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
Authors: Thierry Moreau, Tianqi Chen, Luis Vega, Jared Roesch, Eddie Yan, Lianmin Zheng, Josh Fromm, Ziheng Jiang, Luis Ceze, Carlos Guestrin, Arvind Krishnamurthy
Institutions: University of Washington, Shanghai Jiao Tong University
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1274507311, G5643820060, G850323970
OpenAlex ID: W2942862658
