Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu. Benanza: Automatic μBenchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs. In 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), New Orleans, LA, USA, May 18-22, 2020. pages 440-450, IEEE, 2020. [doi]
@inproceedings{LiDXH20-0, title = {Benanza: Automatic μBenchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs}, author = {Cheng Li and Abdul Dakkak and Jinjun Xiong and Wen-mei Hwu}, year = {2020}, doi = {10.1109/IPDPS47924.2020.00053}, url = {https://doi.org/10.1109/IPDPS47924.2020.00053}, researchr = {https://researchr.org/publication/LiDXH20-0}, cites = {0}, citedby = {0}, pages = {440-450}, booktitle = {2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), New Orleans, LA, USA, May 18-22, 2020}, publisher = {IEEE}, isbn = {978-1-7281-6876-0}, }