Patent · US Active

Software-defined memory bandwidth reduction by hierarchical stream buffering for general matrix multiplication in a programmable IC

US10354733B1 · kind B1 · utility

17Cited by
6References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 17, 2017
Grant dateJul 16, 2019
Priority date
Expiry dateOct 17, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/044
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods and apparatus are described for partitioning and reordering block-based matrix multiplications for high-speed data streaming in general matrix multiplication (GEMM), which may be implemented by a programmable integrated circuit (IC). By preloading and hierarchically caching the blocks, examples of the present disclosure reduce the double data rate (DDR) memory intake bandwidth for software-defined GEMM accelerators.

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