Imperial College London

ProfessorWayneLuk

Faculty of EngineeringDepartment of Computing

Professor of Computer Engineering
 
 
 
//

Contact

 

+44 (0)20 7594 8313w.luk Website

 
 
//

Location

 

434Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Grigoras:2016:10.1145/2847263.2847338,
author = {Grigoras, P and Burovskiy, P and Luk, W},
doi = {10.1145/2847263.2847338},
pages = {179--184},
publisher = {ACM},
title = {CASK - Open-source custom architectures for sparse kernels},
url = {http://dx.doi.org/10.1145/2847263.2847338},
year = {2016}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Sparse matrix vector multiplication (SpMV) is an important kernel in many scientific applications. To improve the performance and applicability of FPGA based SpMV, we propose an approach for exploiting properties of the input matrix to generate optimised custom architectures. The architectures generated by our approach are between 3.8 to 48 times faster than the worst case architectures for each matrix, showing the benefits of instance specific design for SpMV.
AU - Grigoras,P
AU - Burovskiy,P
AU - Luk,W
DO - 10.1145/2847263.2847338
EP - 184
PB - ACM
PY - 2016///
SP - 179
TI - CASK - Open-source custom architectures for sparse kernels
UR - http://dx.doi.org/10.1145/2847263.2847338
UR - http://hdl.handle.net/10044/1/33329
ER -