Imminent read failure detection using high/low read voltage levels
View Patent ↗Methods and systems are disclosed for imminent read failure detection using high/low read voltage levels. In certain embodiments, data stored within an array of non-volatile memory (NVM) cells is checked using read voltage levels below and above a normal read voltage level. An imminent read failure is then indicated if errors are detected within the same address for both voltage checks. Further, data stored can be checked using read voltage levels that are incrementally decreased below and incrementally increased above a normal read voltage level. An imminent read failure is then indicated if read errors are detected within the same address for both voltage sweeps and if high/low read voltage levels triggering faults differ by less than a predetermined threshold value. An address sequencer, error correction code (ECC) logic, and a bias generator can be used to implement the imminent failure detection.
1. A method for detecting imminent read failures for a non-volatile memory (NVM) system, comprising:
using a normal read voltage level for read operations for an array of non-volatile memory (NVM) cells;
adjusting a read voltage level to one or more low voltage levels below the normal read voltage level and for each of the one or more low voltage levels:
performing one or more first read and error correction operations for a plurality of addresses associated with the array of NVM cells; and
recording one or more first addresses for bit errors detected with respect to the one or more first read and error correction operations;
adjusting a read voltage level to one or more high voltage levels above the normal read voltage level and for each of the one or more high voltage levels:
performing one or more second read and error correction operations for a plurality of addresses associated with the array of NVM cells; and
recording one or more second addresses for bit errors detected with respect to the one or more second read and error correction operations;
comparing the one or more first addresses and the one or more second addresses to determine one or more address matches; and
indicating an imminent read failure for the array of NVM cells at least in part based upon the comparison.
2. The method of claim 1 , wherein a predetermined low voltage level and a predetermined high voltage level are used for the adjusting steps.
3. The method of claim 2 , wherein the predetermined low voltage level is between 0.3 to 1.0 volts below the normal read voltage level, and wherein the predetermined high voltage level is between 0.3 to 1.5 volts above the normal voltage level.
4. The method of claim 1 , wherein for the adjusting steps the read voltage level is incrementally decreased to read voltage levels below the normal read voltage level until a low bit error is detected and the read voltage level is incrementally increased to read voltage levels above a normal read voltage level until a high bit error is detected.
5. The method of claim 4 , wherein the recording steps comprise recording a low error address and a low error voltage level for the low bit error and a high error address a high error voltage level for the high bit error.
6. The method of claim 5 , wherein the comparing step comprises comparing the first error address to the second error address and if they match, further comparing a difference between the low error voltage level and the high error voltage level to a voltage threshold value.
7. The method of claim 6 , wherein for the adjusting steps the read voltage levels are incrementally decreased and increased from the normal read voltage level by between 0.05 to 0.10 volt steps.
8. The method of claim 1 , further comprising using error correction code (ECC) logic to run one or more ECC routines for the error correction operations, the one or more ECC routines being configured to detect single-bit errors.
9. The method of claim 1 , wherein the indicating step comprises storing within a data storage medium matching addresses and a flag indicating that an imminent read failure condition has been detected.
10. The method of claim 9 , further comprising allowing read access to the matching addresses and the flag within the data storage medium.
11. The method of claim 1 , wherein the indicating step comprises outputting a failure indicator signal.
12. The method of claim 1 , wherein the adjusting, comparing, and indicating steps are performed within a diagnostic mode for the NVM system.
13. The method of claim 1 , further entering the diagnostic mode only after a read error is detected and corrected by the NVM system during a normal read operation.
14. A non-volatile memory (NVM) system having imminent read failure detection, comprising:
a non-volatile memory (NVM) including an array of NVM cells;
a memory management unit coupled to the array of NVM cells;
a controller within the memory management unit coupled to the NVM and configured to perform read operations for the NVM cells using a normal read voltage level;
the controller being configured to adjust a read voltage level to one or more low voltage levels below a normal read voltage level and for each of the one or more low voltage levels:
to perform one or more first read and error correction operations for a plurality of addresses associated with the array of NVM cells, and
to record one or more first addresses for bit errors detected with respect to the one or more first read and error correction operations;
the controller being configured to adjust a read voltage level to one or more high voltage levels above the normal read voltage level and for each of the one or more high voltages levels:
to perform one or more second read and error correction operations for a plurality of addresses associated with the array of NVM cells, and
to record one or more second addresses for bit errors detected with respect to the one or more second read and error correction operations; and
the controller being configured to compare the one or more first addresses and the one or more second addresses to determine one or more address matches and to indicate an imminent read failure for the array of NVM cells at least in part based upon the comparison.
15. The NVM system of claim 14 , wherein a predetermined low voltage level and a predetermined high voltage level are used for the adjustments.
16. The NVM system of claim 14 , wherein for the adjustments the controller is further configured to incrementally decrease the read voltage level to read voltage levels below the normal read voltage level until a low bit error is detected and to incrementally increase the read voltage level to read voltage levels above a normal read voltage level until a high bit error is detected.
17. The NVM system of claim 16 , wherein the controller is further configured to record a low error address and a low error voltage level for the low bit error and a high error address a high error voltage level for the high bit error.
18. The NVM system of claim 17 , wherein the controller is further configured to compare the low error address to the high error address and if they match, further compare a difference between the low error voltage level and the high error voltage level to a voltage threshold value.
19. The NVM system of claim 14 , wherein the memory management unit further comprises error correction code (ECC) logic configured to run one or more ECC routines, and wherein the controller is further configured to use the ECC logic for the error correction operations.
20. The NVM system of claim 14 , further comprising a data storage medium configured to store the one or more first addresses, the one or more second addresses, and a flag indicating that an imminent read failure condition has been detected.