Analysis of Schedule and Layout Tuning for Sparse Matrices With Compound Entries on GPUs,Computer Graphics Forum

当前位置： X-MOL 学术 › Comput. Graph. Forum › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Analysis of Schedule and Layout Tuning for Sparse Matrices With Compound Entries on GPUs
Computer Graphics Forum ( IF 2.7 ) Pub Date : 2020-03-30 , DOI: 10.1111/cgf.13957
J. S. Mueller‐Roemer ₁ , A. Stork ₁ , D. Fellner _{1,

2}

Affiliation

Large sparse matrices with compound entries, i.e. complex and quaternionic matrices as well as matrices with dense blocks, are a core component of many algorithms in geometry processing, physically based animation and other areas of computer graphics. We generalize several matrix layouts and apply joint schedule and layout autotuning to improve the performance of the sparse matrix‐vector product on massively parallel graphics processing units. Compared to schedule tuning without layout tuning, we achieve speedups of up to 5.5 × . In comparison to cuSPARSE, we achieve speedups of up to 4.7 × .

中文翻译：

GPU 上具有复合条目的稀疏矩阵的调度和布局调整分析

具有复合条目的大型稀疏矩阵，即复杂和四元数矩阵以及具有密集块的矩阵，是几何处理、基于物理的动画和其他计算机图形领域的许多算法的核心组件。我们概括了几种矩阵布局，并应用联合调度和布局自动调整来提高大规模并行图形处理单元上的稀疏矩阵向量乘积的性能。与没有布局调整的调度调整相比，我们实现了高达 5.5 × 的加速。与 cuSPARSE 相比，我们实现了高达 4.7 × 的加速。

更新日期：2020-03-30

点击分享查看原文

点击收藏

公开下载

阅读更多本刊最新论文本刊介绍/投稿指南11