Interface layout for stacked memory architecture

By adopting the silicon-through-silicon path stacking and asynchronous synchronous interface block layout of multiple memory dies in the memory system, the problem of increasing delay in memory system when improving performance is solved, and efficient and low-latency memory density and bandwidth are achieved. Supports artificial intelligence applications.

CN119065994APending Publication Date: 2024-12-03MICRON TECHNOLOGY INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410687224.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-05-21
Filing Date
2024-05-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing memory systems face problems with increasing latency and increasing component count when improving performance to support intensive operations, especially in graphics performance and artificial intelligence applications, it is difficult to efficiently arrange memory systems without increasing latency.

Method used

The layout of memory interface blocks, which includes a silicon-through-silicon stack of multiple memory dies, is equipped with controllers and data path blocks associated with each memory die, supports asynchronous and synchronous interfaces, through queueing, error correction codes and The fixes increase memory density and bandwidth.

Benefits of technology

It realizes efficient and low latency to form memory devices with larger capacity and higher density, supports artificial intelligence and machine learning applications, and improves the coupling efficiency with host processing capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065994A_ABST
    Figure CN119065994A_ABST
Patent Text Reader

Abstract

The invention relates to an interface layout for a stacked memory architecture. A memory interface block may interface a plurality of memory dies to a host controller. The memory interface block may include an interface block coupled with a plurality of memory dies, which may be stacked on the memory interface block using through silicon vias. The memory interface block may include a controller, a data path block, and an interface block associated with each memory die. Thus, the memory interface block may perform functions such as queuing, ECC, and performing row repair and column repair procedures. In some examples, the layout of the memory interface blocks may include pairing controllers of at least two memory devices such that a pair of controllers may share command ports of a pair of memory dies. Further, the memory interface block may include an interface of the host controller that is different from an interface of each memory die.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Cross Reference

[0002] This patent application claims priority to U.S. Patent Application No. 18 / 670,074, filed by ECKEL et al. on May 21, 2024, entitled “INTERFACE LAYOUT FOR STACKED MEMORY ARCHITECTURES,” and U.S. Provisional Patent Application No. 63 / 470,651, filed by ECKEL et al. on June 2, 2023, entitled “INTERFACE LAYOUT FOR STACKED MEMORY ARCHITECTURES,” each of which is assigned to its assignee and the entire contents of each of which are expressly incorporated herein by reference.

[0003] The technical field relates to interface layout for stacked memory architecture. Background Art

[0004] Memory devices are widely used to store information in devices such as computers, user devices, communication devices, cameras, digital displays, and others. Information is stored by programming memory cells within the memory device to various states. For example, a binary memory cell is programmable to one of two supported states, typically represented by a logical 1 or a logical 0. In some examples, a single memory cell may support more than two states, either of which may be stored. To access stored information, a memory device may read (e.g., sense, detect, retrieve, determine) a state from a memory cell. To store information, a memory device may write (e.g., program, set, assign) a state to a memory cell.

[0005] There are various types of memory devices, including magnetic hard disks, random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), self-selection memory, chalcogenide memory technology, NOR and NAND memory devices, and others. Memory cells can be described in terms of volatile configurations or non-volatile configurations. Memory cells in non-volatile configurations can maintain a stored logic state for a long time, even in the absence of external power. Memory cells in volatile configurations lose their stored state when disconnected from external power. Summary of the invention

[0006] An apparatus is described. The apparatus may include: a plurality of interface blocks, each of the plurality of interface blocks including a first port configured for data communication with a host controller and a second port configured for command communication with the host controller; a first set of controllers, each of the first set of controllers coupled to one of a first subset of the plurality of interface blocks; a second set of controllers, each of the second set of controllers coupled to one of a second subset of the plurality of interface blocks; and a plurality of contact blocks, each of the plurality of contact blocks including a set of third ports configured for data communication with a plurality of memory dies and a fourth port configured for command communication with the plurality of memory dies, wherein for each of the plurality of contact blocks, each third port of the set of third ports is coupled to one of the first set of controllers or one of the second set of controllers, and each of the fourth ports is shared by the one of the first set of controllers and the one of the second set of controllers.

[0007] Another apparatus is described. The apparatus may include: a first set of controllers, each respective controller in the first set of controllers coupled to a respective memory die in a first set of memory dies via a first data port and a command port of a respective interface block in a set of interface blocks; a second set of controllers, each respective controller in the second set of controllers coupled to a respective memory die in a second set of memory dies via a second data port and the command port of the respective interface block; and a set of repair blocks, each respective repair block in the set of repair blocks configured to perform an address swap based on receiving repair data from a first set of fuses via the respective command port, the repair data being associated with the first set of memory dies and a second set of fuses being associated with the second set of memory dies, wherein each respective repair block in the set of repair blocks includes a respective memory array for storing the repair data.

[0008] A method is described. The method may include: receiving a set of parameters for a memory interface block, wherein the set of parameters includes a number of memory dies, a memory size, or a combination thereof; generating a layout of a host controller interface block including a plurality of interface blocks based at least in part on the set of parameters, each interface block including a first port configured for data communication with a host controller and a second port configured for command communication with the host controller; generating a layout of a section including a plurality of contact blocks based at least in part on the set of parameters, each of the plurality of contact blocks including a set of third ports configured for data communication with a plurality of memory dies and a fourth port configured for command communication with the plurality of memory dies, wherein the set of third ports includes a first subset of the set of third ports located in a first portion of the memory interface block and a second subset of the set of third ports located in a second portion of the memory interface block; and generating a layout of an intermediate block including a plurality of controllers and a plurality of data path blocks between the host controller interface block and the memory interface block based at least in part on the set of parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 An example of a system supporting interface layout for a stacked memory architecture according to examples disclosed herein is presented.

[0010] Figure 2 An example of a memory die supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown.

[0011] Figures 3A to 3C An example of a device supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown.

[0012] Figure 4 An example of a system supporting interface layout for a stacked memory architecture according to examples disclosed herein is presented.

[0013] Figure 5 An example of a system supporting interface layout for a stacked memory architecture according to examples disclosed herein is presented.

[0014] Figure 6 An example of a contact layout supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown.

[0015] Figure 7 An example of a bay layout supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown.

[0016] Figure 8A flow chart illustrating one or several methods of supporting interface layout for a stacked memory architecture according to examples disclosed herein is shown. DETAILED DESCRIPTION

[0017] In some instances, in order to support intensive operations such as graphics performance or artificial intelligence operations, it may be desirable to improve the performance of the memory system. For example, the memory system may become larger, thereby increasing the capacity of the memory system. However, in some cases, larger memory systems may result in more latency for operations performed by the memory system. In addition, these memory systems may require a larger number of interface components, which may increase the difficulty of increasing the capacity of the memory system. Thus, as the size of the memory system increases, it may be desirable to have techniques for efficiently arranging the components of the memory system without increasing latency.

[0018] Described herein are techniques and examples of a memory interface block that exemplifies an interface to a host controller, such as a graphics processing unit (GPU), an artificial intelligence processor, or another host controller. The memory interface block may include an interface block coupled to a plurality of memory dies that may be stacked on the memory interface block using through-silicon vias. The memory interface block may include a controller, a data path block, and an interface block associated with each memory die. Thus, the memory interface block may perform functions such as queuing, executing error correction code (ECC), and executing row repair and column repair procedures. In some examples, the layout of the memory interface block may include pairing controllers of at least two memory devices so that a pair of controllers may share command ports (e.g., drivers) of a pair of memory dies. In addition, the memory interface block may include an interface of a host controller that is different from an interface of each memory die. For example, the interface of the host controller may be synchronous and may have independent channels for read and write operations, while the interface of each memory die may be asynchronous and include channels that perform both read (e.g., access) and write operations. Thus, the memory interface block layout may support the formation of larger capacity and higher density memory devices efficiently and with reduced latency.

[0019] In addition to being applied in the memory systems described herein, the techniques for the interface layout of the stacked memory architecture may also be generally implemented to support artificial intelligence or analytical applications. As the use of artificial intelligence increases to support machine learning, analysis, decision making, or other related applications, semiconductor systems that support artificial intelligence applications and processes may be desired. For example, artificial intelligence applications may be associated with accessing relatively large amounts of data for analytical purposes and may benefit from memory systems that can effectively and efficiently store relatively large amounts of data or access stored data relatively quickly. Implementation of the techniques described herein may support artificial intelligence or machine learning techniques by providing a larger bandwidth memory device with a higher memory density, which may be more directly coupled to host processing capabilities, among other benefits.

[0020] First, in reference Figures 1 to 5 Features of the present disclosure are described in the context of the systems, dies, and devices described herein. Figure 6 The features of the present disclosure are described in the context of the contact layout described in the present disclosure. Figure 7 These and other features of the present disclosure are further illustrated and described with reference to flowcharts described in connection with interface layout for a stacked memory architecture.

[0021] Figure 1 An example of a system 100 supporting a layout interface for a stacked memory architecture in a coupled semiconductor system according to examples disclosed herein is illustrated. The system 100 may include a portion of an electronic device, such as a computing device, a mobile computing device, a communication device, a graphics processing device, a vehicle, or other system. The system 100 includes a host system 105, a memory system 110, and one or more channels 115 (e.g., for providing a communicative coupling) coupling the host system 105 and the memory system 110. The system 100 may include one or more memory systems 110, but aspects of the one or more memory systems 110 may be described in the context of a single memory system 110.

[0022] The host system 105 may be an example of a processor (e.g., circuitry, processing circuitry, processing component) that uses memory to perform processes, such as a processing system of a computing device, a mobile computing device, a communication device, a graphics processing device, a wearable device, an Internet connection device, a vehicle controller, a single chip system (SoC), or other fixed or portable electronic device, among other examples. The host system 105 may include one or more of an external memory controller 120, a processor 125, a basic input / output system (BIOS) component 130, or other components (e.g., peripheral components, input / output controllers not shown). The components of the host system 105 may be coupled to each other using a bus 135.

[0023] The external memory controller 120 may be configured to enable information (e.g., data, commands, control information, configuration information) communication between components of the system 100 (e.g., between components of the host system 105 (e.g., the processor 125) and the memory system 110). The external memory controller 120 may process (e.g., convert, translate) communications exchanged between the host system 105 and the memory system 110. In some examples, the external memory controller 120 or other components of the system 100 or associated functionality described herein may be implemented by or be part of the processor 125. For example, the external memory controller 120 may be hardware, firmware, or software (e.g., instructions), or some combination thereof, implemented by the processor 125 or other components of the system 100 or the host system 105. Although the external memory controller 120 is illustrated as being external to the memory system 110, in some examples, the external memory controller 120 or its functionality described herein may be implemented by one or more components of the memory system 110 (e.g., the memory system controller 155, the local memory controller 165), or vice versa. In various examples, the host system 105 or the external memory controller 120 may be referred to as a host.

[0024] Processor 125 is operable to provide functionality (e.g., control functionality) for system 100 or host system 105. Processor 125 may be a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. In some examples, processor 125 may be an example of a central processing unit (CPU), a graphics processing unit (GPU), a general purpose GPU (GPGPU), or a SoC, among other examples.

[0025] In some examples, the system 100 or the host system 105 may include an input component, an output component, or a combination thereof. The input component may include a sensor, a microphone, a keyboard, another processor (e.g., on a printed circuit board), an interface (e.g., a user interface, an interface between other devices), or a peripheral device that interfaces with the system 100 via one or more peripheral components, as well as other examples. The output component may include a display, an audio speaker, a printing device, another processor on a printed circuit board, or a peripheral device that interfaces with the system 100 via one or more peripheral components, as well as other examples.

[0026] The memory system 110 may be a component of the system 100 operable to provide physical memory locations (e.g., addresses) that may be used or referenced by the system 100. The memory system 110 may include a memory system controller 155 and one or more memory dies 160 (e.g., memory chips) for supporting data storage capacity. The memory system 110 may be configured to cooperate with one or more different types of host systems 105, and may respond to and execute commands provided by the host system 105 (e.g., via the external memory controller 120). For example, the memory system 110 (e.g., the memory system controller 155) may receive a write command indicating that the memory system 110 will store data received from the host system 105, or receive a read command indicating that the memory system 110 will provide data stored in the memory die 160 to the host system 105, or receive a refresh command indicating that the memory system 110 will refresh data stored in the memory die 160, as well as other types of commands and operations.

[0027] The memory system controller 155 may include components (e.g., circuitry, logic) operable to control the operation of the memory system 110. The memory system controller 155 may include hardware, firmware, or instructions that enable the memory system 110 to perform various operations, and may be operable to receive, transmit, or execute commands, data, or control information related to the operation of the memory system 110. The memory system controller 155 may be operable to communicate with one or more of the external memory controller 120, one or more memory dies 160, or the processor 125. In some examples, the memory system controller 155 may cooperate with the local memory controller 165 of the memory die 160 to control the operation of the memory system 110.

[0028] Each memory die 160 may include a local memory controller 165 and a memory array 170. The memory array 170 may be a collection of memory cells, each of which may be operable to store one or more bits of data. The memory die 160 may include a two-dimensional (2D) array of memory cells or a three-dimensional (3D) array of memory cells. In some examples, the memory die 160 may include two or more memory arrays 170, which may be stacked on top of each other or positioned side-by-side (e.g., relative to a substrate).

[0029] The local memory controller 165 may include components (e.g., circuitry, logic) operable to control the operation of the memory die 160. In some examples, the local memory controller 165 may be operable to communicate (e.g., receive or transmit data or commands or both) with the memory system controller 155. In some examples, the memory system 110 may not include a memory system controller 155 and a local memory controller 165, or an external memory controller 120 may perform the various functions described herein. Thus, the local memory controller 165 may be operable to communicate with the memory system controller 155, with other local memory controllers 165, or directly with the external memory controller 120 or processor 125, or any combination thereof. Examples of components that may be included in the memory system controller 155 or the local memory controller 165 or both may include a receiver for receiving signals (e.g., from the external memory controller 120), a transmitter for transmitting signals (e.g., to the external memory controller 120), a decoder for decoding or demodulating received signals, an encoder for encoding or modulating signals to be transmitted, a sensing component for sensing the state of memory cells of the memory array 170, a writing component for writing the state to the memory cells of the memory array 170, or various other components operable to support the described operations of the memory system 110.

[0030] The host system 105 (e.g., external memory controller 120) and the memory system 110 (e.g., memory system controller 155) may communicate information (e.g., data, commands, control information, configuration information) using one or more channels 115. Each channel 115 may be an example of a transmission medium that carries information, and each channel 115 may include one or more signal paths (e.g., transmission media, electrical conductors, conductive paths) between terminals associated with components of the system 100. For example, a channel 115 may be associated with a first terminal (e.g., including one or more pins, including one or more pads) at the host system 105 and a second terminal at the memory system 110. A terminal may be an example of a conductive input or output point of a device of the system 100, and a terminal may be operable to serve as part of a channel 115. In some implementations, at least the channel 115 between the host system 105 and the memory system 110 may include or be referred to as a host interface (e.g., a physical host interface). In some implementations, the host interface may include or be associated with interface circuitry (e.g., signal drivers, signal latches) at the host system 105 (e.g., at the external memory controller 120) or at the memory system 110 (e.g., at the memory system controller 155), or both.

[0031] In some examples, channel 115 (e.g., associated signal paths and terminals) may be dedicated to conveying one or more types of information. For example, channel 115 may include one or more command and address channels, one or more clock signal channels, one or more data channels, and other channels or combinations thereof. In some examples, signaling may be conveyed via channel 115 using single data rate (SDR) signaling or double data rate (DDR) signaling. In SDR signaling, one modulation symbol (e.g., signal level) of a signal may be recorded for each clock cycle (e.g., on a rising or falling edge of a clock signal). In DDR signaling, two modulation symbols of a signal may be recorded for each clock cycle (e.g., on both a rising edge and a falling edge of a clock signal). In some cases, channel 115 may be or include one or more memory interfaces, such as an Advanced eXtensible Interface (AXI), for signaling communications.

[0032] In some implementations, the memory system 110 may include one or more data paths between the memory array 170 and the host interface (e.g., between the memory array 170 and the channel 115, between the memory array 170 and at least a portion of the memory system controller 155). To support data rates along the data paths, the memory system 110 may include SERDES circuitry that converts signaling between relatively slower signaling that uses relatively more signal paths and relatively faster signaling that uses relatively fewer signal paths. However, the SERDES circuitry, as well as other data path circuitry, may involve multiple signal amplification stages to maintain signal integrity along the data paths, which may occupy area of ​​the memory die or may be associated with power consumption at the memory die, among other characteristics.

[0033] According to examples disclosed herein, a memory interface block that interfaces with a host system 105 (e.g., via an external memory controller 120) may be instantiated (e.g., within a memory system 110). The memory interface block may include one or more contacts coupled to a plurality of memory dies 160, which may be stacked on the memory interface block using through-silicon vias. The memory interface block may include a controller, a data path block, and an interface block (e.g., to the host system 105) associated with each memory die 160. Thus, the memory interface block may perform functions such as queuing, performing ECC, and performing row and column repair procedures for each of the memory dies 160 while acting as an interface with the host system 105.

[0034] In some examples, the layout of the memory interface block may include pairing the controllers of at least two memory dies 160 so that a pair of controllers can share the command ports of a pair of memory dies 160. In addition, the memory interface block may include an interface of a host controller that is different from the interface of each memory die. For example, the interface of the host controller may be synchronous and may have independent channels for read and write operations, while the interface of each memory die may be asynchronous and include channels that perform both read (e.g., access) and write operations. Thus, the memory interface block layout may support the formation of larger capacity and higher density memory devices with high efficiency and reduced latency.

[0035] Figure 2 An example of a system 200 supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The system 200 illustrates an example of a substrate 205 (e.g., a semiconductor die, a host die, a processor die, a logic die, a GPU die) coupled with one or more memory dies 240 (e.g., memory die 240-1 and memory die 240-2, a semiconductor die, a memory array die). The substrate 205 or memory die 240 can be formed using a respective semiconductor substrate (e.g., a crystalline semiconductor material substrate such as silicon, germanium, silicon-germanium, gallium arsenide, or gallium nitride) or a silicon-on-insulator (SOI) substrate (e.g., silicon on glass (SOG), silicon on sapphire (SOS)), or an epitaxial semiconductor material formed on another substrate, among other examples. Although the illustrated example of the system 200 includes two memory dies 240, the system 200 according to the described technology can include any number of one or more memory dies 240 coupled with the substrate 205.

[0036] System 200 illustrates an example of interface circuitry between a host and memory (e.g., via a host interface, via a physical host interface) implemented in (e.g., distributed among) multiple semiconductor memory dies. For example, substrate 205 may include a set of one or more memory interface blocks 220 (e.g., memory interface block 220-1 and memory interface block 220-2), and each memory die 240 may include a set of one or more array interfaces 260 and one or more memory arrays 250 (e.g., memory die 240-1 includes array interface 260-1 coupled to a set of one or more memory arrays 250-1, memory die 240-2 includes array interface 260-2 coupled to a set of one or more memory arrays 250-2). In some implementations, substrate 205 may also include host processor 210. However, in some other implementations, the host processor 210 may be external to the substrate 205, such as in another semiconductor memory die or other component that is coupled (e.g., communicatively coupled, directly coupled) to the substrate 205 via one or more contacts 211. Although the example of the system 200 is illustrated as including one array interface 260 in each memory die 240, the memory die 240 according to the described techniques may include any number of one or more array interfaces 260, each coupled to a set of corresponding one or more memory arrays 250 and each coupled to a corresponding memory interface block 220 of the substrate 205. Thus, the interface circuitry of the system 200 may include one or more memory interface blocks 220 of the substrate 205, wherein each memory interface block 220 is coupled (e.g., communicates) to a corresponding array interface 260 of the memory die 240 (e.g., external to the substrate 205). In some examples, the coupled combination of the memory interface block 220 and the array interface 260 may include or be referred to as a data path associated with a set of corresponding one or more memory arrays 250.

[0037] The host processor 210 may be an instance of the host system 105 or a portion thereof (e.g., the processor 125, the external memory controller 120, or both). The host processor 210 may be configured to perform operations utilizing the storage of the memory array 250. For example, the host processor 210 may receive data read from the memory array 250 or transmit data written to the memory array 250, or both (e.g., depending on an application or other operation of the host processor 210). The memory array 250 may be an instance of the memory array 170 and may include memory cells of various architectures, such as RAM, DRAM, SDRAM, SRAM, FeRAM, MRAM, RRAM, PCM, chalcogenide, NOR, or NAND memory cells, or any combination thereof. The host processor 210 may be configured to perform signaling communications (e.g., transmit, receive) with the interface block 220 via a host interface 215 (e.g., a physical host interface), which may implement a reference Figure 1 For example, the host processor 210 may be configured to transmit access signaling (eg, control signaling, access command signaling), which may be received by the interface block 220 to support access operations (eg, read operations, write operations) to the memory array 250.

[0038] The host interface 215 may include a set of one or more corresponding signal paths for each memory interface block 220, such that the host processor 210 communicates with each memory interface block 220 via a corresponding set of signal paths (e.g., according to selection of a corresponding set for performing access operations via a memory interface block 220 selected by the host processor 210). Additionally or alternatively, the host interface 215 may include one or more signal paths shared between multiple interface blocks 220, and the memory interface blocks 220 or the host processor 210 or both may interpret, ignore, respond to, or suppress response signaling via the shared signal paths of the host interface 215 based on logic indications (e.g., addressing indications associated with the memory interface blocks 220 or interface enable signals, which may be provided by the host processor 210 or the corresponding memory interface blocks 220, depending on the signaling direction).

[0039] Each memory interface block 220 may be coupled with at least one respective bus 225 of the substrate 205 and a respective bus 265 of the memory die 240 that is configured to communicate signaling with the corresponding array interface 260 (e.g., via one or more associated signal paths). For example, the memory interface block 220-1 may be coupled with the array interface 260-1 via bus 225-1 and bus 265-1, and the memory interface block 220-2 may be coupled with the array interface 260-2 via bus 225-2 and bus 265-2. In some examples, the memory die 240 may include a bus, such as bus 290, that bypasses the operating circuitry of the memory die 240 (e.g., bypasses the array interface 260 of a given memory die 240). For example, memory interface block 220-2 may be coupled to array interface 260-2 of memory die 240-2 via bus 290-1 of memory die 240-1 which may bypass array interface 260 of memory die 240-1. Other buses, such as bus 290-2, may be coupled to contacts of other memory dies 240, but remain unconnected to substrate 205. For example, bus 290-2 may couple contact 275-2 to contact 280-2. Additionally, contact 285-2 of memory die 240-2 may not be connected to another memory die 240. Such techniques may be extended for interconnection between more than two memory dies 240 (e.g., for interconnection via respective buses 290 of multiple memory dies 240).

[0040] The respective signal paths of buses 225, 265, and 290 may be coupled to one another from one memory die to another memory die via various arrangements of contacts at the surfaces of the interfacing memory dies. For example, bus 225-1 may be coupled to bus 265-1 via contacts 230-1 of substrate 205 (e.g., at the surface of substrate 205) and contacts 270-1 of memory die 240-1, bus 225-2 may be coupled to bus 290-1 via contacts 230-2 of substrate 205 and contacts 275-1 of memory die 240-1, bus 290-1 may be coupled to bus 265-2 via contacts 280-1 of memory die 240-1 and contacts 270-2 of memory die 240-2, and so on. Although each respective bus is illustrated with a single line coupled via a singular contact, it should be understood that each signal path of a bus may be associated with a respective contact to support separate communication couplings via each signal path of a given bus. In some examples, bus 290 may traverse a portion of memory die 240 (e.g., in an in-plane direction, along a direction different from the thickness direction, in a waterfall arrangement), which may support an arrangement of contacts 230 along a surface of substrate 205 to couple with array interfaces 260 of different memory dies 240 along a stacking direction (e.g., via contacts 275 and 280 that do not overlap when viewed along the thickness direction).

[0041] The interconnection of the interface contacts may be supported by a variety of techniques. For example, in a hybrid bonding implementation, the interface contacts may be coupled by fusion of the conductive material (e.g., electrically conductive material) of the interface contacts (e.g., without solder or other intervening material between the contacts). For example, in an assembled condition, the coupling of substrate 205 to memory die 240-1 may include fusion of the conductive material of contact 230-2 with the conductive material of contact 275-1, and the coupling of memory die 240-1 to memory die 240-2 may include fusion of the conductive material of contact 280-1 with the conductive material of contact 270-2, and so on. In some examples, such coupling may include inoperable fusion of contacts (e.g., non-communicative coupling, physical coupling), such as fusion of contact 285-1 with contact 275-2, neither of which is coupled to the operable circuitry of memory die 240-1 or 240-2. In some examples, such techniques may be implemented to improve coupling strength or uniformity (e.g., implementing contacts 285 that may not be operably coupled to array interface 260 or memory interface block 220), or such coupling may be a byproduct of duplication of components that may or may not be operable in various configurations (e.g., where for a co-arranged memory die 240 with contacts 275 and 285, contacts 275-1 and 280-1 provide a communication path for array interface 260-2 and memory interface block 220-2, but contacts 275-2 and 280-2 do not provide a communication path between array interface 260 and memory interface block 220).

[0042] In some examples, the fusion of conductive materials between memory dies (e.g., between contacts) can be accompanied by fusion of other materials at one or more surfaces interfacing the memory dies. For example, in an assembled condition, the coupling of substrate 205 and memory die 240-1 can include fusion of memory dielectric material 235 (e.g., non-conductive material) of substrate 205 with memory dielectric material 295 of memory die 240-1, and the coupling of memory die 240-1 and memory die 240-2 can include fusion of memory dielectric material 295 of memory die 240-1 with memory dielectric material 295 of memory die 240-2. In some examples, such memory dielectric materials can include oxides, nitrides, carbides, oxide-nitrides, oxide-carbides, or other conversions or doping of semiconductor materials of substrate 205 or memory die 240, and other materials that can support such fusion. However, the coupling between substrate 205 and memory die 240 may be implemented according to other techniques, which may implement solder, adhesives, thermal interface materials, and other intervening materials.

[0043] In some examples, the memory dies 240 may be coupled into a stack (e.g., forming a "cube" or other arrangement of memory dies 240), and the stack may then be coupled with the substrate 205. In some examples, a group of respective one or more memory dies 240 may be coupled with each substrate 205 of a plurality of substrates 205 formed in a wafer (e.g., in a chip-to-wafer bonding arrangement, before dicing the wafer of substrates 205), and the substrates 205 coupled with their respective groups of memory dies 240 may be separated from each other (e.g., by at least dicing the wafer of substrates 205). In some other examples, a group of respective one or more memory dies 240 may be coupled with the respective substrates 205 after the substrates 205 are separated from the wafer of substrates 205 (e.g., in a chip-to-chip bonding arrangement).

[0044] The buses 225, 265, and 290 may be configured to provide signaling (e.g., coordinated signaling, logical signaling, modulated signaling, digital signaling) between the memory interface block 220 and the corresponding array interface 260, which may involve various modulation or coding techniques through the transmission interface block (e.g., via a driver component of the transmission interface block). In some examples, this signaling may be supported (e.g., accompanied) by clock signaling communicated (e.g., coordinated with the signal transmission) via the respective buses. For example, the bus may be configured to pass one or more clock signals transmitted by the memory interface block 220 for reception by the array interface 260 (e.g., for triggering a latch or other receiving component of the array interface 260 to receive a signal, for supporting a clocked operation of the array interface 260). Additionally or alternatively, the bus may be configured to pass one or more clock signals transmitted by the array interface 260 for reception by the memory interface block 220 (e.g., for triggering a latch or other receiving component of the memory interface block 220 to receive a signal, for supporting a clocked operation of the memory interface block 220). Such clock signals may be associated with various communications (e.g., unidirectional communications, bidirectional communications) such as control signaling, command signaling, data signaling, or any combination thereof. For example, a bus may include one or more signal paths for a data bus (e.g., a DQ bus, via a data interface of an interface block) to communicate according to one or more corresponding clock signals (e.g., a data clock signal) or one or more signal paths for a control bus (e.g., a command / address (C / A) bus, via a command interface of an interface block) to communicate according to one or more clock signals (e.g., a control clock signal), or any combination thereof.

[0045] The interface block 220 and the array interface 260 may each include circuitry in various configurations (e.g., hardware configurations, logic configurations, software or instruction configurations) that support functionality assigned to the respective interface block for accessing a set of corresponding memory arrays 250. For example, the interface block 220 may include circuitry configured to perform a first subset of operations supporting access of the memory arrays 250, and the array interface 260 may include circuitry configured to support a second subset of operations supporting access of the memory arrays 250. In some examples, the interface block 220 and the array interface 260 may support functional division or distribution of functionality associated with the memory system controller 155, the local memory controller 165, or both across multiple memory dies (e.g., the substrate 205 and at least one memory die 240). Such subsets of operations may include operations performed in response to commands from the host processor 210 or operations performed without commands from the host processor 210 (e.g., operations determined within the memory interface block 220 or the array interface 260), or various combinations thereof. In some examples, the circuitry of interface block 220 or array interface 260 or both may include components (e.g., transistors) formed at least in part from doped portions of a substrate of a corresponding memory die, where, in some examples, the substrate of substrate 205 may have characteristics that differ from characteristics of a substrate of memory die 240.

[0046] In some examples, the interface block 220 may include circuitry configured to receive first access command signaling from the host processor 210 (e.g., via the host interface 215, via the one or more contacts 211, as appropriate) and transmit second access command signaling to the corresponding (e.g., coupled) array interface 260 based on (e.g., in response to) the received first access command signaling. The array interface 260 may thus include circuitry configured to receive second access command signaling from the corresponding memory interface block 220 and access a corresponding set of one or more memory arrays 250 based on (e.g., in response to) the received second access command signaling. In various examples, the first access command signaling may include an access command associated with an operation type (e.g., a read operation, a write operation, a refresh operation, a memory management operation), which may be associated with an indication of an address (e.g., a logical address, a physical address) of the one or more memory arrays 250. In some examples, the first access command signaling may include an indication of a logical address associated with the memory array 250, and the circuit system of the memory interface block 220 may be configured to generate a second access command signaling to indicate a physical address associated with the memory array 250 (e.g., a row address, a column address, using a logical-to-physical (L2P) table or other mapping or calculation functionality of the memory interface block 220).

[0047] In some examples, to support write operations of the system 200, the circuitry of the interface block 220 may be configured to receive first data signaling associated with a first access command signaling (e.g., from the host processor 210, via the host interface 215, via one or more contacts 211, as appropriate) and transmit second data signaling (e.g., associated with a second access command signaling) to the one or more array interfaces 260 based on the received first access command signaling and the first data signaling. The array interface 260 may thus be configured to receive the second data signaling and write data to the one or more memory arrays 250 based on the received second access command signaling and the second data signaling (e.g., according to an indicated address associated with the first access command signaling). In some instances, interface block 220 may include error control functionality (e.g., error detection circuitry, error correction circuitry, ECC logic, an ECC engine) that supports interface block 220 in performing error control operations (e.g., detecting or correcting errors in the first data signaling, determining one or more parity bits communicated in the second data signaling and written with the data) to generate a second data signaling based on using the received first data signaling.

[0048] In some examples, to support read operations of system 200, the circuitry of array interface 260 may be configured to read data from memory array 250 based on received second access command signaling and to transmit first data signaling based on the read data. Interface block 220 may thus be configured to receive first data signaling and to transmit second data signaling based on the received first data signaling (e.g., via host interface 215, via one or more contacts 211 to host processor 210, as appropriate). In some examples, interface block 220 may include error control functionality that enables interface block 220 to generate second data signaling based on performing error control operations using received first data signaling (e.g., detecting or correcting errors in the first data signaling, which may include calculations involving one or more parity bits received with the first data signaling).

[0049] In some examples, access command signaling transmitted by the interface block 220 to the array interface 260 may be generated (e.g., based on access command signaling received from the host processor 210, based on initiation signaling received from the host processor 210, without receiving signaling from the host processor 210, or otherwise independent of signaling from the host processor 210) according to various determination or generation techniques configured at the interface block 220 (e.g., based on a configuration modified at the interface block 220 for accessing the memory array 250). Such techniques may enable the interface block 220 to configure aspects of access operations performed by the corresponding array interface 260 on the memory array 250.

[0050] The memory die 240 may include one or more cells 262 (e.g., modules) separate from a semiconductor wafer having a pattern of cells 262. Although each memory die 240 of the system 200 is illustrated as having a single cell 262 (e.g., cell 262-1 of memory die 240-1, cell 262-2 of memory die 240-2), a memory die 240 according to the described techniques may include any number of cells 262 that may be arranged in various patterns (e.g., groups of one or more cells 262 along a row direction, groups of one or more cells 262 along a column direction, and other patterns). Each cell 262 may include at least the circuitry of a corresponding array interface 260 and a memory array 250, a bus 255, a bus 265, and one or more contacts 270 corresponding to the corresponding array interface 260. For example, array interface 260-1 may be coupled to one or more memory arrays 250-1 via bus 255-1 and array interface 260-2 may be coupled to one or more memory arrays 250-2 via bus 255-2. In some examples, each unit 262 may also include one or more buses 290, contacts 275, contacts 280, or contacts 285 as appropriate (e.g., associated with respective array interfaces 260 of units 262 of different memory dies 240), which may support various degrees of stackability between or via units 262 of other memory dies 240.

[0051] In some cases, the host processor 210 may be an efficient and high-performance solution based on memory-centric logic (e.g., a GPU), which may benefit from a higher amount of memory with low latency. In some cases, cache-based memory may be used to provide low-latency memory. However, the use of memory caches may be associated with unpredictability in the time used to access memory because data is fetched from the memory cache or other external memory at the beginning of the access operation. Thus, the system may use a tightly coupled memory (TCM) architecture to achieve higher performance. For example, in a TCM architecture, low-latency memory may be associated with and located within a dedicated base address range, which may improve access time.

[0052] According to the examples described herein, the system 200 may illustrate an example of a TCM architecture such as a tightly coupled dynamic random access memory (TCDRAM). Thus, the memory die 240-1 and the memory die 240-2 may each include a plurality of memory arrays 250 that can be accessed by the host processor 210 (e.g., a host system, a processor of the host system) in a single data cycle. For example, the memory arrays 250 of the memory die 240-1 and the memory die 240-2 may store time-critical routines and data. If the memory die 240-1 and the memory die 240-2 include an example of a TCM architecture, the host processor 210 may access routines and data stored in the memory arrays 250 (e.g., a memory bank) in one data cycle instead of waiting for various fetch codes and processes external to the system.

[0053] The examples and techniques described herein support implementation of a memory interface block 220 that can serve as a common interface for a TCM architecture with a host processor 210. The memory interface block 220 can each be coupled to a plurality of memory dies 240, which can be stacked on the memory interface block 220. The memory interface block 220 can include a controller, a data path block, and an interface block associated with each memory die 240 of the plurality of memory dies 240. Thus, the memory interface block 220 can perform functions such as queuing, performing ECC, and performing row repair and column repair procedures. In some examples, the layout of the memory interface block 220 can include pairing the controllers of at least two memory dies 240 so that a pair of controllers can share the command ports of a pair of memory dies 240. In addition, the memory interface block 220 can include a host interface 215 of the host processor 210 that is different from the interface of each memory die 240. For example, the host interface 215 may be synchronous and may have separate channels for read and write operations, while the interface of each memory die 240 may be asynchronous and include channels that perform both read (e.g., access) and write operations. The layout of the memory interface block 220 is referred to herein as Figure 4 and 5 Thus, the layout of system 200 including memory interface block 220 can support interfacing with TCM architectures that can provide increased capacity for low latency memory.

[0054] Figure 3A An example of a device 300-a supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The device 300-a may be an example of a device in which an application specific integrated circuit (ASIC) 305 (e.g., another integrated circuit, a die) is coupled to a memory device 310 using an interposer 315 (e.g., a silicon interposer, a glass interposer) and a packaging substrate 325. The device 300-a may be a reference Figure 2ASIC 305 may be referenced to an example of system 200. Figure 1 and 2 2 and other host devices described herein. Device 300-a may include a memory interface block 335 and a physical interface 340, which may be included within a memory interface block described herein. Memory device 310 may include one or more memory dies 320. Memory dies 320 may each be referenced Figure 2 3. Depicted are examples of die 240 or memory array 250. In some cases, memory die 320 may be referred to as a memory array, a memory cell array, or a memory cell hierarchy.

[0055] In some examples, to improve power usage and efficiency, a memory interface block 335 may be included in the buffer layer 330-a and coupled with the memory device 310 and the ASIC 305-a. For example, the memory interface block 335 may be included in the buffer layer 330-a between the memory device 310 and the interposer 315. The memory interface block 335 may be coupled to the ASIC 305-a via one or more physical interfaces 340, which may be physically connected via a channel passing through the interposer 315. As described in reference Figure 2 As described above, the memory interface blocks 335 may help control the flow of commands and data between the ASIC 305-a and the memory die 320 by providing temporary storage and scheduling of commands received from the ASIC 305-a and destined for the memory device 310. One or more of the memory interface blocks 335 may receive commands from the ASIC 305-a (e.g., from a memory controller of the ASIC 305-a), may temporarily store the commands in a memory bank managed by a shallow queue (e.g., a FIFO queue), and may subsequently determine when the commands are to be sent to the memory device and via which channels the commands are to be sent (e.g., as described in reference to FIG. 1 ). Figure 2 description) to convey.

[0056] In some examples, the layout of the memory interface block 335 may be selected based on user input. For example, a user (e.g., a customer) may select a certain number of memory dies 320 desired for the device 300-a. The layout of the device 300-a and the layout, size, number, or any combination thereof of the memory interface block 335 may be based on the number of memory dies 320 (e.g., or desired bandwidth or memory capacity) such that the memory interface block 335 can support the number of memory dies 320. The layout of the memory interface block 335 is referred to herein as Figure 4 and 5 Describe in more detail.

[0057] Figure 3BAn example of a device 300-b supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The device 300-b may be an example of a device in which an ASIC 305-b is coupled with a memory device 310 via a packaging substrate 325. The device 300-b may be similar to the device 300-a, except that the ASIC 305-b of the device 300-b may be positioned between a buffer layer 330-b and the packaging substrate 325. Thus, one or more memory interface blocks 335 and one or more physical interfaces 340 may be included within the buffer layer 330-b (e.g., as an interface shim) and facilitate control of command and data flow between the ASIC 305-b and the one or more memory dies 320 of the memory device 310. This interface shim configuration may result in increased bandwidth and improved power efficiency for the device 300-b.

[0058] In some examples, the layout of the memory interface block 335 may be selected based on user input. For example, a user (e.g., a customer) may select a certain number of memory dies 320 desired for the device 300-b. The layout of the device 300-b and the layout, size, number, or any combination thereof of the memory interface block 335 may be based on the number of memory dies 320 (e.g., or desired bandwidth or memory capacity) such that the memory interface block 335 can support the certain number of memory dies 320. The layout of the memory interface block 335 is referred to herein as Figure 4 and 5 Describe in more detail.

[0059] Figure 3C An example of a device 300-c supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The device 300-c may be an example of a device in which an ASIC 305-c is coupled to a memory device 310 via a packaging substrate 325. The device 300-c may be similar to the device 300-b, except that one or more memory interface blocks 335 and one or more physical interfaces 340 may be included in the ASIC 305-c. Additionally, the ASIC 305-c of the device 300-b may be positioned between the memory device 310 and the packaging substrate 325. Thus, the one or more memory interface blocks 335 and one or more physical interfaces 340 included in the ASIC 305-c may facilitate control of command and data flow between the ASIC 305-c and one or more memory dies 320 of the memory device 310. Such a configuration of incorporating the memory interface block 335 and the physical interface 340 into the ASIC 305 - c may result in increased bandwidth, power efficiency, reduced latency, and high access speeds for the device 300 - c .

[0060] In some examples, the layout of the memory interface block 335 may be selected based on user input. For example, a user (e.g., a customer) may select a certain number of memory dies 320 desired for the device 300-c. The layout of the device 300-c and the layout, size, number, or any combination thereof of the memory interface block 335 may be based on the number of memory dies 320 (e.g., or desired bandwidth or memory capacity) such that the memory interface block 335 can support the certain number of memory dies 320. The layout of the memory interface block 335 is referred to herein as Figure 4 and 5 Describe in more detail.

[0061] Figure 4 An example of a system 400 supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The system 400 may be referenced herein. Figures 1 to 3C 2 or 335 described herein. In addition, system 400 may serve as a plurality of memory dies (e.g., Figures 3A to 3C The memory die 320 described herein) and the host system (such as the memory die 320 described herein) Figures 1 to 3C An interface between the host system 105, the host processor 210, the ASIC 305, or any combination thereof) described herein.

[0062] In some examples, system 400 may include a section 405 corresponding to a plurality of interface blocks that may contain contacts (e.g., ports, interfaces) for through-silicon vias associated with a plurality of memory dies. For example, section 405 may include a group of contacts 410-a for through-silicon vias corresponding to a first subset of memory dies of the plurality of memory dies, and section 405 may also include a group of contacts 410-b for one or more through-silicon vias corresponding to a second subset of memory dies of the plurality of memory dies. Each group of contacts 410 may be arranged as one or more rows of contacts that may form a stack. For example, contact group 410-a may include 8 rows of contacts, and each row of contacts may correspond to a memory die in the first subset of memory dies. The rows of contacts may be arranged along a second dimension, such as the y-direction. However, the number of contacts in each group of contacts 410 may be variable and may be adjusted based on the number of memory dies supported by system 400, as described with reference to FIG. Figure 5 In this example, for example, system 400 can be arranged to support 16 memory dies.

[0063] In some examples, section 405 may include a set of contacts 415, which may include one or more rows of command contacts (e.g., interface blocks, command port rows) associated with receiving commands for multiple memory dies. In some examples, contact set 410-a and contact set 410-b may be arranged on both sides of contact set 415. This may allow each row of command contacts of contact set 415 to correspond to two memory dies, one for each subset of memory dies. For example, the lowest row of command contacts of contact set 415 may be associated with receiving commands for both a first memory die in a first subset of memory dies (e.g., associated with a row of contacts with index 0 of contact set 410-a) and a first memory die in a second subset of memory dies (e.g., associated with a row of contacts with index 8 of contact set 410-b). In addition, the top row of command contacts of contact group 415 can be associated with commands for both the last memory die in the first subset of memory die (e.g., associated with the contact row with index 7 of contact group 410-a) and the last memory die in the second subset of memory die (e.g., associated with the contact row with index 15 of contact group 410-b), and similarly for other command contact rows of contact group 415.

[0064] Thus, the number of command contact rows of contact group 415 can correspond to the number of contact rows in each of contact group 410-a and contact group 410-b (e.g., 8 in this case), which can support receiving commands from each of multiple memory dies (e.g., 16 in this case). In addition, because each row of contacts of contact group 415 is shared by two memory dies, the layout of system 400 can have a smaller size.

[0065] Contact group 410-a, contact group 410-b and contact group 415 can be arranged in multiple contact blocks 408, wherein each contact block 408 can include a subset of contact group 410-a (e.g., configured for data communication with a first memory die), a subset of contact group 410-b (e.g., configured for data communication with a second memory die) and a subset of contact group 415 (e.g., configured for command communication with both the first memory die and the second memory die associated with contact group 410-a and the subset of contact group 410-b).

[0066] System 400 may include a segment 420 that may include drivers (e.g., transmitter circuitry, receiver circuitry, interfaces, ports) for sending or receiving read data, write data, and commands to or from multiple memory dies via contacts of segment 405. For example, contact set 410-a and contact set 410-b may be coupled to a set of drivers 425-a and a set of drivers 425-b associated with receiving and sending data, respectively. Similarly, contact set 415 may be coupled to a set of drivers 430 associated with receiving and sending commands, which may include one or more row command drivers (e.g., command ports).

[0067] In some examples, driver group 425-a may include a row of drivers (e.g., a row of one or more drivers, ports) coupled to a row of corresponding contacts in contact group 410-a. For example, a driver row with index 0 may communicate data (e.g., transmit and receive) with a first memory die in a first subset of memory dies via the row of contacts with index 0 in contact group 410-a. Similarly, a driver row with index 8 in driver group 425-b may communicate data with a first memory die in a second subset of memory dies based on coupling with a row of corresponding contacts in contact group 410-b with index 8, and so on for other driver rows of driver group 425-a and driver group 425-b.

[0068] In some examples, driver group 430 can be ordered so that each row of command drivers is coupled to a row of corresponding command contacts of contact group 415 (e.g., the lowest row of command drivers corresponds to the lowest row of command contacts, and so on). Thus, each row of command drivers can communicate commands to a row of corresponding command contacts. Thus, each row of command drivers can also be shared by two memory dies, one for each subset of memory dies. By sharing the use of driver group 430 and contact group 415, system 400 can be reduced in size while still supporting interface operations between a large number of memory dies and a host device.

[0069] In some examples, the system 400 may include a plurality of data path blocks 435 corresponding to a plurality of memory dies. Each data path block 435 may receive data directed from or to a corresponding memory die of the plurality of memory dies. The data path blocks 435 may be arranged such that a first subset of the data path blocks 435 corresponding to a first subset of the memory dies is located in a first region of a segment 450 of the system 400, and a second subset of the data path blocks 435 corresponding to a second subset of the memory dies is located in a second region of the segment 450, as illustrated. This may facilitate routing between the data path blocks 435 and corresponding driver rows (e.g., having the same index value) of the driver group 425-a and the driver group 425-b. For example, a data path block 435 having an index value between 0 and 7 may be located in a region of the segment 450 near the driver group 425-a, while a data path block 435 having an index value between 8 and 15 may be located in a region of the segment 450 near the driver group 425-b.

[0070] In some cases, the size (e.g., aspect ratio), positioning (e.g., horizontal or vertical orientation relative to other components such as a set of drivers 425), or both of the data path blocks 435 can be based on the number of multiple memory dies. For example, the data path blocks 435 can be arranged along a first dimension (e.g., an x-direction), as shown in reference to Figure 4 Similarly, the size and positioning of other components can also be based on the number of memory dies, as shown in Figure 2. Figure 5 Describe in more detail.

[0071] In some cases, the data path block 435 may be configured to perform an error correction procedure. For example, each data path block 435 may be configured to generate an ECC and perform the ECC to perform an error correction procedure on the corresponding memory die. The ECC bits generated by the data path block 435 may be stored at the memory die together with the data. The data path block 435 may then perform an ECC process on the read operation to check the data read from the memory die using the associated ECC and correct the bit error before passing the data to the host device via the interface block 460. By performing ECC at the data path block 435, the system 400 may support the execution of error correction procedures concurrently with other operations. For example, the error correction procedure of the memory may be executed during the same time as other operations at the memory die (such as command execution, data read operation, or data write operation). Additionally or alternatively, performing ECC at the data path block 435 may allow ECC to be performed according to a smaller feature size (such as a complementary metal oxide semiconductor (CMOS) feature size) relative to performing ECC at the memory die. Furthermore, by performing error correction at the data path block 435, each memory die can be reduced in size by omitting components that would perform error correction at the memory die.

[0072] In some examples, the system 400 may include multiple controllers 440 associated with receiving commands from a host device and performing control operations. For example, the controllers 440 may participate in cross-bank scheduling (e.g., scheduling row and column commands), monitoring timing associated with multiple memory dies (e.g., DRAM timing, column address strobe (CAS) timing), mapping logical addresses to physical addresses associated with multiple memory dies, performing column repair and row repair procedures, or any combination thereof. In some examples, the system 400 may include a controller 440 for each of the multiple memory dies, and the controllers 440 may be located within the segment 450 between a first subset of data path blocks 435 corresponding to a first subset of memory dies and a second subset of data path blocks 435 corresponding to a second subset of memory dies.

[0073] Due to the shared nature of the contact group 415 and the driver group 430, each row of command drivers of the driver group 430 may be shared by a pair of two controllers 440 in order to process and receive commands for two memory dies. For example, the lowest row of command drivers may be coupled with a controller 440 having an index of 0 and a controller 440 having an index of 8, which may correspond to a first memory die in a first subset of memory dies and a first memory die in a second subset of memory dies, respectively. The next row of drivers (e.g., the second row from the bottom) may be coupled with a controller 440 having an index of 1 and a controller 440 having an index of 9, which may correspond to a second memory die in a first subset of memory dies and a second memory die in a second subset of memory dies, respectively, and so on. Thus, each respective row driver of the driver group 430 can be coupled with a pair of respective controllers 440, wherein one controller 440 in the pair corresponds to a memory die in a first subset of memory die and the other controller 440 in the pair corresponds to a memory die in a second subset of memory die. For example, for increasing rows of respective drivers from bottom to top (e.g., in the positive y-direction), the index of each controller 440 in a pair of respective controllers 440 would increase by 1, wherein the bottom row of drivers starts with a pair of controllers 440 having indices 0 and 8 and the top row of drivers ends with a pair of controllers 440 having indices 7 and 15.

[0074] To facilitate routing each row of drivers of driver group 430 to two controllers 440 of corresponding memory dies, controllers 440 may be arranged in an alternating manner, such as Figure 4. For example, each controller 440 configured to receive commands for memory dies in a first subset of memory dies may be adjacent to a controller 440 configured to receive commands for memory dies in a second subset of memory dies, and vice versa. Thus, the controllers 440 may form an interleaving pattern between controllers associated with the first subset of memory dies and controllers associated with the second subset of memory dies.

[0075] The layout of the controller pairs (e.g., each pair corresponding to a row of respective drivers of the driver group 430) may also be arranged to facilitate routing. For example and as illustrated, the 4 pairs of controllers 440 corresponding to the upper 4 rows of drivers of the driver group 430 are arranged in descending order (e.g., the controller pairs 440 have indices 7-15, followed by indices 6-14, indices 5-13, and indices 4-12), which may reduce the crossing of routes for coupling with the corresponding upper 4 rows of drivers. Following these controller pairs, the 4 additional pairs of controllers 440 corresponding to the lower 4 rows of drivers of the driver group 430 are arranged in ascending order (e.g., the controller pairs 440 have indices 0-8, followed by indices 1-9, indices 2-10, and indices 3-11), which may reduce the crossing of routes for coupling with the corresponding lower 4 rows of drivers. The pairing of the controllers 440 may be based on the number of each subset of memory dies. For example, for the number N of memory dies per subset of memory dies (e.g., 2N memory dies total), a first pair of controllers 440 may have indices 0 and N, and these may be incremented by 1 for each pair of respective controllers 440 until all memory dies have corresponding controllers 440 (e.g., controllers 440 with indices N-1 and 2N-1). In some cases, a first pair of controllers 440 and a second pair of controllers associated with indices N / 2 and 3N / 2 may be adjacent to the center of a segment 450, and the indices may be incremented by 1 for each pair of controllers extending out (e.g., in the x-direction) from the pair of controllers adjacent to the center.

[0076] In some cases, the driver group 430 may be associated with one or more bits (e.g., pseudo channel bits) that may control which controller 440 of a pair of controllers 440 will be coupled to a corresponding memory die or which commands queued from the controller pair 440 will be executed. For example, for the lowest row of drivers, the one or more bits may be set to a first value indicating that the command is transmitted to a first memory die in a first subset of memory dies associated with the controller 440 having index 0. Alternatively, the one or more bits may be set to a second value indicating that the command is transmitted to a first memory die in a first subset of memory dies associated with the controller 440 having index 8. In some examples, arbitration of the pseudo channel bits may be based on a multiple access scheme such as clock cycle dependent access or may be based on a priority of operations (e.g., a read operation may take precedence over a write operation, or an earlier received command may be processed first). In some cases, each row of command drivers may be associated with a corresponding bit to select which controller 440 of the corresponding controller pair 440 will be coupled. Thus, driver group 430 can support receiving and sending commands to both the first subset of memory dies and the second subset of memory dies.

[0077] In some examples, the system 400 may include a set of repair blocks 445, and each repair block 445 may be common to and shared by a pair of controllers 440. For example, a single repair block 445 may be associated with performing repair operations (e.g., column repair and row repair operations) on a pair of memory dies corresponding to the controller pair (e.g., a memory die in a first subset of memory dies and a memory die in a second subset of memory dies). In some cases, the repair block set 445 may be configured to perform address swapping based on repair data received from fuses in a first set of fuses associated with the first subset of memory dies and a second set of fuses associated with the second subset of memory dies. In some examples, the fuses may store repair data associated with a single memory die. Alternatively, there may be an entire set of fuses, and a subset of the entire set of fuses may store data for a pair of memory dies (e.g., a first memory die in a first subset of memory dies and a first memory die in a second subset of memory dies). In some examples, the repair block 445 can store repair data received in a memory array (e.g., a volatile memory array, such as an SRAM array) of the repair block 445. By sharing the repair block 445 between the controller pair 440, the system 400 can have a smaller size, for example, by reducing the number of repair blocks 445 and memory arrays associated with the repair blocks 445.

[0078] To perform the address swap, the repair block 445 as part of a row repair procedure may redirect the row address from a first row of memory dies in the plurality of memory dies to a second row of memory dies based on the repair data received via the fuse. Additionally or alternatively, the repair block 445 may perform the address swap as part of a column repair procedure, which may involve redirecting the column address from a first column of memory dies in the plurality of memory dies to a second column of memory dies based on the repair data received via the fuse. In some cases, the column repair procedure may include replacing a data channel of a memory die. For example, the repair block 445 may be configured to swap a data channel (e.g., a failed data channel) of a corresponding memory die with another data channel (e.g., a spare data channel). Thus, each repair block 445 may perform a row repair procedure and a column repair procedure on at least two memory dies (e.g., a memory die in the first subset of memory dies and a memory die in the second subset of memory dies).

[0079] In some examples, the system 400 may include a processor 455 (e.g., a built-in self-test processor). The processor 455 may be coupled to each of the controllers 440 and may be operable to execute a program to test each memory die (e.g., through the corresponding controller 440) by issuing commands associated with a test program (e.g., performed in manufacturing testing). In some examples, the processor 455 may additionally or alternatively initiate or assist in executing a row repair program and a column repair program (e.g., via a repair block 445), such as by storing or providing logic associated with the row repair program and the column repair program. In some examples, the processor 455 may additionally receive repair data from the first set of fuses and the second set of fuses and may initiate a row repair program or a column repair program based on the repair data (e.g., via a corresponding repair block 445). For example, the processor 455 may send a command received from a host device to the corresponding repair block 445, and the repair block 445 may perform queuing of the received commands and execute the commands via the controller 440 in the corresponding controller pair 440 that matches the memory die associated with the command. Additionally or alternatively, the processor 455 may instruct the repair block 445 to read fuse data associated with the corresponding memory die (e.g., repair data stored in one or more fuses). In some cases, the processor 455 may additionally or alternatively execute a boot program associated with the system 400 and may perform operations associated with the boot program for each of the plurality of memory dies, which may include clearing or initializing a queue (e.g., a command queue) or a buffer (e.g., a data buffer).

[0080] In some examples, the system 400 may include a plurality of interface blocks 460 for interfacing with a host device (e.g., receiving and sending data and commands to the host device). For example, an interface block 460 designated with the letter 'D' may be referred to as a data interface block 460 for receiving or sending data from a host device, while an interface block 460 designated with the letter 'C' may be referred to as a command interface block 460 for receiving commands from a host device. Each data interface block 460 may be coupled to a corresponding data path block 435, while each command interface block 460 may be coupled to a corresponding controller 440. The plurality of interface blocks 460 may thus be arranged in a manner that facilitates coupling with corresponding data path blocks 435 or controllers 440 and may be aligned relative to corresponding components.

[0081] In some cases, the data path block 435 and the controller 440 may receive data and commands from or send data and commands to the corresponding interface block 460 via a set of multiplexers 465. For example, the multiplexer set 465 may be operable to route incoming or outgoing data from the interface block 460 to the corresponding controller 440 or data path block 435. In some cases, the processor 455 may be positioned between the multiplexers 465 and the plurality of interface blocks 460, which may facilitate operations performed by the processor 455 that may involve receiving data from a host device (e.g., boot procedures, test operations, repair operations).

[0082] Figure 5 An example of a system 500 supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The system 400 may serve as a plurality of memory dies (e.g., Figures 3A to 3C The memory die 320 described herein) and the host system (such as the memory die 320 described herein) Figures 1 to 3C The system 500 may be an interface between the host system 105, the host processor 210, the ASIC 305, or any combination thereof described herein. Figure 4 4. For example, system 500 may include a set of contacts 510-a, a set of contacts 510-b, and a set of contacts 515 within section 505 and arranged in contact block 508, a set of drivers 525-a, a set of drivers 525-b, and a set of drivers 530 within section 520, a data path block 535 within section 550, a controller 540 and a repair block 545, a processor 555, an interface block 560, and a multiplexer 565, which may be referenced herein. Figure 4 An instance of the corresponding component described.

[0083] System 500 may illustrate memory interface blocks for a fewer number of memory dies than system 400. For example, the layout of system 500 may be adjusted according to a set of parameters, which may include memory bandwidth (e.g., size), device size, number of memory dies, or any combination thereof. In this example, system 500 may be laid out to support 4 memory dies. Thus, the number of components of system 500 may be based on the number of 4 supported memory dies. For example, the number of data path blocks 535 and controllers 540 may be equal to the number of memory dies supported by system 500. Similarly, the number of other components may be adjusted accordingly, as illustrated.

[0084] In some examples, some dimensions of sections 505 and 520 may be independent of parameter sets. For example, the dimensions of sections 505 and 520 (e.g., along the x-dimension) may be independent of parameter sets and may be shared between system 500 and system 400 regardless of the number of supporting memory dies. Similarly, the size of interface block 560 may also be independent of parameter sets. In some cases, interface block 560 may be expanded to cover an area of ​​system 500 along the x-dimension, as shown.

[0085] In some examples, some components of system 500 may depend on parameter groups. For example, segment 550 may have dimensions (e.g., along the x-dimension) that are independent of the parameter group and may be the same as the dimensions of segment 505 and segment 520. However, repair block 545, controller 540, and data path block 535 may be sized to fit segment 550. Thus, a first dimension (e.g., along the x-dimension) of repair block 545, controller 540, and data path block 535 may be based on the length of segment 550 along the x-dimension, which may be based on the length of segment 505 and segment 520 along the x-dimension. Furthermore, the length of data path block 535 along the y-dimension may be based on the number of data path blocks 535. Similarly, the length of controller 540 along the y-dimension may be based on the number of controllers 540, and the length of repair block 545 along the y-dimension may be based on the number of repair blocks 545.

[0086] Thus, a layout of system 500 can be generated according to a parameter set, which can include the number of memory dies, and the components of system 500 can be resized accordingly so that the aspect ratio of one or more of the components changes based on the number of components. This can result in providing a standard or independent first dimension (e.g., a width dimension) for system 500 while modifying a second dimension (e.g., a height dimension) based on the number of memory dies to be supported.

[0087] Figure 6 An example of a contact layout 600 supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The contact layout 600 may illustrate the positioning of contacts 605 of a through silicon via, such as with reference to Figure 4 and 5 The contact group 410, contact group 415, contact group 510, and contact group 515 are described. In some cases, the contact layout 600 can include multiple rows of contacts 605 (e.g., two rows), and the contacts 605 within the contact rows 605 can be staggered, such as Figure 6 In the description.

[0088] Some contacts 605 may be associated with transmitting (e.g., receiving or sending) data to or from a memory die, and other contacts 605 may be associated with transmitting commands to or from a memory die. For example, contacts 605 positioned within region 660-a may be data contacts 605 of a first memory die and may correspond to contacts 605 within a single row of contacts of contact group 410-a, as described herein with reference to Figure 4 Additionally, contacts 605 positioned within region 665 may be command contacts 605 and may correspond to contacts within a single row of contacts of contact group 415, as described herein with reference to Figure 4 Additionally, contacts 605 positioned within region 660-b may be data contacts 605 of a second memory die and may correspond to contacts 605 within a single row of contacts of contact group 410-b, as described herein with reference to Figure 4 describe.

[0089] Within region 660-a, contact layout 600 may include section 610 containing data input or output contacts 605 (e.g., input / output DQ contacts). Contacts 605 within this section may have indices numbered from a value of 0 to a value of 31 and, in some examples, may be divided into two sections of 16 contacts 605. In some examples, contacts 605 within section 615 may be associated with a read data strobe (e.g., RDQS). In some cases, two contacts 605 of section 615 may be used for a read data strobe signal, and the other two may be spare contacts 605 (e.g., if a contact 605 used for a read data strobe signal fails). In some examples, section 620 may contain additional data input or output contacts 605 (e.g., input / output DQ contacts). Contacts 605 within segment 620 may have indexes numbered from a value of 32 to a value of 63 and, in some examples, may be divided into two segments of 16 contacts 605. In some examples, segment 625-a may contain contacts 605 associated with data transfer for an ECC procedure, and segment 630-a may contain spare data input or output contacts 605. In some cases, two of the contacts 605 within segment 630-a (e.g., the two closest to routing segment 670-a) may be unused (e.g., may be spare contacts for a spare data channel).

[0090] Within a region 665 corresponding to command contacts 605, the contact layout 600 may include a section 635 containing two contacts 605 associated with a row hammer alarm (e.g., an alarm associated with mitigating a row hammer attack). In some examples, section 640 may include contacts 605 associated with communicating row commands to a memory die (e.g., 12 contacts). Section 645 may include contacts 605 associated with clock timing. In some cases, two contacts 605 may be associated with a clock signal, and two may be spare contacts 605 (e.g., if two contacts 605 associated with a clock signal fail). Section 650 may include contacts 605 associated with communicating column commands to a memory die (e.g., 8 contacts). In some examples, section 655 may contain another two contacts 605 associated with a row hammer alarm.

[0091] In some examples, contacts 605 within region 660-b may be arranged in a manner that mirrors the arrangement of contacts 605 within region 660-a, separated by routing segments 670-b. For example, contacts 605 within segment 630-b may mirror the arrangement of contacts 605 within segment 630-a, contacts within segment 625-b may mirror the arrangement of contacts within segment 625-a, and so on.

[0092] Figure 7 A system layout 700 is shown that supports an interface layout for a stacked memory architecture according to examples disclosed herein. The system layout 700 illustrates the spacing between a plurality of memory interface blocks 705, which may be referred to herein as Figures 2 to 5 Examples of memory interface block 220, memory interface block 335, system 400, or system 500 are described.

[0093] The memory system may include multiple memory interface blocks 705. In some examples, the memory interface blocks 705 may be spaced based on spacing between the memory interface blocks 705 and other components. For example, the memory interface blocks 705 may be spaced based on spacing 710 in the x-direction. Similarly, the memory interface blocks 705 may be spaced from other components based on spacing 715 in the y-direction. For example, multiple memory dies may be stacked atop a substrate including the memory interface blocks 705 and additional circuitry (e.g., host device circuitry 725). The size of the memory interface blocks 705 may be variable (e.g., as described herein with reference to Figure 5 715 ), while maintaining the overall layout of the memory device. For example, the memory interface block 705 can increase in size (e.g., in the y-direction) to support a larger number of memory dies. The memory interface block 705 can still accommodate the pitch 715, and the overall layout can be maintained while still allowing memory interface blocks 705 of different sizes to support different numbers of memory dies.

[0094] Figure 8 A flowchart illustrating a method 800 for supporting an interface layout for a stacked memory architecture according to examples disclosed herein is shown. The operations of the method 800 may be implemented by a manufacturing system or components thereof described herein. For example, the operations of the method 800 may be implemented by reference to Figures 1 to 6 The manufacturing system described herein performs. In some examples, the manufacturing system may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally or alternatively, the manufacturing system may use dedicated hardware to perform aspects of the described functions.

[0095] At 805, the method may include receiving a set of parameters for a memory interface block (e.g., memory interface block 220, memory interface block 335, memory interface block 705), wherein the parameter set includes the number of memory dies, memory size, or a combination thereof. Operation 805 may be performed according to examples disclosed herein.

[0096] At 810, the method may include generating a layout of a host controller interface block including a plurality of interface blocks (e.g., interface block 460, interface block 560) based at least in part on the parameter set, each interface block including a first port (e.g., data interface block 460, data interface block 560) configured for data communication with the host controller and a second port (e.g., command interface block 460, command interface block 560) configured for command communication with the host controller. Operation 810 may be performed according to examples disclosed herein.

[0097] At 815, the method may include generating a layout of a memory interface block including a plurality of contact blocks (e.g., contact block 408, contact block 508) based at least in part on the parameter group, each of the plurality of contact blocks including a set of third ports (e.g., a subset of the set of contacts 410, a subset of the set of contacts 510) configured for data communication with the plurality of memory dies and fourth ports (e.g., a subset of the set of contacts 415, a subset of the set of contacts 515) configured for command communication with the plurality of memory dies, wherein the set of third ports includes a first subset of the set of third ports located in a first portion of the memory interface block and a second subset of the set of third ports located in a second portion of the memory interface block. Operation 815 may be performed according to examples disclosed herein.

[0098] At 820, the method may include generating a layout of an intermediate block including a plurality of controllers (e.g., controller 440, controller 540) and a plurality of data path blocks (e.g., data path block 435, data path block 535) between the host controller interface block and the memory interface block based at least in part on the parameter set. Operation 820 may be performed according to examples disclosed herein.

[0099] In some examples, the apparatus described herein may perform one or several methods, such as method 800. The apparatus may include features, circuitry, logic, means, or instructions (such as a non-transitory computer-readable medium storing instructions executable by a processor) for performing the following aspects of the present disclosure, or any combination thereof:

[0100] Aspect 1: A method, apparatus, or non-transitory computer-readable medium comprising operations, features, circuitry, logic, means, or instructions, or any combination thereof, for: receiving a set of parameters for a memory interface block, wherein the set of parameters comprises a number of memory dies, a memory size, or a combination thereof; generating a layout of a host controller interface block comprising a plurality of interface blocks based at least in part on the set of parameters, each interface block comprising a first port configured for data communication with a host controller and a second port configured for command communication with the host controller; generating a layout of a memory interface block comprising a plurality of contact blocks based at least in part on the set of parameters, each of the plurality of contact blocks comprising a set of third ports configured for data communication with a plurality of memory dies and a fourth port configured for command communication with the plurality of memory dies, wherein the set of third ports comprises a first subset of the set of third ports located in a first portion of the memory interface block and a second subset of the set of third ports located in a second portion of the memory interface block; and generating a layout of an intermediate block comprising a plurality of controllers and a plurality of data path blocks between the host controller interface block and the memory interface block based at least in part on the set of parameters.

[0101] Aspect 2: A method, apparatus, or non-transitory computer-readable medium according to Aspect 1, wherein generating the layout of the intermediate block further includes operations, features, circuit systems, logic, components, or instructions, or any combination thereof, for: generating the intermediate block based on a first dimension and a second dimension, wherein the first dimension is based on the set of parameters and the second dimension is independent of the set of parameters.

[0102] Aspect 3: A method, apparatus, or non-transitory computer-readable medium according to Aspect 2, wherein the number of the multiple controllers is based on the set of parameters, the number of the multiple data path blocks is based on the set of parameters, and the layout for generating the intermediate block further includes operations, features, circuit systems, logic, components, or instructions, or any combination thereof, for: generating each of the multiple controllers based on the first dimension and a third dimension, the third dimension being based on the number of the multiple controllers; and generating each of the multiple data path blocks based on the first dimension and a fourth dimension, the fourth dimension being based on the number of the multiple data path blocks.

[0103] Aspect 4: A method, apparatus, or non-transitory computer-readable medium according to any one of Aspects 1 to 3, wherein the fourth port is positioned in a third portion of the memory interface block, the third portion of the memory interface block is positioned between the first portion of the memory interface block and the second portion of the memory interface block and is adjacent to the first portion and the second portion.

[0104] Aspect 5: A method, an apparatus, or a non-transitory computer-readable medium according to any one of Aspects 1 to 4, wherein the plurality of data path blocks include a first subset of the plurality of data path blocks positioned in a first portion of the intermediate block and a second subset of the plurality of data path blocks positioned in a second portion of the intermediate block, and the plurality of controllers are positioned in a third portion of the intermediate block, the third portion of the intermediate block being positioned between the first portion of the intermediate block and the second portion of the intermediate block and adjacent to the first portion and the second portion.

[0105] Aspect 6: A method, apparatus, or non-transitory computer-readable medium according to any one of Aspects 1 to 5, wherein a first subset of the multiple controllers is configured for command communication with a first subset of the multiple memory dies and a second subset of the multiple controllers is configured for command communication with a second subset of the multiple memory dies, each controller in the first subset of the multiple controllers is adjacent to a corresponding controller in the second subset of the multiple controllers and forms an interleaved pattern.

[0106] It should be noted that the methods described herein describe possible implementations, and that the operations and steps may be rearranged or otherwise modified and other implementations are possible. Furthermore, portions from two or more of the methods may be combined.

[0107] An apparatus is described. The following provides an overview of aspects of the apparatus described herein:

[0108] Aspect 7: An apparatus comprising: a plurality of interface blocks, each of the plurality of interface blocks comprising a first port configured for data communication with a host controller and a second port configured for command communication with the host controller; a first group of controllers, each of the first group of controllers being coupled to one of a first subset of the plurality of interface blocks; a second group of controllers, each of the second group of controllers being coupled to one of a second subset of the plurality of interface blocks; and a plurality of contact blocks, each of the plurality of contact blocks comprising a set of third ports configured for data communication with a plurality of memory dies and a fourth port configured for command communication with the plurality of memory dies, wherein for each of the plurality of contact blocks, each third port of the set of third ports is coupled to one of the first group of controllers or one of the second group of controllers, and each of the fourth ports is shared by the one of the first group of controllers and the one of the second group of controllers.

[0109] Aspect 8: The apparatus of aspect 7, wherein each of the plurality of contact blocks is operable to couple a respective controller of the first set of controllers with a respective first memory die of the plurality of memory die via the fourth port and a respective third port of the set of third ports.

[0110] Aspect 9: An apparatus according to Aspect 8, wherein each of the plurality of contact blocks is operable to couple a corresponding controller in the second group of controllers with a corresponding second memory die in the plurality of memory dies via the fourth port and a corresponding third port in the set of third ports, the corresponding second memory die being different from the corresponding first memory die.

[0111] Aspect 10: An apparatus according to Aspect 9, wherein coupling the first controller with a first memory die in a first subset of the plurality of memory die via a fourth port in the fourth port is based on a first bit associated with the fourth port containing a first value, and coupling the second controller with a second memory die in a second subset of the plurality of memory die via the fourth port is based on the first bit containing a second value.

[0112] Aspect 11: An apparatus according to any one of Aspects 7 to 10, further comprising: a first set of data path blocks coupled to a first subset of the plurality of memory dies and a second set of data path blocks coupled to a second subset of the plurality of memory dies, wherein each of the first set of data path blocks and the second set of data path blocks is configured to perform an error correction procedure on data communicated between the host controller and the corresponding memory die.

[0113] Aspect 12: An apparatus according to Aspect 11, wherein the first group of data path blocks is positioned in a first part of an intermediate block, the second group of data path blocks is positioned in a second part of the intermediate block, and the first group of controllers and the second group of controllers are positioned in a third part of the intermediate block, the third part being positioned between the first part and the second part and adjacent to the first part and the second part.

[0114] Aspect 13: The apparatus of aspect 12, wherein each controller in the first set of controllers is adjacent to a controller in the second set of controllers.

[0115] Aspect 14: The device according to any one of Aspects 7 to 13 further comprises: a group of repair blocks, each repair block in the group of repair blocks is configured to perform a repair program on a group of memory dies among the multiple memory dies coupled to a fourth port, and the fourth port is shared by a corresponding controller in the first group of controllers and a corresponding controller in the second group of controllers.

[0116] Aspect 15: The device according to any one of Aspects 7 to 14 further comprises: a processor coupled to the multiple interface blocks and configured to execute a boot program of the device, the processor being configured to receive repair data from one or more fuses via the first group of controllers or the second group of controllers, the repair data being associated with a repair program of the multiple memory dies.

[0117] Aspect 16: The apparatus of aspect 15, wherein the processor is configured to initiate a procedure to redirect, via the first set of controllers or the second set of controllers, a rank associated with a memory die in the plurality of memory dies from a first rank of the memory dies to a second rank of the memory dies.

[0118] Aspect 17: An apparatus according to any one of Aspects 7 to 16, wherein: each third port in the set of third ports includes a plurality of contacts configured to couple with one or more through-silicon vias associated with the plurality of memory dies; and each of the fourth ports includes a driver configured to receive commands associated with a memory die in the plurality of memory dies via the one of the first set of controllers and the one of the second set of controllers.

[0119] An apparatus is described. The following provides an overview of aspects of the apparatus described herein:

[0120] Aspect 18: A device comprising: a first group of controllers, each corresponding controller in the first group of controllers is coupled to a corresponding memory die in a first group of memory dies via a first data port and a command port of a corresponding interface block in a group of interface blocks; a second group of controllers, each corresponding controller in the second group of controllers is coupled to a corresponding memory die in a second group of memory dies via a second data port and the command port of the corresponding interface block; and a group of repair blocks, each corresponding repair block in the group of repair blocks is configured to perform address swapping based on receiving repair data from a first group of fuses via the corresponding command port, the repair data being associated with the first group of memory dies and a second group of fuses being associated with the second group of memory dies, wherein each corresponding repair block in the group of repair blocks includes a corresponding memory array for storing the repair data.

[0121] Aspect 19: An apparatus according to Aspect 18, wherein, in order to perform address swapping, each corresponding repair block in the set of repair blocks is configured to: redirect the row address from the first row of the corresponding first memory die in the first group of memory die to the second row of the corresponding first memory die based on the repair data received from the corresponding first group of fuses; and redirect the row address from the third row of the corresponding second memory die in the second group of memory die to the fourth row of the corresponding second memory die based on the repair data received from the corresponding second fuses.

[0122] Aspect 20: An apparatus according to any one of Aspects 18 to 19, wherein, in order to perform address swapping, each corresponding repair block in the set of repair blocks is configured to: redirect the column address from the first column of the corresponding first memory die in the first group of memory die to the second column of the corresponding first memory die based on the repair data received from the corresponding first group of fuses via the corresponding command port; and redirect the column address from the third column of the corresponding second memory die in the second group of memory die to the fourth column of the corresponding second memory die based on the repair data received from the corresponding second group of fuses via the corresponding command port.

[0123] Aspect 21: The apparatus of any of aspects 18 to 20, wherein each respective repair block in the set of repair blocks includes a respective memory array for storing the repair data.

[0124] The information and signals described herein may be represented using any of a variety of different techniques and technologies. For example, data, instructions, commands, information, signals, bits, or signaling symbols that may be referenced throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof. Some figures may illustrate a signal as a single signal; however, a signal may represent a signal bus, where the bus may have various bit widths.

[0125] The terms "electronic communication," "conductive contact," "connection," and "coupling" may refer to a relationship between components that supports the flow of signals between the components. Components are considered to be in electronic communication (e.g., conductive contact, connection, coupling) with each other if there is any electrical path (e.g., conductive path) between the components that can support the flow of signals (e.g., charge, current, voltage) between the components at any time. At any given time, the conductive path between components that are in electronic communication (e.g., conductive contact, connection, coupling) with each other may be an open circuit or a closed circuit based on the operation of the device that includes the connected components. The conductive path between the connected components may be a direct conductive path between the components, or the conductive path between the connected components may be an indirect conductive path that may include intermediate components (e.g., switches, transistors, or other components). In some examples, the flow of signals between the connected components may be interrupted for a period of time, for example, using one or more intermediate components (e.g., switches or transistors).

[0126] The term "coupled" (e.g., "electrically coupled") may refer to a condition that transitions from an open-circuit relationship between components, where signals cannot currently be communicated between the components (e.g., via conductive paths), to a closed-circuit relationship between the components, where signals can be communicated between the components (e.g., via conductive paths). When a component, such as a controller, couples other components together, the component causes a change that allows signals to flow between the other components via conductive paths that previously did not allow signals to flow.

[0127] The term "isolation" refers to a relationship between components where a signal cannot currently flow between the components. Components are isolated from one another if an open circuit exists between the components. For example, when a switch positioned between two components is opened, the components separated by the switch are isolated from one another. When a controller isolates two components, the controller causes a change that prevents a signal from flowing between the components using a conductive path that previously permitted the signal to flow.

[0128] As used herein, the terms "layer" and "step" refer to an organization (e.g., layer, sheet) of a geometric structure (e.g., relative to a substrate). Each layer or step may have three dimensions (e.g., height, width, and depth) and may cover at least a portion of a surface. For example, a layer or step may be a three-dimensional structure in which two dimensions are greater than the third dimension, such as a film. A layer or step may include different elements, components, or materials. In some examples, a layer or step may be composed of two or more sub-layers or sub-steps.

[0129] The devices discussed herein, including memory arrays, may be formed on a semiconductor substrate, such as silicon, germanium, silicon-germanium alloys, gallium arsenide, gallium nitride, etc. In some examples, the substrate is a semiconductor wafer. In other examples, the substrate may be a silicon-on-insulator (SOI) substrate, such as silicon-on-glass (SOG) or silicon-on-sapphire (SOP), or an epitaxial layer of semiconductor material on another substrate. The conductivity of the substrate or a sub-region of the substrate may be controlled by doping with various chemical species, including but not limited to phosphorus, boron, or arsenic. Doping may be performed by ion implantation during the initial formation or growth of the substrate or by any other doping method.

[0130] The switch components (e.g., transistors) discussed herein may represent field effect transistors (FETs) and may include a three-terminal component including a source (e.g., a source terminal), a drain (e.g., a drain terminal), and a gate (e.g., a gate terminal). The terminals may be connected to other electronic components by conductive materials (e.g., metals, alloys). The source and drain may be conductive and may include doped (e.g., heavily doped, degenerate) semiconductor regions. The source and drain may be separated by a doped (e.g., lightly doped) semiconductor region or channel. If the channel is n-type (e.g., most carriers are electrons), then the FET may be referred to as an n-type FET. If the channel is p-type (e.g., most carriers are holes), then the FET may be referred to as a p-type FET. The channel may be covered by an insulating gate oxide. Channel conductivity may be controlled by applying a voltage to the gate. For example, applying a positive voltage or a negative voltage to an n-type FET or a p-type FET, respectively, may cause the channel to become conductive. When a voltage greater than or equal to the threshold voltage of the transistor is applied to the transistor gate, the transistor may be "turned on" or "activated." A transistor may be turned “off” or “deactivated” when a voltage less than the transistor's threshold voltage is applied to the transistor gate.

[0131] The description set forth herein describes example configurations in conjunction with the accompanying drawings and does not represent all examples that may be implemented or within the scope of the claims. The term "exemplary" as used herein means "serving as an example, instance, or illustration" rather than "preferred" or "superior to other examples". The "Detailed Description" includes specific details for providing an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some examples, well-known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0132] In the accompanying drawings, similar components or features may have the same reference label. In addition, various components of the same type may be distinguished by following the reference label with a dash and a second label that distinguishes the similar components. If only the first reference label is used in the specification, the description applies to any of the similar components having the same first reference label, regardless of the second reference label.

[0133] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions (e.g., code) on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope of the present disclosure and the appended claims. For example, due to the nature of software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Features implementing the functions may also be physically located at various locations, including being distributed so that portions of the functions are implemented at different physical locations.

[0134] For example, the various descriptive blocks and modules described in connection with the present disclosure may be implemented or executed with a processor designed to perform the functions described herein, such as a DSP, ASIC, FPGA, discrete gate logic, discrete transistor logic, discrete hardware components, other programmable logic devices, or any combination thereof. A processor may be an example of a microprocessor, a controller, a microcontroller, a state machine, or any type of processor. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0135] As used herein (including in the claims), "or" used in a list of items (e.g., a list of items preceded by a phrase such as "at least one of" or "one or more of") indicates an inclusive list, so that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Moreover, as used herein, the phrase "based on" should not be interpreted as referring to a closed set of conditions. For example, an exemplary step described as "based on condition A" may be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "based at least in part on."

[0136] As used herein (including in the claims), the article "a" before a noun is open-ended and should be understood to refer to "at least one" of those nouns or "one or more" of those nouns. Therefore, the terms "one", "at least one", "one or more", and "at least one of one or more" are interchangeable. For example, if a claim recites "a component" that performs one or more functions, each of the individual functions may be performed by a single component or any combination of multiple components. Therefore, the term "a component" having a characteristic or performing a function may refer to "at least one of one or more components" having a specific characteristic or performing a specific function. The subsequent use of the term "the / said" to refer to the component introduced with the article "a" may refer to any or all of the one or more components. For example, a component introduced with the article "a" may be understood to mean "one or more components", and the subsequent reference to "the component" in the claim may be understood to be equivalent to referring to "at least one of one or more components". Similarly, a component introduced as "one or more components" subsequently referenced using the term "the / said" may refer to any or all of the one or more components. For example, a subsequent reference to "one or more components" in a claim may be understood to be equivalent to referring to "at least one of the one or more components."

[0137] Computer-readable media include both non-transitory computer storage media and communication media, including any media that facilitates the transfer of a computer program from one location to another. Non-transitory storage media may be any available media that can be accessed by a computer. For example, but not limited to, non-transitory computer-readable media may include RAM, ROM, electrically erasable programmable read-only memory (EEPROM), compact disk (CD) ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices or any other non-transitory media that can be used to carry or store desired program code components in the form of instructions or data structures and can be accessed by a computer or processor. Moreover, any connection is appropriately referred to as computer-readable media. For example, if the software is transmitted from a website, server or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technology (such as infrared, radio and microwave), then coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technology (such as infrared, radio and microwave) are included in the definition of media. As used herein, disk and disc include CD, laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above are also included within the scope of computer-readable media.

[0138] The description herein is provided to enable persons skilled in the art to make or use the present disclosure. Persons skilled in the art will appreciate various modifications of the present disclosure, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Therefore, the present disclosure is not limited to the examples and designs described herein, but should be given the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A device comprising: a plurality of interface blocks, each of the plurality of interface blocks comprising a first port configured for data communication with a host controller and a second port configured for command communication with the host controller; a first set of controllers, each controller of the first set of controllers coupled to one of a first subset of the plurality of interface blocks; a second set of controllers, each controller of the second set of controllers coupled to one of a second subset of the plurality of interface blocks; and a plurality of contact blocks, each of the plurality of contact blocks comprising a set of third ports configured for data communication with a plurality of memory dies and a fourth port configured for command communication with the plurality of memory dies, wherein for each of the plurality of contact blocks, each third port in the set of third ports is coupled to one of the first group of controllers or one of the second group of controllers, and each of the fourth ports is shared by the one of the first group of controllers and the one of the second group of controllers.

2. The apparatus of claim 1 , wherein each of the plurality of contact blocks is operable to couple a respective controller of the first set of controllers with a respective first memory die of the plurality of memory die via the fourth port and a respective third port of the set of third ports.

3. The apparatus of claim 2 , wherein each of the plurality of contact blocks is operable to couple a corresponding controller in the second group of controllers with a corresponding second memory die in the plurality of memory die via the fourth port and a corresponding third port in the set of third ports, the corresponding second memory die being different from the corresponding first memory die.

4. The apparatus according to claim 3, wherein: coupling the first controller to a first memory die of the first subset of the plurality of memory die via a fourth port of the fourth ports is based on a first bit associated with the fourth port comprising a first value; and Coupling a second controller with a second memory die of a second subset of the plurality of memory die via the fourth port is based on the first bit comprising a second value.

5. The apparatus of claim 1, further comprising: A first set of data path blocks coupled to a first subset of the plurality of memory dies and a second set of data path blocks coupled to a second subset of the plurality of memory dies, wherein each of the first set of data path blocks and the second set of data path blocks is configured to perform an error correction procedure on data communicated between the host controller and the respective memory die.

6. The apparatus of claim 5 , wherein the first set of data path blocks are positioned in a first portion of an intermediate block, the second set of data path blocks are positioned in a second portion of the intermediate block, and the first set of controllers and the second set of controllers are positioned in a third portion of the intermediate block, the third portion being positioned between and adjacent to the first portion and the second portion.

7. The apparatus of claim 6, wherein each controller in the first set of controllers is adjacent to a controller in the second set of controllers.

8. The apparatus of claim 1, further comprising: A set of repair blocks, each repair block in the set of repair blocks is configured to perform a repair procedure on a set of memory dies in the plurality of memory dies coupled to a fourth port, the fourth port being shared by a corresponding controller in the first set of controllers and a corresponding controller in the second set of controllers.

9. The apparatus of claim 1, further comprising: A processor, coupled to the plurality of interface blocks, is configured to execute a boot program of the device, the processor being configured to receive repair data from one or more fuses via the first set of controllers or the second set of controllers, the repair data being associated with a repair program for the plurality of memory dies.

10. The apparatus of claim 9, wherein the processor is configured to initiate a program to redirect, via the first set of controllers or the second set of controllers, a rank associated with a memory die in the plurality of memory dies from a first rank of the memory dies to a second rank of the memory dies.

11. The apparatus of claim 1, wherein: Each third port of the set of third ports includes a plurality of contacts configured to couple with one or more through silicon vias associated with the plurality of memory dies; and Each of the fourth ports includes a driver configured to receive commands associated with a memory die of the plurality of memory dies via the one of the first set of controllers and the one of the second set of controllers.

12. A device comprising: a first set of controllers, each respective controller of the first set of controllers coupled to a respective memory die of a first set of memory die via a first data port and a command port of a respective interface block of a set of interface blocks; a second set of controllers, each respective controller of the second set of controllers coupled to a respective memory die of a second set of memory die via a second data port of the respective interface block and the command port; and A set of repair blocks, each respective repair block in the set of repair blocks being configured to perform an address swap based on receiving repair data from a first set of fuses via the respective command port, the repair data being associated with the first set of memory dies and a second set of fuses being associated with the second set of memory dies, wherein each respective repair block in the set of repair blocks includes a respective memory array for storing the repair data.

13. The apparatus of claim 12, wherein to perform address swapping, each respective repair block in the set of repair blocks is configured to: redirecting a row address from a first row of a corresponding first memory die in the first group of memory die to a second row of the corresponding first memory die based on the repair data received from the corresponding first set of fuses; and A row address is redirected from a third row of a corresponding second memory die in the second group of memory die to a fourth row of the corresponding second memory die based on the repair data received from the corresponding second fuse.

14. The apparatus of claim 12, wherein to perform address swapping, each respective repair block in the set of repair blocks is configured to: redirecting a column address from a first column of a corresponding first memory die in the first group of memory die to a second column of the corresponding first memory die based on the repair data received from the corresponding first set of fuses via the corresponding command port; and A column address is redirected from a third column of a corresponding second memory die in the second group of memory die to a fourth column of the corresponding second memory die based on the repair data received from the corresponding second set of fuses via the corresponding command port.

15. The apparatus of claim 12, wherein each respective repair block in the set of repair blocks comprises a respective memory array for storing the repair data.

16. A method comprising: receiving a set of parameters for a memory interface block, wherein the set of parameters includes a number of memory dies, a memory size, or a combination thereof; generating a layout of a host controller interface block comprising a plurality of interface blocks based at least in part on the set of parameters, each interface block comprising a first port configured for data communications with a host controller and a second port configured for command communications with the host controller; generating a layout of a section including a plurality of contact blocks based at least in part on the set of parameters, each of the plurality of contact blocks including a set of third ports configured for data communications with a plurality of memory dies and a fourth port configured for command communications with the plurality of memory dies, wherein the set of third ports includes a first subset of the set of third ports located in a first portion of the memory interface block and a second subset of the set of third ports located in a second portion of the memory interface block; and A layout of an intermediate block including a plurality of controllers and a plurality of data path blocks between the host controller interface block and the memory interface block is generated based at least in part on the set of parameters.

17. The method of claim 16, wherein generating the layout of the intermediate block further comprises: The intermediate block is generated based on a first dimension and a second dimension, wherein the first dimension is based on the set of parameters and the second dimension is independent of the set of parameters.

18. The method of claim 17, wherein the number of the plurality of controllers is based on the set of parameters, the number of the plurality of datapath blocks is based on the set of parameters, and generating the layout of the intermediate blocks further comprises: generating each controller of the plurality of controllers based on the first dimension and a third dimension, the third dimension being based on the number of the plurality of controllers; and Each data path block of the plurality of data path blocks is generated based on the first dimension and a fourth dimension, the fourth dimension being based on the number of the plurality of data path blocks.

19. The method of claim 16, wherein the fourth port is positioned in a third portion of the memory interface block, the third portion of the memory interface block being positioned between the first portion of the memory interface block and the second portion of the memory interface block and adjacent to the first portion and the second portion.

20. The method of claim 16, wherein: The plurality of data path blocks include a first subset of the plurality of data path blocks positioned in a first portion of the middle block and a second subset of the plurality of data path blocks positioned in a second portion of the middle block; and The plurality of controllers are positioned in a third portion of the intermediate block, the third portion of the intermediate block being positioned between the first portion of the intermediate block and the second portion of the intermediate block and adjacent to the first portion and the second portion.

21. The method of claim 16, wherein a first subset of the plurality of controllers is configured for command communication with a first subset of the plurality of memory dies and a second subset of the plurality of controllers is configured for command communication with a second subset of the plurality of memory dies, each controller in the first subset of the plurality of controllers being adjacent to a corresponding controller in the second subset of the plurality of controllers and forming an interleaved pattern.