Apparatus, system, and method for dynamic recovery and restoration from design defects in an integrated circuit

• US 7,590,901 B2
• Filed: 05/19/2006
• Issued: 09/15/2009
• Est. Priority Date: 05/19/2006
• Status: Active Grant

• Current Assignee: Taiwan Semiconductor Manufacturing Company Limited
• Original Assignee: International Business Machines Corporation
• Inventors: Kuo, Lih-Chung
• Primary Examiner(s): Britt; Cynthia
• Assistant Examiner(s): GANDHI, DIPAKKUMAR B
• Application Number:
  US11/419,271
• Publication Number:
  US 20070283222A1
• Time in Patent Office: 1,215 Days
• Field of Search: None
• US Class Current: 714/724
• CPC Class Codes: G06F 11/1008 in individual solid state devices G06F11/1004 takes precedence

Abstract

An apparatus, system, and method are disclosed for the recovery from a design defect in an integrated circuit. The apparatus includes an error check module, a control settings module, a retry module, and a recovery module. The error check module discovers that an error has occurred during an operation. The control settings module changes the contents of one or more system control registers according to a set of system control settings that change the logic path of one or more system signals. The retry module executes the operation. The recovery module discovers that the operation was executed successfully.

Claims

1. An apparatus to assist in recovery from a design defect in an integrated circuit, the apparatus comprising:

an error check module configured to discover that an error has occurred during an operation within the integrated circuit;

a control settings module configured to change the contents of one or more system control registers according to a set of system control settings, the set of system control settings changing the logic path of one or more system signals within the integrated circuit;

a retry module configured to execute the operation within the integrated circuit; and

a recovery module configured to determine if the operation was executed successfully.

2. The apparatus of claim 1, further comprising a settings reset module configured to return the one or more system control registers to a previous state in response to a successful execution of the operation.

3. The apparatus of claim 1, further comprising a resume module configured to save the status of one or more concurrently executing operations in response to the error, and to resume execution of the operations in response to a successful execution of the operation.

4. The apparatus of claim 1, further comprising a restart module configured to save a list of one or more concurrently executing operations in response to the error, and to restart execution of the operations in response to a successful execution of the operation.

5. The apparatus of claim 1, further comprising a randomizer module configured to choose a set of random system control settings from a list of valid system control settings.

6. The apparatus of claim 1, further comprising a knowledge database comprising a list of one or more errors and one or more system control settings corresponding to each error.

7. The apparatus of claim 6, wherein the knowledge database further comprises one or more statistics corresponding to each error.

8. The apparatus of claim 6, wherein the knowledge database further comprises a recovery policy corresponding to each error.

9. The apparatus of claim 6, further comprising an update module configured to update the knowledge database with one or more errors or system control settings.

10. A system to recover from a design defect in an integrated circuit, the system comprising:

a circuit board configured to provide an insulating base for one or more electronic devices;

an integrated circuit coupled to the circuit board, the integrated circuit configured to;

discover that an error has occurred during an operation;

retrieve a set of system control settings associated with the error from a knowledge database, the knowledge database comprising a list of one or more errors and one or more system control settings corresponding to each error;

change the contents of one or more system control registers according to the set of system control settings;

execute the operation; and

determine if the operation was executed successfully; and

an external interface coupled to the circuit board and in communication with the integrated circuit, the external interface configured to receive updates for the knowledge database from a separate device.

11. The system of claim 10, wherein the knowledge database further comprises one or more statistics corresponding to each error.

12. The system of claim 10, wherein the knowledge database further comprises a recovery policy corresponding to each error.

13. A computer program product comprising a computer readable medium having computer usable program code programmed for recovery from a design defect in an integrated circuit, the operations of the computer program product comprising:

discovering that an error has occurred during an operation within the integrated circuit;

retrieving a set of system control settings associated with the error from a knowledge database, the knowledge database comprising a list of one or more errors and one or more system control settings corresponding to each error;

changing the contents of one or more system control registers according to the set of system control settings, the set of system control settings changing the logic path of one or more system signals within the integrated circuit;

executing the operation within the integrated circuit; and

determining if the operation was executed successfully.

14. The computer program product of claim 13, further comprising returning the one or more system control registers to a previous state in response to a successful execution of the operation.

15. The computer program product of claim 13, further comprising saving the status of one or more concurrently executing operations in response to the error, and resuming execution of the operations in response to a successful execution of the operation.

16. The computer program product of claim 13, further comprising saving a list of one or more concurrently executing operations in response to an error, and restarting execution of the operations in response to a successful execution of the operation.

17. A method for providing a customer with a knowledge database for recovery from a design defect in an integrated circuit, the method comprising:

providing a knowledge database to the integrated circuit of a customer using an external interface coupled to the integrated circuit, the knowledge database comprising a list of one or more errors known to occur in the integrated circuit, and one or more system control settings corresponding to each error, the system control settings configured to change the logic path of one or more signals in the integrated circuit; and

updating the knowledge database for the customer using the external interface coupled to the integrated circuit.

18. The method of claim 17, wherein the knowledge database further comprises a recovery policy corresponding to each error.

19. The method of claim 17, wherein the knowledge database is updated remotely over a network.

20. The method of claim 19, wherein the knowledge database is updated based on errors reported by other customers.