Computing device sort function

1. A method comprises:

receiving, by a computing device, a sort request regarding data of a table, wherein the table includes a plurality of rows and a plurality of columns, wherein a row of the plurality of rows of data includes data elements in fields of the plurality of columns to produce a data unit;

determining, by the computing device, a plurality of probability traits of the data;

dividing, by the computing device, the sort request into a plurality of sub-sort requests based on the plurality of probability traits;

identifying, by the computing device, processing core resources of the computing device to perform the plurality of sub-sort requests based on the plurality of probability traits, wherein the computing device includes a plurality of nodes, and wherein a node of the plurality of nodes includes a plurality of computing core resources;

allocating, by the computing device, the plurality of sub-sort requests to the identified processing core resources in accordance with the plurality of probability traits;

allocating, by the computing device, a plurality of data portions of the data to the identified processing core resources in accordance with the plurality of probability traits;

executing, by a computing core resources of the identified computing core resources, an allocated sub-sort request of the plurality of sub-sort requests on a corresponding divided portion of the data to produce a sorted data portion; and

joining, by the computing device, a plurality of sorted data portions produced by the identified computing core resources to produce sorted data.

2. The method of claim 1 , wherein the determining the plurality of probability traits comprises:

performing a probability density function on data elements of a first column of the plurality of columns to produce a first probability density;

performing the probability density function on data elements of a second column of the plurality of columns to produce a second probability density; and

performing the probability density function on the data elements of the first and second columns to produce a third probability density, wherein the first, second, and third probability densities correspond to probability traits of the plurality of probability traits.

3. The method of claim 1 , wherein the determining the plurality of probability traits comprises:

performing a kernel density estimation on data elements of a first column of the plurality of columns to produce a first probability estimation;

performing the kernel density estimation on data elements of a second column of the plurality of columns to produce a second probability estimation; and

performing the kernel density estimation on the data elements of the first and second columns to produce a third probability estimation, wherein the first, second, and third probability densities correspond to probability traits of the plurality of probability traits.

4. The method of claim 1 , wherein dividing the sort request comprises:

determining a number of ranges based on the probability density function; and

dividing the sort request into a number of sub-sort requests corresponding to a multiple of the number of ranges to produce the plurality of sub-sort requests.

5. The method of claim 1 , wherein the identifying the processing core resources comprises:

determining a number of sub-sort requests in the plurality of sub-sort requests;

determining a number of processing core resources of the plurality of processing core resources of the plurality of nodes that will execute multiple sub-sort requests of the plurality of sub-sort requests; and

based on the number of sub-sort requests and the number of processing core resources executing multiple sub-sort requests, identifying the processing core resources.

6. The method of claim 1 further comprises:

dividing the data into streams of data based on a number of ranges;

dividing the streams of data into the plurality of data portions in accordance with the plurality of probability traits; and

depositing the plurality of data portions into a plurality of memory bins.

7. The method of claim 6 further comprises:

executing, by the computing core resources, the allocated sub-sort request on a data portion of the plurality of data portions in a memory bin of the plurality of memory bins to produce the sorted data portion; and

retrieving, by the computing device, the plurality of sorted data portions from the plurality of memory bins in order to produce the sorted data.