(Enter summary)
Abstract: We analyze single-node performance of sparse
matrix-vector multiplication by investigating issues of
data locality and fine-grained parallelism. We examine
the data-locality characteristics of the compressedsparse
-row representation and consider improvements
in locality through matrix permutation. Motivated
by potential improvements in fine-grained parallelism,
we evaluate modified sparse-matrix representations.
The results lead to general conclusions about improving
single-node performance of ... (Update)
Context of citations to this paper: More
.... While a detailed performance modeling of this operation can be complex, particularly when data reference patterns are included [14 16], a simplified analysis can still yield upper bounds on the achievable performance of this operation. To illustrate the effect of...
...due to their particular sparsity patterns, exhibit more conflicts or reduced spatial locality. Some form of matrix reordering [30, 19, 24, 15], or the use of multiple rc block sizes are likely to be the most e#ective way to address this performance issue. On the Power3,...
Cited by: More
Performance Tuning and Analysis of Sparse Triangular Solve .. - Richie Bebop Computer (2002)
(Correct)
Performance Optimizations and Bounds for Sparse.. - Vuduc, Demmel, Yelick (2002)
(Correct)
Memory Hierarchy Optimizations and Performance Bounds.. - Vuduc, Gyulassy.. (2003)
(Correct)
System load high. Please wait...
Timeout. Please try your query later.
Similar documents based on text: More All
0.2: Reverse Communication Interface for Linear Algebra.. - Dongarra, Eijkhout.. (1995)
(Correct)
0.1: A Fast Parallel Krylov Subspace Method for the Radiosity.. - Chien, Leem, Oliveira
(Correct)
0.1: Block-Row Sparse Matrix-Vector Multiplication on SIMD Machines - Kapadia, Fortes (1995)
(Correct)
Related documents from co-citation: More All
6: Characterizing the Behavior of Sparse Algorithms on Caches
- Temam, Jalby - 1992
5: Improving memory-system performance of sparse matrix-vector multiplication
- Toledo - 1997
4: Automatic nonzero structure analysis (context) - Bik, Wijshoff - 1999
BibTeX entry: (Update)
J. White and P. Sadayappan. On improving the performance of sparse matrix-vector multiplication. In Proceedings of the 4th International Conference on High Performance Computing (HiPC '97), pages 578--587. IEEE Computer Society, 1997. http://citeseer.ist.psu.edu/white97improving.html More
@misc{ white97improving,
author = "J. White and P. Sadayappan",
title = "On improving the performance of sparse matrix-vector multiplication",
text = "J. White and P. Sadayappan. On improving the performance of sparse matrix-vector
multiplication. In Proceedings of the 4th International Conference on High
Performance Computing (HiPC '97), pages 578--587. IEEE Computer Society,
1997.",
year = "1997",
url = "citeseer.ist.psu.edu/white97improving.html" }
Citations (may not include all citations):
1
MatrixMarket (context) - Boisvert, Pozo et al.
1
Sparse Matrix Project: Directory (context) - Davis
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://hipc.org/hipc97/total.html): More
An Object Oriented System for Developing Distributed Applications - Singh, Gu (1997)
(Correct)
ELMO: Extending (Sequential) Languages with Migratable.. - Richards, Ramkumar..
(Correct)
Lazy Home Migration for Distributed Shared Memory Systems - Baylor, Ekanadham.. (1997)
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC