Sparse column-aware encodings for numeric data types

A computing system comprising

• a processor;
• row and column addressable memory media having plurality of rows and columns of memory cells;
• and
• circuitry connected to the memory media and operatively connected to the processor, wherein the computing system is configured to:
• store data comprising a plurality of sparse binary bit vectors in respective rows in the memory media;
• receive a query from a requesting entity for matching an integer or floating-point number;
• convert the integer or floating-point number to generate a search key having an encoded format comprising a bit vector having a predetermined number k set bits;
• perform column-wise reads of the memory media on only k columns of the plurality of columns, each of the k columns associated with a respective one of the k set bits, to obtain a plurality of vertical bit vectors;
• aggregate set bits in the plurality of vertical bit vectors on a row-wise basis;
• based on the aggregation, calculate similarity scores for a plurality of rows;
• determine, based on the similarity scores, rows, of the plurality of rows, that store data matching the search key;
• and
• return the rows that store data matching the search key to the requesting entity.

A method comprising:

• receiving a query from a requesting entity for matching an integer or floating-point number previously written to a memory media having a plurality of rows and columns of memory cells using an encoded version of the integer or floating-point number using an m-of-n constant weight encoding;
• converting the integer or floating-point number to a Hexadecimal (Hex) format;
• for each of a plurality of Hex values in the Hex format, encoding the Hex value using the m-of-n constant weight encoding to generate encoded Hex values;
• concatenating the encoded Hex values to form a search key comprising a bit vector having k set bits;
• performing column-wise reads of the memory media on only k columns of the plurality of columns, each of the k columns associated with a respective one of the k set bits, to obtain a plurality of vertical bit vectors, each vertical bit vector associated with a respective column and comprising a sequence of binary data having bit positions associated with respective rows;
• aggregating set bits in the plurality of vertical bit vectors on a row-wise basis;
• based on the aggregation, calculating similarity scores for a plurality of rows;
• determining, based on the similarity scores, rows, of the plurality of rows, that store data matching the search key;
• and
• returning the rows that store data matching the search key to the requesting entity.