Sk Hynix Memory Solutions Inc.

Link a Media Devices Corporation

Integrated Device Technology, Inc.

Meng-Kun Lee

Kwok Wah Yeung

Yingquan Wu

Kin Ming Chan

Kwok Alfred Yeung

Kin Man Ng

Gubo Huang

Priyanka Thakore

Peter Onufryk

Nishant P Patil

Derrick Preston Chu

A second controller is communicated with from a first controller via an interface. Storage is also communicated with from the first controller via the interface. The first controller is configured to be a master on the interface and the second controller and the storage are configured to be targets on the interface.

Interface between multiple controllers

A method of writing data to non-volatile computer storage is disclosed. A logical page of data is received and stored in an intermediate storage. A first portion of the logical page is read from the intermediate storage and written to a first physical page in the non-volatile computer storage. A second portion of the logical page is read from the intermediate storage and written to a second physical page in the non-volatile computer storage. A method of reading data from non-volatile computer storage is disclosed. A first portion of a logical page is read from a first physical page in the non-volatile computer storage and written in an intermediate storage. A second portion of the logical page is read from a second physical page and written in the intermediate storage. The first portion and the second portion of the logical page are concatenated to form the logical page.

Cross page management to avoid NAND physical page size limitation

An instruction to write to a location in the Flash memory is received. It is determining if the Flash memory exposes a level placement setting associated with defining what voltage range corresponds to what level. In the event it is determined that the Flash memory exposes a level placement setting, an accurate coarse write is performed on the location, including by configuring the level placement setting to be a first value, and after the accurate coarse write is performed on the location, a fine write is performed on the location, including by configuring the level placement setting to be a second value, in response to receiving the instruction.

Flash multiple-pass write with accurate first-pass write

A method for correcting a cell voltage driftage in a NAND flash device is disclosed. An indicator indicating a cell voltage driftage in a memory unit of a NAND flash device is monitored by a processor. A cell voltage driftage in the NAND flash device is detected based at least in part on the indicator. One or more NAND commands correcting the cell voltage driftage are generated. The one or more NAND commands include a NAND command associated with changing a configuration setting of the NAND flash device.

Hardware acceleration of DSP error recovery for flash memory

An indication to store a data value in Flash memory is received. An accurate coarse write is performed on the Flash memory, including by: storing a first voltage level in the Flash memory and setting a configuration setting of the Flash memory to a first setting. The first voltage level, when interpreted using the configuration setting at the first setting, corresponds to the data value. A fine write is performed on the Flash memory, including by: storing a second voltage level in the Flash memory and setting the configuration setting of the Flash memory to a second setting. The second voltage level, when interpreted using the configuration setting at the second setting, corresponds to the data value.

Old user data, old metadata, and old error correction parity information are received. New metadata corresponding to the old user data is generated. The old metadata and the new metadata are combined to obtain combined metadata. New error correction parity information is generated using the combined metadata. The old error correction parity information and new error correction parity information are combined to obtain combined error correction parity information. The old user data, new metadata, and combined error correction parity information are stored in solid state storage.

Write processing for unchanged data with new metadata

A data signal is sampled by generating a read enable signal at a first semiconductor device which is intended for a second semiconductor device. A read enable signal with at least some I/O pad delay included is obtained, including by passing the read enable signal intended for the second semiconductor device at least partially through an input/output (I/O) pad on the first semiconductor device. At the first semiconductor device, a data signal from the second semiconductor is sampled using the read enable signal with at least some I/O pad delay included.

Delay matching across semiconductor devices using input/output pads

An indication to store a data value in Flash memory is received. An accurate coarse write is performed, including by storing a first voltage level in the Flash memory and setting a configuration setting to a first setting. The first voltage level, when interpreted using the configuration setting at the first setting, corresponds to the data value. A fine write is performed, including by storing a second voltage level in the Flash memory and setting the configuration setting of the Flash memory to a second setting. The second voltage level, when interpreted using the configuration setting at the second setting, corresponds to the data value.

An instruction to perform an erase on a group of one or more memory cells is sent. An indication that the erasure of the group of memory cells is unsuccessful is received. In response to receiving the indication that the erasure of the group of memory cells is unsuccessful, the value of a voltage threshold, associated with the group of memory cells, is changed to a new voltage threshold and the new voltage threshold and identification information associated with the group of memory cells is stored.

E/P durability by using a sub-range of a full programming range

Processing a sequence of data frames in an error correction code (ECC) decoder is disclosed. Processing includes receiving a first data frame in the sequence of data frames, storing the first data frame, initiating processing of the first data frame through the ECC decoder, receiving a second data frame from the input sequence of data frames, storing the second data frame, and initiating processing of the second data frame through the ECC decoder before the first data frame is finished being processed through the ECC decoder.

ECC with out of order completion

A NAND Flash memory controller is used to perform an erase operation on a NAND Flash memory chip including to a cell on the NAND Flash memory chip; the cell is configured to store a first number of bits. It is determined whether the erase operation performed on the NAND Flash memory chip is successful. In the event it is determined that the erase operation performed on the NAND Flash memory chip is unsuccessful, the number of bits stored by the cell is reduced from the first number of bits to a second number of bits; the second number of bits is strictly less than the first number of bits.

Processing polynomials is disclosed. At least a portion of processing associated with an error evaluator polynomial and at least a portion of processing associated with an error locator polynomial are performed simultaneously. The error evaluator polynomial and the error locator polynomial are associated with Berlekamp-Massey processing. Data associated with the error evaluator polynomial is removed, including by shifting data in an array so that at least one element in the array is emptied in a shift.

Reduced processing in high-speed Reed-Solomon decoding

Processing a sequence of data frames in an error correction code (ECC) decoder is disclosed. Processing includes receiving a first data frame in the sequence of data frames, storing the first data frame, initiating processing of the first data frame using the ECC decoder that includes a faster stage and a slower stage, receiving a second data frame from the input sequence of data frames, storing the second data frame, and initiating processing of the second data frame through the ECC decoder before the first data frame is finished being processed using the ECC decoder.

Growing community of inventors

Cupertino, CA, United States of America

Meng-Kun Lee