# US 2019/0171536 A1 · Data processing system having lockstep operation

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

- Number: US 2019/0171536 A1
- Document ID: US20190171536A1
- Status: Published application
- Kind: A1
- Application number: 15/830,154
- Filed: 2017-12-04
- Published: 2019-06-06
- Earliest claimed: 2017-12-04
- Assignees: NXP USA, Inc.
- Applicants: NXP USA, Inc.
- Inventors: JEHODA REFAELI; Nancy Hing-Che Amedeo; Larry Alan Woodrum
- Web page: https://patentgrep.com/patent/US20190171536A1

## CPC

- G06F 11/203: {using migration}
- G06F 11/16: Error detection or correction of the data by redundancy in hardware
- G06F 11/1629: {Error detection by comparing the output of redundant processing systems}
- G06F 11/1641: {where the comparison is not performed by the redundant processing components}
- G06F 11/165: {with continued operation after detection of the error}
- G06F 11/1695: {which are operating with time diversity}
- G01R 31/3177: Testing of logic operation, e.g. by logic analysers
- G06F 2201/805: Real-time
- G06F 2201/82: Solving problems relating to consistency
- G11C 29/38: Response verification devices
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)
- G11C: STATIC STORES (semiconductor memory devices H10B)

## Abstract

A data processing system and methods for operating the same are disclosed. The method includes detecting a fault by comparing output signals from a first processing core and a second processing core, entering a safe mode based upon detecting the fault, completing transactions while in the safe mode, and determining whether the fault corresponds to a hard error. Based upon the fault corresponding to a hard error, one of processing cores is identified as a faulty core. The faulty core is inhibited from executing instructions and the other processing core is allowed to execute instructions.

## Claims

### Claim 1

A method of operating a data processing system comprising:
detecting a fault by comparing output signals from a first processing core and a second processing core;
entering a safe mode based upon detecting the fault;
completing transactions while in the safe mode;
determining whether the fault corresponds to a hard error; and
based upon the fault corresponding to a hard error:
identifying one of processing cores as a faulty core, the faulty core associated with the hard error; and
inhibiting the faulty core from executing instructions and allowing the other processing core to resume executing instructions.

### Claim 2 (depends on 1)

The method of claim 1, further comprising operating the first processing core and the second processing core in a lockstep mode, the second processing core shadowing the first processing core.

### Claim 3 (depends on 1)

The method of claim 1, further comprising receiving at a controller an interrupt signal corresponding to the fault, and responsive to the interrupt signal, invoking a service routine to analyze the fault.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining whether the fault corresponds to a hard error further comprises:
performing a memory built-in self-test (MBIST) on at least one of a first cache memory coupled to a first processor of the first processing core and a second cache memory coupled to a second processor of the second processing core; and
performing a logic built-in self-test (LBIST) on at least one of the first processor and the second processor.

### Claim 5 (depends on 4)

The method of claim 4, wherein the hard error is determined when the MBIST or LBIST fails.

### Claim 6 (depends on 1)

The method of claim 1, further comprising coupling a first core domain to a system bus of the data processing system, the core domain comprising the first processing core and the second processing core.

### Claim 7 (depends on 6)

The method of claim 6, wherein the safe mode comprises isolating the first processing core and the second processing core from the system bus.

### Claim 8 (depends on 6)

The method of claim 6, further comprising based upon the fault not corresponding to a hard error, resetting the first core domain, other portions of the processing system continue normal operation during reset of the first core domain.

### Claim 9 (depends on 1)

The method of claim 1, wherein detecting the fault by comparing output signals comprises delaying output signals from the first processing core to temporally align with output signals from the second processing core.

### Claim 10

A data processing system comprising:
a core domain coupled to a system bus, the core domain comprising:
a first processing core comprising a first processor coupled to a first cache memory,
a second processing core comprising a second processor coupled to a second cache memory, and
a lockstep control circuit coupled to the first processing core and the second processing core, the lockstep control circuit configured to detect a fault by comparing output signals from the first processing core and the second processing core, enter a safe mode based upon the detected fault, and complete transactions while in the safe mode; and
a controller coupled to the lockstep control circuit, the controller configured to determine whether the fault corresponds to a hard error, and responsive to the fault corresponding to the hard error, allow one of the first processing core and second processing core not associated with the hard error to continue executing instructions.

### Claim 11 (depends on 10)

The system of claim 10, wherein the lockstep control circuit comprises a compare circuit, the compare circuit configured to detect a fault when output signals from the first processing core and the second processing core do not match.

### Claim 12 (depends on 10)

The system of claim 10, wherein the safe mode comprises isolation of the first processing core and the second processing core from the system bus.

### Claim 13 (depends on 10)

The system of claim 10, wherein the controller is configured to receive an interrupt signal corresponding to the fault, and responsive to the interrupt signal, invokes a service routine to analyze the fault.

### Claim 14 (depends on 13)

The system of claim 13, wherein the service routine to analyze the fault comprises a memory built-in self-test (MBIST) to be executed on at least one of the first cache memory and the second cache memory, and a logic built-in self-test (LBIST) to be executed on at least one of the first processor and the second processor.

### Claim 15 (depends on 10)

The system of claim 10, wherein based upon the fault not corresponding to a hard error, the controller is configured to reset first core domain and allow other portions of the processing system continue normal operation during reset of the core domain.

### Claim 16

A method of operating a data processing system comprising:
operating a core domain in a lockstep mode, the core domain comprising a first processing core shadowing a second processing core;
detecting a fault by comparing output signals from the first processing core and the second processing core;
entering a safe mode based upon detecting the fault, the safe mode isolating the core domain from a system bus;
determining whether the fault corresponds to a hard error;
identifying one of processing cores as a faulty core, the faulty core associated with the hard error; and
based upon the fault corresponding to a hard error, inhibiting the faulty core from executing instructions and allowing the processing core not associated with the hard error to resume executing instructions.

### Claim 17 (depends on 16)

The method of claim 16, wherein detecting the fault by comparing output signals comprises delaying output signals from the second processing core to temporally align with output signals from the first processing core.

### Claim 18 (depends on 16)

The method of claim 16, further comprising generating an interrupt signal corresponding to the fault, and responsive to the interrupt signal at a controller, invoking a service routine to analyze the fault.

### Claim 19 (depends on 16)

The method of claim 16, wherein determining whether the fault corresponds to a hard error further comprises:
performing a memory built-in self-test (MBIST) on at least one of a first cache memory coupled to a first processor of the first processing core and a second cache memory coupled to a second processor of the second processing core; and
performing a logic built-in self-test (LBIST) on at least one of the first processor and the second processor;
wherein the hard error is determined when the MBIST or LBIST fails.

### Claim 20 (depends on 16)

The method of claim 16, further comprising based upon the fault not corresponding to a hard error, resetting the core domain and allowing other portions of the data processing system continue normal operation during reset of the core domain.
