Chetan Jhurani, Paul Mullowney. A GEMM interface and implementation on NVIDIA GPUs for multiple small matrices. J. Parallel Distrib. Comput., 75:133-140, 2015. [doi]
@article{JhuraniM15, title = {A GEMM interface and implementation on NVIDIA GPUs for multiple small matrices}, author = {Chetan Jhurani and Paul Mullowney}, year = {2015}, doi = {10.1016/j.jpdc.2014.09.003}, url = {http://dx.doi.org/10.1016/j.jpdc.2014.09.003}, researchr = {https://researchr.org/publication/JhuraniM15}, cites = {0}, citedby = {0}, journal = {J. Parallel Distrib. Comput.}, volume = {75}, pages = {133-140}, }