MEMORY CONTROLLER AND OPERATING METHOD OF MEMORY CONTROLLER

• US 20120290896A1
• Filed: 05/08/2012
• Published: 11/15/2012
• Est. Priority Date: 05/09/2011
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: CHO, Yongwon, KONG, JaePhil, SONG, Jong-uk
• Granted Patent: US 8,667,369 B2
• Time in Patent Office: Days
• US Class Current: 714/763
• CPC Class Codes: G06F 11/076 by exceeding a count or rate limit, e.g. word- or bit count limit
• CPC Class Codes: G06F 11/1048 using arrangements adapted for a specific error detection or correction feature
• CPC Class Codes: H03M 13/152 Bose-Chaudhuri-Hocquenghem [BCH] codes
• CPC Class Codes: H03M 13/1545 Determination of error locations, e.g. Chien search or other methods or arrangements for the determination of the roots of the error locator polynomial
• CPC Class Codes: H03M 13/1555 Pipelined decoder implementations
• CPC Class Codes: H03M 13/3715 Adaptation to the number of estimated errors or to the channel state
• CPC Class Codes: H03M 13/6502 Reduction of hardware complexity or efficient processing

Abstract

A method of operating a memory controller to control a memory device includes reading a read vector from the memory device and correcting one or more errors in the read vector, where a power consumed at the correcting is varied according to the number of errors in the read vector.

Claims

1. A method of operating a memory controller to control a memory device, the method comprising:

reading a read vector from the memory device;

estimating a number of errors from the read vector;

performing an error search on one of i) part of the read vector and (ii) the entire read vector based the estimated number, to determine actual errors in the read vector; and

correcting the determined actual errors in the read vector.

2. The method of claim 1, wherein power consumption of the memory controller increases when the number of estimated errors in the read vector is over a threshold value.

3. The method of claim 1, wherein the read vector includes a data portion and a parity portion, and

wherein the error search on the part of the read vector excludes an error search on the parity portion of the read vector when the number of estimated errors in the read vector is below a threshold value.

4. The method of claim 1, wherein the estimating the number of errors comprises:

calculating a syndrome code from the read vector;

calculating an error location polynomial from the syndrome code; and

setting the estimated number of errors based on the error location polynomial.

5. The method of claim 4, wherein the setting the estimated number of errors based on the error location polynomial comprises setting the estimated number of errors based on an index of the highest degree of the error location polynomial.

6. The method of claim 4, wherein the error search is performed on the part by selecting a number of bits to be searched of the read vector.

7. The method of claim 1, wherein the performing the error search on the entire read vector comprises performing a normal chien search when the estimated error number is over a threshold value, and wherein the performing the error search on the part of the read vector comprises performing a parity-skipped chien search when the estimated error number is below a threshold value.

8. The method of claim 7, wherein performing the normal chien search comprises conducting a forward chien search on data and parity portions of the read vector.

9. The method of claim 7, wherein performing the parity-skipped chien search comprises conducting a forward chien search only on a data portion of the read vector.

10. A memory controller comprising:

an ECC encoder configured to generate a code vector to be written in a memory device by encoding a write data vector; and

an ECC decoder configured to correct one or more errors in a read vector read from the memory device and to output an error-corrected data vector,

wherein power consumption of the ECC decoder is adjusted according to an estimated number of errors in the read vector.

11. The memory controller of claim 10, wherein the power consumption increases when the estimated number of errors in the read vector is over a threshold value.

12. The memory controller of claim 10, wherein the read vector includes a data portion and a parity portion, and

wherein an error search on the parity portion of the read vector is omitted when the number of estimated errors in the read vector is below a threshold value.

13. The memory controller of claim 10, wherein the ECC decoder comprises:

a syndrome calculation unit configured to calculate a syndrome code from the read vector;

a key equation solving unit configured to calculate an error location polynomial based on the syndrome code;

a chien search unit configured to calculate error location information based on the error location polynomial;

an error correcting unit configured to correct one or more errors in the read vector based on the error location information; and

a controller configured to estimate the number of errors in the read vector from the error location polynomial and to control power consumption of the chien search unit according to the estimated error number.

14. The memory controller of claim 13, wherein the controller controls the chien search unit to skip a search operation on a parity portion of the read vector when the estimated error number is below a threshold value.

15. The memory controller of claim 13, wherein the controller is configured to determine the estimated number of errors of the read vector based on an index of the highest degree of the error location polynomial.

16. A method of operating a memory controller to control a memory device, the method comprising:

reading a read vector from the memory device that comprises a data portion and a parity portion;

estimating a number of errors from the read vector;

changing an operating mode of the memory controller from a normal mode to a power-saving mode when the number of estimated errors is less than a threshold value, wherein during the power-saving mode, the method comprises;

performing an error search on only the data portion to determine actual errors in the read vector; and

correcting the determined actual errors in the read vector.

17. The method of claim 16, wherein during the normal mode, the method comprises:

performing an error search on both the data portion and the parity portion to determine actual errors; and

correcting the determined actual errors in the read vector.

18. The method of claim 17, wherein the error searches are forward chien searches.

19. The method of claim 16, wherein the estimating comprises:

generating a syndrome code by multiplying the read vector by a parity check matrix;

generating a polynomial from the syndrome code; and

setting the estimated number of errors to the number of roots of the polynomial.

20. The method of claim 19, further comprising outputting the read vector when the syndrome code is zero and outputting data of the correcting otherwise.