Using error information from nearby locations to recover uncorrectable data in non-volatile memory
View Patent ↗In various embodiments, the reference voltage used for read operations in a non-volatile memory may be adjusted up or down in an attempt to read data from an area that previously produced at least one uncorrectable error. The direction and amount of this adjustment may be based on the number and direction of correctable errors in surrounding data.
1. An apparatus, comprising
a non-volatile (NV) memory, the NV memory comprising a memory controller to control reading a memory array, the controller to perform operations comprising:
using a first reference voltage to read, from the memory array, data comprising multiple units of data;
performing an error checking and correction process on the data;
determining that at least one of the units contains an uncorrectable error;
determining a direction and net quantity of correctable errors for each unit that contains at least one correctable error but that does not contain an uncorrectable error;
adjusting the first reference voltage by an amount based on said determining the direction and the net quantity; and
reading the data again, subsequent to said adjusting.
2. The apparatus of claim 1 , wherein the data comprises a page of data, and each of the units comprises a sector of data within the page.
3. The apparatus of claim 1 , wherein the operation of determining a direction and net quantity comprises determining a difference between a number of decreasing value errors and a number of increasing value errors for a particular unit.
4. The apparatus of claim 1 , wherein the non-volatile memory comprises multiple-bits-per-cell technology, and the operation of adjusting comprises adjusting a second reference voltage.
5. The apparatus of claim 1 , further comprising a processor coupled to the NV memory controller.
6. The apparatus of claim 1 , further comprising the memory array coupled to the memory controller.
7. The apparatus of claim 6 , wherein the memory array comprises a flash memory array.
8. The apparatus of claim 6 , wherein the memory array comprises a NAND flash memory array.
9. A method, comprising:
reading, from a non-volatile memory, data comprising multiple units of data, wherein said reading comprises using a first reference voltage;
performing an error checking and correction process on the data;
determining that at least one of the units contains an uncorrectable error;
determining a direction and net quantity of correctable errors for each unit not containing an uncorrectable error but containing at least one correctable error;
adjusting the first reference voltage by an amount based on said determining the direction and the net quantity; and
reading the data again, subsequent to said adjusting.
10. The method of claim 9 , wherein said reading the data comprises reading a page of data, and each of said units comprises a sector of data within the page.
11. The method of claim 9 , wherein said determining a direction and net quantity comprises determining a difference between a number of decreasing value errors and a number of increasing value errors for a particular unit.
12. The method of claim 9 , wherein the non-volatile memory comprises multiple-bits-per-cell technology, and said adjusting comprises adjusting a second reference voltage.
13. The method of claim 9 , further comprising:
saving, after said reading, a first set of data comprising corrected data from the units not containing the uncorrectable errors;
saving, after said reading again, a second set of data comprising corrected data from the unit that contained the uncorrectable errors after said reading; and
combining the first set of data with the second set of data.
14. The method of claim 9 , wherein said determining the direction and net quantity comprises considering a difference between all correctable increasing value errors and all correctable decreasing value errors in the data.
15. The method of claim 9 , wherein said determining the direction and net quantity comprises considering an average per unit of a difference between the correctable increasing and decreasing value errors in each unit.
16. An article comprising
a tangible computer-readable medium that contains instructions, which when executed by one or more processors result in performing operations comprising:
reading, from a non-volatile memory, data comprising multiple units of data, wherein said reading comprises using a first reference voltage;
performing an error checking and correction process on the data;
determining that at least one of the units contains an uncorrectable error;
determining a direction and net quantity of correctable errors for each unit not containing an uncorrectable error but containing at least one correctable error;
adjusting the first reference voltage by an amount based on said determining the direction and the net quantity; and
reading the data again, subsequent to said adjusting.
17. The article of claim 16 , wherein the operation of reading the data comprises reading a page of data, and each of said units comprises a sector of data within the page.
18. The article of claim 16 , wherein the operation of determining a direction and net quantity comprises determining a difference between a number of decreasing value errors and a number of increasing value errors for a particular unit.
19. The article of claim 16 , wherein the non-volatile memory comprises multiple-bits-per-cell technology, and the operation of adjusting comprises adjusting a second reference voltage.
20. The article of claim 16 , wherein the operations further comprise:
saving, after said reading, a first set of data comprising corrected data from the units not containing the uncorrectable errors;
saving, after said reading again, a second set of data comprising corrected data from the unit that contained the uncorrectable errors after said reading; and
combining the first set of data with the second set of data.
21. The article of claim 16 , wherein the operation of determining the direction and net quantity comprises considering a difference between all correctable increasing value errors and all correctable decreasing value errors in the data.
22. The article of claim 16 , wherein the operation of determining the direction and net quantity comprises considering an average per unit of a difference between the correctable increasing and decreasing value errors in each unit.