A New Approach for Accelerating the Sparse Matrix-Vector Multiplication

@article{Tvrdk2006ANA,
title={A New Approach for Accelerating the Sparse Matrix-Vector Multiplication},
author={Pavel Tvrd{\'i}k and Ivan Simecek},
journal={2006 Eighth International Symposium on Symbolic and Numeric Algorithms for Scientific Computing},
year={2006},
pages={156-163}
}

Sparse matrix-vector multiplication (shortly SpMtimesV) is one of most common subroutines in the numerical linear algebra. The problem is that the memory access patterns during the SpMtimesV are irregular and the utilization of cache can suffer from low spatial or temporal locality. This paper introduces new approach for the acceleration the SpMtimesV. This approach consists of 3 steps. The first step divides the whole matrix into smaller parts (regions) those can fit in the cache. The second… CONTINUE READING