Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning and HPC Workloads

Evangelos Georganas, Dhiraj D. Kalamkar, Sasikanth Avancha, Menachem Adelman, Deepti Aggarwal, Cristina Anderson, Alexander Breuer, Jeremy Bruestle, Narendra Chaudhary, Abhisek Kundu, Denise Kutnick, Frank Laub, Md. Vasimuddin, Sanchit Misra, Ramanarayan Mohanty, Hans Pabst, Brian Retford, Barukh Ziv, Alexander Heinecke

Abstract: p>During the past decade, novel Deep Learning (DL) algorithms, workloads and hardware have been developed to tackle a wide range of problems. Despite the advances in workload and hardware ecosystems, the programming methodology of DL systems is stagnant. DL workloads leverage either highly-optimized, yet platform-specific and inflexible kernels from DL libraries, or in the case of novel operators, reference implementations are built <italic>via</italic> DL framework primitives with underwhelming performance. This work introduces the Tensor Processing Primitives (TPP), a programming abstraction striving for efficient, portable implementation of DL workloads with high-productivity. TPPs define a compact, yet versatile set of 2D-tensor operators [or a virtual Tensor Instruction Set Architecture (ISA)], which subsequently can be utilized as building-blocks to construct complex operators on high-dimensional tensors. The TPP specification is platform-agnostic, thus, code expressed <italic>via</italic> TPPs is portable, whereas the TPP implementation is highly-optimized and platform-specific. We demonstrate the efficacy and viability of our approach using standalone kernels and end-to-end DL & High Performance Computing (HPC) workloads expressed entirely <italic>via</italic> TPPs that outperform state-of-the-art implementations on multiple platforms.</p>