@inproceedings{Zhang:2017,
 author = {Zhang, Xiuxia and Tan, Guangming and Xue, Shuangbai and Li, Jiajia and Zhou, Keren and Chen, Mingyu},
 title = {Understanding the GPU Microarchitecture to Achieve Bare-Metal Performance Tuning},
 booktitle = {Proceedings of the 22Nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming},
 series = {PPoPP '17},
 year = {2017},
 isbn = {978-1-4503-4493-7},
 location = {Austin, Texas, USA},
 pages = {31--43},
 numpages = {13},
 url = {http://doi.acm.org/10.1145/3018743.3018755},
 doi = {10.1145/3018743.3018755},
 acmid = {3018755},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {assembler, convolution, gpu, performance, reverse-engineering gpu isa encoding, sgemm},
}