DEVICES AND METHOD FOR WEAR ESTIMATION BASED MEMORY MANAGEMENT

• US 20120216085A1
• Filed: 01/03/2012
• Published: 08/23/2012
• Est. Priority Date: 02/23/2011
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: DensBits Technologies Ltd. (Broadcom, Inc.)
• Inventors: Weingarten, Hanan, Steiner, Avi
• Granted Patent: US 10,079,068 B2
• Time in Patent Office: Days
• US Class Current: 714/718
• CPC Class Codes: G11C 11/56 using storage elements with more than two stable states represented by steps, e.g. of voltage, current, phase, frequency
• CPC Class Codes: G11C 16/00 Erasable programmable read-only memories G11C14/00 takes precedence
• CPC Class Codes: G11C 16/349 Arrangements for evaluating degradation, retention or wearout, e.g. by counting erase cycles
• CPC Class Codes: G11C 2029/5002 Characteristic
• CPC Class Codes: G11C 29/028 with adaption or trimming of parameters
• CPC Class Codes: G11C 29/50004 of threshold voltage

Abstract

A system, a non-transitory computer readable medium and a method for wear estimation of a flash memory device, the method may include: programming information to a first portion of the flash memory device during a test programming process; measuring a duration of the test programming process; and estimating a wear characteristic of the first portion of the flash memory device thereby providing an estimated wear characteristic, wherein the estimating is responsive to the duration of the test programming process.

Claims

1. A method for wear estimation of a flash memory device, the method comprises:

programming information to a first portion of the flash memory device during a test programming process;

measuring a duration of the test programming process; and

estimating a wear characteristic of the first portion of the flash memory device thereby providing an estimated wear characteristic, wherein the estimating is responsive to the duration of the test programming process.

2. The method according to claim 1, wherein the test programming process comprises programming test information, wherein the test programming process is dedicated solely for the estimating of the wear characteristic.

3. The method according to claim 1, wherein the information is random information having a random content or pseudo-random information generated by a pseudo-random process.

4. The method according to claim 1, wherein the information is selected to comprise a substantially same amount of zero valued bits and one valued bits.

5. The method according to claim 1, wherein the programming of the information comprises applying multiple types of programming that differ from each other by significance.

6. The method according to claim 1, comprising triggering the test programming process in a random or pseudo-random manner.

7. The method according to claim 1, comprising triggering the test programming process in response to events selected from:

(a) an occurrence of read errors of data previously programmed to the flash memory device, (b) reaching a predefined number of program and erase cycles of the first portion of the flash memory device, (c) detecting another portion of the flash memory device that has a wear level of a predetermined value, (d) a failure in evaluating a wear level of another portion of the flash memory device, and (e) a success in evaluating a wear level of another portion of the flash memory device.

8. The method according to claim 1, comprising programming non-test information using first programming parameters and programming the information, during the test programming process, using second programming parameters that differ from the first programming parameters;

wherein each of the first and second programming parameters comprise at least one out of an initial programming voltage, an allowable number of programming steps, a bias voltage supplied to flash memory cells that are not programmed, a maximal programming voltage and a programming voltage step.

9. The method according to claim 1, wherein the information is non-test information that is scheduled to be programmed to the flash memory module even at an absence of the test programming process.

10. The method according to claim 9, comprising:

programming the non-test information during the test programming process;

storing the non-test information in a buffer;

checking if the programming of the non-test information succeeded;

deleting the non-test information from the buffer if the programming of the non-test information succeeded; and

re-programming the non-test information if the programming of the non-test information failed.

11. The method according to claim 10, comprising re-programming the non-test information to another portion of the flash memory device.

12. The method according to claim 10, comprising re-programming the non-test information while using at least one programming parameter that differs from a programming parameter used during the programming of the non-test information.

13. The method according to claim 9, comprising determining whether to re-program the non-test information in response to the wear characteristic evaluated during the evaluating of the wear characteristic.

14. The method according to claim 9, comprising receiving non-test information to be programmed during the test programming process, wherein the non-test information is encoded with an error correction code that is stronger than an error correction code applied on non-test information that is programmed during a non-test programming process.

15. The method according to claim 9, comprising applying a first error correction code to generate non-test information to be programmed during the test programming process;

and applying a second error correction code to generate non-test information to be programmed during a non-test programming process;

wherein the first error correction code is stronger than the second error correction code.

16. The method according to claim 1, comprising:

programming the information while using first programming parameters;

determining values of third programming parameters based upon the estimated wear characteristic; and

programming additional information while using the third programming parameters.

17. The method according to claim 1, wherein the programming of the information comprises utilization of programming parameters that emphasize differences between wear characteristics of different portions of the flash memory device.

18. The method according to claim 17, comprising finding programming parameters that emphasize differences between wear characteristics of different portions of the flash memory device.

19. The method according to claim 1, comprising altering at least one programming parameter during the test programming period.

20. The method according to claim 1, comprising allocating portions of the flash memory device for programming based upon estimated wear characteristics of the portions of the flash memory device.

21. The method according to claim 18, wherein the allocating comprises applying a wear balancing scheme.

22. The method according to claim 18, wherein the allocating comprises:

allocating the first portion of the flash memory device to store an information entity that is expected to be stored for a first term; and

allocating another portion of the flash memory device to store another information entity that is expected to stored for a second term;

wherein the first term is longer than the second term and the estimated wear characteristics of the first and second portions of the flash memory device indicate that the first portion of the flash memory device is less worn than the second portion of the flash memory device.

23. The method according to claim 1, selecting programming parameters to be used when programming non-test information in response to the estimated wear characteristic.

24. The method according to claim 1, comprising:

performing multiple sets of test programming processes on multiple portions of the flash memory device in proximity to a beginning of a lifetime of the flash memory device;

wherein different portions of the flash memory devices undergo different amounts of test programming processes;

wherein the test programming processes of each set are executed in a continuous manner;

wherein durations of the multiple sets of test programming process are measured to provide multiple durations; and

generating, in response to the multiple durations, a time to wear mapping.

25. The method according to claim 24, comprising selecting, out of the multiple durations, a subset of durations, as a time to wear mapping.

26. The method according to claim 24, comprising executing each set of test programming processes without long idle periods between adjacent test programming processes of the set such as to prevent substantially charge trap discharge.

27. A non-transitory computer readable medium that stores instructions for:

programming information to a first portion of the flash memory device during a test programming process;

measuring a duration of the test programming process; and

estimating a wear characteristic of at least the first portion of the flash memory device thereby providing an estimated wear characteristic, wherein the estimating is response to the duration of the test programming process.

28. A system comprising a memory controller and a flash memory device:

wherein the memory controller is arranged to program information to a first portion of the flash memory device during a test programming process;

measure a duration of the test programming process; and

estimate a wear characteristic of at least the first portion of the flash memory device thereby providing an estimated wear characteristic, wherein the estimate is responsive to the duration of the test programming process.