A Hardware–Software Blueprint for Flexible Deep Learning Specialization

Thierry Moreau,Tianqi Chen,Luis Vega,Jared Roesch,Lianmin Zheng,Josh Fromm,Ziheng Jiang,Luis Ceze,Carlos Guestrin,Arvind Krishnamurthy

arXiv: Learning（2019）

引用 162|浏览637

暂无评分

摘要

This article describes the Versatile Tensor Accelerator (VTA), a programmable DL architecture designed to be extensible in the face of evolving workloads. VTA achieves “flexible specialization” via a parameterizable architecture, two-level Instruction Set Architecture (ISA), and a Just in Time (JIT) compiler.

查看译文

关键词

Machine learning,Computer architecture,Runtime,Task analysis,Computational modeling,Deep learning

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要