Micron Technology Incorporated

Lodestar Licensing Group LLC

Xinghui Duan

Eric Kwok Fung Yuen

Giuseppe D'Eliseo

Massimo Iaculo

Giuseppe Ferrari

Xu Zhang

Guan Zhong Wang

Lalla Fatima Drissi

Guanzhong Wang

Zhao Cui

Luigi Esposito

Lucia Santojanni

Zhong Xian Li

Xing Wang

Huachen Li

Tian Liang

Zhi Ping Yu

Hua Chen Li

David Aaron Palmer

Bin Zhao

Massimo Zucchinali

Jianxiong Huang

A computing system () having a storage system that includes a storage device () and a host device (), where the host device () is configured to issue memory access commands to the storage device (). The computing system () further includes a prediction system () comprising processing circuitry that is configured to perform operations that cause the prediction system () to identify one or more components of the storage system () that limit random rad performance of the storage system (). The operations further cause the prediction system () to obtain characterization data that is indicative of the impact of the one or more components on random read performance and generate a model based on the characterization data to predict random read performance of the storage system (). The operations additionally cause the prediction system () to execute the model in a simulation of the storage system () to generate a random read performance parameter for the storage system ().

Mobile storage random read performance estimation enhancements

Apparatus and methods are disclosed, including a sequential mapping table located within a flash memory array of a flash memory device. Selected examples include firmware in the flash memory device to load the sequential mapping table into a cache upon power and perform read and write operations using the sequential mapping table. Selected examples include firmware in the flash memory device to store an updated sequential mapping table into the flash memory array upon power down of the flash memory device.

Memory mapping device and method

Devices and techniques for NAND logical-to-physical table region tracking are described herein. A write request, including a logical page and data to be written at the logical page, is received at a controller of a NAND device. The NAND controller may then establish an entry in a logical-to-physical (L2P) mapping table between the logical page and a physical page of a physical block of the NAND device to which the data is written. Here, the entry may be in a region of the L2P mapping table that is one of multiple regions. An indication of the region may be written in a data structure corresponding to the physical block.

NAND logical-to-physical table region tracking

Devices and techniques for improving memory access operations of a memory device are provided. In an example, a method can include loading multiple LBA-to-physical address (L2P) regions of an L2P table from memory arrays of the memory device to a mapping cache in response to determining the LBA of the memory access command is not within the L2P region including of a mapping cache. When the memory access command is a sequential command, the multiple L2P regions loaded to the mapping cache can provide improved memory access performance.

Pre-load techniques for improved sequential memory access in a memory device

Devices and techniques for variable width superblock addressing are described herein. A superblock width, specified in number of planes, is obtained. A superblock entry is created in a translation table of a NAND device. Here, the superblock entry may include a set of blocks, from the NAND device, that have the same block indexes across multiple die of the NAND device. The number of unique block indexes are equal to the number of planes and in different planes. A request, received from a requesting entity, is performed using the superblock entry. Performing the request includes providing a single instruction to multiple die of the NAND device and multiple data segments. Here, a data segment corresponds to a block in the set of blocks specified by a tuple of block index and die. A result of the request is then returned to the requesting entity.

Variable width superblock addressing

Devices and techniques for data removal marking in a memory device are described herein. A delete command can be received at the memory device. A count of data portions in the delete command can be compared to determine whether the count is below a threshold. In response to determining that the count of data portions is below the threshold, the data portions can be written to a buffer. When a buffer full event is detected, a segment of an L2P data structure can be loaded into working memory of the memory device. Then, each record in the segment of the L2P data structure that has a corresponding entry in the buffer can be updated to mark the data as removable (e.g., invalid).

Data removal marking in a memory device

A variety of applications can include apparatus and/or methods of operating the apparatus in which storage in the memory device is managed. An allocation can include conducting a garbage collection procedure to free up one or more blocks. In various embodiments, execution of a garbage collection procedure can be based on operation of two tables with respect to a logical to physical mapping table split into logical to physical mapping table regions saved in the memory device. The first table can maintain counts of valid pages in blocks for a logical to physical mapping table region. The second table can include bits to identify logical to physical mapping table regions involved in the garbage collection procedure based on the entries in the first table. Search of the second table can determine logical to physical mapping table regions involved in the garbage collection. Additional apparatus, systems, and methods are disclosed.

Scheme to improve efficiency of device garbage collection in memory devices

Devices and techniques for controlling NAND operation latency are described herein. A controlled can receive a write request. The controller can then calculate a number of garbage collection operations to perform on a physical block that is closed. Here, the calculation includes adding a logical-to-physical (L2P) region search ratio to a cadence calculation for garbage collection. Garbage collection operations can be performed on the physical block in accordance with the calculated number of garbage collection operations to perform. Then, the controller can perform the write request in response to completing the calculated number of garbage collection operations.

Controlling NAND operation latency

Disclosed in some examples are memory devices which feature intelligent adjustments to SLC cache configurations that balances memory cell lifetime with performance. The size of the SLC cache can be adjusted during usage of the memory device based upon a write amplification (WA) metric of the memory device. In some examples, the size of the SLC cache can be adjusted during usage of the memory device based upon a write amplification (WA) metric of the memory device and a memory device logical saturation metric (percentage of valid user data written in the device of the total user size).

SLC cache allocation

A memory device comprises a memory array including memory cells, a communication interface to a host device, and a memory control unit operatively coupled to the memory array and the communication interface. The memory control unit is configured to store requests to access the memory in the queue, determine whether queued memory access requests are to sequential addresses of the memory array or to random addresses of the memory array, reduce an operating rate of one or more first components of the memory control unit when the queued memory access requests are to sequential addresses of the memory array, and reduce an operating rate of one or more second components of the memory control unit when the queued memory access requests are to random addresses of the memory array.

Reduce system active power based on memory usage patterns

Scheme to improve efficiency of garbage collection in cached flash translation layer

Devices and techniques for synchronizing NAND logical-to-physical table region tracking are described herein. Table region data structures for physical blocks are maintained. These structures include logical-to-physical (L2P) mapping table portions that point to the respective physical blocks. When garbage collection is performed on a block, table region structures for that block, and another (e.g., the next block to be garbage collected) are read to avoid loading L2P table regions that do not point to the block. If any of the read portions of the L2P table region fail to point to either the block or the other block, these L2P table portions are removed from the loaded table region data structures.

Growing community of inventors

Shanghai, China

Xinghui Duan