# US 2006/0156123 A1 · Fault free store data path for software implementation of redundant multithreading environments

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

- Number: US 2006/0156123 A1
- Document ID: US20060156123A1
- Status: Published application
- Kind: A1
- Application number: 11/022,600
- Filed: 2004-12-22
- Published: 2006-07-13
- Earliest claimed: 2004-12-22
- Assignees: Intel Corporation
- Inventors: Shubhendu Mukherjee; Robert Cohn
- Web page: https://patentgrep.com/patent/US20060156123A1

## CPC

- G06F 11/1497: Time redundant execution of software on a single processing unit
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method for a fault free store data path in a software implementation of redundant multithreading environments is described. In one embodiment, after a check is performed by a hardware/software checker, the processor still needs to ensure that the data just checked reaches protected memory without any faults. The present implementation provides sufficient redundant information along the path of a store from register read to commit, such that it may detect any single bit upset error in the path.

## Claims

### Claim 1

A method comprising:
obtaining an instruction into a pipeline;
issuing the instruction;
reading error bit from a register;
committing the instruction with the error bit; and
determining if error occurred in instruction path of the pipeline.

### Claim 2 (depends on 1)

The method of claim 1 wherein the issuing of instruction further comprising issuing a control portion and data portion of the instruction.

### Claim 3 (depends on 2)

The method of claim 2 further comprising generating checker bits for control portion of the instruction.

### Claim 4 (depends on 3)

The method of claim 3 wherein the generating of checker bits includes generating error bits.

### Claim 5 (depends on 3)

The method of claim 3 wherein the checker bits for the control portion of the instruction flows with the instruction through the pipeline.

### Claim 6 (depends on 5)

The method of claim 5 wherein the reading error bit from a register includes the data portion of the instruction reading the error bit.

### Claim 7 (depends on 6)

The method of claim 6 further comprising generating error bits by the data portion of the instruction in the register.

### Claim 8 (depends on 6)

The method of claim 6 further comprising generating error bits by the register.

### Claim 9 (depends on 6)

The method of claim 6 further comprising control and data portions of the instruction flowing through the pipeline with their own error bits.

### Claim 10 (depends on 9)

The method of claim 9 wherein the determining if error occurred further comprising comparing the error bits.

### Claim 11 (depends on 10)

The method of claim 10 wherein the instruction is from an IA-64 instruction set.

### Claim 12 (depends on 9)

The method of claim 9 further comprising decoding the instruction.

### Claim 13 (depends on 12)

The method of claim 12 wherein the decoding of the instruction further comprises duplicating the instruction.

### Claim 14 (depends on 13)

The method of claim 13 wherein the duplicating the instruction further comprises creating a first instruction and a second instruction.

### Claim 15 (depends on 14)

The method of claim 14 wherein the creating a first and second instruction further comprises tagging the first and second instructions.

### Claim 16 (depends on 14)

The method of claim 14 wherein the creating the first and second instructions further comprises creating them in a leading thread.

### Claim 17 (depends on 14)

The method of claim 14 further comprising flowing the first and second instructions through the pipeline.

### Claim 18 (depends on 14)

The method of claim 14 further comprising flowing the first and second instructions through an execution unit in the pipeline.

### Claim 19 (depends on 18)

The method of claim 18 further comprising computing an effective address for the first and second instructions.

### Claim 20 (depends on 19)

The method of claim 19 wherein the determining if error occurred in data path further comprises comparing the first and second instructions.

### Claim 21 (depends on 20)

The method of claim 20 further comprising writing the instruction into memory if no error.

### Claim 22 (depends on 1)

The method of claim 1 wherein the instruction is a store instruction.

### Claim 23 (depends on 20)

The method of claim 20 wherein the instruction is from a non-IA64 instruction set.

### Claim 24

A processor comprising:
a decode unit decodes an instruction in a pipeline;
an instruction queue, coupled to the decode unit, issues the instruction, wherein the instruction queue issues a first portion and a second portion of the instruction; and
a commit unit, coupled to the instruction queue, wherein the first and second portion of the instructions commit with error bits.

### Claim 25 (depends on 24)

The processor of claim 24 further comprising a fetch unit, coupled to the decode unit, issues the instruction.

### Claim 26 (depends on 25)

The processor of claim 25 wherein the first portion of the instruction includes error bits that flow in the pipeline.

### Claim 27 (depends on 26)

The processor of claim 26 further comprising a register coupled to the instruction queue, where the second portion of the instruction reads the register.

### Claim 28 (depends on 27)

The processor of claim 27 wherein the second portion generates error bits carried through the pipeline with the second portion of the instruction.

### Claim 29 (depends on 28)

The processor of claim 28 wherein the first and second portions of the instruction flow through memory, wherein the memory is coupled to the register.

### Claim 30 (depends on 29)

The processor of claim 29 wherein the decode unit generates an original instruction and a pseudo instruction.

### Claim 31 (depends on 30)

The processor of claim 30 wherein the original and pseudo instructions are located in a leading thread.

### Claim 32 (depends on 31)

The processor of claim 31 wherein the leading thread tags the original and pseudo instructions.

### Claim 33 (depends on 30)

The processor of claim 30 further comprising an execution unit, coupled to the register, wherein the execution unit generates an address for the original and pseudo instructions.

### Claim 34 (depends on 33)

The processor of claim 33 wherein the commit unit commits both the original and pseudo instructions.

### Claim 35 (depends on 24)

The processor of claim 24 wherein the instruction is a store instruction.

### Claim 36

A system comprising:
a first processor comprising:
a decode unit decodes an instruction in a pipeline;
an instruction queue, coupled to the decode unit, issues the instruction, wherein the instruction queue issues a first portion and a second portion of the instruction; and
a commit unit, coupled to the instruction queue, wherein the first and second portion of the instructions commit with error bits.
a first interface to a second processor;
a second interface coupled to input/output devices; and
an audio input/output device coupled to the second interface.

### Claim 37 (depends on 36)

The system of claim 36 wherein the first and second interfaces are point to point interfaces.

### Claim 38 (depends on 36)

The system of claim 36 wherein the first portion of the instruction includes error bits that flow in the pipeline.

### Claim 39 (depends on 38)

The system of claim 38 further comprising a register coupled to the instruction queue, where the second portion of the instruction reads the register.

### Claim 40 (depends on 39)

The system of claim 39 wherein the second portion generates error bits carried through the pipeline with the second portion of the instruction.

### Claim 41 (depends on 40)

The system of claim 40 wherein the decode unit generates an original instruction and a pseudo instruction.

### Claim 42 (depends on 41)

The system of claim 41 further comprising an execution unit, coupled to the register, wherein the execution unit generates an address for the original and pseudo instructions.

### Claim 43 (depends on 42)

The system of claim 42 wherein the commit unit commits both the original and pseudo instructions.
