Fast programming scheme for power loss protection—a machine learning based algorithm

A storage controller for controlling a storage device, the storage controller comprising:

• at least one processor,
• wherein, based on detecting a power loss corresponding to the storage device, the at least one processor is configured to:
• obtain a word from a volatile memory included in the storage device;
• apply first programming pulses to a first word line from among a plurality of word lines to write the word to the first word line, wherein the plurality of word lines are included in a non-volatile memory included in the storage device;
• determine a number of unprogrammed cells, wherein the unprogrammed cells correspond to remainder data included in the word;
• based on determining that the number of unprogrammed cells is less than or equal to a first threshold number, determine an expected number of second programming pulses for reducing the number of unprogrammed cells in the first word line to below a second threshold number, and an expected number of third programming pulses for writing the remainder data to a second word line;
• compare the expected number of second programming pulses and the expected number of third programming pulses to obtain a comparison result;
• and
• write the remainder data to the first word line or the second word line based on the comparison result.

A method of storing data in a storage device, the method comprising:

• writing a word to a first word line from among a plurality of word lines;
• comparing a number of unprogrammed cells included in the first word line to a first threshold number and a second threshold number, wherein the unprogrammed cells correspond to remainder data included in the word;
• based on determining that the number of unprogrammed cells is less than or equal to the first threshold number and greater than the second threshold number, determining whether to continue writing the word to the first word line by providing information about the first word line to a machine learning model;
• and
• based on determining not to continue writing the word to the first word line, writing the remainder data to a second word line from among the plurality of word lines.