Patent · US Active

Spatial tiling of compute arrays with shared control

US11954580B2 · kind B2 · utility

0Cited by
8References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 16, 2020
Grant dateApr 9, 2024
Priority date
Expiry dateOct 16, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/046
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In one embodiment, a method for machine learning acceleration includes receiving, by a shared controller of a tensor processor cluster that includes multiple tensor processors, a multi-cycle instruction, determining, based on the instruction, a sequence of vector operations to be executed by the tensor processors and address information usable to determine a respective spatial partition of an input tensor on which each tensor processor is to operate when performing each vector operation. The method also includes, for each vector operation in the sequence, generating, based on the address information, a common address offset, relative to a respective base address associated with each tensor processor, at which each tensor processor is to retrieve the respective spatial partition on which the tensor processor is to operate, multicasting the common address offset to the tensor processors, and controlling the tensor processors to execute the vector operation in parallel and in lock step.

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