## Reducing Inter-Process Communication Overhead in Parallel Sparse Matrix-Matrix Multiplication

- Md. Salman Ahmed, Jennifer Houser, Mohammad A. Hoque, Rezaul Raju, Phil Pfeiffer
- IJGHPC
- 2017

Highly Influenced

@article{Hoque2015ParallelSM, title={Parallel sparse matrix-matrix multiplication: a scalable solution with 1D algorithm}, author={Mohammad Asadul Hoque and Md Rezaul Karim Raju and Christopher John Tymczak and Daniel Vrinceanu and Kiran Chilakamarri}, journal={IJCSE}, year={2015}, volume={11}, pages={391-401} }

- Published 2015 in IJCSE
DOI:10.1504/IJCSE.2015.073498

This paper presents a novel implementation of parallel sparse matrix-matrix multiplication using distributed memory systems on heterogeneous hardware architecture. The proposed algorithm is expected to be linearly scalable up to several thousands of processors for matrices with dimensions over 10 (million). Our approach of parallelism is based on 1D decomposition and can work for both structured and unstructured sparse matrices. The storage mechanism is based on distributed hash lists, which… CONTINUE READING

Highly Influenced