2000 character limit reached
Proposal for a High Precision Tensor Processing Unit
Published 10 Jun 2017 in cs.AR | (1706.03251v1)
Abstract: This whitepaper proposes the design and adoption of a new generation of Tensor Processing Unit which has the performance of Google's TPU, yet performs operations on wide precision data. The new generation TPU is made possible by implementing arithmetic circuits which compute using a new general purpose, fractional arithmetic based on the residue number system.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.