17550493. ENERGY-EFFICIENT ANALOG-TO-DIGITAL CONVERSION IN MIXED SIGNAL CIRCUITRY simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

From WikiPatents
Jump to navigation Jump to search

ENERGY-EFFICIENT ANALOG-TO-DIGITAL CONVERSION IN MIXED SIGNAL CIRCUITRY

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Kyu-hyoun Kim of Chappaqua NY (US)

Mingu Kang of Old Tappan NJ (US)

Ankur Agrawal of Chappaqua NY (US)

Monodeep Kar of New York NY (US)

ENERGY-EFFICIENT ANALOG-TO-DIGITAL CONVERSION IN MIXED SIGNAL CIRCUITRY - A simplified explanation of the abstract

This abstract first appeared for US patent application 17550493 titled 'ENERGY-EFFICIENT ANALOG-TO-DIGITAL CONVERSION IN MIXED SIGNAL CIRCUITRY

Simplified Explanation

The patent application describes an apparatus that performs a successive approximation analog-to-digital conversion of an analog input, which represents the result of multiplying two vectors, to a digital output. The apparatus uses a processor and memory to determine an upper bound on the multiplication result and based on this upper bound, identifies and skips a portion of the conversion process.

  • The apparatus performs a successive approximation analog-to-digital conversion of an analog input.
  • The analog input represents the result of multiplying two vectors.
  • The apparatus determines an upper bound on the multiplication result.
  • Based on the determined upper bound, the apparatus identifies a portion of the conversion process to be skipped.
  • The identified portion of the conversion process is then skipped.

Potential Applications

  • This technology can be applied in various fields that require analog-to-digital conversion, such as telecommunications, audio processing, and instrumentation.
  • It can be used in systems that involve multiplying vectors and converting the analog result to digital form, such as signal processing applications and machine learning algorithms.

Problems Solved

  • The apparatus solves the problem of efficiently converting an analog input representing the result of multiplying two vectors to a digital output.
  • By determining an upper bound and skipping unnecessary portions of the conversion process, the apparatus improves the efficiency and speed of the analog-to-digital conversion.

Benefits

  • The apparatus provides a more efficient and faster method for analog-to-digital conversion.
  • By skipping unnecessary portions of the conversion process, the apparatus reduces computational requirements and improves overall system performance.
  • The technology can lead to cost savings in terms of reduced power consumption and improved processing efficiency.


Original Abstract Submitted

An apparatus comprises at least one processor and at least one memory including instruction code configured to, with the at least one processor, cause the apparatus at least to perform a successive approximation analog-to-digital conversion of an analog input, representing a result of multiplication of first and second vectors, to a digital output by determining an upper bound on the result of multiplication of the first and second vectors, identifying, based at least in part on the determined upper bound, at least a portion of the successive approximation analog-to-digital conversion to be skipped, and skipping the identified portion of the successive approximation analog-to-digital conversion.