Generating optimal CUDA sparse matrix-vector product implementations for evolving GPU hardware
Date
2012
Authors
El Zein, Ahmed
Rendell, Alistair
Journal Title
Journal ISSN
Volume Title
Publisher
John Wiley & Sons Inc
Abstract
The CUDA model for graphics processing units (GPUs) presents the programmer with a plethora of different programming options. These includes different memory types, different memory access methods and different data types. Identifying which options to use and when is a non-trivial exercise. This paper explores the effect of these different options on the performance of a routine that evaluates sparse matrix-vector products (SpMV) across three different generations of NVIDIA GPU hardware. A process for analysing performance and selecting the subset of implementations that perform best is proposed. The potential for mapping sparse matrix attributes to optimal CUDA SpMV implementations is discussed.
Description
Keywords
Keywords: CUDA; Fermi; GPU; Matrix-vector; NVIDIA; S2050; sparse; Multicore programming; Optimization; Program processors; Matrix algebra CUDA; Fermi; GPU; matrix-vector; NVIDIA; S2050; sparse
Citation
Collections
Source
Concurrency and Computation: Practice and Experience
Type
Journal article
Book Title
Entity type
Access Statement
License Rights
DOI
Restricted until
2037-12-31
Downloads
File
Description