Patent · US Active

Hardware architecture for processing data in neural network

US11106972B1 · kind B1 · utility

4Cited by
2References
30Claims
0Family size

Assignees

Inventors

Key dates

Filing dateMar 9, 2021
Grant dateAug 31, 2021
Priority date
Expiry dateMar 9, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2207/4824
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A hardware accelerator that is efficient at performing computations related to a neural network. In one embodiment, the hardware accelerator includes a first data buffer that receives input data of a layer in the neural network and shift the input data slice by slice downstream. The hardware accelerator includes a second data buffer that receives kernel data of the layer in the neural network and shift the kernel data slice by slice downstream. The hardware accelerator includes a first input shift register that receives an input data slice from the first data buffer. The first input shift register may correspond to a two-dimensional shift register configured to shift values in the input data slice in x and y directions. The hardware accelerator includes a second input shift register that receives a kernel data slice from the second data buffer. A multiplication block performs convolution of the input and kernel data.

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