# US 2024/0004654 A1 · Computing System with Hardware and Methods for Handling Immediate Operands in Machine Instructions

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

- Number: US 2024/0004654 A1
- Document ID: US20240004654A1
- Status: Published application
- Kind: A1
- Application number: 18/219,575
- Filed: 2023-07-07
- Published: 2024-01-04
- Earliest claimed: 2016-04-26
- Assignees: Onnivation LLC
- Applicants: Onnivation LLC
- Inventors: Sitaram Yadavalli
- Web page: https://patentgrep.com/patent/US20240004654A1

## CPC

- G06F 9/30101: {Special purpose registers}
- G06F 9/30007: {to perform operations on data operands}
- G06F 9/3001: {Arithmetic 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 9/30043: {LOAD or STORE instructions; Clear instruction}
- G06F 9/3013: {according to data content, e.g. floating-point registers, address registers}
- G06F 9/30149: {of variable length instructions}
- G06F 9/30167: {of immediate specifier, e.g. constants}
- G06F 9/30185: {according to one or more bits in the instruction, e.g. prefix, sub-opcode}
- G06F 9/34: Addressing or accessing the instruction operand or the result {; Formation of operand address; Addressing modes (address translation G06F12/00)}
- G06F 9/345: of multiple operands or results {(addressing multiple banks G06F12/06)}
- G06F 12/0207: {with multidimensional access, e.g. row/column, matrix}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

This disclosure relates to methods and mechanisms for matrix computing which include machine embodiments with one or more matrix storage spaces for holding matrices and arrays for computing, where a matrix or an array is accessible by its columns, by its rows, or both, individually, or concurrently. A set of methods and mechanisms to build a large capacity instruction set with multi-length instructions to load, store, and compute with these matrices and arrays are also disclosed. Methods and access control mechanisms with keys to secure, share, lock and unlock regions in the storage space for matrices and arrays under the control of an operating system or a virtual machine hypervisor by permitted threads and processes are also disclosed. Methods and mechanisms to handle long immediate operands for use by shorter instructions using a payload instruction are also disclosed. The structure of the instructions with key instruction fields and a method for determining instruction length are also disclosed.

## Claims

### Claim 1

(canceled)

### Claim 2

(canceled)

### Claim 3

(canceled)

### Claim 4

(canceled)

### Claim 5

(canceled)

### Claim 6

(canceled)

### Claim 7

(canceled)

### Claim 8

(canceled)

### Claim 9

(canceled)

### Claim 10

(canceled)

### Claim 11

(canceled)

### Claim 12

(canceled)

### Claim 13

(canceled)

### Claim 14

A computing machine comprising:
a first instruction comprising at least one first opcode and a first immediate operand;
a subsequent instruction comprising at least one second opcode and a second immediate operand; and
a first resultant immediate operand generated by combining the first immediate operand with the second immediate operand, and
wherein, the subsequent instruction is configured to execute upon the first resultant immediate operand.

### Claim 15 (depends on 14)

The computing machine of claim 14, where in the first immediate operand is combined with the second immediate operand using a concatenation operation.

### Claim 16 (depends on 14)

The computing machine of claim 14, wherein the subsequent instruction is decoded independent of the first instruction.

### Claim 17 (depends on 14)

The computing machine of claim 14, wherein the first resultant immediate operand is used in an arithmetic operation or logical operation or a vector operation or a matrix operation.

### Claim 18 (depends on 14)

The computer machine of claim 14, wherein the first resultant immediate operand is combined with a third immediate operand of a third instruction to create a second resultant immediate operand, and wherein the second resultant immediate operand is used in a computation.

### Claim 19 (depends on 14)

The computing machine of claim 14, wherein the first instruction is a payload immediate instruction.

### Claim 20

A computing machine comprising:
at least one instruction decoder that decodes a first instruction comprising at least one first opcode and a first immediate operand, wherein the first instruction is an immediate operand instruction of the computing machine; and
further, the at least one instruction decoder decodes a subsequent instruction comprising at least one second opcode and a second immediate operand, and wherein the at least one instruction decoder configures the subsequent instruction comprising the at least one second opcode to operate upon a combination of the first immediate operand and the second immediate operand.

### Claim 21 (depends on 20)

The computing machine of claim 20 further comprising:
at least one payload mechanism which comprises:
a shifter that receives the second immediate operand at a first input;
a shift controller that presents a shift control value at a second input to the shifter, wherein the shifter generates a shifted value from the second immediate operand in response to the shift control value;
a logic circuit that combines the first immediate operand and the shifted value to generate a resultant immediate operand; and
an immediate operand register that stores the resultant immediate operand.

### Claim 22 (depends on 21)

The computing machine of claim 21, wherein the shift controller generates the shift control value in response to a shift value received from the instruction decoder.

### Claim 23 (depends on 21)

The computing machine of claim 21, wherein the first immediate operand is stored in the immediate operand register.

### Claim 24 (depends on 21)

The computing machine of claim 21, wherein the subsequent instruction is configured to operate upon the resultant immediate operand by the instruction decoder.

### Claim 25 (depends on 21)

The computing machine of claim 21, wherein the first instruction is a payload instruction; and wherein the first instruction is a 16-bit payload instruction or wherein the first instruction is a 32-bit payload instruction or wherein the first instruction is a 48-bit payload instruction or wherein the first instruction is a 64-bit payload instruction.

### Claim 26 (depends on 21)

The computing machine of claim 21, wherein the instruction decoder decodes the subsequent instruction of a length that is a multiple of 16 bits, and wherein the subsequent instruction comprises a plurality of 4-bit fields and/or 8-bit fields.

### Claim 27

A computing machine comprising:
a first instruction comprising at least one first opcode and a first immediate operand, wherein the first instruction is a payload immediate instruction; and
a second instruction comprising at least one second opcode wherein the second instruction is configured with the at least one second opcode to operate upon the first immediate operand.

### Claim 28 (depends on 27)

The computing machine of claim 27, wherein the payload instruction is a 16-bit instruction with an immediate operand of fewer than 13-bits.

### Claim 29 (depends on 27)

The computing machine of claim 27, wherein the first instruction succeeds the second instruction.

### Claim 30

A method for instruction decoding comprising:
decoding a length field (LEN) of an instruction to determine a length of the instruction; decoding an architecture field of the instruction to determine at least one subset of an instruction set architecture comprising the instruction;
decoding a co-processor field (CoP) of the instruction to determine a co-processor that operates upon the instruction; or
decoding an opcode of the instruction to concatenate the instruction with a next adjacent instruction to decode as a long instruction.

### Claim 31 (depends on 30)

The method of claim 30, wherein a LEN field in the instruction is used by a decoder to decode the instruction as a 16-bit instruction or wherein the LEN field in the instruction is used by the decoder to decode the instruction as a 32-bit instruction.

### Claim 32 (depends on 30)

The method of claim 30, wherein an instruction set architecture (ISA) field of the instruction is decoded by an instruction decoder to determine an instruction subset to configure when the instruction set architecture is partitioned into two or more instruction sub-sets.

### Claim 33 (depends on 30)

The method of claim 30, wherein a 4 bit field of the instruction comprises a LEN field, wherein the LEN field configures the length of the instruction as either 16 bits or more than 16 bits.

### Claim 34 (depends on 30)

The method of claim 30, wherein a payload instruction is decoded along with a second 16-bit instruction that receives an immediate operand or wherein the payload instruction is decoded along with a second 32-bit instruction that receives an immediate operand.

### Claim 35 (depends on 34)

The method of claim 34, wherein the payload instruction is a 16-bit instruction with an immediate operand of fewer than 13-bits.

### Claim 36 (depends on 34)

The method of claim 34, wherein the payload instruction is a 32-bit instruction with an immediate operand of fewer than 29-bits.

### Claim 37 (depends on 34)

The method of claim 34, wherein the payload instruction is a 64-bit instruction with an immediate operand of fewer than 61-bits.

### Claim 38 (depends on 30)

The method of claim 30, wherein an instruction decoder is configured to decode the co-processor field of the instruction to configure the instruction to run on a co-processor.
