IP Library Granted Patent US 10,460,818
Granted Patent B2
US 10,460,818 · App. 15/472,793 · Granted Oct 29, 2019

Retention-drift-history-based non-volatile memory read threshold optimization

Inventors: Earl T. Cohen (Oakland, CA); Hao Zhong (Milpitas, CA)
Assignee: Seagate Technology LLC
G11C16/3495G01R19/0084G11C16/0483G11C16/26G11C16/28G11C16/349G11C16/3418G11C16/3427G11C29/021G11C29/028G11C7/14
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,460,818
App. No.
15/472,793
Granted
Oct 29, 2019
Kind
B2
Abstract

Methods, systems and computer-readable storage media for selecting a retention drift predictor scheme, reading retention drift history associated with reference cells of a plurality of groups of pages of a non-volatile memory (NVM), and predicting values for an optimal read threshold voltage of at least some of the plurality of groups of pages. The predicting of values for an optimal read threshold voltage may be based at least on the selected retention drift predictor scheme and the read retention drift history.

Claims (31)

1. A method comprising:

selecting a retention drift predictor scheme for predicting optimal read threshold voltages in a non-volatile memory (NVM) from retention drift history;

reading the retention drift history associated with reference cells of a plurality of groups of pages of the NVM; and

predicting values for an optimal read threshold voltage of at least some of the plurality of groups of pages based at least on the selected retention drift predictor scheme and the read retention drift history.

2. The method of claim 1 , wherein the retention drift predictor scheme is selected dynamically in accordance with a predetermined criteria.

3. The method of claim 1 , wherein the retention drift predictor scheme comprises a one-to-one function, wherein non-reference cells of the plurality of groups of pages are predicted to behave identically to the reference cells.

4. The method of claim 1 , wherein the retention drift predictor scheme comprises a time-based function, wherein read threshold values obtained from the reference cells are modified in view of the retention drift history and an elapsed time since the reference cells were last written.

5. The method of claim 1 , wherein the retention drift predictor scheme comprises a compensation function, wherein read threshold values obtained from the reference cells are modified in view of characterization data accounting for differences between non-reference cells of the plurality of groups of pages and the reference cells.

6. The method of claim 5 , wherein the differences between the non-reference cells and the reference cells further comprise differences that are time-dependent and wear-dependent.

7. The method of claim 1 , further comprising compensating, by a compensating predictor, for variations between non-reference cells of the plurality of groups of pages and the reference cells based on a determination that the non-reference cells exhibit a different retention drift compared to the reference cells.

8. The method of claim 7 , wherein the compensation applied by the compensating predictor comprises at least one of a linear function with a time variable, a linear function without a time variable, a unity function, a non-linear function with a time variable, and a non-linear function without a time variable.

9. A storage system comprising:

a non-volatile memory (NVM); and

a storage controller communicatively coupled to the NVM, the storage controller configured to

select a retention drift predictor scheme for predicting optimal read threshold voltages in the NVM from retention drift history;

read retention drift history associated with reference cells of a plurality of groups of pages of the NVM; and

predict values for an optimal read threshold voltage of at least some of the plurality of groups of pages based at least on the selected retention drift predictor scheme and the read retention drift history.

10. The storage system of claim 9 , wherein the retention drift predictor scheme is selected dynamically in accordance with a predetermined criteria.

11. The storage system of claim 9 , wherein the retention drift predictor scheme comprises a one-to-one function, wherein non-reference cells of the plurality of groups of pages are predicted to behave identically to the reference cells.

12. The storage system of claim 9 , wherein the retention drift predictor scheme comprises a time-based function, wherein read threshold values obtained from the reference cells are modified in view of the retention drift history and an elapsed time since the reference cells were last written.

13. The storage system of claim 9 , wherein the retention drift predictor scheme comprises a compensation function, wherein read threshold values obtained from the reference cells are modified in view of characterization data accounting for differences between non-reference cells of the plurality of groups of pages and the reference cells.

14. The storage system of claim 13 , wherein the differences between the non-reference cells and the reference cells further comprise differences that are time-dependent and wear-dependent.

15. The storage system of claim 9 , wherein the storage controller is further configured to compensate for variations between non-reference cells of the plurality of groups of pages and the reference cells based on a determination that the non-reference cells exhibit a different retention drift compared to the reference cells.

16. The storage system of claim 15 , wherein the compensation applied by the storage controller comprises at least one of a linear function with a time variable, a linear function without a time variable, a unity function, a non-linear function with a time variable, and a non-linear function without a time variable.

17. A non-transitory computer readable storage medium having processor-executable instructions stored thereon that, when executed by a processor, cause the processor to:

select a retention drift predictor scheme for predicting optimal read threshold voltages in a non-volatile memory (NVM) from retention drift history;

read retention drift history associated with reference cells of a plurality of groups of pages of the NVM; and

predict values for an optimal read threshold voltage of at least some of the plurality of groups of pages based at least on the selected retention drift predictor scheme and the read retention drift history.

18. The non-transitory computer readable storage medium of claim 17 , wherein the retention drift predictor scheme comprises a compensation function, wherein read threshold values obtained from the reference cells are modified in view of characterization data accounting for differences between non-reference cells of the plurality of groups of pages and the reference cells.

19. The non-transitory computer readable storage medium of claim 17 , wherein the processor is further configured to compensate for variations between non-reference cells of the plurality of groups of pages and the reference cells based on a determination that the non-reference cells exhibit a different retention drift compared to the reference cells.

20. The non-transitory computer readable storage medium of claim 19 , wherein the compensation comprises at least one of a linear function with a time variable, a linear function without a time variable, a unity function, a non-linear function with a time variable, and a non-linear function without a time variable.

Continuity (3)
Continuation 14170008 · Jan 31, 2014
Provisional Application 61762955 · Feb 10, 2013
Related Publication 20170206979A1 · Jul 20, 2017
Cited By (1)
US 12,374,413