Seagate Technology Incorporated

Arvind Sridharan

Ara Patapoutian

Bruce Douglas Buch

Deepak Sridhara

Mark A Gaertner

Ryan James Goss

Bernardo Rub

Ching He

Raman Venkataramani

Rose Shao

Raman Venkataranmani

Method and apparatus for managing data in a memory, such as a flash memory. In accordance with some embodiments, a memory has a plurality of solid-state non-volatile memory cells. A processing circuit is connected to the memory and configured to direct the execution of a plurality of read error recovery routines in response to at least one uncorrectable read error in a data set retrieved from the memory. The recovery routines are executed in a selected order based on an elapsed recovery time parameter for each of the recovery routines and an estimated probability of success of each of the recovery routines.

Variable data recovery scheme hierarchy

Method and apparatus for managing data in a memory, such as a flash memory. In accordance with some embodiments, the apparatus has a solid-state non-volatile memory and a processing circuit configured to write data to a selected location of the memory. The data are arranged in the form of multi-bit code words each comprising a user data payload and associated parity data configured to correct one or more bit errors in the user data payload. The processing circuit adjusts at least a selected one of a size of the code words, a size of the user data payloads or a size of the parity data responsive to at least a selected one of an accumulated count of access operations upon the selected location or an error rate associated with the selected location.

Memory device with variable code rate

Cells of a solid-state, non-volatile memory are assigned to one of a plurality of groups. Each group is defined by expected symbols stored in the cells in view of actual symbols read from the cells. Based on cell counts within the groups, it can be determined that a shift in a reference voltage will reduce a collective bit error rate of the cells. The shift can be applied to data access operations affecting the cells.

Shifting cell voltage based on grouping of solid-state, non-volatile memory cells

A storage medium includes at least one data unit defining a plurality of symbol-based inner code words and a plurality of symbol-based outer code words. Each symbol included in one of the inner code words is also included in one of the outer code words. A processor is configured to perform a first iteration of inner code error correction on the plurality of symbol-based inner code words, a first iteration of outer code error correction on the plurality of symbol-based outer code words and a second iteration of inner code error correction on the plurality of symbol-based inner code words. In the first iteration of outer code error corrections, at least one of the outer code words is correctable. In the second iteration of inner code error correction, at least one of the inner code words is correctable.

Iterating inner and outer codes for data recovery

A method for re-using a soft decoder involves receiving soft data and hard data from memory cells in a memory device, mapping the soft data to a first set of soft information, mapping the hard data to a second set of soft information, and using the soft decoder to decode both the first set and second set of soft information.

Using a soft decoder with hard data

Symmetrical or asymmetrical noise distributions for voltages corresponding to symbols that can be stored in multi-level memory cells (MLCs) of a memory device are used to determine read reference and/or programming voltages. The read reference voltages and/or programming voltages for the MLCs are jointly determined using the symmetrical distributions and a maximum likelihood estimation (MLE) and/or by determining at least one of the read reference voltages and the programming voltages using the asymmetrical distributions.

Determination of memory read reference and programming voltages

Bit errors affecting cells of a solid-state, non-volatile memory are assigned to at least a first or a second category based on a relative amount of voltage shift that caused the respective bit errors in the respective cells. A reference voltage used to access the respective cells is adjusted to manage the respective bit errors of the first category. Additional corrective measures are taken to manage the respective bit errors of the second category.

Categorizing bit errors of solid-state, non-volatile memory

Approaches for operating a memory device comprising memory cells are disclosed. Optimal values for one or more of programming voltages used to program memory cells of the memory device and read reference voltages used to read the memory cells are determined using a mutual information function, I(X; Y), where X represents data values programmed to the memory cells and Y represents data values read from the memory cells. The read reference and/or programming voltages used for reading and/or programming the memory cells are adjusted using the optimal values.

Determining optimal read reference and programming voltages for non-volatile memory using mutual information

Outer code words can span multiple data blocks, multiple die, or multiple chips of a memory device to protect against errors in the data stored in the blocks, die and/or chips. A solid state memory device is arranged in multiple data blocks, each block including an array of memory cells arranged in a plurality of pages. The data is encoded into inner code words and symbol-based outer code words. The inner code words and the symbol-based outer code words are stored in the memory cells of the multiple blocks. One or more inner code words are stored in each page of each block and one or more symbols of each outer code word are stored in at least one page of each block. The inner code words and the outer code words are read from the memory device and are used to correct the errors in the data.

Outer code protection for solid state memory devices

A decoding system comprises an iterative decoder that utilizes parity constraints to iteratively decode a block of data that consists of multiple code words, and a processor that controls the iterative decoder to selectively remove a subset of the parity constraints for a number of decoder iterations and include one or more of the selectively removed parity constraints in other decoder iterations.

Low density parity check decoder using multiple variable node degree distribution codes

In accordance with one or more embodiments, a decoder may determine whether a lowest reliability value of a plurality of codeword bits that correspond to a particular output reliability value for a particular constraint node of a parity-check matrix is greater than a threshold value (e.g., an offset), and if so, selectively applies a modified min-sum approximation constraint node update with a reliability value modification (e.g., an offset or normalized min-sum approximation).

Selectively applied hybrid min-sum approximation for constraint node updates of LDPC decoders

A method includes writing data to a bit-patterned media at times determined by a clock having a period that is offset from a bit island period by a fixed offset to create one insertion or one deletion approximately within a predetermined number of bit islands, reading the data, and correcting the read data using error correction. An apparatus that implements the method is also provided.

Converting timing errors into symbol errors to handle write mis-synchronization in bit-patterned media recording systems

A method includes: writing data to a bit-patterned media at times determined by a clock having a period that is offset from a bit island period by a fixed offset to create one insertion or one deletion approximately within a predetermined number of bit islands, reading the data, and correcting the read data using error correction. An apparatus that implements the method is also provided.

Growing community of inventors

Longmont, CO, United States of America

Arvind Sridharan