# US 2024/0004660 A1 · Conditional load and/or store

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

- Number: US 2024/0004660 A1
- Document ID: US20240004660A1
- Status: Published application
- Kind: A1
- Application number: 17/856,976
- Filed: 2022-07-02
- Published: 2024-01-04
- Earliest claimed: 2022-07-02
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Venkateswara Rao MADDURI; Igor ASTAKHOV
- Web page: https://patentgrep.com/patent/US20240004660A1

## CPC

- G06F 9/30032: {Movement instructions, e.g. MOVE, SHIFT, ROTATE, SHUFFLE}
- G06F 9/30043: {LOAD or STORE instructions; Clear instruction}
- G06F 9/30018: {Bit or string instructions}
- G06F 9/30036: {Instructions to perform operations on packed data, e.g. vector, tile or matrix operations}
- G06F 9/3016: {Decoding the operand specifier, e.g. specifier format}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Techniques for conditional loads and/or stores using an instance of a single instruction are described. In some examples, the instance of the single instruction at least includes one or more fields for an opcode, one or more fields to reference a first source operand, one or more fields to reference a second source operand, and one or more fields to reference a destination memory location, wherein the opcode indicates execution circuitry is to conditionally store data elements from data element positions of the second source operand into corresponding data element positions of the memory location of the referenced destination operand based on masking information stored in the referenced first source operand. In some examples, the masking information is provided by a value of a most significant bit position of each data element of the first source operand.

## Claims

### Claim 1

An apparatus comprising:
decoder circuitry to decode an instance of a single instruction, the instance of the single instruction to at least include one or more fields for an opcode, one or more fields to reference a first source operand, one or more fields to reference a second source operand, and one or more fields to reference a destination memory location, wherein the opcode indicates execution circuitry is to conditionally store data elements from data element positions of the second source operand into corresponding data element positions of the memory location of the referenced destination operand based on masking information stored in the referenced first source operand; and
execution circuitry configured to execute the decoded instruction according to the opcode.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the first source operand is a vector register.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the masking information is provided by a value of a most significant bit position of each data element of the first source operand.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the data elements to conditionally store are 8-bit.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the data element of the second source operand is 128-bit.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein masked data element positions are left unchanged.

### Claim 7

A method comprising:
translating an instance of a single instruction of a first instruction set architecture to one or more instructions of a second instruction set architecture, the instance of the single instruction to at least include one or more fields for an opcode, one or more fields to reference a first source operand, one or more fields to reference a second source operand, and one or more fields to reference a destination memory location, wherein the opcode indicates execution circuitry is to conditionally store data elements from data element positions of the second source operand into corresponding data element positions of the memory location of the referenced destination operand based on masking information stored in the referenced first source operand;
decoding the one or more instructions of a second instruction set architecture; and
executing the decoded instruction according to the opcode of the instance of the single instruction of the first instruction set architecture.

### Claim 8 (depends on 7)

The method of claim 7, wherein the first source operand is a vector register.

### Claim 9 (depends on 7)

The method of claim 7, wherein the masking information is provided by a value of a most significant bit position of each data element of the first source operand.

### Claim 10 (depends on 7)

The method of claim 7, wherein the data elements to conditionally store are 8-bit.

### Claim 11 (depends on 7)

The method of claim 7, wherein the data element of the second source operand is 128-bit.

### Claim 12 (depends on 7)

The method of claim 7, wherein masked data element positions are left unchanged.

### Claim 13

A system comprising:
a general purpose processor core; and
a digital signal processing core coupled to the general purpose processor core, the digital signal processing core including:
decoder circuitry to decode an instance of a single instruction, the instance of the single instruction to at least include one or more fields for an opcode, one or more fields to reference a first source operand, one or more fields to reference a second source operand, and one or more fields to reference a destination memory location, wherein the opcode indicates execution circuitry is to conditionally store data elements from data element positions of the second source operand into corresponding data element positions of the memory location of the referenced destination operand based on masking information stored in the referenced first source operand; and
execution circuitry configured to execute the decoded instruction according to the opcode.

### Claim 14 (depends on 13)

The system of claim 13, wherein the first source operand is a vector register.

### Claim 15 (depends on 13)

The system of claim 13 wherein the masking information is provided by a value of a most significant bit position of each data element of the first source operand.

### Claim 16 (depends on 13)

The system of claim 13, wherein the data elements to conditionally store are 8-bit.

### Claim 17 (depends on 13)

The system of claim 13, wherein the data element of the second source operand is 128-bit.

### Claim 18 (depends on 13)

The system of claim 13, wherein masked data element positions are left unchanged.
