Methods for Error Correction with Resistive Change Element Arrays

A method of error correction for a resistive change element array comprising:

• providing a resistive change element array, said resistive change element array comprising:
• a plurality of resistive change elements, each of said plurality of resistive change elements capable of adjusting between at least two non-volatile resistive states responsive to applied electrical stimuli, wherein one of said non-volatile resistive states is an initialized state;
• wherein said plurality of resistive change elements within said array are organized into a plurality of subsections, each of said subsections including at least one subset, each of said at least one subsets including a plurality of resistive change elements assigned as data cells and one resistive change element assigned as a flag cell;
• receiving a set of input data to be programmed into at least one of said subsections;
• initializing all of said data cells and said flag cells within at least one of said subsections into said initialized state;
• reading said data cells within said at least one initialized subsection to identify any data cells with an initialization error;
• comparing said data cells with an initialization error to corresponding bits within said input data to identify effective initialization errors, wherein said effective initialization errors are said data cells with an initialization error which have a different logical value to said corresponding bits within said set of input data;
• activating said flag cell of each of said subsets within said initialized subsection which contain at least one effective initialization error;
• encoding said input data by inverting all input data bits corresponding to said data cells within each of said subsets containing an activated flag cell to generate encoded input data;
• programming said encoded input data into at least one of said initialized subsections;
• accessing said programmed data during a read operation to obtain encoded read data;
• and
• decoding said encoded read data by inverting all read data bits corresponding to said data cells within each subset containing an activated flag cell to generate output data;
• wherein each of said subsets comprises a number of data cells equal to the number of data cells in said subsection divided by the number of flag cells in said subsection;
• and
• wherein said encoding step provides a first error correction operation.