# US 2012/0254871 A1 · Combinatorial computing

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0254871 A1
- Document ID: US20120254871A1
- Status: Published application
- Kind: A1
- Application number: 13/432,080
- Filed: 2012-03-28
- Published: 2012-10-04
- Earliest claimed: 2011-03-31
- Assignees: International Business Machines Corporation
- Inventors: Yan Li; Haibo Lin; Liu Tao; Yudong Yang
- Web page: https://patentgrep.com/patent/US20120254871A1

## CPC

- G06F 9/5066: {Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs (mappping at compile time, see G06F8/451)}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A combinational computing apparatus and method. The combinational computing method includes the steps of: receiving a first setting relating to multiple groups of input data and a second setting relating to a combinatorial mode among multiple groups of input data, obtaining the data combination of the multiple groups of input data according to the first setting and the second setting, and performing a desired calculating operation on the data combination.

## Claims

### Claim 1

A combinatorial computing apparatus in a parallel computing system, comprising:
an input-setting unit configured to receive a first setting relating to multiple groups of input data and a second setting relating to the combinatorial mode among the multiple groups of input data;
a data-obtaining unit configured to obtain a data combination of the multiple groups of input data according to the first setting and the second setting; and
at least one combinatorial operating unit configured to perform a desired calculating operation on the data combination.

### Claim 2 (depends on 1)

The apparatus according to claim 1, wherein the first setting includes the information on the data source of the multiple groups of input data and the setting on the format of the input data.

### Claim 3 (depends on 2)

The apparatus according to claim 2, wherein the setting on the format of the input data includes setting the input data in format of key value pairs.

### Claim 4 (depends on 2)

The apparatus according to claim 2, wherein the input-setting unit is further configured to refine information on the data source in the first setting that is specific to the at least one combinatorial operating unit.

### Claim 5 (depends on 1)

The apparatus according to claim 1, wherein the data-obtaining unit comprises:
a data-reading module configured to read multiple groups of input data according to the first setting; and
a data-combining module configured to form data combinations by combining the read multiple groups of input data according to the second setting.

### Claim 6 (depends on 1)

The apparatus according to claim 1, wherein the data-obtaining unit is further configured to arrange the data combination into a format of single data set according to a certain rule, and wherein the at least one combinatorial operating unit is configured to convert the single data set back to data combination of the multiple groups of input data according to the certain rule.

### Claim 7 (depends on 1)

The apparatus according to claim 1, wherein the at least one combinatorial operating unit comprises an interface for receiving an operational function and performs calculating operation on the data combination according to the received operational function.

### Claim 8 (depends on 1)

The apparatus according to claim 1, wherein the combinational computing apparatus produces intermediate data and further comprises a reduce computing apparatus that includes a plurality of reducing units, wherein each reducing unit is configured to reduce and merge the intermediate data to produce a final result.

### Claim 9

A combinatorial computing method comprising the steps of:
receiving a first setting relating to multiple groups of input data and a second setting relating to a combinatorial mode among the multiple groups of input data;
obtaining a data combination of the multiple groups of input data according to the first setting and the second setting; and
performing a desired calculating operation on the data combination.

### Claim 10 (depends on 9)

The method according to claim 9, wherein the first setting includes information on the data source of the multiple groups of input data and a setting on the format of the input data.

### Claim 11 (depends on 10)

The method according to claim 10, wherein the setting on the format of the input data includes setting the input data in format of key value pairs.

### Claim 12 (depends on 10)

The method according to claim 10, further comprising the step of: refining the information on the data source in the first setting.

### Claim 13 (depends on 9)

The method according to f claims 9, wherein the obtaining the data combination of multiple groups of input data step comprises:
reading multiple groups of input data according to the first setting; and
combining the read multiple groups of input data according to the second setting to form data combinations.

### Claim 14 (depends on 9)

The method according to claim 9, wherein the obtaining the data combination step comprises: arranging the data combination into a format of a single data set according to a certain rule, and wherein the performing the desired calculating operation step comprises: converting the single data set back to a data combination of the multiple groups of input data according to the certain rule.

### Claim 15 (depends on 9)

The method according to claim 9, further comprising the step of:
receiving an operational function, wherein the performing the desired calculating operation step comprises:
performing a calculating operation on the data combination according to the received operational function.

### Claim 16 (depends on 9)

A non-transitory article of manufacture tangibly embodying computer readable instructions, which when implemented on a computer device cause the computer devices to carry out the steps of the method according to claim 9.
