Method for decoding data in non-volatile storage using reliability metrics based on multiple reads
Data stored in non-volatile storage is decoded using iterative probabilistic decoding and multiple read operations to achieve greater reliability. An error correcting code such as a low density parity check code may be used. In one approach, initial reliability metrics, such as logarithmic likelihood ratios, are used in decoding read data of a set of non-volatile storage element. The decoding attempts to converge by adjusting the reliability metrics for bits in code words which represent the sensed state. If convergence does not occur, e.g., within a set time period, the state of the non-volatile storage element is sensed again, current values of the reliability metrics in the decoder are adjusted, and the decoding again attempts to converge.
1. A method for decoding data in non-volatile storage, comprising:
performing a first sense operation on at least one non-volatile storage element;
providing a first code word based on the first sense operation;
performing a decoding process for the first code word using a first set of reliability metrics which is based on the first code word; and
if the decoding process does not meet a first condition, the first condition comprises the decoding process converging within a given time period, performing a second sense operation on the at least one non-volatile storage element and continuing the decoding process based on the second sense operation.
2. The method of claim 1 , wherein the decoding process attempts to satisfy parity checks of an error correction code, and the decoding process converges when the parity checks are satisfied.
3. The method of claim 2 , wherein the error correction code comprises a low density parity check code which is applied over a set of non-volatile storage elements which includes the at least one non-volatile storage element.
4. The method of claim 1 , wherein the sense operations comprise read operations.
5. The method of claim 1 , wherein the first condition comprises the decoding process converging within a given number of iterations.
6. The method of claim 1 , wherein the first condition comprises the decoding process satisfying a given number of parity checks.
7. The method of claim 1 , wherein the first code word comprises bits which indicate whether a voltage threshold of the at least one non-volatile storage element is above or below each of a plurality of different voltage threshold levels, as indicated by the first sense operation.
8. The method of claim 1 , wherein, if the decoding process does not meet a second condition, the method further comprises:
performing a third sense operation on the at least one non-volatile storage element; and
continuing the decoding process based on the third sense operation.
9. The method of claim 1 , wherein the first set of reliability metrics comprises logarithmic likelihood ratios, the first code word comprises multiple bits, and the logarithmic likelihood ratios are provided for each bit.
10. A non-volatile storage system, comprising:
a set of non-volatile storage elements; and
one or more control circuits in communication with the set of non-volatile storage elements, the one or more control circuits perform a first sense operation on at least one non-volatile storage element of the set, provide a first code word based on the first sense operation, perform a decoding process for the first code word using a first set of reliability metrics which is based on the first code word, and if the decoding process does not meet a first condition, perform a second sense operation on the at least one non-volatile storage element and continue the decoding process based on the second sense operation, wherein the first code word comprises bits which indicate whether a voltage threshold of the at least one non-volatile storage element is above or below each of a plurality of different voltage threshold levels, as indicated by the first sense operation.
11. The non-volatile storage system of claim 10 , wherein the first condition comprises the decoding process converging within a given time period.
12. The non-volatile storage system of claim 10 , wherein if the decoding process does not meet a second condition, the one or more control circuits perform a third sense operation on the at least one non-volatile storage element and continue the decoding process based on the third sense operation.
13. The non-volatile storage system of claim 10 , wherein the first set of reliability metrics comprises logarithmic likelihood ratios, the first code word comprises multiple bits, and the logarithmic likelihood ratios are provided for each bit.
14. The non-volatile storage system of claim 10 , wherein the decoding process is adjusted based on: (a) reliability metrics which are based on the second sense operation and (b) reliability metrics in the decoding process.
15. The non-volatile storage system of claim 10 , wherein the first condition comprises the decoding process converging within a given number of iterations.
16. The non-volatile storage system of claim 10 , wherein the first condition comprises the decoding process converging within a given number of parity checks.
17. A method for decoding data in non-volatile storage, comprising:
performing a first sense operation on at least one non-volatile storage element;
providing a first code word based on the first sense operation;
performing a decoding process for the first code word using a first set of reliability metrics which is based on the first code word, the first code word comprises multiple bits in respective bit positions, and the first set of reliability metrics includes reliability metrics for each bit; and
if the decoding process does not meet a first condition, performing a second sense operation on the at least one non-volatile storage element and continuing the decoding process based on the second sense operation, the continuing the decoding process based on the second sense operation comprises, for at least one of the bit positions of the first code word, adjusting the reliability metric to indicate a higher reliability when a sensed programming state of the first sense operation is consistent with a sensed programming state of the second sense operation.
18. The method of claim 17 , wherein one of the bit positions of the first code word is associated with one of the reliability metrics in the decoding process, and the continuing the decoding process based on the second sense operation comprises adjusting a current value of the one of the reliability metrics in the decoding process to indicate a lower reliability when a sensed programming state of the first sense operation is inconsistent with a sensed programming state of the second sense operation.
19. The method of claim 17 , wherein for each bit position, the reliability metric in the first set of reliability metrics represents a probability that an associated bit of the multiple bits is not errored.