Abstract: Apparatuses and methods can be related to implementing a transformer neural network in a memory. A transformer neural network can be implemented utilizing a resistive memory array. The memory array can comprise programmable memory cells that can be programed and used to store weights of the transformer neural network and perform operations consistent with the transformer neural network.

Abstract: The present disclosure is directed to logic based read sample offset operations in a memory sub-system. A processing device performs a first read, a second read, and a third read of data from a memory devices using a first center value corresponding to a first read level threshold, a negative offset value, and a positive offset value, respectively. The processing device performs a XOR operation on results from the first and second reads to obtain a first value and a XOR operation on results from the second and third reads to obtain a second value. The processing device performs a first count operation on the first value to determine a first difference bit count and a second count operation on the second value to determine a second difference bit count. The processing device can store or output the first difference bit count and the second difference bit count.

Abstract: The present disclosure includes apparatuses, methods, and systems for data relocation in memory. An embodiment includes a controller, and a memory having a plurality of physical units of memory cells. Each of the physical units has a different sequential physical address associated therewith, a first number of the physical units have data stored therein, a second number of the physical units do not have data stored therein, and the physical address associated with each respective one of the second number of physical units is a different consecutive physical address in the sequence. The controller can relocate the data stored in the physical unit of the first number of physical units, whose physical address in the sequence is immediately before the first of the consecutive physical addresses associated with the second number of physical units, to the last of the consecutive physical addresses associated with the second number of physical units.

Abstract: A processing device in a memory sub-system identifies a first memory device and a second memory device and configures the second memory device with a zone namespace. The processing device identifies a first portion and a second portion of the first memory device, the first portion storing zone namespace metadata corresponding to the zone namespace on the second memory device. The processing device further exposes the second portion of the first memory device to a host system as a non-zoned addressable memory region.

Abstract: A memory system configured to dynamically adjust the amount of redundant information stored in memory cells of a wordline on an integrated circuit die based on a bit error rate. For example, in response to a determination that a bit error rate of the wordline is above a threshold, the memory system can store first data items as independent first codewords of an error correction code technique into a first portion of the memory cells of the wordline, generate second data items as redundant information from the first codewords, and store the second data items in a second portion of the memory cells of the wordline. If the bit error rate is below the threshold, third data items can be stored as independent second codewords of the same length as the first codewords in the memory cells of the wordline.

Abstract: An electronic device, such as a memory device, may include various circuit components. The electronic device may also include one or more voltage testing circuits to determine whether signals of one or more of the circuit components are within acceptable voltage ranges of the respective circuit components. Systems and methods are described to improve correct voltage measurement of the received signals by a voltage testing circuit. In particular, multiple supply voltage levels are provided to different components of the voltage testing circuit to provide a sufficient headroom voltage gap between received signals and the supply voltages. For example, some active circuits (e.g., operational amplifiers) of the voltage testing circuit may receive a higher supply voltage of the electronic device compared to one or more other circuits of the voltage testing circuit.

Abstract: Memory devices may have internal circuitry that employs voltages higher and/or lower than voltages provided by an external power source. Charge pumps are DC/DC converters that may be used to generate the higher voltages internally. The number of available charge pumps in a memory device may be conservatively dimensioned to be high, in some systems to protect yields. Some of the available charge pumps may be disabled during manufacturing or testing to reduce the number of active charge pumps. The testing process may employ dedicated logic in the memory device and the disabling may employ fuse circuitry.

Abstract: Methods, systems, and devices for host recovery for a stuck condition of a memory system are described. The host system may transmit a first command for the memory system to transition from a first power mode to a second power mode (e.g., low-power mode). In some cases, the host system may transmit a second command for the memory system to exit the second power mode shortly after transmitting the first command. The host system may activate a timer associated with a time-out condition for exiting the second power mode and may determine that a duration indicated by the timer expires. In some examples, the host system may transmit a third command for the memory system to perform a hardware reset operation based on determining that the duration of the timer expires.

Abstract: Some embodiments include apparatuses and methods of forming the apparatus. One of the apparatuses and methods includes a memory cell having a first transistor and a second transistor located over a substrate. The first transistor includes a channel region. The second transistor includes a channel region located over the channel region of the first transistor and electrically separated from the first channel region. The memory cell includes a memory element located on at least one side of the channel region of the first transistor. The memory element is electrically separated from the channel region of the first transistor, and electrically coupled to the channel of the second transistor.

Abstract: A memory device to perform a read disturb mitigation operation. For example, the memory device can measure signal and noise characteristics of a group of memory cells to determine an optimized read voltage of the group of memory cells and determine a margin of read disturb accumulated in the group of memory cells. Subsequently, the memory device can identify the group of memory cells for the read disturb mitigation operation based on the margin of read disturb and a predetermined threshold.

Abstract: A microelectronic device may include a stack structure comprising a vertically alternating sequence of insulative structures and conductive structures, the stack structure divided into block portions. The microelectronic device may additionally include slit structures horizontally interposed between the block portions of the stack structure. Each of the slit structures may include a dielectric liner covering side surfaces of the stack structure and an upper surface of an additional structure underlying the stack structure, and a plug structure comprising at least one metal surrounded by the dielectric liner.

Abstract: The address of victim rows may be determined based on rows that are accessed in a memory. The victim addresses may be stored and associated with a count for every time a victim row is “victimized.” When the count for a victim row reaches a threshold, the victim row may be refreshed to preserve data stored in the row. After the victim row has been refreshed, the count may be reset. When a victim row is accessed, the count may also be reset. The counts may be adjusted for closer victim rows (e.g., +/?1) at a faster rate than counts for more distant victim rows (e.g., +/?2). This may cause closer victim rows to be refreshed at a higher rate than more distant victim rows.

Abstract: Apparatuses and methods for coupling semiconductor devices are disclosed. Terminals (e.g., die pads) of a plurality of semiconductor devices may be coupled in a daisy chain manner through conductive structures that couple one or more terminals of a semiconductor device to two conductive bond pads. The conductive structures may be included in a redistribution layer (RDL) structure. The RDL structure may have a “U” shape in some embodiments of the disclosure. Each end of the “U” shape may be coupled to a respective one of the two conductive bond pads, and the terminal of the semiconductor device may be coupled to the RDL structure. The conductive bond pads of a semiconductor device may be coupled to conductive bond pads of other semiconductor devices by conductors (e.g., bond wires). As a result, the terminals of the semiconductor devices may be coupled in a daisy chain manner through the RDL structures, conductive bond pads, and conductors.

Abstract: Embodiments of the disclosure are drawn to apparatuses and methods for soft post-package repair (SPPR). After packaging, it may be necessary to perform post-package repair operations on rows of the memory. During a scan mode of an SPPR operation, addresses provided by a fuse bank may be examined to determine if they are open addresses or if the bad row of memory is a redundant row of memory. The open addresses and the bad redundant addresses may be stored in volatile storage elements, such as in latch circuits. During a soft send mode of a SPPR operation, the address previously associated with the bad row of memory may be associated with the open address instead, and the address of the bad redundant row may be disabled.

Abstract: Implementations described herein relate to enabling or disabling on-die error-correcting code for a memory built-in self-test. A memory device may read one or more bits, associated with a memory built-in self-test, that are stored in a mode register of the memory device. The memory device may identify, based on the one or more bits, whether the memory built-in self-test is to be performed with on-die error-correcting code (ECC) disabled or with on-die ECC enabled. The memory device may perform the memory built-in self-test, and selectively test for one or more single-bit errors, based on identifying whether the memory built-in self-test is to be performed with the on-die ECC disabled or with the on-die ECC enabled.

Abstract: Methods, apparatuses, and systems for repairing defective memory cells in regions of a memory array associated with high or low priority levels are disclosed. A repair address generator may be configured to generate a memory address map for repair (e.g., blowing fuses at a fuse circuit), depending on whether certain applications may operate at a high priority level indicative of a low bit error rate or a low priority level indicative of a higher bit error rate. For example, a specified error rate associated with a low priority level may correspond to a threshold error rate for certain applications, such as a neural network application that stores trained weights. Such neural network applications may access trained weights being partially stored in defective memory cells, with the least significant bits of such trained weights being stored in defective memory cells that are not repaired according to the memory address map.

Abstract: Devices and techniques for packet arbitration for buffered packets in a network device are described herein. A packet can be received at an input of the network device. The packet can be placed in a buffer for the input and a characteristic of the packet can be obtained. A record for the packet, that includes the characteristic, is written into a data structure that is independent of the buffer. Arbitration, based on the characteristic of the packet in the record, can then be performed among multiple packets to select a next packet from the buffer for delivery to an output.

Abstract: Methods, systems, and devices for an interactive environmental control system are described. In some examples, operating temperatures for individual zones of an environment may be determined based on inputs received from occupants of the respective zones. For example, a building may be separated into zones, and environmental conditions at each zone may be monitored and adjusted independently. Each occupant of a zone may update their environmental preference and the system may utilize the user inputs to set and adjust an operating temperature for the respective zone based on the occupants' preferences. In some examples, the system may implement machine learning techniques to predict and set operating conditions for the zones based on inputs, such as a history of inputs, from building occupants (e.g., from occupants of a respective zone).

Abstract: Semiconductor devices and semiconductor device packages may include at least one first semiconductor die supported on a first side of a substrate. The at least one first semiconductor die may include a first active surface. A second semiconductor die may be supported on a second, opposite side of the substrate. The second semiconductor die may include a second active surface located on a side of the second semiconductor die facing the substrate. The second semiconductor die may be configured to have higher median power consumption than the at least one first semiconductor die during operation. An electronic system incorporating a semiconductor device package is disclosed, as are related methods.

Abstract: Disclosed herein is an apparatus that includes a first wiring layer including a first bit line extending in a first direction, a first sense amplifier configured to amplify a potential of the first bit line, and a first transistor configured to supply an operation voltage to the first sense amplifier when a first control signal supplied to a gate electrode of the first transistor is activated. The first wiring layer further includes a first pattern coupled to the gate electrode of the first transistor and a second pattern having a first section arranged between the first bit line and the first pattern in a second direction perpendicular to the first direction.