2010 · 21 citations · 5 references
ComputingComputer ScienceHigh-performance ComputingComputer ArchitectureComputer GraphicsParallel ComputingData ParallelismGraphics Processing Unit ArchitectureGraphics Processing Unit ComputingGraphics Processing UnitsParallel ArchitecturesParallel Computing SystemsCuda ProgrammingDivergenceGpu ArchitectureGpu Programming ModelsMatrix MultiplicationParallel SystemScientific Computing On GpusSparse Matrix Computation
In recent years, GPUs have attracted the attention of many application developers as powerful massively parallel system. CUDA as a general purpose parallel computing architecture make GPUs an appealing choice to solve many complex computational problems in a more efficient way. In this paper, we discuss implementing optimizing spare matrix-vector multiplication on NVIDIA GPUs using CUDA programming model. We outline three optimizations include: (1) optimized CSR storage format, (2) optimized threads mapping, and (3) avoiding divergence judgment. We experimentally evaluate our optimizations on GeForce 9600 GTX, connect to Windows xp 64-bit system. In comparison with NVIDIA's SpMV library and NVIDIA's CUDDPA library, the results show that optimizing sparse matrix-vector multiplication on CUDA achieves better performance than other SpMV implementations.
5
Ecient Sparse Matrix-Vector Multiplication on CUDA
Nathan Bell, Michael Garland · 2008 · 581 citations
Automatic performance tuning of sparse matrix kernels
Richard Vuduc, James Demmel · 2003 · 229 citations
Fast scan algorithms on graphics processors
Yuri Dotsenko, Naga K. Govindaraju, Peter‐Pike Sloan et al. · 2008 · 129 citations