Abstract: Described herein are embodiments related to first-pass dynamic program targeting (DPT) operations on memory cells of memory systems. A processing device determines that a first programming pass of a programming operation has been performed on a memory cell of a memory component. The processing device, before a second programming pass of the programming operation is performed on the memory cell, determines information about a first programming distribution and a second programming distribution of the memory cell, the first programming distribution corresponding to a first page type and the second programming distribution corresponding to a second page type. The processing device adjusts, using the information, a placement of the first programming distribution relative to the second programming distribution that balances a bit error rate (BER) between the first page type and the second page type.

Abstract: A processing device determines difference error counts for a difference error that is indicative of a margin for a valley that is located between programming distributions of a memory cell of the memory component. A processing device scales each of the plurality of difference error counts by a respective scale factor of the scale factors. The processing device adjusts the valley margins of the memory cell in accordance with the scaled difference error counts.

Abstract: A processing device determines that read level thresholds between first programming distributions of a second programming pass associated the memory component are calibrated. The processing device changes one or more of the read level thresholds between the first programming distributions. The processing device adjusts one or more read level threshold between second programming distributions of a first programming pass based on the change to the one or more read level thresholds between the first programming distributions.

Abstract: Embodiments can include a scan of data associated with programmed memory cells is performed. The scan of data results in a bit error count (BEC) histogram. A trigger margin is determined from the BEC histogram. The determined trigger margin and a target trigger margin are compared. In response to the determined trigger margin being different than the target trigger margin, one or more program step characteristics is adjusted to adjust the determined trigger margin toward the target trigger margin.

Abstract: A processing device determines difference error counts that are indicative of relative widths of valleys. Each of the valleys is located between a respective pair of programming distributions of a memory cell of the memory component. A program targeting operation is performed on the memory cell to calibrate one or more program verify (PV) targets associated with the programming distributions. To perform the program targeting operation, a rule from a set of rules is selected based on the difference error counts. The set of rules corresponds to an adjusting of a PV target of a programming distribution adjacent to an initial programming distribution. One or more program verify (PV) targets associated with the programming distributions are adjusted based on the selected rule.

Abstract: Several embodiments of systems incorporating memory sub-systems are disclosed herein. In one embodiment, a memory sub-system can include a memory component and a processing device configured to perform a background scan on a memory region of the memory component. In some embodiments, the background scan includes generating a bit error count (BEC) of a codeword saved on the memory region and saving statistical information corresponding to the BEC of the codeword to a histogram statistics log. In some embodiments, when the BEC of the codeword is greater than a BEC threshold, a refresh operation is scheduled for the memory region and/or logged. In these and other embodiments, when one or more error recovery error correction code (ECC) operations do not correct bit errors in the codeword, a refresh and/or retirement operation is schedule for the memory region and/or is logged.

Abstract: A read window budget (RWB) corresponding a group of memory cells is determined. The determined RWB and a target RWB is compared. In response to the determined RWB being different than the target RWB, one or more program step characteristics are adjusted to adjust the determined RWB toward the target RWB.

Abstract: A memory sub-system is disclosed that makes accessible accumulated memory temperature statistics in relation to a target memory portion. This can be accomplished by maintaining one or more hold variables and one or more accumulation variables. The accumulation variables can be iteratively updated upon triggers such as a timer expiration or I/O event. Updating the accumulation variables can include obtaining a current temperature and tracking one or more of: a maximum, minimum, and mean temperature across the iterations. An accumulation value can track how many times the accumulation variables have been updated. When the accumulation value reaches an accumulation action threshold, the current state of the accumulation variables can be used to update the hold variables. The accumulation value and accumulation variables can then be reset and used for accumulation of additional temperature statistics.

Abstract: A level width corresponding to a group of memory cells of a memory component is determined. The determined level width and a target level width is compared. In response to the determined level width being different than the target level width, one or more program step characteristics are adjusted to adjust the determined level width to the target level width.

Abstract: A processing device determines difference error counts for a difference error that is indicative of a margin for a valley that is located between programming distributions of a memory cell of the memory component. A processing device scales each of the plurality of difference error counts by a respective scale factor of the scale factors. The processing device adjusts the valley margins of the memory cell in accordance with the scaled difference error counts.

Abstract: Described herein are embodiments related to first-pass continuous read level calibration (cRLC) operations on memory cells of memory systems. A processing device determines that a first programming pass of a programming operation has been performed on a memory cell of a memory component. The processing device performs a cRLC operation on the memory cell to calibrate a read level threshold between a first first-pass programming distribution and a second first-pass programming distribution before a second programming pass of the programming operation is performed on the memory cell.

Abstract: A memory system can identify target memory units to characterize by generating Cumulative Distribution Function (CDF)-based data for each memory unit and analyzing the CDF-based data to identify target memory units that are exceptional. Such target memory units can be those with CDF-based data with extrinsic tails or that crosses an info limit threshold. The memory system can perform characterization processes for the target memory units, e.g. using an Auto Read Calibration (ARC) analysis or a Continuous Read Level Calibration (cRLC) analysis. A manufacturing process for the memory device can use results of the characterization processes, e.g. by mapping them to types of problems observed during testing. Alternatively, results of the characterization processes to can be used during operation of the memory device, e.g. to adjust the initial read voltage threshold, the read retry voltage values, or the order of read retry voltages used in data recovery.

Abstract: A read window budget (RWB) corresponding a group of memory cells is determined. The determined RWB and a target RWB is compared. In response to the determined RWB being different than the target RWB, one or more program step characteristics are adjusted to adjust the determined RWB toward the target RWB.

Abstract: Embodiments can include a scan of data associated with programmed memory cells is performed. The scan of data results in a bit error count (BEC) histogram. A trigger margin is determined from the BEC histogram. The determined trigger margin and a target trigger margin are compared. In response to the determined trigger margin being different than the target trigger margin, one or more program step characteristics is adjusted to adjust the determined trigger margin toward the target trigger margin.

Abstract: A level width corresponding to a group of memory cells of a memory component is determined. The determined level width and a target level width is compared. In response to the determined level width being different than the target level width, one or more program step characteristics are adjusted to adjust the determined level width to the target level width.

Abstract: A program effective time (PET) for programming at least a portion of a plurality of memory cells based on one or more program step characteristics is determined. The determined PET and a target PET is compared. In response to the determined PET being different than the target PET, the one or more program step characteristics is adjusted to adjust the determined PET to the target PET.

Abstract: A read window budget (RWB) corresponding a group of memory cells is determined. The determined RWB and a target RWB is compared. In response to the determined RWB being different than the target RWB, one or more program step characteristics are adjusted to adjust the determined RWB toward the target RWB.

Abstract: A BER corresponding to a group of memory cells programmed via a programing signal having one or more program step characteristics is determined. The determined BER and a target BER is compared. In response to the determined BER being different than the target BER, one or more program step characteristics are adjusted to adjust the determined BER to the target BER.

Abstract: Embodiments can include a scan of data associated with programmed memory cells is performed. The scan of data results in a bit error count (BEC) histogram. A trigger margin is determined from the BEC histogram. The determined trigger margin and a target trigger margin are compared. In response to the determined trigger margin being different than the target trigger margin, one or more program step characteristics is adjusted to adjust the determined trigger margin toward the target trigger margin.

Abstract: Aspects of the present disclosure are directed to generating endurance measures for a memory sub-system and using endurance measures to classify memory sub-systems, to predict memory system remaining life, and to create memory systems with consistently performing sub-systems. An endurance measure can be generated by computing multiple metric points. Each metric point can be based on a margin between a point, in cumulative distribution function (CDF)-based data at an acceptable memory unit failure rate, and an error amount threshold condition. Once a there are sufficient metric points related to the memory device, the metric points can be fit to a function. The endurance measure is then obtained by extrapolating the function to a point at which the function reaches a threshold.