Parallel processing of data having data dependencies for accelerating the launch and performance of operating systems and other computing applications

A non-transitory, tangible medium storing computer- or processor-readable software having a plurality of executable instructions for execution by one or more processors or processor cores for parallel decompression of a compressed file, the plurality of executable instructions operative in a smartphone or tablet to accelerate booting of an operating system or to accelerate launching of a computing application, the compressed file having a plurality of compressed blocks, the compressed file comprising independent data and dependent, run length encoded (“RLE”) data having data-dependent references spanning multiple compressed blocks of the plurality of blocks, the non-transitory, tangible medium comprising:

• one or more executable instructions, of the plurality of executable instructions, to cause one or more decompression processors or processor cores, of a plurality of processors or processor cores, to partially decompress a selected block into the independent data, the dependent RLE data, and any linked dependent RLE data;
• and
• one or more executable instructions, of the plurality of executable instructions, to cause one or more aggregation and merge processors or processor cores, of the plurality of processors or processor cores, to sequence the independent data, dependent RLE data, and linked dependent RLE data from a plurality of partial decompressions of the plurality of compressed blocks, to obtain data specified by the dependent RLE data and linked dependent RLE data, and to insert the obtained data into corresponding locations to form an uncompressed data file.

An apparatus for parallel decompression of a compressed file, the apparatus comprising:

• a first, nonvolatile memory storing the compressed file, the compressed file having a plurality of compressed blocks, the compressed file comprising independent data and dependent, run length encoded (“RLE”) data having data-dependent references spanning multiple compressed blocks of the plurality of blocks, the first memory further storing metadata indicating a start or end of each compressed block of the plurality of compressed blocks;
• at least one distributor processor or processor core, of a plurality of processors or processor cores, programmed, adapted or configured to utilize the stored metadata to identify the start or end of the selected compressed block of the plurality of compressed blocks;
• a plurality of decompression processors or processor cores, of the plurality of processors or processor cores, each decompression processor or processor core of the plurality of decompression processors or processor cores programmed, adapted or configured to partially decompress a corresponding selected block of the plurality of compressed blocks, in parallel, into independent data, dependent RLE data, and any linked dependent RLE data;
• and
• one or more aggregation and merge processors or processor cores, of the plurality of processors or processor cores, at least one aggregation and merge processor or processor core programmed, adapted or configured to sequence the independent data, dependent RLE data, and linked dependent RLE data from a plurality of partial decompressions of the plurality of compressed blocks, and at least one aggregation and merge processor or processor core programmed, adapted or configured to obtain data specified by the dependent RLE data and linked dependent RLE data, and insert the obtained data into corresponding locations to form an uncompressed data file.

An apparatus for parallel processing of a file, the apparatus comprising:

• a first, nonvolatile memory storing the file, the file having a plurality of blocks, the file including independent data and dependent data having data dependencies spanning multiple blocks of the plurality of blocks;
• a second, random access memory;
• at least one distributor processor or processor core, of a plurality of processors or processor cores, programmed, adapted or configured to identify a start or end of each block of the plurality of blocks and transfer a single or individuated block to the one or more computation processors or processor cores;
• a plurality of computation processors or processor cores, of the plurality of processors or processor cores, each computation processor or processor core coupled to the at least one distributor processor or processor core and programmed, adapted or configured to partially transform, in parallel, a selected block into independent data, dependent data, and linked dependent data;
• and
• one or more aggregation and merge processors or processor cores, of the plurality of processors or processor cores, at least one aggregation and merge processor or processor core coupled to the plurality of computation processors or processor cores and programmed, adapted or configured to sequence the independent data, dependent data, and linked dependent data from a plurality of partial transformations of a plurality of blocks, and at least one aggregation and merge processor or processor core programmed, adapted or configured to store the independent data in order in the second memory, to subsequently obtain data specified by the dependent data and linked dependent data, and insert the obtained data into a corresponding location in the second memory to form a resulting processed file.