Yufan Xu, Qiwei Yuan, Erik Curtis Barton, Rui Li 0033, P. Sadayappan, Aravind Sukumaran-Rajam. Effective Performance Modeling and Domain-Specific Compiler Optimization of CNNs for GPUs. In Andreas Klöckner, José Moreira, editors, Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, PACT 2022, Chicago, Illinois, October 8-12, 2022. pages 252-264, ACM, 2022. [doi]
@inproceedings{XuYB0SS22, title = {Effective Performance Modeling and Domain-Specific Compiler Optimization of CNNs for GPUs}, author = {Yufan Xu and Qiwei Yuan and Erik Curtis Barton and Rui Li 0033 and P. Sadayappan and Aravind Sukumaran-Rajam}, year = {2022}, doi = {10.1145/3559009.3569674}, url = {https://doi.org/10.1145/3559009.3569674}, researchr = {https://researchr.org/publication/XuYB0SS22}, cites = {0}, citedby = {0}, pages = {252-264}, booktitle = {Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, PACT 2022, Chicago, Illinois, October 8-12, 2022}, editor = {Andreas Klöckner and José Moreira}, publisher = {ACM}, isbn = {978-1-4503-9868-8}, }