Litcius/Paper detail

Heron: Automatically Constrained High-Performance Library Generation for Deep Learning Accelerators

Jun Bi, Qi Guo, Xiaqing Li, Yongwei Zhao, Yuanbo Wen, Yuxuan Guo, Enshuai Zhou, Xing Hu, Zidong Du, Ling Li, Huaping Chen, Tianshi Chen

202324 citationsDOI

Abstract

Deep Learning Accelerators (DLAs) are effective to improve both performance and energy efficiency of compute-intensive deep learning algorithms. A flexible and portable mean to exploit DLAs is using high-performance software libraries with well-established APIs, which are typically either manually implemented or automatically generated by exploration-based compilation approaches. Though exploration-based approaches significantly reduce programming efforts, they fail to find optimal or near-optimal programs from a large but low-quality search space because the massive inherent constraints of DLAs cannot be accurately characterized.

Topics & Concepts

Computer scienceExploitDeep learningArtificial intelligenceSoftwareHeronQuality (philosophy)Space (punctuation)Computer engineeringMachine learningOperating systemComputer securityEpistemologyBiologyPhilosophyPaleontologyParallel Computing and Optimization TechniquesAdvanced Neural Network ApplicationsMachine Learning and Data Classification
Heron: Automatically Constrained High-Performance Library Generation for Deep Learning Accelerators | Litcius