Imperial College London
Portrait Picture

ProfessorSpencerSherwin

Faculty of Engineering, Department of Aeronautics

Head of the Department of Aeronautics
 
 
 
//

Contact

 

+44 (0)20 7594 5052s.sherwin Website

 
 
//

Location

 

318City and Guilds BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Grigoras:2016:10.1109/FPL.2016.7577352,
author = {Grigoras, P and Burovskiy, P and Luk, W and Sherwin, S},
doi = {10.1109/FPL.2016.7577352},
title = {Optimising Sparse Matrix Vector multiplication for large scale FEM problems on FPGA},
url = {http://dx.doi.org/10.1109/FPL.2016.7577352},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Sparse Matrix Vector multiplication (SpMV) is an important kernel in many scientific applications. In this work we propose an architecture and an automated customisation method to detect and optimise the architecture for block diagonal sparse matrices. We evaluate the proposed approach in the context of the spectral/hp Finite Element Method, using the local matrix assembly approach. This problem leads to a large sparse system of linear equations with block diagonal matrix which is typically solved using an iterative method such as the Preconditioned Conjugate Gradient. The efficiency of the proposed architecture combined with the effectiveness of the proposed customisation method reduces BRAM resource utilisation by as much as 10 times, while achieving identical throughput with existing state of the art designs and requiring minimal development effort from the end user. In the context of the Finite Element Method, our approach enables the solution of larger problems than previously possible, enabling the applicability of FPGAs to more interesting HPC problems.
AU  - Grigoras,P
AU  - Burovskiy,P
AU  - Luk,W
AU  - Sherwin,S
DO  - 10.1109/FPL.2016.7577352
PY  - 2016///
SN  - 1946-1488
TI  - Optimising Sparse Matrix Vector multiplication for large scale FEM problems on FPGA
UR  - http://dx.doi.org/10.1109/FPL.2016.7577352
UR  - http://hdl.handle.net/10044/1/42864
ER  -
Download