Dominik Ernst, Georg Hager, Jonas Thies, Gerhard Wellein. Performance Engineering for a Tall & Skinny Matrix Multiplication Kernels on GPUs. In Roman Wyrzykowski, Ewa Deelman, Jack J. Dongarra, Konrad Karczewski, editors, Parallel Processing and Applied Mathematics - 13th International Conference, PPAM 2019, Bialystok, Poland, September 8-11, 2019, Revised Selected Papers, Part I. Volume 12043 of Lecture Notes in Computer Science, pages 505-515, Springer, 2019. [doi]
@inproceedings{ErnstHTW19, title = {Performance Engineering for a Tall & Skinny Matrix Multiplication Kernels on GPUs}, author = {Dominik Ernst and Georg Hager and Jonas Thies and Gerhard Wellein}, year = {2019}, doi = {10.1007/978-3-030-43229-4_43}, url = {https://doi.org/10.1007/978-3-030-43229-4_43}, researchr = {https://researchr.org/publication/ErnstHTW19}, cites = {0}, citedby = {0}, pages = {505-515}, booktitle = {Parallel Processing and Applied Mathematics - 13th International Conference, PPAM 2019, Bialystok, Poland, September 8-11, 2019, Revised Selected Papers, Part I}, editor = {Roman Wyrzykowski and Ewa Deelman and Jack J. Dongarra and Konrad Karczewski}, volume = {12043}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-030-43229-4}, }