Systems and methods for usage of spare cores in connection with in-field tests of operational cores
The technology generally relates to systems and methods for performing in-field testing of processing cores within a system-on-chip (SoC), so as to identify faults, including those associated with silent data corruption. For example, an SoC may contain operational cores and spare cores. An operational core may be selected for testing while a spare core is used to replace the tested core. In addition, a spare core may be used to replace an operational core that has been determined to be corrupted.
1. A method comprising:
determining that a first core, from a plurality of operational cores, meets one or more criteria for an in-field test;
identifying a first ID of the first core that identifies the first core to an operating system;
identifying that a first spare core is available;
initializing the first spare core to be in an operational mode, wherein initializing comprises assigning the first ID to the first spare core;
placing the first core into a test mode; and
performing the in-field test of the first core in a manner that is transparent to the operating system while maintaining the first spare core in the operation mode under the first ID.
2. The method of claim 1 , further comprising:
determining, based on the in-field test, that the first core is not corrupted;
designating the first core as an available spare core under a spare ID; and
maintaining the first spare core as an operational core under the first ID.
3. The method of claim 1 , wherein one of the criteria for the in-field test is that the first core has not been tested for a predetermined period of time.
4. The method of claim 1 , wherein one of the criteria for the in-field test occurs while the first core is in a low power mode, and wherein the first core is maintained in a low power mode during initialization of the spare core.
5. The method of claim 1 , further comprising:
determining, based on the in-field test, that the first core is corrupted; and
designating the first core as an inoperable core that is not available as either an operational core or as spare core.
6. The method of claim 5 , further comprising:
determining that no additional spare cores are available in connection with the plurality of operational cores; and
altering one or more testing procedures for the plurality of cores based on determining that no additional spare cores are available.
7. The method of claim 1 , further comprising:
while the first core is in the test mode, determining that a second core, from the plurality of operational cores, meets one or more criteria for the in-field test;
identifying a second ID of the second core;
identifying that a second spare core is available;
initializing the second spare core to be in an operational mode, wherein initializing comprises assigning the second ID to the second spare core;
placing the second core into a test mode; and
performing the in-field test of the second core in a manner that is transparent to the operating system while maintaining the second spare core in the operation mode under the first ID.
8. A system comprising:
an SoC having one or more controllers and a plurality of operational cores, wherein the one or more controllers are configured to:
determine that a first core, from the plurality of operational cores, meets one or more criteria for an in-field test;
identify a first ID of the first core that identifies the first core to an operating system;
identify that a first spare core is available;
initialize the first spare core to be in an operational mode, wherein initializing comprises assigning the first ID to the first spare and performing all hardware operations to enable the first spare core to enter operation mode;
place the first core into a test mode; and
perform the in-field test of the first core in a manner that is transparent to the operating system while maintaining the first spare core in the operation mode under the first ID.
9. The system of claim 8 , wherein the one or more controllers are further configured to:
determine, based on the in-field test, that the first core is not corrupted;
designate the first core as an available spare core under a spare ID; and
maintain the first spare core as an operational core under the first ID.
10. The system of claim 8 , wherein one of the criteria for the in-field test is that the first core has not been tested for a predetermined period of time.
11. The system of claim 8 , wherein one of the criteria for the in-field test occurs while the first core is in a low power mode, and wherein the first core is maintained in a low power mode during initialization of the spare core.
12. The system of claim 8 , wherein the one or more controllers are further configured to:
determine, based on the in-field test, that the first core is corrupted; and
designate the first core as an inoperable core that is not available as either an operational core or as spare core.
13. The system of claim 12 , wherein the one or more controllers are further configured to:
determine that no additional spare cores are available in connection with the plurality of operational cores; and
alter one or more testing procedures for the plurality of cores based on determining that no additional spare cores are available.
14. The system of claim 8 , wherein the one or more controllers are further configured to:
determine, while the first core is in the test mode, that a second core, from the plurality of operational cores, meets one or more criteria for the in-field test;
identify a second ID of the second core;
identify that a second spare core is available;
initialize the second spare core to be in an operational mode, wherein initializing comprises assigning the second ID to the second spare;
place the second core into a test mode; and
perform the in-field test of the second core in a manner that is transparent to the operating system while maintaining the second spare core in the operation mode under the first ID.
15. A method comprising:
identifying one or more criteria within an SoC for an in-field test of at least one of a plurality of operational cores within the SoC, wherein each of the plurality of operational cores has a corresponding that identifies the operational core to an operating system and wherein the SoC contains one or more spare cores;
performing the in-field test for at least one of the plurality of operational cores within an SoC in a manner that is transparent to the operating system;
determining, based on the in-field test, that a first core from the plurality of cores is corrupted;
designating the first core as an inoperable core; and
maintaining a first spare core, from the one or more spare cores, as operational under the core ID corresponding to the first core.
16. The method of claim 15 , wherein the one or more criteria comprises the SoC entering into a boot-time power-up.
17. The method of claim 15 , wherein the plurality of operational cores are contained on a chiplet of the SoC, and wherein the in-field test comprises testing each of the operational cores contained on the chiplet.
18. The method of claim 15 , wherein the in-field test is an online in-field test of the first core, and wherein the method further comprises assigning the first spare core with the core ID corresponding to the first core prior to performing the online in-field test of the first core.
19. The method of claim 15 , further comprising:
determining that, after the first spare core is maintained as operational, the SoC does not contain additional spare cores; and
transmitting a notification that SoC does not contain additional spare cores.
20. The method of claim 15 , wherein the one or more criteria are variable over time.