Patent · US Active

Method and system for parallel statistical inference on highly parallel platforms

US8566259B2 · kind B2 · utility

7Cited by
0References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 7, 2010
Grant dateOct 22, 2013
Priority date
Expiry dateJan 1, 2032

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/285
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods for faster statistical inference in computation based recognition problems on highly parallel processors with multiple cores on-a-chip are disclosed, which include: selectively flattening levels of the recognition network to improve inference speed (improving the recognition model); selectively duplicating parts of the recognition network to minimize a critical section in atomic accesses to as few as one atomic instruction (improving the recognition procedure); and combining weight and source port into one 32-bit word to minimize the number of atomic operations. These methods have been implemented on an NVIDIA GTX 280 processor in a Large Vocabulary Continuous Speech Recognition (LVCSR) embodiment, and achieve more than a 10× speed up compared to a highly optimized sequential implementation on an Intel Core i7 processor.

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