@article{benanzaautomaticubenchmarkgenerationto,
  title = {Benanza: Automatic $μ$Benchmark 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 = {2019},
  eprint = {1911.06922},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1911.06922v3},
}