A processing device for executing a machine learning neural network operation includes memory and a processor. The processor is configured to receive input data at a layer of the machine learning neural network operation, receive a plurality of sorted filters to be applied to the input data, apply the plurality of sorted filters to the input data to produce a plurality of different feature maps, compress the plurality of different feature maps according to a sparsity of the feature maps and store the plurality of different feature maps in the memory.

Systems, computer-implemented methods and/or computer program products are provided for facilitating waveform synthesis. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a composing component that compresses data defining a waveform by employing amplitude partitioning of the data using equivalent sizing. The composing component can further employ run-length encoding to generate a string of integers representing a plurality of groups of the data as partitioned according both to amplitude and progressing time. In an embodiment, a decoding component can employ a binary search to decode a running sum array of integers representing at least a portion of the data, to decompress the data.

A request for performing a data storing operation directed to a database table that comprises a plurality of table columns is received. Columnar compression metadata is accessed to identify one or more table columns in the database table, each of the one or more table columns being designated to store compressed columnar values. The columnar compression metadata is used to apply one or more columnar compression methods to generate, from one or more uncompressed columnar values received with the request for the data storing operation, one or more compressed columnar values to be persisted in the one or more table columns in the database table. A database statement is executed to persist the one or more compressed columnar values in the one or more table columns in the database table.

A method for encoding a sequence of records, each record of said sequence of records comprising a plurality of different fields, said different fields being identical for each record of said sequence of records, said method comprising selecting an encoding algorithm for each field of said plurality of fields such that said each field is associated with a selected encoding algorithm; encoding data of said each field using said selected encoding algorithm to determine encoded field data for said each field for said each record; and for said each record, interleaving said encoded field data for said each field to produce an encoded sequence of said records wherein said encoded field data are interleaved for said each record.

A method for encoding a sequence of records, each record of said sequence of records comprising a plurality of different fields, said different fields being identical for each record of said sequence of records, said method comprising selecting an encoding algorithm for each field of said plurality of fields such that said each field is associated with a selected encoding algorithm; encoding data of said each field using said selected encoding algorithm to determine encoded field data for said each field for said each record; and for said each record, interleaving said encoded field data for said each field to produce an encoded sequence of said records wherein said encoded field data are interleaved for said each record.

Techniques and systems are provided for compressing data in a neural network. For example, output data can be obtained from a node of the neural network. Re-arranged output data having a re-arranged scanning pattern can be generated. The re-arranged output data can be generated by re-arranging the output data into the re-arranged scanning pattern. One or more residual values can be determined for the re-arranged output data by applying a prediction mode to the re-arranged output data. The one or more residual values can then be compressed using a coding mode.

Methods of image compression are described. A stream of color image data is filtered with a prediction routine using a pixel neighborhood. The filtered stream of color image data is sorted with a block sorting routing. A version of the color image data is compressed based on the sorted and filtered stream of color image data.

Methods of image compression are described. A stream of color image data is filtered with a prediction routine using a pixel neighborhood. The filtered stream of color image data is sorted with a block sorting routing. A version of the color image data is compressed based on the sorted and filtered stream of color image data.

Partition information associated with one or more partitions that divide a range of values into at least a higher and lower set of values is received. An uncompressed value that falls within the range of values is received and a compressed value that includes a set indicator and intra-set information is generated using the uncompressed value. This includes generating the set indicator based at least in part on whether the uncompressed value falls in the higher or lower set of values, determining whether the uncompressed value includes an extraneous bit where it is necessary but not sufficient that the uncompressed value fall in the higher set of values for the uncompressed value to include the extraneous bit, and generating the intra-set information, including by: excluding the extraneous bit in the uncompressed value from the intra-set information if it is determined to be included. The compressed value is output.

Examples described herein relate to performing data compression by performing dictionary matching of data using hardware circuitry to generate dictionary matched results and post-processing of dictionary matched results using software executed by a processor. In some examples, dictionary matching includes LZ77 dictionary matching. In some examples, dictionary matching occurs on multiple segments of data in parallel.