogeneous processor is proposed, where the CPU part of the same chip is triggered to re-arrange the predicted partial sums for a correct resulting vector.

TL;DR: In this article, the authors present an easily accessible introduction to one of the most important methods used to solve partial differential equations, which they call finite element methods for integral equations (FEME).

TL;DR: This paper develops a general purpose molecular dynamics code that runs entirely on a single GPU and shows that the GPU implementation provides a performance equivalent to that of fast 30 processor core distributed memory cluster.

TL;DR: This work proposes a stream model for arithmetic operations on vectors and matrices that exploits the intrinsic parallelism and efficient communication on modern GPUs and introduces a framework for the implementation of linear algebra operators on programmable graphics processors (GPUs), thus providing the building blocks for the design of more complex numerical algorithms.

TL;DR: This work shows that high-intensity numerical simulation computations can be performed efficiently on the GPU, which is regarded as a full function streaming system.