Micron Technology Incorporated

Hyun Yoo Lee

Kang-Yong Kim

John David Porter

Suryanarayana B Tatapudi

Yang Lu

John Christopher Sancon

Keun Soo Song

Ferdinando Bedeschi

Timothy Mowry Hollis

Umberto Di Vincenzo

Huy Thanh Vo

Riccardo Muzzetto

Jongtae Kwak

Dong Soon Lim

Mark K Hadrick

Francesco Douglas Verna-Ketel

Smruti Subhash Jhaveri

Atsushi Hatakeyama

Venkatraghavan Bringivijayaraghavan

Vijayakrishna J Vankayala

Sourabh Dhir

Creston M Dupree

Akiyoshi Yamamoto

Jason McBride Brown

Described apparatuses and methods relate to a bank-level self-refresh for a memory system. A memory device can include a controller with logic that implements self-refresh operations in the memory device. The logic may perform self-refresh operations on a set of banks of the memory device that is less than all banks within the memory device. The set of banks of the memory device may be determined such that the peak current in a power distribution network of the memory device is bounded when the self-refresh operation is performed. Accordingly, bank-level self-refresh can reduce a cost of the memory device of a memory system by enabling use of a less complicated power distribution network. The bank-level self-refresh may also be implemented with different types of refresh operations. Amongst other scenarios, bank-level self-refresh can be deployed in memory-expansion environments.

Bank-level self-refresh

Methods, systems, and apparatuses related to memory operation with common clock signals are provided. A memory device or system that includes one or more memory devices may be operable with a common clock signal without a delay from switching on-die termination on or off. For example, a memory device may comprise first impedance adjustment circuitry configured to provide a first impedance to a received clock signal having a clock impedance and second impedance adjustment circuitry configured to provide a second impedance to the received clock signal. The first impedance and the second impedance may be configured to provide a combined impedance about equal to the clock impedance when the first impedance adjustment circuitry and the second impedance adjustment circuitry are connected to the received clock signal in parallel.

Memory devices and systems with parallel impedance adjustment circuitry and methods for operating the same

Described apparatuses and methods provide automated error correction with memory refresh. Memory devices can include error correction code (ECC) technology to detect or correct one or more bit-errors in data. Dynamic random-access memory (DRAM), including low-power double data rate (LPPDR) synchronous DRAM (SDRAM), performs refresh operations to maintain data stored in a memory array. A refresh operation can be a self-refresh operation or an auto-refresh operation. Described implementations can combine ECC technology with refresh operations to determine a data error with data that is being refreshed or to correct erroneous data that is being refreshed. In an example, data for a read operation is checked for errors. If an error is detected, a corresponding address can be stored. Responsive to the corresponding address being refreshed, corrected data is stored at the corresponding address in conjunction with the refresh operation. Alternatively, data being refreshed can be checked for an error.

Automated error correction with memory refresh

This document describes apparatuses and techniques for write timing compensation. In various aspects, a write timing compensator of a memory controller can apply a delay to data signals transmitted to a memory circuit based on various operating parameters, which may include voltage or latency information. In some cases, the memory controller or memory circuit powers components of write timing compensation circuitry using a dynamic power rail that scales with an operating voltage of the memory circuit. By so doing, the write timing compensator or compensation circuits may improve signal integrity of data signals communicated between the memory controller and the memory circuit at different frequencies and voltages.

Write timing compensation

Apparatuses and techniques for implementing an asymmetric read-write sequence for interconnected dies are described. The asymmetric read-write sequence refers to an asymmetric die-access sequence for read versus write operations. The 'asymmetric' term refers to a difference in an order in which data is written to or read from interface and linked dies of the interconnected die architecture. The orders for the read and write operations can be chosen such that a delay associated with transferring data between the interconnected dies occurs as data passes between the interface die and a memory controller. With asymmetric read-write burst sequences, overall timing of the read and write operations of a memory device may be impacted less, if at all, by a timing delay associated with the interconnected die architecture.

Asymmetric read-write sequence for interconnected dies

Described apparatuses and methods relate to a bank-level self-refresh for a memory system. A memory device can include logic that implements self-refresh operations in the memory device. The logic may perform self-refresh operations on a set of banks of the memory device that is less than all banks within the memory device. The set of banks of the memory device may be determined such that the peak current in a power distribution network of the memory device is bounded when the self-refresh operation is performed. Accordingly, bank-level self-refresh can reduce a cost of the memory device of a memory system by enabling use of a less complicated power distribution network. The bank-level self-refresh may also be implemented with different types of refresh operations. Amongst other scenarios, bank-level self-refresh can be deployed in memory-expansion environments.

Described apparatuses and methods facilitate bus training with multiple dice, such as multiple memory dice. A controller can communicate with multiple dice over a bus to perform bus training by sending a test pattern and receiving in return a feedback pattern indicative of the bits detected by the dice. Because suitable signal timing can differ between dice, even those using the same bus, the controller may attempt to train each die separately from the others. In some situations, however, individualized training may be infeasible. To accommodate such situations, logic associated with two or more dice can combine the bits as detected from the test pattern into a combined feedback pattern. A timing parameter that is jointly suitable for multiple dice can be determined, and the bus training may be concluded, responsive to the combined feedback pattern matching the test pattern. The multiple dice may be stacked or linked.

Bus training with interconnected dice

Described apparatuses and methods facilitate bus training with multiple dice, such as multiple memory dice. A controller can communicate with multiple dice to perform bus training by sending a test pattern and receiving in return a feedback pattern indicative of the bits detected by the dice. Because suitable signal timing can differ between dice, even those using the same bus, a controller may train each die separately from the others. In some situations, however, individualized training may be infeasible. To accommodate such situations, logic associated with two or more dice can combine, using at least one logical operation, bits as detected from the test pattern into a combined feedback pattern. A timing parameter that is jointly suitable for multiple dice can be determined, and the bus training may be concluded, responsive to the combined feedback pattern matching the test pattern. The multiple dice may be stacked or linked.

Described apparatuses and methods relate to adaptive memory registers for a memory system that may support a nondeterministic protocol. To help manage power-delivery networks in a memory system, a device includes logic that can write values to memory registers associated with memory blocks of a memory array. The values indicate whether an associated memory block has been refreshed within a refresh interval. Other logic can read the registers to determine whether a block has been refreshed. The device also includes logic that can access data indicating a row address that was most recently, or is next to be, refreshed and write values representing the address to another register. The register can be read by other logic to determine whether a wordline potentially affected by an activation-based disturb event is near to being refreshed. These techniques can reduce the number of refresh operations performed, saving power and reducing costs.

Adaptive memory registers

Described apparatuses and methods enable communication between a host device and a memory device to establish relative delays between different data lines. If data signals propagate along a bus with the same timing, simultaneous switching output (SSO) and crosstalk can adversely impact channel timing budget parameters. An example system includes an interconnect having multiple data lines that couple the host device to the memory device. In example operations, the host device can transmit to the memory device a command indicative of a phase offset between two or more data lines of the multiple data lines. The memory device can implement the command by transmitting or receiving signals via the interconnect with different relative phase offsets between data lines. The host device (e.g., a memory controller) can determine appropriate offsets for a given apparatus. Lengths of the offsets can vary. Further, a system can activate the phase offsets based on frequency.

Programmable memory timing

This document describes apparatuses and techniques for multi-rail power transition. In various aspects, a power rail controller transitions a memory circuit (e.g., of a memory die) from a first power rail to a second power rail. The power rail controller then changes a voltage of the first power rail from a first voltage to a second voltage. The power rail controller may also adjust termination impedance or a clock frequency of the memory circuit before transitioning the memory circuit to the second power rail. The power rail controller then transitions the memory circuit from the second power rail to the first power rail to enable operation of the memory circuit at the second voltage. By so doing, the power rail controller may improve the reliability of memory operations when transitioning operation of the memory circuit from the first voltage to the second voltage.

Multi-rail power transition

Described apparatuses and methods provide configurable error correction code (ECC) circuitry and schemes that can utilize a shared ECC engine between multiple memory banks of a memory, including a low-power double data rate (LPDDR) memory. A memory device may include one or more dies with multiple memory banks. The configurable ECC circuitry can use an ECC engine that services a memory bank by producing ECC values based on data stored in the memory bank when data-masking functionality is enabled. When data-masking functionality is disabled, the configurable ECC circuitry can use the shared ECC engine that services at least two memory banks by producing ECC values with a larger quantity of bits based on respective data stored in the at least two memory banks. By using the shared ECC engine responsive to the data-masking functionality being disabled, the ECC functionality can provide higher data reliability with lower die area utilization.

Multiple error correction code (ECC) engines and ECC schemes

Described apparatuses and methods are directed to equalization with pulse-amplitude modulation (PAM) signaling. As bus frequencies have increased, the time for correctly transitioning between voltage levels has decreased, which can lead to errors. Symbol decoding reliability can be improved with equalization, like with decision-feedback equalization (DFE). DFE, however, can be expensive for chip area and power usage. Therefore, instead of applying DFE to all voltage level determination paths in a receiver, DFE can be applied to a subset of such determination paths. With PAM4 signaling, for example, a DFE circuit can be coupled between an output and an input of a middle slicer. In some cases, symbol detection reliability can be maintained even with fewer DFE circuits by compressing a middle eye of the PAM4 signal. The other two eyes thus have additional headroom for expansion. Encoding schemes, impedance terminations, or reference voltage levels can be tailored accordingly.

Equalization for pulse-amplitude modulation

Described systems, apparatuses, and methods relate to volatile memories that are refreshed to maintain data integrity, such as dynamic random-access memory (DRAM) and synchronous DRAM (SDRAM). A memory device includes multiple dies, with each die having a memory array to be refreshed. The multiple dies may be interconnected via at least one inter-die bus of the memory device. A memory controller sends a command to the memory device to enter a self-refresh mode. In response, a die of the multiple dies can enter the self-refresh mode and initiate or otherwise coordinate refresh operations of the other dies. To do so, the die may transmit at least one refresh-related command to at least one other die using the inter-die bus. Multiple different signaling schemes and timing approaches are disclosed. The described inter-die refresh control principles may be implemented in energy-efficient applications, such as in low-power double data rate (LPDDR) SDRAM.

Growing community of inventors

Boise, ID, United States of America

Hyun Yoo Lee