Matrix Semiconductor, Inc.

Rambus Inc.

Sandisk Technologies Inc.

Sandisk 3d LLC

J James Tringali

Christopher S Moore

Derek Bosch

Daniel C Steere

Frederick Abbott Ware

Roy E Scheuerlein

Ely K Tsern

Mark G Johnson

James E Schneider

Alper Ilkbahar

Roger March

David Russell Friedman

Sergey Anatolievich Gorobets

Brent Steven Haukness

Thomas H Lee

Shai Traister

P Michael Farmwald

Yosief Ataklti

Hongzhong Zheng

John Eric Linstadt

Trung Am Diep

Eric Linstadt

Colm P Lysaght

A buffer/interface device of the memory node may read and compress blocks of data (e.g., pages). When a memory buffer device compresses a block of data, it may keep storing the original uncompressed version in the original memory location (e.g., physical memory page). In this manner, an access directed to the block of data may be satisfied with the uncompressed version retrieved from the original memory location (e.g., physical memory page) without having to perform a decompression operation. As memory space is needed for other purposes (e.g., for an uncompressed copy of a recently decompressed block or as host allocated memory occupies more space), the original uncompressed versions of blocks (pages) that have not been accessed relatively recently (e.g., relative to other kept original uncompressed versions) may be evicted and replaced by other blocks of data (e.g., either compressed or uncompressed).

Page table entries for uncompressed page caching

The embodiments described herein describe technologies for non-volatile memory persistence in a multi-tiered memory system including two or more memory technologies for volatile memory and non-volatile memory.

High performance persistent memory

A method of operating a memory device that includes groups of memory cells is presented. The groups include a first group of memory cells. Each one of the groups has a respective physical address and is initially associated with a respective logical address. The device also includes an additional group of memory cells that has a physical address but is not initially associated with a logical address. In the method, a difference in the future endurance between the first group of memory cells and the additional group of memory cells is identified. When the difference in the future endurance between the first group and the additional group exceeds a predetermined threshold difference, the association between the first group and the logical address initially associated with the first group is ended and the additional group is associated with the logical address that was initially associated with the first group.

Remapping memory cells based on future endurance measurements

Disclosed is a memory including a plurality of resistive change memory cells, including at least a first group and a second group of the memory cells and a comparison circuit configured to conduct a direct relative comparison of a remaining endurance of the first group of memory cells to a remaining endurance of the second group of memory cells.

Direct relative measurement of memory durability

The variable latency associated with flash memory due to background data integrity operations is managed in order to allow the flash memory to be used in isochronous systems. A system processor is notified regularly of the nature and urgency of requests for time to ensure data integrity. Minimal interruptions of system processing are achieved and operation is ensured in the event of a power interruption.

Urgency and time window manipulation to accommodate unpredictable memory operations

Command cycles incorporate mechanisms to inform a host processor in advance of a need to service the memory so that the host can respond when it suits the host, but in time for the service to be performed before a catastrophic failure. The regular host cycle need not be interrupted for such notification.

Managing processing delays in an isochronous system

A digital storage system is coupled to a write-once memory array. File delete commands are implemented by over-writing a destructive digital pattern to at least a portion of the memory cells associated with the file to be deleted. One disclosed system alters the manner in which a file delete command is implemented, depending upon whether the file is stored in a write-once memory or in a re-writable memory.

Method for deleting stored digital data from write-once memory device

The preferred embodiments described herein provide a method for reading data in a write-once memory device using a write-many file system. In one preferred embodiment, data traffic between a data storage device and a write-once memory device is redirected so that file system structures of a write-many file system do not overwrite previously-stored file system structures. Data traffic between the write-once storage device and a data reading device is also redirected so that a current file system structure of the write-many file system is provided to the data reading device instead of an out-of- date file system structure. In another preferred embodiment, a non-volatile write-many memory array is provided in the write-once memory device to store file system structures of a write-many file system. With these preferred embodiments, data stored during multiple sessions using a write-once file system can be read by a write-many file system, thereby increasing the memory device's interoperability among existing data reading devices. Other preferred embodiments are provided, and each of the preferred embodiments described herein can be used alone or in combination with one another.

Method for reading data in a write-once memory device using a write-many file system

The preferred embodiments described herein provide a memory device and method for storing and reading a file system structure in a write-once memory array. In one preferred embodiment, a plurality of bits representing a file system structure is inverted and stored in a write-once memory array. When the inverted plurality of bits is read from the memory array, the bits are inverted to provide the file system structure bits in their original, non-inverted configuration. With this preferred embodiment, a file system structure can be updated to reflect data stored in the memory array after the file system structure was written. Other preferred embodiments are provided, and each of the preferred embodiments described herein can be used alone or in combination with one another.

Memory device and method for storing and reading a file system structure in a write-once memory array

The preferred embodiments described herein provide a write-many memory device and method for limiting a number of writes to the write-many memory device. In one preferred embodiment, a write-many memory device is provided comprising a plurality of blocks of memory, each block being limited to N number of writes. Data can be stored in a block of memory only if there has been fewer than N number of writes to the block. In another preferred embodiment, a write-many memory device is provided comprising a plurality of blocks of memory, wherein each block comprises a first sideband field storing data indicating whether the block is free and a second sideband field storing data indicating how many times the block has been written into. The first and second sideband fields are used in a method for limiting a number of writes to the write-many memory device. Other preferred embodiments are provided, and each of the preferred embodiments can be used alone or in combination with one another.

Write-many memory device and method for limiting a number of writes to the write-many memory device

The preferred embodiments described herein provide a memory device and method for storing and reading data in a write-once memory array. In one preferred embodiment, a plurality of bits representing data is inverted and stored in a write-once memory array. When the inverted plurality of bits is read from the memory array, the bits are inverted to provide the data in its original, non-inverted configuration. By storing data bits in an inverted form, the initial, un-programmed digital state of the memory array is redefined as the alternative, programmed digital state. Other preferred embodiments are provided, and each of the preferred embodiments described herein can be used alone or in combination with one another. For example, the embodiments in which data bits are inverted can be used alone or in combination with the embodiments in which data is redirected.

Memory device and method for storing and reading data in a write-once memory array

The preferred embodiments described herein relate to a redundant memory structure using bad bit pointers. In one preferred embodiment, data is written in a first plurality of memory cells, and an error is detected in writing data in one of the memory cells. In response to the detected error, a pointer is written in a second plurality of memory cells, the pointer identifying which memory cell in the first plurality of memory cells contains the error. During a read operation, the data is read from the first plurality of memory cells, and the pointer is read from the second plurality of memory cells. From the pointer, the memory cell containing the error is identified, and the error is corrected. Other preferred embodiments are provided, and each of the preferred embodiments can be used alone or in combination with one another.

Growing community of inventors

Los Altos, CA, United States of America

J James Tringali