Abstract: A controller performs an access operation on a word line which is in a portion of a memory array in a memory device. The controller counts accesses on a portion-by-portion basis (e.g., a bank-by-bank basis, a sub-bank-by-sub-bank basis, etc.). The memory counts accesses on a word line-by-word line basis. The memory sets a refresh management (RFM) flag for a portion based on the counts associated with the word lines in that portion. The controller checks the RFM flag for a portion based on the access count for the portion. The controller issues an RFM command after checking the RFM flag if the RFM flag is set.

Abstract: Memory devices and methods of operating memory devices in which refresh management operations can be scheduled on an as-needed basis for those memory portions where activity (e.g., activations in excess of a predetermined threshold) warrants a refresh management operation are disclosed. In one embodiment, an apparatus comprises a memory including a memory location, and circuitry configured to determine a count corresponding to a number of activations at the memory location, to schedule a refresh management operation for the memory location in response to the count exceeding a first predetermined threshold, and to decrease the count by an amount corresponding to the first predetermined threshold in response to executing the scheduled refresh management operation. The circuitry may be further configured to disallow, in response to determining that the count has reached a maximum permitted value, further activations at the memory location until after the count has been decreased.

Abstract: Apparatuses and methods per-row count based refresh target identification. A memory device stores count values associated with the word lines. An aggressor detector circuit stores a maximum of the count values and a row address associated with the maximum count value. Responsive to a targeted refresh signal, the stored count value is compared to a threshold. If the count value has crossed the threshold, then a targeted refresh operation may be performed on one or more refresh addresses based on the stored address, and the count value may be reset.

Abstract: Methods for operating a memory system are disclosed herein. In one embodiment, a method comprises receiving first data to be written at a logical address of a memory array, storing the first data at a first physical address corresponding to the logical address, and remapping the logical address to a second physical address, for example, using a soft post package repair operation. The method can further include receiving second data different from the first data to be written at the logical address, storing the second data at the second physical address, and remapping the logical address to the first physical address. In some embodiments, the method can comprise storing first and second ECC data corresponding to the first and second data, respectively. The method can further comprise outputting the first data and/or the second ECC data in response to a read request corresponding to the logical address.

Abstract: Memory devices and methods of operating memory devices in which refresh management operations can be scheduled on an as-needed basis for those memory portions where activity (e.g., activations in excess of a predetermined threshold) warrants a refresh management operation are disclosed. In one embodiment, an apparatus comprises a memory including a memory location, and circuitry configured to determine a count corresponding to a number of activations at the memory location, to schedule a refresh management operation for the memory location in response to the count exceeding a first predetermined threshold, and to decrease the count by an amount corresponding to the first predetermined threshold in response to executing the scheduled refresh management operation. The circuitry may be further configured to disallow, in response to determining that the count has reached a maximum permitted value, further activations at the memory location until after the count has been decreased.

Abstract: Apparatuses, systems, and methods for multiple types of alert along an alert bus. A memory device may detect multiple types of alert and use an alert signal along an alert bus to signal a controller of these alerts. Different pulse widths of the alert signal may be used to indicate the type of alert. For example if the alert signal is at an active level between a first duration and a second duration, it may indicate a first type of alert, if the alert signal is active between a third duration and a fourth duration, it may indicate a second type of alert. If the alert signal remains active for longer than a threshold amount of time, it may indicate a third type of alert.

Abstract: Methods, systems, and apparatuses for a memory device (e.g., DRAM) including an error check and scrub (ECS) procedure in conjunction with refresh operations are described. The ECS procedure may include read/modify-write cycles when errors are detected in code words. In some embodiments, the memory device may complete the ECS procedure over multiple refresh commands, namely by performing a read (or read/modify) portion of the ECS procedure while a first refresh command is executed, and by performing a write portion of the ECS procedure while a second refresh command is executed. The ECS procedure described herein may facilitate avoiding signaling conflicts or interferences that may occur between the ECS procedure and other memory operations.

Abstract: Memory devices, systems including memory devices, and methods of operating memory devices are described in which waterfall attacks can be prevented from degrading data by alerting a memory controller that the memory device requests time to perform internal management operations, and should not be sent any further commands (e.g., activate commands) for a predetermined amount of time. In one embodiment, a memory device includes an external pin, a mode register, a memory array including a plurality of rows of memory cells, and circuitry configured to: determine that a criterion to perform an internal management operation on a subset of the plurality of rows has been met, transmit, in response to determining the criterion has been met, a signal to the external pin, determine a duration corresponding to the internal management operation, and write a bit value indicative of the determined duration to the mode register.

Abstract: An apparatus comprising a memory array including a plurality of memory cells arranged in a plurality of columns and a plurality of rows is provided. The apparatus further comprises circuitry configured to perform an error detection operation on the memory array to determine a raw count of detected errors, to compare the raw count of detected errors to a threshold value to determine an over-threshold amount, to scale the over-threshold amount according to a scaling algorithm to determine a scaled error count, and to store the scaled error count in a user-accessible storage location.

Abstract: Methods, systems, and apparatuses for a memory device (e.g., DRAM) including an error check and scrub (ECS) procedure in conjunction with refresh operations are described. The ECS procedure may include read/modify-write cycles when errors are detected in code words. In some embodiments, the memory device may complete the ECS procedure over multiple refresh commands, namely by performing a read (or read/modify) portion of the ECS procedure while a first refresh command is executed, and by performing a write portion of the ECS procedure while a second refresh command is executed. The ECS procedure described herein may facilitate avoiding signaling conflicts or interferences that may occur between the ECS procedure and other memory operations.

Abstract: Memory devices, memory systems, and methods of operating the same are disclosed in which a memory device, in response to receiving a mode register read (MRR) command directed to one or more write-only bits of a mode register, reads data indicative of a status of the memory device about the memory device from one or more cells of a memory array of the memory device that are different from the write-only mode register. The data can include device settings, environmental conditions, usage statistics, metadata, feature support, feature implementation, device status, temperature, etc. The status information mode can be optionally enabled or disabled. The memory devices can include DDR5 DRAM memory devices.

Abstract: Memory devices, systems including memory devices, and methods of operating memory devices are described, in which memory devices are configured to poison data based on an indication provided by a host device coupled with the memory devices. The indication may include which one or more bits to poison (invert) at which stages of performing write or read operations. In some embodiments, the memory device may invert one or more bits according to the indication and then correct one or more errors associated with inverting the one or more bit to verify its on-die ECC functionality. In some embodiments, the memory device may provide the host device with poisoned data including one or more bits inverted according to the indication such that the host device may test system-level ECC functionality using the poisoned data.

Abstract: Memory devices, systems including memory devices, and methods of operating memory devices are described in which waterfall attacks can be prevented from degrading data by alerting a memory controller that the memory device requests time to perform internal management operations, and should not be sent any further commands (e.g., activate commands) for a predetermined amount of time. In one embodiment, a memory device includes an external pin, a mode register, a memory array including a plurality of rows of memory cells, and circuitry configured to: determine that a criterion to perform an internal management operation on a subset of the plurality of rows has been met, transmit, in response to determining the criterion has been met, a signal to the external pin, determine a duration corresponding to the internal management operation, and write a bit value indicative of the determined duration to the mode register.

Abstract: An apparatus comprising a memory array including a plurality of memory cells arranged in a plurality of columns and a plurality of rows is provided. The apparatus further comprises circuitry configured to perform an error detection operation on the memory array to determine a raw count of detected errors, to compare the raw count of detected errors to a threshold value to determine an over-threshold amount, to scale the over-threshold amount according to a scaling algorithm to determine a scaled error count, and to store the scaled error count in a user-accessible storage location.

Abstract: Memory devices, memory systems, and methods of operating memory devices and systems are disclosed in which a single command can trigger a memory device to perform multiple operations, such as a single refresh command that triggers the memory device to both perform a refresh command and to perform a mode register read. One such memory device comprises a memory, a mode register, and circuitry configured, in response to receiving a command to perform a refresh operation at the memory, to perform the refresh operation at the memory, and to perform a read of the mode register. The memory can be a first memory portion, the memory device can comprise a second memory portion, and the circuitry can be further configured, in response to the command, to provide on-die termination at the second memory portion of the memory system during at least a portion of the read of the mode register.

Abstract: Memory devices and methods of operating memory devices in which refresh management operations can be scheduled on an as-needed basis for those memory portions where activity (e.g., activations in excess of a predetermined threshold) warrants a refresh management operation are disclosed. In one embodiment, an apparatus comprises a memory including a memory location, and circuitry configured to determine a count corresponding to a number of activations at the memory location, to schedule a refresh management operation for the memory location in response to the count exceeding a first predetermined threshold, and to decrease the count by an amount corresponding to the first predetermined threshold in response to executing the scheduled refresh management operation. The circuitry may be further configured to disallow, in response to determining that the count has reached a maximum permitted value, further activations at the memory location until after the count has been decreased.

Abstract: Memory with deterministic worst-case row address servicing is disclosed herein. A method of the present technology comprises (1) updating a counter value corresponding to a memory row of a memory device in response to detecting activation of the memory row; (2) comparing the updated counter value to a worst-case count value; and (3) in response to determining that the updated counter value is greater than the worst-case count value, setting the worst-case count value equal to the updated counter value and storing a memory row address of the memory row as a worst-case memory row address. The counter value can be one of a plurality of counter values, each counter value (a) corresponding to a respective memory row and (b) configured to track a number of activations of the respective memory row. The method can further comprise performing a row disturb refresh operation using the worst-case memory row address.

Abstract: Methods, systems, and apparatuses for a memory device (e.g., DRAM) including an error check and scrub (ECS) procedure in conjunction with refresh operations are described. The ECS procedure may include read/modify-write cycles when errors are detected in code words. In some embodiments, the memory device may complete the ECS procedure over multiple refresh commands, namely by performing a read (or read/modify) portion of the ECS procedure while a first refresh command is executed, and by performing a write portion of the ECS procedure while a second refresh command is executed. The ECS procedure described herein may facilitate avoiding signaling conflicts or interferences that may occur between the ECS procedure and other memory operations.

Abstract: Memory devices, memory systems, and methods of operating the same are disclosed in which a memory device, in response to receiving a mode register read (MRR) command directed to one or more write-only bits of a mode register, reads data indicative of a status of the memory device about the memory device from one or more cells of a memory array of the memory device that are different from the write-only mode register. The data can include device settings, environmental conditions, usage statistics, metadata, feature support, feature implementation, device status, temperature, etc. The status information mode can be optionally enabled or disabled. The memory devices can include DDR5 DRAM memory devices.

Abstract: Memory devices and methods of operating memory devices in which refresh management operations can be scheduled on an as-needed basis for those memory portions where activity (e.g., activations in excess of a predetermined threshold) warrants a refresh management operation are disclosed. In one embodiment, an apparatus comprises a memory including a memory location, and circuitry configured to determine a count corresponding to a number of activations at the memory location, to schedule a refresh management operation for the memory location in response to the count exceeding a first predetermined threshold, and to decrease the count by an amount corresponding to the first predetermined threshold in response to executing the scheduled refresh management operation. The circuitry may be further configured to disallow, in response to determining that the count has reached a maximum permitted value, further activations at the memory location until after the count has been decreased.