Xiang Cui, Yifeng Chen, Changyou Zhang, Hong Mei. Auto-tuning Dense Matrix Multiplication for GPGPU with Cache. In IEEE 16th International Conference on Parallel and Distributed Systems, ICPADS 2010, 8-10 Dec. 2010, Shanghai, China. pages 237-242, IEEE, 2010. [doi]
@inproceedings{CuiCZM10, title = {Auto-tuning Dense Matrix Multiplication for GPGPU with Cache}, author = {Xiang Cui and Yifeng Chen and Changyou Zhang and Hong Mei}, year = {2010}, doi = {10.1109/ICPADS.2010.64}, url = {http://dx.doi.org/10.1109/ICPADS.2010.64}, tags = {caching}, researchr = {https://researchr.org/publication/CuiCZM10}, cites = {0}, citedby = {0}, pages = {237-242}, booktitle = {IEEE 16th International Conference on Parallel and Distributed Systems, ICPADS 2010, 8-10 Dec. 2010, Shanghai, China}, publisher = {IEEE}, }