Jing Wu, Joseph JáJá. Achieving Native GPU Performance for Out-of-Card Large Dense Matrix Multiplication. Parallel Processing Letters, 26(2):1-17, 2016. [doi]
@article{WuJ16,
title = {Achieving Native GPU Performance for Out-of-Card Large Dense Matrix Multiplication},
author = {Jing Wu and Joseph JáJá},
year = {2016},
doi = {10.1142/S0129626416500079},
url = {http://dx.doi.org/10.1142/S0129626416500079},
researchr = {https://researchr.org/publication/WuJ16},
cites = {0},
citedby = {0},
journal = {Parallel Processing Letters},
volume = {26},
number = {2},
pages = {1-17},
}