Micron Technology Incorporated

Western Digital Technologies, Inc.

Jameer Mulani

Nitul Gohain

Anindya Rai

Kapil Sundrani

Jonathan Scott Parry

Giuseppe Cariello

Amiya Banerjee

Rakeshkumar Dayabhai Vaghasiya

Dhruv Chauhan

Anil Sindhi

Devanathan Balasundaram

Saugata Das Purkayastha

Jotiba Koparde

Techniques for memory operations are described. Indications of temperature levels at a memory device may be received, where each of the indications may be associated with a respective time point. Based on an indicated temperature level satisfying a first threshold, a derivative of a temperature of the memory device may be calculated using the indicated temperature levels. Based on calculating the derivative, a determination as to whether the derivative satisfies a second threshold may be determined. If the derivative satisfies the second threshold, operations for accessing the memory device may be modified. A second derivative of the temperature of the memory device may similarly be calculated and compared against a third threshold based on the indicated temperature level satisfying the first threshold. If the second derivative satisfies the third threshold, operations for accessing the memory device may be modified by a different amount.

Modifying access operations based on temperature projections

Methods, systems, and devices to enhance read performance for memory data word decoding using power allocation based on error pattern detection in both QLC and TLC in both QLC and TLC products are described. A plurality of data words may be processed using a first decoder engine of a decoder of a memory device according to a first power setting. The decoder may detect a pattern of errors in the plurality of data words. The decoder may further communicate a status signal based on detecting the pattern of errors. The resource manager may allocate based on the status signal, a second amount of power credits to the decoder. The decoder may process a portion of the plurality of data words using a second decoder engine according to the second amount of power credits.

Enhanced read performance for memory data word decoding using power allocation based on error pattern detection

Methods, systems, and devices for multi-level cell maintenance operations are described. A controller of a memory device may perform a two-portion maintenance operation in order to transfer data from a first block of memory cells to a second block of memory cells. For example, during a first portion of the maintenance operation, the controller may read first data from the first block of memory cells and perform a first error control operation to correct the first data. The controller may store second data associated with the first error control operation to volatile memory of the memory device in response to performing the first error control operation. During a second portion of the maintenance operation, the controller may perform a second error control operation using the second data associated with the first error control operations stored to the volatile memory of the memory device.

Multi-level cell maintenance operations

Methods, systems, and devices for data layout configurations for access operations are described. The memory system may write data to a first set of memory cells using a first write operation having a first type of layout for mapping the data to physical addresses of the memory system in response to receiving a write command. The first set of memory cells may be written to as single-level cells (SLCs), multi-level cells (MLCs), or triple-level cells (TLCs). The memory system may transfer the data to a second set of memory cells of the memory system using a second write operation having the first type of layout. The second set of memory cells may be written to as quad-level cells (QLCs). The memory system may read the data from the second set of memory cells using a read operation having a second type of layout different than the first type of layout.

Data layout configurations for access operations

Methods, systems, and devices for techniques for improving host write performance during data transferring (e.g., folding) are described. A memory system may determine to transfer first data from one or more source data blocks of the memory system to one or more destination data blocks, where the source data blocks and the destination data blocks are associated with one or more memory dies of a set of memory dies of the memory system. The memory system may also receive, from a host system, a command to write second data to a first memory die of the one or more memory dies, and write, concurrent with transferring the first data, the second data to a second memory die of the set of memory dies different than the one or more memory dies based on the transfer of the first data being associated with the first memory die.

Techniques for improving host write performance during data folding by writing to another die

Methods, systems, and devices for techniques for concurrent host system access and data folding are described. A memory system may determine to transfer (e.g., fold) data from a set of source data blocks to a set of destination data blocks. The memory system may receive a command to access a first source data block of the set of source data blocks concurrent with the data transfer. The memory system may generate a first order for transferring respective portions of the data that is based on a second order associated with a sequential read of the data from the set of destination data blocks. Based on the accessing the first source data block being concurrent with the data transfer, the first order may exclude a first portion of the data from the first source data block such that the data transfer and the accessing may be concurrently performed.

Techniques for concurrent host system access and data folding

Methods, systems, and devices for managing single-level and multi-level programming operations are described. During a first duration, a first set of resources of a memory system may be configured for single-level operations and a second set of resources of a memory system may be configured to multi-level operations. Also, during the first duration, a first set of data may be received and written to a first virtual block that spans the first set of resources in accordance with a single-level programming operation. Additionally, during the first duration, a second set of data may be transferred from the first set of resources or the second set of resources to a second virtual block that spans the second set of resources in accordance with a multi-level programming operation.

Managing single-level and multi-level programming operations

Methods, systems, and devices for determining locations in memory for boot-up code are described. An indication of one or more timeout durations for a boot sequence is received. Information for the boot sequence is stored in one or more memory cells based on the one or more timeout durations, where the one or more memory cells is selected based on a read latency, an error rate, or a storage-level of the one or more memory cells with relation to the indicated one or more timeout durations. The information for the boot sequence stored in the one or more memory cells is accessed based on an initialization of the boot sequence.

Determining locations in NAND memory for boot-up code

A memory system may include a volatile memory that is configured to store an address data structure that includes a plurality of logical-to-physical address entries. The address data structure may be stored across a plurality of bank groups of the volatile memory. A controller may be configured to store consecutive logical-to-physical address entries across different bank groups. In turn, during read and write operations for data sets associated with consecutive logical addresses, read requests for physical addresses where the data sets are stored may be sent to multiple bank groups and processed by the multiple banks in parallel.

Distribution of logical-to-physical address entries across multiple memory areas

Distribution of logical-to-physical address entries across bank groups

Apparatuses and techniques are provided for switching a solid-state device (SSD) between a traditional SSD mode and an open-channel SSD (OCSSD) mode. In one aspect, a set of commands are defined for communicating different types of data from a Flash Translation Layer (FTL) between the host and SSD. The commands can include different predetermined sets of bits which carry different types of FTL data in a standardized format. The commands can be transmitted using reserved data words in an interface specification which interfaces the host to the SSD. The commands can include commands to transfer a logical-to-physical address table, a validity bitmap and a wear table. A switch mode command can include a bit indicating whether the mode is to be switched from traditional SSD to OCSSD, or from OCSSD to traditional SSD.

Method to switch between traditional SSD and open-channel SSD without data loss

A method and apparatus are provided to divide a logical to physical table into multiple parts, one part in a first fast memory and a second part in a second non-volatile memory, wherein an algorithm may be used in the division.

System and method to improve input output command latency by dynamic size logical to physical caching

Technology is described herein that provides a partial reset of a non-volatile memory controller. In one aspect, a non-volatile memory controller persists memory addresses of I/O queues across a partial reset of the non-volatile memory controller. The non-volatile memory controller may also persist a mapping between each I/O submission queue and a corresponding I/O completion queue across the partial reset. Persisting the addresses of the I/O queues and/or mappings alleviates the need for a host system and non-volatile memory controller to perform a lengthy process of sharing the addresses of the I/O queues and/or mappings.

Growing community of inventors

Bengaluru, India

Jameer Mulani