Example embodiments of the present invention relate to methods, systems, and a computer program product for storing data compressed according to available system resources. The method includes evaluating system resources of a data storage system and selecting a compression algorithm according to the system resources. The data set then may be compressed according to the selected compression algorithm and the compressed data stored in the data storage system.

Techniques and computing devices for compression memory coloring are described. In one embodiment, for example, an apparatus may include at least one memory, at least on processor, and logic for compression memory coloring, at least a portion of the logic comprised in hardware coupled to the at least one memory and the at least one processor, the logic to determine whether data to be written to memory is compressible, generate a compressed data element responsive to determining data is compressible, the data element comprising a compression indicator, a color, and compressed data, and write the compressed data element to memory. Other embodiments are described and claimed.

In various embodiments, the system and method described herein provide functionality for selecting an appropriate compression algorithm and settings given a cost model. Specifically, in selecting a compression method and configuration, the described system and method use a cost model to take into account the financial cost of a number of aspects of a particular compression scenario, including, but not limited to, the cost of performing the compression/decompression and the cost of storing the data. In this manner, intelligent trade-offs can be made between CPU/computing cost and data storage/transmission cost in an environment where a dollar amount can be associated with CPU processing time and storage/transmission volume. The described system and method can make such decisions dynamically, so that compression and/or decompression operations can respond to changing conditions on the fly, thus leading to better and more cost-effective management of resources.

A method for compressing is provided. The method includes compressing, via a processor, a portion of a first data packet to generate a second data packet having a compressed portion. The method includes transmitting the second data packet having the compressed portion via an interface to a co-processor. The processor and the co-processor are communicatively coupled via the interface. The method also includes unpacking, via the co-processor, the compressed portion of the second data packet to restore the first data packet.

An example apparatus, method, and computer program product are provided. The apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: encode or decode a high-level bitstream syntax for at least one neural network; wherein the high-level bitstream syntax comprises at least one information unit, wherein the at least one information unit comprises syntax definitions for the at least one neural network or a portion of the at least one neural network; and wherein a neural network representation (NNR) bitstream comprises one or more of the at least one information units, and wherein the syntax definitions provide one or more mechanisms for introducing a weight update compression interpretation into the NNR bitstream.

A matrix compression/decompression accelerator (MCA) system/method that coordinates lossless data compression (LDC) and lossless data decompression (LDD) transfers between an external data memory (EDM) and a local data memory (LDM) is disclosed. The system implements LDC using a 2D-to-1D transformation of 2D uncompressed data blocks (2DU) within LDM to generate 1D uncompressed data blocks (1DU). The 1DU is then compressed to generate a 1D compressed superblock (CSB) in LDM. This LDM CSB may then be written to EDM with a reduced number of EDM bus cycles. The system implements LDD using decompression of CSB data retrieved from EDM to generate a 1D decompressed data block (1DD) in LDM. A 1D-to-2D transformation is then applied to the LDM 1DD to generate a 2D decompressed data block (2DD) in LDM. This 2DD may then be operated on by a matrix compute engine (MCE) using a variety of function operators.

A system configured to generate a set of compression dictionary snapshots. The system can determine a subset of a set of compression dictionary definitions, the subset having a first subset comprising one or more definitions that have changed since a time of a previous snapshot and a second subset having one or more definitions associated with a predetermined portion of the dictionary. The system can further generate and store snapshots based at least in part on the determined subset of one or more definitions and determine a plurality of active snapshots from the set of snapshots such that the set of one or more definitions is included in the plurality of active snapshots.

A data compression method based on sampling and estimation is provided. The method includes: receiving a piece of data; extracting N data regions from M data regions of the piece of data; examining a data redundancy ratio in the N data regions; and determining, according to a value of the data redundancy ratio, whether to compress the piece of data.

The systems and methods described herein can pre-process a blendshape matrix via a global clusterization process and a local clusterization process. The pre-processing can cause the blendshape matrix to be divided into multiple blocks. The techniques can further apply a matrix compression technique to each block of the blendshape matrix to generate a compression result. The matrix compression technique can comprise a matrix approximation step, an accuracy verification step, and a recursive compression step. The compression result for each block may be combined to generate a compressed blendshape matrix for rendering a virtual entity.

An electrically erasable programmable read only memory (EEPROM) emulation (EEE) system includes a non-volatile memory arranged to have a plurality of sectors in which each sector is arranged to have a plurality of record locations. A new record of new data is programmed into a record location of an active sector of the plurality of sectors. After successfully completing the programming of the new record, a number of failure-to-program (FTP) occurrences during the programming is compared to a first threshold. When the number of FTP occurrences is greater than the first threshold, a determination is made as to whether compression is needed, and in response to determining that compression is needed, the method includes selectively performing compression based on a second threshold.