A statistically-based multi-algorithmic approach for load-balancing sparse matrix computations

Authors:
S. Nastea;T. El-Ghazawi;O. Frieder
Affiliations:
-;-;-
Venue:
FRONTIERS '96 Proceedings of the 6th Symposium on the Frontiers of Massively Parallel Computation
Year:
1996

Citing 7
Cited 0

Sparse matrix test problems

ACM Transactions on Mathematical Software (TOMS)
Sparse matrix computations on parallel processor arrays

SIAM Journal on Scientific Computing
High-performance I/O for massively parallel computers: problems and prospects

Computer
A load balanced multicomputer relational database system for highly skewed data

Parallel Computing
Load-balanced sparse matrix-vector multiplication on parallel computers

Journal of Parallel and Distributed Computing
Improved load distribution in parallel sparse cholesky factorization

Proceedings of the 1994 ACM/IEEE conference on Supercomputing
Bucket Spreading Parallel Hash: A New, Robust, Parallel Hash Join Method for Data Skew in the Super Database Computer (SDC)

VLDB '90 Proceedings of the 16th International Conference on Very Large Data Bases

Quantified Score

Hi-index	0.00

Visualization

Abstract

Load-balancing represents a challenging requirement for sparse matrix computations, especially when the matrix order and the associated computations are large. The performance of allocation algorithms could be data dependent, making it a non-trivial task to choose one algorithm that consistently yields the best overall performance for a given set of data. In this paper, we propose a method that statistically analyzes the sparse matrix data to identify, the best algorithm to use, over each region of the problem parameter space. We test our approach on sparse benchmark matrices for matrix-vector computations and show that the best allocation algorithm can be predicted accurately, to produce overall best performance.