Apparatuses and methods for parallel analytics

A apparatus for data processing, the apparatus comprising:

• a processor configured to:
• receive a dataset;
• determine a control number of a processing system, where the control number defines a maximum number of evaluation units that can be used to concurrently process data, with each evaluation unit representing a discrete computing resource used to process data;
• and
• process the dataset using a plurality of evaluation units, where processing the dataset comprises:
• allocating a free evaluation unit to form a busy evaluation unit;
• creating a data subdivision for the busy evaluation unit using one or more configurable subdivision strategies implemented before and during the processing of the dataset;
• dynamically modifying, during the processing of the dataset, the one or more configurable subdivision strategies based, at least in part, on contents of the dataset;
• evaluating the data subdivision;
• creating a status message reporting an estimated duration time for processing the dataset;
• and
• releasing the busy evaluation unit;
• wherein the evaluation step is performed concurrently by the plurality of evaluation units.

A computer program product comprising a non-transitory computer readable medium having computer usable program code executable to perform operations for processing data, the operations of the computer program product comprising:

• receiving a dataset;
• determining a control number of a processing system, where the control number defines a maximum number of evaluation units that can be used to concurrently process data, with each evaluation unit representing a discrete computing resource used to process data;
• processing the dataset using a plurality of evaluation units, where processing the dataset comprises:
• allocating a free evaluation unit to form a busy evaluation unit;
• creating a data subdivision for the busy evaluation unit using one or more configurable subdivision strategies implemented before and during the processing of the dataset;
• dynamically modifying, during the processing of the dataset, the one or more configurable subdivision strategies based, at least in part, on contents of the dataset;
• evaluating the data subdivision;
• creating a status message reporting an estimated duration time for processing the dataset;
• and
• releasing the busy evaluation unit;
• wherein the evaluating step is performed concurrently by the plurality of evaluation units.