Valley search in read error recovery for a memory device using low-density parity check syndrome weight and auto-read calibration
A processing device in a memory sub-system identifies a plurality of read retry offset voltages having respective check-fail bit counts that are within a target check-fail bit count range for a programming level of a memory device, performs one or more auto-read calibration operations for each of the plurality of read retry offset voltages, and determines respective syndrome weights for sense words read from the memory device using each of the plurality of read retry offset voltages. The processing device further identifies a read retry offset voltage of the plurality of read retry offset voltages having a lowest respective syndrome weight, and performs an error recovery operation using the identified read retry offset voltage.
1 . A system comprising:
a memory device; and
a processing device, operatively coupled with the memory device, to perform operations comprising:
identifying a plurality of read retry offset voltages having respective check-fail bit counts that are within a target check-fail bit count range for a programming level of the memory device;
performing one or more auto-read calibration operations for each of the plurality of read retry offset voltages and determining respective syndrome weights for sense words read from the memory device using each of the plurality of read retry offset voltages;
identifying a read retry offset voltage of the plurality of read retry offset voltages having a lowest respective syndrome weight; and
performing an error recovery operation using the identified read retry offset voltage.
2 . The system of claim 1 , wherein the processing device is to perform operations further comprising:
performing a read operation to read data from the memory device using a default read voltage;
detecting an error in the data read from the memory device; and
initiating an error recovery flow using the plurality of read retry offset voltage.
3 . The system of claim 1 , wherein identifying the plurality of read retry offset voltages comprises:
performing read operations on the memory device using the plurality of read retry offset voltages;
receiving, from the memory device, respective check-fail bit counts corresponding to the plurality of read retry offset voltages; and
comparing the respective check-fail bit counts to the target check-fail bit count range for the programming level of the memory device.
4 . The system of claim 1 , wherein the target check-fail bit count range is based on a threshold value representing a number of memory cells associated with the programming level relative to a number of different programming levels in the memory device.
5 . The system of claim 1 , wherein the processing device is to perform operations further comprising:
reading the sense words from the memory device using the plurality of read retry offset voltages;
executing a plurality of parity check equations on corresponding subsets of the sense words to determine respective pluralities of parity check equation results; and
determining respective syndromes for the sense words using the plurality respective pluralities of parity check equation results, wherein the respective syndrome weights represent a number of bits in the respective syndromes set to a particular state.
6 . The system of claim 5 , wherein each parity check equation corresponds to a different subset of the sense words, and wherein each of the plurality of parity check equation results indicates whether a number of bits set to a value of ‘1’ in a corresponding subset of the sense words is even or odd.
7 . The system of claim 1 , wherein performing the error recovery operation using the identified read retry offset voltage comprises performing at least one of an additional auto-read calibration operation or a deep retry operation.
8 . A method comprising:
identifying a plurality of read retry offset voltages having respective check-fail bit counts that are within a target check-fail bit count range for a programming level of a memory device;
performing one or more auto-read calibration operations for each of the plurality of read retry offset voltages and determining respective syndrome weights for sense words read from the memory device using each of the plurality of read retry offset voltages;
identifying a read retry offset voltage of the plurality of read retry offset voltages having a lowest respective syndrome weight; and
performing an error recovery operation using the identified read retry offset voltage.
9 . The method of claim 8 , further comprising:
performing a read operation to read data from the memory device using a default read voltage;
detecting an error in the data read from the memory device; and
initiating an error recovery flow using the plurality of read retry offset voltage.
10 . The method of claim 8 , wherein identifying the plurality of read retry offset voltages comprises:
performing read operations on the memory device using the plurality of read retry offset voltages;
receiving, from the memory device, respective check-fail bit counts corresponding to the plurality of read retry offset voltages; and
comparing the respective check-fail bit counts to the target check-fail bit count range for the programming level of the memory device.
11 . The method of claim 8 , wherein the target check-fail bit count range is based on a threshold value representing a number of memory cells associated with the programming level relative to a number of different programming levels in the memory device.
12 . The method of claim 8 , further comprising:
reading the sense words from the memory device using the plurality of read retry offset voltages;
executing a plurality of parity check equations on corresponding subsets of the sense words to determine respective pluralities of parity check equation results; and
determining respective syndromes for the sense words using the plurality respective pluralities of parity check equation results, wherein the respective syndrome weights represent a number of bits in the respective syndromes set to a particular state.
13 . The method of claim 12 , wherein each parity check equation corresponds to a different subset of the sense words, and wherein each of the plurality of parity check equation results indicates whether a number of bits set to a value of ‘1’ in a corresponding subset of the sense words is even or odd.
14 . The method of claim 8 , wherein performing the error recovery operation using the identified read retry offset voltage comprises performing at least one of an additional auto-read calibration operation or a deep retry operation.
15 . A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:
identifying a plurality of read retry offset voltages having respective check-fail bit counts that are within a target check-fail bit count range for a programming level of a memory device;
performing one or more auto-read calibration operations for each of the plurality of read retry offset voltages and determining respective syndrome weights for sense words read from the memory device using each of the plurality of read retry offset voltages;
identifying a read retry offset voltage of the plurality of read retry offset voltages having a lowest respective syndrome weight; and
performing an error recovery operation using the identified read retry offset voltage.
16 . The non-transitory computer-readable storage medium of claim 15 , wherein the instructions cause the processing device to perform operations further comprising:
performing a read operation to read data from the memory device using a default read voltage;
detecting an error in the data read from the memory device; and
initiating an error recovery flow using the plurality of read retry offset voltage.
17 . The non-transitory computer-readable storage medium of claim 15 , wherein identifying the plurality of read retry offset voltages comprises:
performing read operations on the memory device using the plurality of read retry offset voltages;
receiving, from the memory device, respective check-fail bit counts corresponding to the plurality of read retry offset voltages; and
comparing the respective check-fail bit counts to the target check-fail bit count range for the programming level of the memory device.
18 . The non-transitory computer-readable storage medium of claim 15 , wherein the target check-fail bit count range is based on a threshold value representing a number of memory cells associated with the programming level relative to a number of different programming levels in the memory device.
19 . The non-transitory computer-readable storage medium of claim 15 , wherein the instructions cause the processing device to perform operations further comprising:
reading the sense words from the memory device using the plurality of read retry offset voltages;
executing a plurality of parity check equations on corresponding subsets of the sense words to determine respective pluralities of parity check equation results; and
determining respective syndromes for the sense words using the plurality respective pluralities of parity check equation results, wherein the respective syndrome weights represent a number of bits in the respective syndromes set to a particular state.
20 . The non-transitory computer-readable storage medium of claim 19 , wherein each parity check equation corresponds to a different subset of the sense words, and wherein each of the plurality of parity check equation results indicates whether a number of bits set to a value of ‘1’ in a corresponding subset of the sense words is even or odd.