Patent · US Active

Fabric vectors for deep learning acceleration

US11232347B2 · kind B2 · utility

7Cited by
46References
52Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 17, 2018
Grant dateJan 25, 2022
Priority date
Expiry dateApr 17, 2038

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04L49/506
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements performs flow-based computations on wavelets of data. Each processing element has a respective compute element and a respective routing element. Instructions executed by the compute element include operand specifiers, some specifying a data structure register storing a data structure descriptor describing an operand as a fabric vector or a memory vector. The data structure descriptor further describes various attributes of the fabric vector: length, microthreading eligibility, number of data elements to receive, transmit, and/or process in parallel, virtual channel and task identification information, whether to terminate upon receiving a control wavelet, and whether to mark an outgoing wavelet a control wavelet.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.