# US 2017/0255470 A1 · Coalescing adjacent gather/scatter operations

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

- Number: US 2017/0255470 A1
- Document ID: US20170255470A1
- Status: Published application
- Kind: A1
- Application number: 15/601,003
- Filed: 2017-05-22
- Published: 2017-09-07
- Earliest claimed: 2013-06-25
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Andrew T. Forsyth; Brian J. Hickmann; Jonathan C. Hall; Christopher J. Hughes
- Web page: https://patentgrep.com/patent/US20170255470A1

## CPC

- G06F 9/3853: {of compound instructions}
- G06F 9/30018: {Bit or string instructions}
- G06F 9/30032: {Movement instructions, e.g. MOVE, SHIFT, ROTATE, SHUFFLE}
- G06F 9/30036: {Instructions to perform operations on packed data, e.g. vector, tile or matrix operations}
- G06F 9/30038: {using a mask}
- G06F 9/30043: {LOAD or STORE instructions; Clear instruction}
- G06F 9/30098: {Register arrangements}
- G06F 9/30105: {Register structure}
- G06F 9/30145: {Instruction analysis, e.g. decoding, instruction word fields}
- G06F 9/30163: {with implied specifier, e.g. top of stack}
- G06F 9/3017: {Runtime instruction translation, e.g. macros}
- G06F 9/30181: {Instruction operation extension or modification}
- G06F 9/3804: {for branches, e.g. hedging, branch folding}
- G06F 9/3836: {Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution}
- G06F 9/3887: {controlled by a single instruction for multiple data lanes [SIMD]}
- G06F 9/3888: {controlled by a single instruction for multiple threads [SIMT] in parallel}
- G06F 12/0875: with dedicated cache, e.g. instruction or stack
- G06F 12/1027: using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB]
- G06F 13/4282: {on a serial bus, e.g. I2C bus, SPI bus (on daisy chain buses G06F13/4247)}
- G06F 15/8007: {single instruction multiple data [SIMD] multiprocessors}
- G06F 9/3824: {Operand accessing}
- G06F 2212/1016: Performance improvement
- G06F 2212/452: Instruction code
- G06F 2212/68: Details of translation look-aside buffer [TLB]
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

According to one embodiment, a processor includes an instruction decoder to decode a first instruction to gather data elements from memory, the first instruction having a first operand specifying a first storage location and a second operand specifying a first memory address storing a plurality of data elements. The processor further includes an execution unit coupled to the instruction decoder, in response to the first instruction, to read contiguous a first and a second of the data elements from a memory location based on the first memory address indicated by the second operand, and to store the first data element in a first entry of the first storage location and a second data element in a second entry of a second storage location corresponding to the first entry of the first storage location.

## Claims

### Claim 1

A processor, comprising: an instruction decoder to decode a first instruction to gather data elements from memory, the first instruction having a first operand specifying a first storage location and a second operand specifying a first memory address storing a plurality of data elements; an execution unit coupled to the instruction decoder, in response to the first instruction, to read contiguous a first and a second of the data elements from a memory location based on the first memory address indicated by the second operand, and to store the first data element in a first entry of the first storage location and a second data element in a second entry of a second storage location corresponding to the first entry of the first storage location.

### Claim 2 (depends on 1)

The processor of claim 1, wherein the first instruction further comprises a third operand specifying the second storage location.

### Claim 3 (depends on 1)

The processor of claim 1, wherein the instruction decoder further decodes a second instruction having a third operand specifying the second storage location, and a fourth operand specifying a second memory address, the second memory address being offset from the first memory address by the size of a single data element.

### Claim 4 (depends on 3)

The processor of claim 3, wherein the first instruction further comprises a prefix indicating to the instruction decoder and execution unit that the second instruction follows the first instruction.

### Claim 5 (depends on 3)

The processor of claim 3, wherein the execution unit predicts that the second instruction follows the first instruction.

### Claim 6 (depends on 1)

The processor of claim 1, wherein the first entry of the first storage location is not contiguous to the second entry of the second storage location, and wherein the second storage location is specified by the first operand.

### Claim 7 (depends on 1)

The processor of claim 1, wherein the first data element is stored in a third entry of a third storage location prior to being stored in the first entry of the first storage location, and the second data element is stored in a fourth entry of a fourth storage location prior to being stored in the second entry of the second storage location.

### Claim 8

A method, comprising: decoding a first instruction to gather data elements from memory, the first instruction having a first operand specifying a first storage location and a second operand specifying a first memory address storing a plurality of data elements; reading, in response to the first instruction, contiguous a first and a second of the data elements from a memory location based on the first memory address indicated by the second operand; and storing the first data element in a first entry of the first storage location and a second data element in a second entry of a second storage location corresponding to the first entry of the first storage location.

### Claim 9 (depends on 8)

The method of claim 8, wherein the first instruction further comprises a third operand specifying the second storage location.

### Claim 10 (depends on 8)

The method of claim 8, wherein the instruction decoder further decodes a second instruction having a third operand specifying the second storage location, and a fourth operand specifying a second memory address, the second memory address being offset from the first memory address by the size of a single data element.

### Claim 11 (depends on 10)

The method of claim 10, wherein the first instruction further comprises a prefix indicating to the instruction decoder and execution unit that the second instruction follows the first instruction.

### Claim 12 (depends on 10)

The method of claim 10, wherein the execution unit predicts that the second instruction follows the first instruction.

### Claim 13 (depends on 8)

The method of claim 8, wherein the first entry of the first storage location is not contiguous to the second entry of the second storage location, and wherein the second storage location is specified by the first operand.

### Claim 14 (depends on 8)

The method of claim 8, wherein the first data element is stored in a third entry of a third storage location prior to being stored in the first entry of the first storage location, and the second data element is stored in a fourth entry of a fourth storage location prior to being stored in the second entry of the second storage location.
