Patent · US Active

Neural network training with acceleration

US12136138B2 · kind B2 · utility

0Cited by
23References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 11, 2022
Grant dateNov 5, 2024
Priority date
Expiry dateDec 26, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2212/454
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system and method for training a neural network. In some embodiments, the system includes: a graphics processing unit cluster; and a computational storage cluster connected to the graphics processing unit cluster by a cache-coherent system interconnect. The graphics processing unit cluster may include one or more graphics processing units. The computational storage cluster may include one or more computational storage devices. A first computational storage device of the one or more computational storage devices may be configured to (i) store an embedding table, (ii) receive an index vector including a first index and a second index; and (iii) calculate an embedded vector based on: a first row of the embedding table, corresponding to the first index, and a second row of the embedding table, corresponding to the second index.

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