Tensor processing primitives: a programming abstraction for efficiency and portability in deep learning workloads.
Evangelos Georganas, Dhiraj D. Kalamkar, Sasikanth Avancha, Menachem Adelman, Cristina Anderson, Alexander Breuer, Jeremy Bruestle, Narendra Chaudhary, Abhisek Kundu, Denise Kutnick, Frank Laub, Md. Vasimuddin, Sanchit Misra, Ramanarayan Mohanty, Hans Pabst, Barukh Ziv, Alexander Heinecke
Browse the full SC paper archive.