Western Digital Technologies, Inc.

S-tec Corporation

Hgst Technologies Santa Ana, Inc.

Microsoft Technology Licensing, LLC

Stmicroelectronics Gmbh

Eastman-kodak Company

Anthony Dwayne Weathers

Richard David Barndt

Seyhan Karakulak

Xinde Hu

Majid Nemati Anaraki

Richard Leo Galbraith

Niranjay Ravindran

Jonas Andrew Goode

Aldo Giovanni Cometti

Majid Anaraki Nemati

Scott Kayser

Pablo A Ziperovich

Sivagnanam Parthasarathy

Shayan Srinivasa Garani

Ashot Melik-Martirosian

Srikanth Dakshinamoorthy

Ravinder Kumar

Robert D Swanson

This disclosure describes systems and methods for detecting multiple insertion and deletion errors in the presence of substitution errors in a signal (such as a sequenced DNA string). A convolutional code that includes two or more component convolutional codes is used for encoding. Each of the two or more component convolutional codes generates only a subset of all possible outputs of the convolutional code. The subsets of the two or more component convolutional codes are disjoint from each other. Only one of the two or more convolutional codes is active at any given time. The two or more convolutional codes together define a super code. The two or more convolutional codes are time interlaced within the super code, and the super code defines the convolutional code. A trellis that includes two or more component trellises designed based on the two or more component convolutional codes is used for decoding.

Codes to detect insertion and deletion errors in a dense storage medium

A RAM chip includes host dies and parity dies. A memory controller receives system data to be stored on the RAM chip that is in excess of the storage capacity of the host dies. The memory controller encodes the system data in the parity symbols of the parity dies. The system data is retrieved by decoding the parity symbols and identifying the system data from the decoded information.

Encoding system data in parity symbols

Embodiments generally relate to improving reliability of processing cache lines with metadata symbols encoded into parity symbols of codewords. The data and metadata of a cache line are encoded into codewords where each codeword is a number of (1) message symbols, each including message bits from data of the cache line, and (2) parity symbols, each including parity bits determined from the message symbols and a metadata symbol. For each codeword of the cache line, the plurality of message and parity symbols are rotated so that a location of each symbol of one codeword is different from other codewords of the cache line. The codewords of the cache line are then stored in memory as rotated. In this manner, the reliability is improved by rotating symbols of the codewords of the cache line, with metadata symbols encoded into parity of codewords, before storage in memory.

Symbol rotation of cache line codewords for increased reliability with metadata

The subject technology provides for scanning blocks of a flash memory device for erased pages. A first codeword read from a page of a block in a flash memory device is received and provided to a first decoder for decoding. In response to receiving a first success indicator from the first decoder indicating that the first codeword was successfully decoded, first decoded data is provided from the first decoder to a second decoder for verification of the first decoded data. In response to receiving a first failure indicator from the second decoder indicating that the first decoded data was not verified, the page of the block is identified as being in an erased state based on the first success indicator received from the first decoder and the first failure indicator received from the second decoder.

Method and system for identifying erased memory areas

Systems and methods for read level tracking and optimization are described. Pages from a wordline of a flash memory device read and the raw page data read from the wordline may be buffered in a first set of buffers. The raw page data for each of the pages may be provided to a decoder for decoding and the decoded page data for each of the pages buffered in a second set of buffers. First bin identifiers may be identified for memory cells of the wordline based on the raw page data and second bin identifiers may be identified for the memory cells of the wordline based on the decoded page data. Cell-level statistics may be accumulated based on the first bin identifiers and the second bin identifiers, and a gradient may be determined for respective read levels based on decoding results for each of the pages and the cell-level statistics. Settings for the read levels may be configured in the flash memory device based on the determined gradients.

Read level tracking and optimization

After a predetermined period of time in a life cycle of a flash memory device, a plurality of reliability values corresponding to a plurality of reads of one or more of the plurality of memory cells are generated; each of the reads using a variation of a predetermined read level voltage. An offset voltage is then identified, offset from the read level voltage. The offset voltage corresponds to a zero crossing point in the range of the reliability values. Once the offset voltage is identified, the read level voltage is set to a calibrated voltage based on the offset voltage.

Calibrating optimal read levels

A method for data retrieval includes receiving a set of probability metrics. A set of probability metrics is received for each one of a plurality of read values, and each probability metric of the set of probability metrics corresponds to a statistical likelihood that the read value is representative of one of a number of symbols. The symbols define a set of allowed transitions between a number of states, and a series of successive allowed transitions between states define allowed paths between the states. The method further includes determining a survival path between the states. The survival path is based on an accumulation of probability metrics corresponding to the statistical likelihood that successive ones of the plurality of read values are representative of successive ones of the symbols defining each transition in the survival path. The method further includes decoding a symbol stream based on the survival path.

Systems and methods for encoding and decoding data

A soft information module is coupled between one or more flash memory devices and a decoder. The soft information module receives a putative value of one or more memory cells of the one or more flash memory devices based on a read of the one or more memory cells at an initial read level, and one or more respective indicators of whether the putative value was read at one or more respective different read levels offset from the initial read level, and receives a page indicator for the read. The soft information module determines a cell program region for the read based on the putative value, the one or more respective indicators, and the page indicator, identifies a predetermined confidence value for the region, and provides the confidence value to the decoder for association with the putative value, the confidence value being representative of a likelihood that the one or more memory cells was programmed to the putative value.

Soft information module

Method and system for scanning for erased flash memory pages

Growing community of inventors

San Diego, CA, United States of America

Anthony Dwayne Weathers