Jorge F. Fabeiro, Diego Andrade, Basilio B. Fraguela. Writing a performance-portable matrix multiplication. Parallel Computing, 52:65-77, 2016. [doi]
@article{FabeiroAF16, title = {Writing a performance-portable matrix multiplication}, author = {Jorge F. Fabeiro and Diego Andrade and Basilio B. Fraguela}, year = {2016}, doi = {10.1016/j.parco.2015.12.005}, url = {http://dx.doi.org/10.1016/j.parco.2015.12.005}, researchr = {https://researchr.org/publication/FabeiroAF16}, cites = {0}, citedby = {0}, journal = {Parallel Computing}, volume = {52}, pages = {65-77}, }