A Hardware–Software Blueprint for Flexible Deep Learning Specialization

arXiv: Learning, pp. 8-16, 2019.

Cited by: 28|Bibtex|Views204|DOI:https://doi.org/10.1109/MM.2019.2928962
EI WOS
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

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.

Code:

Data:

Your rating :
0

 

Tags
Comments