# US 2010/0146241 A1 · Modified-SIMD Data Processing Architecture

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

- Number: US 2010/0146241 A1
- Document ID: US20100146241A1
- Status: Published application
- Kind: A1
- Application number: 12/331,345
- Filed: 2008-12-09
- Published: 2010-06-10
- Earliest claimed: 2008-12-09
- Assignees: Novafora, Inc.
- Inventors: Shlomo Selim Rakib; Yoram Zarai
- Web page: https://patentgrep.com/patent/US20100146241A1

## CPC

- G06F 15/8007: {single instruction multiple data [SIMD] multiprocessors}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An apparatus and method for processing data includes an array of processing elements to simultaneously perform operations on multiple data elements using a single instruction. A grouping module assigns each processing element within the array to one of several groups. A modification module designates how each group of processing elements should handle the single instruction. This enables each group of processing elements to handle the single instruction differently. Each processing element is configured to handle the single instruction based on the group the processing element belongs to.

## Claims

### Claim 1

An apparatus for processing data, the apparatus comprising:
an array of processing elements to simultaneously perform operations on a plurality of data elements using a single instruction;
a grouping module to assign each processing element within the array to one of a plurality of groups;
a modification module to designate how each group of processing elements should handle the single instruction, thereby enabling each group of processing elements to handle the single instruction differently; and
each processing element further configured to handle the single instruction based on the group the processing element belongs to.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the grouping module uses a processing element map to designate which group each processing element belongs to.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the modification module uses an instruction modifier to designate how a group of processing elements should handle the single instruction.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the instruction modifier further designates how to modify at least one operand of the single instruction.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the at least one operand includes a source operand.

### Claim 6 (depends on 4)

The apparatus of claim 4, wherein the at least one operand includes a destination operand.

### Claim 7 (depends on 4)

The apparatus of claim 4, wherein the at least one operand includes a source operand and a destination operand.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the array of processing elements is an n×m array of processing elements.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the array of processing elements is an n×n array of processing elements.

### Claim 10

A method for processing data, the method comprising:
simultaneously performing, with an array of processing elements, operations on a plurality of data elements using a single instruction;
assigning each processing element within the array to one of a plurality of groups;
designating how each group of processing elements should handle the single instruction, thereby enabling each group to handle the single instruction differently; and
handling, with each processing element, the single instruction based on the group the processing element belongs to.

### Claim 11 (depends on 10)

The method of claim 10, further comprising providing a processing element map to designate which group each processing element belongs to.

### Claim 12 (depends on 10)

The method of claim 10, further comprising assigning an instruction modifier to each group, the instruction modifier designating how each group of processing elements should handle the single instruction.

### Claim 13 (depends on 12)

The method of claim 12, wherein the instruction modifier further designates how to modify at least one operand of the single instruction.

### Claim 14 (depends on 13)

The method of claim 13, wherein the at least one operand includes a source operand.

### Claim 15 (depends on 13)

The method of claim 13, wherein the at least one operand includes a destination operand.

### Claim 16 (depends on 13)

The method of claim 13, wherein the at least one operand includes a source operand and a destination operand.

### Claim 17 (depends on 10)

The method of claim 10, wherein the array of processing elements is an n×m array of processing elements.

### Claim 18 (depends on 10)

The method of claim 10, wherein the array of processing elements is an n×n array of processing elements.

### Claim 19

An apparatus for processing data, the apparatus comprising:
an array of processing elements to simultaneously perform operations on a plurality of data elements using a single instruction; and
a modification module to designate how each processing element should handle the single instruction, thereby enabling each processing element to handle the single instruction differently.

### Claim 20 (depends on 19)

The apparatus of claim 19, wherein the modification module uses an instruction modifier to designate how each processing element should handle the single instruction.

### Claim 21 (depends on 20)

The apparatus of claim 20, wherein the instruction modifier further designates how to modify at least one operand of the single instruction.

### Claim 22

A method for processing data, the method comprising:
simultaneously performing, with an array of processing elements, operations on a plurality of data elements using a single instruction; and
designating how each processing element should handle the single instruction, thereby enabling each processing element to handle the single instruction differently.

### Claim 23 (depends on 22)

The method of claim 22, further comprising assigning an instruction modifier to each processing element, the instruction modifier designating how each processing element should handle the single instruction.

### Claim 24 (depends on 23)

The method of claim 23, wherein the instruction modifier further designates how to modify at least one operand of the single instruction.
