@INPROCEEDINGS{mazaheri_ea:euro-par:2019,
     author = {Mazaheri, Arya and Schulte, Johannes and Moskewicz, Matthew and Wolf, Felix and Jannesari, Ali},
      month = aug,
      title = {Enhancing the Programmability and Performance Portability of GPU Tensor Operations},
  booktitle = {Proc. of the 25th Euro-Par Conference, G{\"{o}}ttingen, Germany},
     series = {Lecture Notes in Computer Science},
     volume = {11725},
       year = {2019},
      pages = {213--226},
  publisher = {Springer},
       note = {(best paper award)},
        doi = {10.1007/978-3-030-29400-7_16}
}