Abstract: Self-identifying solid-state transducer (SST) modules and associated systems and methods are disclosed herein. In several embodiments, for example, an SST system can include a driver and at least one SST module electrically coupled to the driver. Each SST module can include an SST and a sense resistor. The sense resistors of each SST module can have at least substantially similar resistance values. The SSTs of the SST modules can be coupled in parallel across an SST channel to the driver, and the sense resistors of the SST modules can be coupled in parallel across a sense channel to the driver. The driver can be configured to measure a sense resistance across the sense resistors and deliver a current across the SSTs based on the sense resistance.

Abstract: This document describes aspects of communicating information about repair elements of a memory device. A memory device can include multiple repair elements that can each replace a defective or damaged memory element, such as a memory row, using a repair operation. By knowing a quantity of remaining available repair elements, a user of a memory device can make informed decisions about whether to make a replacement. In operation, a host device can send a command to the memory device requesting repair element information. Logic of the memory device can determine a quantity of repair elements that are available for a repair operation. In some cases, the logic may store this quantity in a register of the memory device. The memory device can signal the quantity of repair elements to the host device in response to the command.

Abstract: Latch circuits with improved single event upset immunity and related systems, apparatuses, and methods are disclosed. An apparatus includes a fuse, a first driver circuit, and a second driver circuit. The fuse is configured to store a bit of information. The first driver circuit includes a first input terminal electrically connected to the fuse and a first output terminal electrically connected to a first latch input terminal. The second driver circuit includes a second input terminal electrically connected to the fuse and a second output terminal electrically connected to a second latch input terminal. The second latch input terminal is electrically isolated from the first latch input terminal by the first driver circuit and the second driver circuit.

Abstract: Apparatuses and techniques for implementing a data-transfer test mode are described. The data-transfer test mode refers to a mode in which the transfer of data from an interface die to a linked die can be tested prior to connecting the interface die to the linked die. In particular, the data-transfer test mode enables the interface die to perform aspects of a write operation and output a portion of write data that is intended for the linked die. With the data-transfer test mode, testing (or debugging) of the interface die can be performed during an earlier stage in the manufacturing process before integrating the interface die into an interconnected die architecture. For example, this type of testing can be performed at a wafer level or at a single-die-package (SDP) level. In general, the data-transfer test mode can be executed independent of whether the interface die is connected to the linked die.

Abstract: Described apparatuses and methods enable a receiver of requests, such as a memory device, to modulate the arrival of future requests using a credit-based communication protocol. A transmitter of requests can be authorized to transmit a request responsive to possession of a credit corresponding to the communication request. In these situations, if the transmitter has exhausted a supply of credits, the transmitter waits until a credit is returned before transmitting another request. The receiver of the requests can manage credit returns based on whether a request queue has space to receive another request. Further, the receiver can delay a credit return based on how many requests are pending at the receiver, even if space is available in the request queue. This delay can prevent an oversupply of requests from developing downstream of the request queue. Latency, for instance, can be improved by managing the presence of requests that are downstream.

Abstract: Described apparatuses and methods balance memory-portion accessing. Some memory architectures are designed to accelerate memory accesses using schemes that may be at least partially dependent on memory access requests being distributed roughly equally across multiple memory portions of a memory. Examples of such memory portions include cache sets of cache memories and memory banks of multibank memories. Some code, however, may execute in a manner that concentrates memory accesses in a subset of the total memory portions, which can reduce memory responsiveness in these memory types. To account for such behaviors, described techniques can shuffle memory addresses based on a shuffle map to produce shuffled memory addresses. The shuffle map can be determined based on a count of the occurrences of a reference bit value at bit positions of the memory addresses. Using the shuffled memory address for memory requests can substantially balance the accesses across the memory portions.

Abstract: This document describes apparatuses and techniques for cache memory with randomized eviction. In various aspects, a cache memory randomly selects a cache line for eviction and/or replacement. The cache memory may also support multi-occupancy whereby the cache memory enters data reused from another cache line to replace the data of the randomly evicted cache line. By so doing, the cache memory may operate in a nondeterministic fashion, which may increase a probability of data remaining in the cache memory for subsequent requests.

Abstract: This document describes apparatuses and techniques for cache memory with randomized eviction. In various aspects, a cache memory randomly selects a cache line for eviction and/or replacement. The cache memory may also support multi-occupancy whereby the cache memory enters data reused from another cache line to replace the data of the randomly evicted cache line. By so doing, the cache memory may operate in a nondeterministic fashion, which may increase a probability of data remaining in the cache memory for subsequent requests.

Abstract: Methods, systems, and apparatuses related to a memory fault map for an accelerated neural network. An artificial neural network can be accelerated by operating memory outside of the memory's baseline operating parameters. Doing so, however, often increases the amount of faulty data locations in the memory. Through creation and use of the disclosed fault map, however, artificial neural networks can be trained more quickly and using less bandwidth, which reduces the neural networks' sensitivity to these additional faulty data locations. Hardening a neural network to these memory faults allows the neural network to operate effectively even when using memory outside of that memory's baseline operating parameters.

Abstract: Described apparatuses and methods enable a receiver of requests, such as a memory device, to control the arrival of future requests using a credit-based communication protocol. A transmitter of requests can be authorized to transmit a request across an interconnect responsive to possession of a credit. If the transmitter exhausts its credits, the transmitter waits until a credit is returned before transmitting another request. The receiver can manage credit returns based on how many responses are present in a response queue. The receiver can change a rate at which the credit returns are transmitted by changing a size of an interval of responses that are being transmitted, with one credit being returned per interval. This can slow the rate of credit returns while the response queue is relatively more filled. The rate adjustment can decrease latency by reducing an amount of requests or responses that are pooling in backend components.

Abstract: Described apparatuses and methods form adaptive cache lines having a configurable capacity from hardware cache lines having a fixed capacity. The adaptive cache lines can be formed in accordance with a programmable cache-line parameter. The programmable cache-line parameter can specify a capacity for the adaptive cache lines. The adaptive cache lines may be formed by combining respective groups of fixed-capacity hardware cache lines. The quantity of fixed-capacity hardware cache lines included in respective adaptive cache lines may be based on the programmable cache-line parameter. The programmable cache-line parameter can be selected in accordance with characteristics of the cache workload.

Abstract: Described apparatuses and methods provide error correction code (ECC) circuitry that is shared between two or more memory banks of a memory, such as a low-power dynamic random-access memory (DRAM). A memory device may include one or more dies, and a die can have multiple memory banks. The ECC circuitry can service at least two memory banks by producing ECC values based on respective data stored in the two memory banks. By sharing the ECC circuitry, instead of including a per-bank ECC engine, a total die area allocated to ECC functionality can be reduced. Thus, the ECC circuitry can be elevated from a one-bit ECC algorithm to a multibit ECC algorithm, which may increase data reliability. In some cases, memory architecture may operate in environments in which a masked-write command or an internal read-modify-write operation is precluded, including with shared ECC circuitry.

Abstract: Techniques and devices are described for embedding data in an address stream on an interconnect, such as a memory bus. Addresses in an address stream indicate at least part of a location in memory (e.g., a memory page and offset), whereas data embedded in the address stream can indicate when metadata or other information is available to lend context to the addresses in the address stream. The indication of data in the address stream can be communicated using, for example, a mailbox, a preamble message in a messaging protocol, a checksum, repetitive transmission, or combinations thereof. The indication of data can be recorded from the address stream and may later be used to interpret memory traces recorded during a test or can be used to communicate with a memory device or other recipient of the data during testing or regular operations.

Abstract: An autonomous memory device in a distributed memory sub-system can receive a database downloaded from a host controller. The autonomous memory device can pass configuration routing information and initiate instructions to disperse portions of the database to neighboring die using an interface that handles inter-die communication. Information is then extracted from the pool of autonomous memory and passed through a host interface to the host controller.

Abstract: Methods, systems, and devices for phase charge sharing are described. In some memory systems or memory devices, one or more decoders may be used to bias access lines of a memory die. The decoders may transfer voltage or current between a first conductive line of the decoder and a second conductive line of the decoder via a shorting device. Transferring the voltage or current may be performed as part of or in association with an operation (e.g., an activate or pre-charge operation) to access one or more memory cells of the memory die. In some examples, the decoders may transfer voltage or current between a first conductive line of a decoder associated with a first refresh activity and a second conductive line of the decoder associated with a second refresh activity via a shorting device.

Abstract: Apparatus including an array of memory cells may include circuit-protection devices that may include first and second circuit-protection units, a first gate having a first source/drain connected to a first node of the first circuit-protection unit, and a second gate having a first source/drain connected to a first node of the second circuit-protection unit, wherein a second source/drain of the first gate is connected to a second source/drain of the second gate.

Abstract: Apparatus, systems, and methods for a compiler are described. One such compiler converts source code into an automaton comprising states and transitions between the states, wherein the states in the automaton include a special purpose state that corresponds to a special purpose hardware element. The compiler converts the automaton into a netlist, and places and routes the netlist to provide machine code for configuring a target device.

Abstract: Proximity coupling interconnect packaging systems and methods. A semiconductor package assembly comprises a substrate, a first semiconductor die disposed adjacent the substrate, and a second semiconductor die stacked over the first semiconductor die. There is at least one proximity coupling interconnect between the first semiconductor die and the second semiconductor die, the proximity coupling interconnect comprising a first conductive pad on the first coupling face on the first semiconductor die and a second conductive pad on a second coupling face of the second semiconductor die, the second conductive pad spaced apart from the first conductive pad by a gap distance and aligned with the first conductive pad. An electrical connector is positioned laterally apart from the proximity coupling interconnect and extends between the second semiconductor die and the substrate, the position of the electrical connector defining the alignment of the first conductive pad and the second conductive pad.

Abstract: A method of forming conductive material of a buried transistor gate line includes adhering a precursor comprising tungsten and chlorine to material within a substrate trench. The precursor is reduced with hydrogen to form elemental-form tungsten material over the material within the substrate trench from the precursor.

Abstract: Some embodiments include semiconductor constructions having semiconductor material patterned into two mesas spaced from one another by at least one dummy projection. The dummy projection has a width along a cross-section of X and the mesas have widths along the cross-section of at least 3X. Some embodiments include semiconductor constructions having a memory array region and a peripheral region adjacent the memory array region. Semiconductor material within the peripheral region is patterned into two relatively wide mesas spaced from one another by at least one relatively narrow projection. The relatively narrow projection has a width along a cross-section of X and the relatively wide mesas have widths along the cross-section of at least 3X.