摘要:
Systems and methods of managing defects in nonvolatile storage systems that can be used to avoid an inadvertent loss of data, while maintaining as much useful memory in the nonvolatile storage systems as possible. The disclosed systems and methods can monitor a plurality of trigger events for detecting possible defects in one or more nonvolatile memory (NVM) devices included in the nonvolatile storage systems, and apply one or more defect management policies to the respective NVM devices based on the types of trigger events that resulted in detection of the possible defects. Such defect management policies can be used proactively to retire memory in the nonvolatile storage systems with increased granularity, focusing the retirement of memory on regions of nonvolatile memory that are likely to contain a defect.
摘要:
Embodiments of the present disclosure describe device, methods, computer-readable media and system configurations for decoding codewords using a side channel. In various embodiments, a memory controller may be configured to determine that m of n die of non-volatile memory (“NVM”) have failed iterative decoding. In various embodiments, the memory controller may be further configured to generate a side channel from n-m non-failed die and the m failed die other than a first failed die. In various embodiments, the memory controller may be further configured to reconstruct, using iterative decoding, a codeword stored on the first failed die of the m failed die based on the generated side channel and on soft input to an attempt to iteratively decode data stored on the first failed die. In various embodiments, the iterative decoding may include low-density parity-check decoding. Other embodiments may be described and/or claimed.
摘要:
Apparatus, systems, and methods manage NAND memory are described. In one embodiment, an apparatus comprises a memory controller logic to apply a binary parity check code to a binary string and convert the binary string to a ternary string. Other embodiments are also disclosed and claimed.
摘要:
Embodiments of the present disclosure describe device, methods, computer-readable media and system configurations for decoding codewords using a side channel. In various embodiments, a memory controller may be configured to determine that m of n die of non-volatile memory (“NVM”) have failed iterative decoding. In various embodiments, the memory controller may be further configured to generate a side channel from n-m non-failed die and the m failed die other than a first failed die. In various embodiments, the memory controller may be further configured to reconstruct, using iterative decoding, a codeword stored on the first failed die of the m failed die based on the generated side channel and on soft input to an attempt to iteratively decode data stored on the first failed die. In various embodiments, the iterative decoding may include low-density parity-check decoding. Other embodiments may be described and/or claimed.
摘要:
Examples are disclosed for techniques associated with protecting system critical data written to non-volatile memory. In some examples, system critical data may be written to a non-volatile memory using a first data protection scheme. User data that includes non-system critical data may also be written to the non-volatile memory using a second data protection scheme. For these examples, both data protection schemes may have a same given data format size. Various examples are provided for use of the first data protection scheme that may provide enhanced protection for the system critical data compared to protection provided to user data using the second data protection scheme. Other examples are described and claimed.
摘要:
For storage drives with LDPC encoded data, read techniques are provided whereby an errantly read memory unit (e.g., faulty LDPC codeword) may be recovered.
摘要:
Methods and apparatus related to utilization of counter(s) for locating faulty die in a distributed codeword storage system are described. In one embodiment, first logic determines a plurality of values. Each of the plurality of values corresponds to a number of zeros or a number of ones in bits read from a portion of each of a plurality of memory dies. Second logic determines one or more candidates as a faulty die amongst the plurality of memory dies based at least in part on a comparison of the plurality of values for the plurality of memory dies. Other embodiments are also disclosed and claimed.
摘要:
Methods, apparatuses, and systems related to use of error correction pointers (ECPs) to handle hard errors in memory are described herein. In embodiments, a read module of a memory controller may read a codeword stored in a memory. The read module may determine a number of hard errors in the codeword. Responsive to a determination that the number of hard errors exceeds a threshold, the read module may store ECP information associated with the hard errors. The read module may include an error correction code (ECC) module to perform an ECC process on the codeword. The read module may use the ECP information to decode the codeword to recover the data responsive to a determination that the ECC process failed. Other embodiments may be described and claimed.
摘要:
Embodiments include methods, apparatuses, and instructions for encoding a codeword of data as codeword portions stored across multiple die in a non-volatile memory. Embodiments further include a decoder which may be configured to decode the portions of the codeword using hard decision reads. The decoder may then be configured to estimate the quality of each die, and apply a scaling factor to the decoded codeword portions such that confidence or reliability information can be determined for the codeword.
摘要:
Embodiments include systems, methods, and apparatuses to estimate respective first and second cumulative density functions (CDFs) for values of a plurality of non-volatile memory (NVM) cells in a page of memory. The CDFs may be based at least in part on one or more decoder outputs of codewords for data stored in the page. Based at least in part on the CDFs, first and second probability density functions (PDFs) may be estimated for the values of the page of memory. A center read reference voltage may then be determined for reading a cell in the page. The center read reference voltage may be based at least in part on the first and second PDFs.