Patent · US Active

Physics simulation on machine-learning accelerated hardware platforms

US11550971B1 · kind B1 · utility

23Cited by
8References
35Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 18, 2019
Grant dateJan 10, 2023
Priority date
Expiry dateSep 1, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

At least one machine-accessible storage medium that provides instructions that, when executed by a machine, will cause the machine to perform operations. The operations comprise configuring a simulated environment to be representative of a physical device based, at least in part, on an initial description of the physical device that described structural parameters of the physical device. The operations further comprise performing a physics simulation with an artificial intelligence (“AI”) accelerator. The AI accelerator includes a matrix multiply unit for computing convolution operations via a plurality of multiply-accumulate units. The operations further comprise computing a field response in response of the physical device in response to an excitation source within the simulated environment when performing the physics simulation. The field response is computed, at least in part, with the convolution operations to perform spatial differencing.

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