A data storage circuit includes memory, an error correcting code (ECC) storage circuit, and control circuitry. The memory is configured to store a data value comprising a plurality of fields. Each of the fields is independently writable. The ECC storage circuit is configured to store an ECC value corresponding to the data value. The control circuitry is configured to receive a field value to be written into one of the fields, and store the field value in the one of the fields by writing only the field value to the memory. The control circuitry is also configured to retrieve the ECC value from the ECC storage circuit, compute an updated ECC value based on the ECC value retrieved from the ECC storage circuit and the field value, and store the updated ECC value in the ECC storage circuit.

A read-disturb-based physical storage read temperature information identification system includes a global read temperature identification subsystem coupled to at least one storage device. Each at least one storage device reads valid data and obsolete data from at least one physical block in that storage device and, based on the reading of the valid data and the obsolete data, generates read disturb information associated with each row provided by the at least one physical block in that storage device. Each at least one storage devices then uses the read disturb information associated with each row provided by the at least one physical block in that storage device to generate a local logical storage element read temperature map for that storage device that it provides to the global read temperature identification subsystem.

Several embodiments of systems incorporating memory components are disclosed herein. In one embodiment, a memory system can include a memory component and a processing device configured to access quality metrics corresponding to memory regions of the memory component. In some embodiments, the processing device can compare the quality metrics to one or more memory management thresholds. In some embodiments, when the quality metrics meet and/or exceed a first threshold, a refresh operation can be scheduled and/or performed on a corresponding memory region. In these and other embodiments, when the quality metrics meet and/or exceed a second threshold, the memory region is retired and removed from an active pool of memory regions.

Methods, systems, and devices for a memory device with status feedback for error correction are described. For example, during a read operation, a memory device may perform an error correction operation on first data read from a memory array of the memory device. The error correction operation may generate second data and an indicator of a state of error corresponding to the second data. In one example, the indicator may indicate one of multiple possible states of error. In another example, the indicator may indicate a corrected error or no detectable error. The memory device may output the first or second data and the indicator of the state of error during a same burst interval. The memory device may output the data on a first channel and the indicator of the state of error on a second channel.

Methods, systems, and devices for memory error correction based on layered error detection are described. In some examples, a memory system identifies, based on a first type of error detection procedure, that a set of bits includes a quantity of erroneous bits that is uncorrectable based on the first type of error detection procedure alone. The memory system generates one or more candidate sets of bits based on altering different groups of bits within the set of bits and evaluate one or more such candidate sets of bits using a second type of error detection procedure until a candidate set of bits is identified as error-free. The memory system then corrects the set of bits based on the candidate set of bits identified as error-free.

Devices and techniques for extended error correction in a storage device are described herein. A first set of data, that has a corresponding logical address and physical address, is received. A second set of data can be selected based on the logical address. Secondary error correction data can be computed from the first set of data and the second set of data. Primary error correction data can be differentiated from the secondary error correction data by being computed from the first set of data and a third set of data. The third set of data can be selected based on the physical address of the first set of data. The secondary error correction data can be written to the storage device based on the logical address.

In described examples, a memory module includes a memory array with a primary access port coupled to the memory array. Error correction logic is coupled to the memory array. A statistics register is coupled to the error correction logic. A secondary access port is coupled to the statistics register to allow access to the statistics register by an external device without using the primary interface.

Systems, apparatuses, and methods related to modified checksum data using a poison data indictor. An example method can include receiving a first set of bits including data and a second set of at least one bit indicating whether the first set of bits includes one or more erroneous or corrupted bits. A first checksum can be generated that is associated with the first set of bits. A second checksum can be generated using the first checksum and the second set of at least one bit. The first set of bits and the second checksum can be written to an array of a memory device. A comparison of the first checksum and the second checksum can indicate whether the first set of bits includes the at least one or more erroneous or corrupted bits.

Techniques for non-deterministic operation of a stacked memory system are provided. In an example, a method of operating a memory package can include receiving a plurality of memory access requests for a channel at a logic die, returning first data to a host in response to a first memory access request of the plurality of memory access requests, returning an indication of data not ready to the host in response to a second memory access request of the plurality of memory access requests for second data, returning a first index to the host with the indication of data not ready, returning an indication data is ready with third data in response to a third memory access request of the plurality of memory access requests, and returning the first index with the indication of data ready.

A memory system includes a non-volatile memory and a memory controller. The memory controller is configured to read a received word from the non-volatile memory, estimate noise by using a plurality of different models for estimating the noise included in the received word to obtain a plurality of noise estimation values, select one noise estimation value from the plurality of noise estimation values, update the received word by using a value obtained by subtracting the selected noise estimation value from the read received word, and decode the updated received word by using a belief-propagation method.