Silicon Storage Technology, Inc.

Sandisk Technologies Inc.

Sandisk Enterprise IP LLC

Western Digital Technologies, Inc.

Jack Frayer

Hieu Van Tran

Bomy A Chen

Dana Lee

Aaron Keith Olbrich

Vidyabhushan Mohan

William Saiki

Sergey Anatolievich Gorobets

Michael S Briner

Thuan Vu

Robert W Ellis

Xian Liu

Alexander Kotov

Eugene Jinglun Tam

Michael James Heinz

Tho Ngoc Dang

Jung Hee Yun

Michael K Doan

Eran Sharon

Idan Alrod

Alexander Bazarsky

Grishma Shah

Tien-Chien Kuo

Ya-Fen Lin

Sohrab Kianian

Yuniarto Widjaja

Vishal Sarin

Chang Hua Siau

Amitay Levi

Kroum Stanimirov Stoev

Liam Michael Parker

Douglas J Lee

Changyuan Chen

Anand Kulkarni

Gopinath Balakrishnan

Paul Roger Stonelake

Kai Man Yue

Gulzar Ahmed Kathawala

Todd Lindberg

Pavel Klinger

Elbert Lin

Felix (Ying-Kit) Tsui

Gianfranco Pellegrini

Xiuhong Chen

Yale Yueh Ma

A non-volatile storage apparatus includes a plurality of non-volatile memory cells formed on a memory die, each non-volatile memory cell configured to hold a plurality of bits of data, and a control circuit formed on the memory die. The control circuit is configured to calculate parity data for data to be stored in the memory cells and program the memory cells to first distributions. The control circuit is also configured to read memory cells in the first distributions, recover the data from results of reading the memory cells in the first distributions combined with the parity data, and further program the memory cells from the first distributions to second distributions to store the data.

Nonvolatile memory with on-chip encoding for foggy-fine programming

A storage apparatus includes non-volatile memory cells formed on a memory die, each memory cell configured to hold bits of data, and a control circuit formed on the memory die. The control circuit is configured to calculate parity data for data to be stored in the memory cells and program the memory cells to first distributions. The control circuit is also configured to read the memory cells in the first distributions, recover the data from results of reading the memory cells in the first distributions combined with the parity data, and further program the memory cells from the first distributions to second distributions to store the data. In some cases, the recovered data may have a high bit error rate. To handle higher bit error rates, the use of soft bit data is incorporated into an encoded foggy-fine scheme.

Nonvolatile memory with encoding for foggy-fine programming with soft bits

A storage apparatus includes non-volatile memory cells formed on a memory die, each memory cell configured to hold bits of data, and a control circuit. The control circuit is configured to calculate parity data for data to be stored in the memory cells and program the memory cells to first distributions. The control circuit is also configured to read memory cells in the first distributions, recover the data from results of reading the memory cells in the first distributions combined with the parity data, and further program the memory cells from the first distributions to second distributions to store the data. To improve the accuracy of recovering the encoded foggy phase data, techniques are presented to calibrate the voltage levels used in sensing the foggy state distributions.

Read threshold calibration for nonvolatile memory with encoded foggy-fine programming

Systems and methods are provided for acquiring status information from a plurality of memory die. An apparatus is provided that includes a plurality of memory die and a memory controller. The memory controller is configured to broadcast a first status command to the plurality of memory die, receive a first status response concurrently from the plurality of memory die based on the first status command, and send a repair command to one or more of the plurality of memory die in response to the first status response not satisfying first predetermined status criteria.

Multi-die status mode for non-volatile storage

A system and method is disclosed for managing data in a non-volatile memory. The system may include a non-volatile memory having multiple non-volatile memory sub-drives, including a staging sub-drive to receive all data from a host and a plurality of other sub-drives each associated with a respective data temperature range. A controller of the memory system is configured to route all incoming host data only to the staging sub-drive and during garbage collection each individual piece of valid data from a selected source block in a selected source sub-drive is routed to a respective one of the sub-drives. The method may include only routing host data to the staging sub-drive and only relocating valid data to sub-drives other than the staging sub-drive based on a determined temperature of valid data and a unique temperature range associated with sub-drives other than the staging sub-drive in the non-volatile memory system.

System and method of managing data in a non-volatile memory having a staging sub-drive

Systems and methods for increasing performance and reducing power consumption of a non-volatile memory system while the system acquires status information from a plurality of memory die are described. The non-volatile memory system may include a plurality of memory die and a system controller for controlling operations performed by each memory die of the plurality of memory die (e.g., read operations, write operations, or erase operations). The system controller may transmit or broadcast a first status command to each memory die of the plurality of memory die and in response simultaneously or concurrently receive one or more sets of status information from each memory die of the plurality of memory die. The status information may include ready/busy status information (e.g., indicating that a memory die is able to receive new data), programming loop count information, and erase loop count information.

Multi-die rolling status mode for non-volatile storage

Systems, methods, and/or devices are used to automate read operations performed at an open erase block. In one aspect, the method includes: receiving a read command, at a storage device, to read data from non-volatile memory of the storage device. In response to receiving the read command, the method further includes: 1) reading data using a first set of memory operation parameters in response to a determination that the read command is not for reading data from a predefined portion of an open erase block (e.g., an erase block that is determined to be an open erase block) of the non-volatile memory and 2) reading data using a second set of memory operation parameters (i.e., the second set is distinct from the first set) in response to a determination that the read command is for reading data from the predefined portion of an open erase block of the non-volatile memory.

Open erase block read automation

Systems, methods, and/or devices are used to manage high-priority NAND operations. In some embodiments, the method includes receiving a first command (e.g., requesting a high-priority memory operation) corresponding to a first location (e.g., having both a first physical address and a first aliased physical address) in a first die of a plurality of physical non-volatile memory die in a storage device. If the first die is performing a blocking low-priority memory operation (e.g., the low-priority operation was sent to the first die using a second physical address), the method includes sending a memory operation command, corresponding to the first memory operation, to the first die using the first aliased physical address. In some embodiments, a predefined die-selection portion of the second physical address matches the predefined die-selection portion of the first physical address and does not match the predefined die-selection portion of the first aliased physical address.

High-priority NAND operations management

The various embodiments described herein include systems, methods and/or devices used to enable physical-to-physical address remapping in a storage module. In one aspect, the method includes, for each of a sequence of two or more units of non-volatile memory, determining a validity state of a respective unit of memory. In accordance with a determination that the validity state of the respective unit of memory is an invalid state, the method includes storing, in a table, a second address assigned to the respective unit of memory. At least a portion of the second address is a physical address portion corresponding to a physical location of a second unit of memory. In accordance with a determination that the validity state of the respective unit of memory is a valid state, the method includes forgoing assignment of the second address corresponding to the unit of memory.

Non-volatile memory module with physical-to-physical address remapping

The various embodiments described herein include systems, methods and/or devices used to package non-volatile memory. In one aspect, the method includes: (1) selecting, from a set of non-volatile memory die, a plurality of non-volatile memory die on which one or more tests have been deferred until after packaging, the selecting in accordance with wafer positions of the plurality of non-volatile memory die and statistical die performance information corresponding to the wafer positions; and (2) packaging the selected plurality of non-volatile memory die. In some embodiments, after said packaging, the method further includes performing a set of tests on the plurality of non-volatile memory die to identify respective units of memory within the plurality of non-volatile memory die that meet predefined validity criteria, wherein the set of tests performed include at least one of the deferred one or more tests.

Low-test memory stack for non-volatile storage

A single command initiates a first read operation and sequence of one or more additional read operations from the same portion of memory. The one or more additional read operations are terminable after the first read operation provides a first plurality of data values that is made available to a requesting device and/or module. In some implementations, the first plurality of data values includes hard information values. Subsequent pluralities of data values are generated from the same portion of memory until a terminating event occurs. In some implementations, until a terminating event occurs, a respective hybrid plurality of data values is generated by combining the latest read plurality of data values with one of a previously generated hybrid plurality of data values and the first plurality of data values. Each hybrid plurality of data values is representative of a corresponding plurality of soft information values.

Performance optimization of data transfer for soft information generation

An error control encoding system produces a codeword from a data word, where the resulting codeword includes the data word and three or more parity segments produced using the data word. The system includes a first encoder to encode the data word in two or more first data segments in order to produce two or more first parity segments, where each of the two or more first data segments includes a respective sequential portion of the data word. The system includes a second encoder to encode the data word in one or more second data segments in order to produce a corresponding one or more second parity segments, where each of the one or more second data segments includes a respective sequential portion of the data word, and each of the one or more second data segments also includes a sequential portion of the data included in a plurality of the two or more first data segments. Further, the system includes a controller configured to provide the two or more first data segments of the data word to the first encoder for encoding and to provide the one or more second data segments of the data word to the second encoder for encoding.

Systems, methods and devices for multi-tiered error correction

The various embodiments described herein include systems, methods and/or devices used to packaging non-volatile memory. In one aspect, the method includes, selecting, from a set of non-volatile memory die, a plurality of non-volatile memory die on which predefined die-level and sub-die level tests have been deferred until after packaging, in accordance with predefined criteria and predefined statistical die performance information corresponding to the set of non-volatile memory die. The method further includes packaging the selected plurality of non-volatile memory die into a memory device. After said packaging, the method further includes performing a set of tests on the plurality of non-volatile memory die in the memory device to identify respective units of memory within the non-volatile memory die in the memory device that meet predefined validity criteria, wherein the set of tests performed include the deferred predefined die-level and sub-die level tests.

An error control system uses an error control code that corresponds to an error density location profile of a storage medium. The system includes an encoder configured to produce one or more codewords from data using an error control code generator matrix corresponding to the error density location profile of the storage medium. The system also includes a decoder configured to produce decoded data from one or more codewords using an error control code parity-check matrix corresponding to the error density location profile of the storage medium, where columns of the parity-check matrix are associated with corresponding data bits of the storage medium, rows of the parity-check matrix are associated with check bits, and each matrix element of the parity-check matrix having a predefined value indicates a connection between a particular data bit and a particular check bit.

Data encoder and decoder using memory-specific parity-check matrix

An error control decoding system decodes a codeword that includes a data word and two or more parity segments. The system includes a first decoder to decode the codeword by utilizing one or more first parity segments and the data word included in the codeword, and a second decoder to decode the codeword by utilizing one or more second parity segments and the data word included in the codeword, wherein the one or more first parity segments are different from the one or more second parity segments. An error estimation module estimates the number of errors in the codeword, and a controller selects which of the first decoder and second decoder to start decoding the codeword, wherein the selection is based on the estimate of the number of errors in the codeword provided by the error estimation module.

Systems, methods and devices for decoding codewords having multiple parity segments

Growing community of inventors

Boulder Creek, CA, United States of America

Jack Frayer