pith. sign in

arxiv: 1407.8168 · v1 · pith:42QJTCT6new · submitted 2014-07-30 · 💻 cs.DC · cs.NA· cs.PF

Quantifying the Effect of Matrix Structure on Multithreaded Performance of the SpMV Kernel

classification 💻 cs.DC cs.NAcs.PF
keywords matricesspmvkernelmatrixperformancestructurearchitecturedifference
0
0 comments X
read the original abstract

Sparse matrix-vector multiplication (SpMV) is the core operation in many common network and graph analytics, but poor performance of the SpMV kernel handicaps these applications. This work quantifies the effect of matrix structure on SpMV performance, using Intel's VTune tool for the Sandy Bridge architecture. Two types of sparse matrices are considered: finite difference (FD) matrices, which are structured, and R-MAT matrices, which are unstructured. Analysis of cache behavior and prefetcher activity reveals that the SpMV kernel performs far worse with R-MAT matrices than with FD matrices, due to the difference in matrix structure. To address the problems caused by unstructured matrices, novel architecture improvements are proposed.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.