US 10,380,386 B1 · Accelerator for k-means clustering with memristor crossbars

Abstract

A crossbar array includes a number of memory elements. A vector input register has N voltage inputs to the crossbar array. A vector output register has M voltage outputs from the crossbar array. An analog-to-digital converter (ADC) is electronically coupled to the vector output register. A digital-to-analog converter (DAC) is electronically coupled to the vector input register. A clustering processor is electronically coupled to the ADC and to the DAC. The clustering processor is configured to program columns of the crossbar array with a set of k cluster center values; apply voltages to rows of the crossbar array where the applied voltages represent a set of data values; and determine a minimum distance of each data value to each k cluster center values based on the voltage output from the output register of each of the plurality of the programmed columns.

Claims17

Dependent claims

A memristive dot product system for vector processing, comprising:

a crossbar array having a number of memory elements, the crossbar array having N rows, M columns and N×M memory elements;
a vector input register comprising N voltage inputs to the crossbar array;
a vector output register comprising M voltage outputs from the crossbar array;
and
an analog-to-digital converter (ADC) electronically coupled to the vector output register;
a digital-to-analog converter (DAC) electronically coupled to the vector input register;
a clustering processor electronically coupled to the ADC and to the DAC, the clustering processor configured to:
program a plurality of columns of the crossbar array with a first set of k cluster center values;
apply voltages to a plurality of rows of the crossbar array, the applied voltages representing a set of data values;
inject a noise signal by applying a voltage to another row of the crossbar array in addition to the voltages applied to the plurality of rows;
and
determine a minimum distance of each data value to each k cluster center values based on the voltage output from the output register of each of the plurality of the programmed columns.

9 more elements

A non-transitory computer storage device storing instructions operable to cause one or more computer methods to perform operations comprising:

programming a plurality of columns of a memristor crossbar array with a first set of k cluster center values, each memory element comprising a memristor and a transistor in series with one another, the crossbar array having N rows, M columns and N×M memory elements;
applying voltages to a plurality of rows of the crossbar array, the applied voltages representing a set of data values;
injecting a noise signal by applying a voltage to another row of the crossbar array in addition to the voltages applied to the plurality of rows;
and
determining a minimum distance of each data value to each k cluster center values based on the voltage output from the output register of each of the plurality of the programmed columns.

2 more elements

Dependencies are inferred from the claim text.

Accelerator for k-means clustering with memristor crossbars

Life of this patent

Accelerator for k-means clustering with memristor crossbars

Life of this patent

Abstract

Claims17