Work

A Hardware–Software Blueprint for Flexible Deep Learning Specialization

Year: 2019
Type: article
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.
Source: IEEE Micro
Language: English
Open Access status: green
OpenAlex ID: W2942862658
FWCI: 23.32
Cites: 18
Cited by: 279
Related to: 10