A data processing apparatus includes a circuit selecting unit and a decoding processor. The circuit selecting unit selects a decoder circuit for each data part of encoded target data. The decoder circuit is suitable for an arrangement of run lengths in the data part. The decoding processor performs reconfiguration to form the decoder circuit selected for the data part, and decodes the target data.

A method for determining an encoding used for a sequence of bytes may be provided. The method comprises providing a set of candidate code pages and transforming them into different groups of sequences of bytes, wherein each group of sequences of bytes corresponds to one of the candidate code pages. Thereby each code point is transformed by applying a transformation from one of the candidate code pages to a reference code point value relating to a reference encoding for each code point. The method comprises further separating each of the transformed sequences of bytes into groups of tokens, wherein each group of tokens relates to one candidate code page, and providing an index relating to a text corpus. Furthermore, the method comprises selecting a code page from the set of candidate code pages at least partially based on how many tokens are found in the index.

A method for data compression includes reading first data representing sensor data capture, compressing the data with a lossless algorithm, transmitting the compressed data as a reference frame, reading subsequent data, calculating a delta between the first data and the subsequent data, compressing the data delta, and determining if the compression ratio of the compressed data delta is within a predetermined tolerance threshold. If the compression ratio is within the threshold, transmitting the compressed data delta frame, and repeating the calculating, compressing, and determining steps for subsequent data; Else if the compression ratio is not within the threshold, compressing the current subsequent data and transmitting the result as an updated reference frame. Then repeating the calculating, compressing, and determining steps for subsequent data. A system and a non-transitory computer-readable medium for implementing the method are also disclosed.

A system having a downhole sensor device and a compression device to obtain a sparse representation of data in downhole telemetry applications is described. The downhole sensor device can collect sensor data while the downhole sensor device is within a borehole. The compression device is coupled to the downhole sensor device and configured to receive the sensor data. The compression device can determine a wavelet coefficient vector for at least one row of n-tuple vectors. The wavelet coefficient vector can have a sparse representation of one or more nonzero elements. The compression device can process the wavelet coefficient vector through a set of compression algorithms, and determine a minimal bit cost of the processed wavelet coefficient vector. The compression device can select a compression algorithm from the set of compression algorithms corresponding to the minimal bit cost. The compression device can generate compressed data based on the selected compression algorithm.

In several aspects, a computing device analyzes data to determine its characteristics. The computing device selects at least one compression process based on the characteristics. A compression switch and a compression level are dynamically adjusted based on multiple factors including available system resources, desired storage savings and performance requirement. The compression level dynamically varies depending on the data being processed and a workload on a system. Performance of compression and decompression operations are continuously monitored for dynamically adjusting compression parameters to optimize performance.

A runtime data-format optimizer for a processing element includes a sparsity-detector and a compression-converter. The sparsity-detector selects a first compression-conversion format during a runtime of the processing element based on a performance model that is based on a first sparsity pattern of first data stored in a first memory that is exterior to the processing element and a second sparsity pattern of second data that is to be stored in a second memory within the processing element. The second sparsity pattern is based on a runtime configuration of the processing element. The first data is stored in the first memory using a first compression format and the second data is to be stored in the second memory using a second compression format. The compression-conversion circuit converts the first compression format of the first data to be the second compression format of the second data based on the first compression-conversion format.

A method for data compression includes reading first data representing sensor data capture, compressing the data with a lossless algorithm, transmitting the compressed data as a reference frame, reading subsequent data, calculating a delta between the first data and the subsequent data, compressing the data delta, and determining if the compression ratio of the compressed data delta is within a predetermined tolerance threshold. If the compression ratio is within the threshold, transmitting the compressed data delta frame, and repeating the calculating, compressing, and determining steps for subsequent data; Else if the compression ratio is not within the threshold, compressing the current subsequent data and transmitting the result as an updated reference frame. Then repeating the calculating, compressing, and determining steps for subsequent data. A system and a non-transitory computer-readable medium for implementing the method are also disclosed.

Systems and methods for adaptive compression mode selection for memory buffers such as those used in or with a portable computing device (PCD) are presented. During operation of the PCD a first compression mode is selected for a buffer and the buffer is formatted to the first compression mode. Any access to the buffer by a component of the PCD, core of the PCD or software application running on the PCD is monitored. Based on the amount and/or type of access to the buffer, a second compression mode for the buffer is selected. The buffer is formatted to the second compression mode, providing a cost effective ability to adaptively format buffers based on the component(s), cores(s), and/or software application(s) accessing the buffers, and allowing for improving or optimizing bandwidth, memory footprint, resource conflict, power consumption, latency, and/or performance of component(s), core(s), or software application(s) accessing buffers as desired.

A method of a method of communicating a data file over a radio frequency data link includes steps of determining a type of data represented in the data file; analyzing the data in the data file; selecting an encoding scheme from a plurality of encoding schemes and encoding one or more messages to represent the data file according to the selected encoding scheme. The one or more messages comply with a protocol for a character-oriented data link and the encoding losslessly compresses the data into the one or more messages.

A method for determining an encoding used for a sequence of bytes may be provided. The method comprises providing a set of candidate code pages and transforming them into different groups of sequences of bytes, wherein each group of sequences of bytes corresponds to one of the candidate code pages. Thereby each code point is transformed by applying a transformation from one of the candidate code pages to a reference code point value relating to a reference encoding for each code point. The method comprises further separating each of the transformed sequences of bytes into groups of tokens, wherein each group of tokens relates to one candidate code page, and providing an index relating to a text corpus. Furthermore, the method comprises selecting a code page from the set of candidate code pages at least partially based on how many tokens are found in the index.