摘要:
Selecting bins in a memory by receiving a target cost for performing writes at an analog memory that is capable of storing a range of values. Possible bins that may be created in the range of values and a cost associated with each possible bin are determined. Each possible bin includes one or more of the values. A group of bins are identified, the group of bins are among the possible bins with associated costs that are within a threshold of the target cost. A maximum number of bins are selected from the group of bins that have non-overlapping values. The selected bins are stored along with the values of the selected bins utilized to encode and decode contents of the analog memory.
摘要:
Methods and apparatus are provided for recording input data in q-level cells of solid-state memory (2), where q>2. Input data words are encoded as respective codewords, each having a plurality of symbols. The coding scheme is such that each symbol can take one of q values corresponding to respective predetermined levels of the q-level cells, and each of the possible input data words is encoded as a codeword with a unique sequence of relative symbol values. The symbols of each codeword are then recorded in respective cells of the solid-state memory by setting each cell to the level corresponding to the recorded symbol value. Input data is thus effectively encoded in the relative positions of cell levels, providing resistance to certain effects of drift noise.
摘要:
A phase-change memory (PCM) includes a matrix of storage cells, including at least a first group with at least one cell. Each cell includes a phase change material having at least a first resistance value and a second resistance value, such that the first group can have an identical message encoded therein in at least a first way and a second way. The memory also includes a controller configured to encode the identical message in the at least first group the first or second way, based on which way causes the least amount of writing cost, given current levels of the group. Another embodiment of memory includes a matrix of storage cells, including at least a first group with at least one cell. Each of the storage cells has at least two levels, such that each of the storage cells can have an identical message encoded therein in at least a first way and a second way (the cells can be PCM or another technology). Each one of the storage cells is arbitrarily individually changeable among the at least two levels, and each of the cells is cost-asymmetric. A controller encodes the identical message in the at least first group using the first way or the second way, based on which way incurs a least cost when writing the message into the at least one cell of the at least first group, given current levels of the at least first group.
摘要:
A method and apparatus for providing a read channel having combined parity and non-parity post processing is disclosed. A post-processor combines parity and non-parity post processing to make both parity and non-parity corrections so that error events that cannot be detected by parity may be corrected. Non-parity detectable error events are only kept for consideration if their likelihood is above a set threshold.
摘要:
Method and apparatus for decoding data in a data storage system. In operation, a detector generates an output bit stream in dependence on a data block received from a storage subsystem of the data storage system. A post processor connected to the detector generates a first error corrected bit stream in dependence on the output bit stream and the data block. An error correction decoder connected to the post processor generates a second error corrected bit stream in dependence on the first error corrected bit stream and also generates a checksum in dependence of the second error corrected bit stream. A feedback path supplies from the error correction decoder to the post processor pinning data indicative of locations of correct bits in the second error corrected bit stream in the event that the checksum is indicative of errors in the second error corrected bit stream and the second error corrected bit stream comprises at least one correct interleave. The post processor regenerates the first error corrected bit stream in dependence on the pinning data received from the error correction decoder.
摘要:
Techniques are provided for applying modulation constraints to data by using periodically changing symbol mappings to replace certain prohibited error prone data patterns. Initially, user data in a first base is mapped to integers of a second base using a base conversion technique. The integers in the second base correspond to symbols. Subsequently, periodically changing symbol mappings are performed during which prohibited symbols generated during base conversion are mapped to permitted symbols. The periodically changing symbol mappings occur in multiple phases, and the prohibited symbols are different in each phase. The resulting data is processed by a precoder in some embodiments.
摘要:
A method for decoding Low Density Parity Check (LDPC) codes comprises executing a sum product algorithm to recover a set of information bits from an LDPC code represented as a bipartite graph of symbol nodes and check nodes, the sum product algorithm being responsive to input log likelihood ratios associated with the symbol nodes. The check nodes are updated by generating a set of forward difference metrics and a set of backward difference metrics in dependence on the ratios of logarithmic probabilities each associated with a corresponding symbol node of the LDPC code, updating each metric in the set of forward difference metrics in dependence on the absolute value of the log likelihood ratio associated with the symbol node and the absolute value of the previous metric in the set, updating each metric in the set of backward difference metrics in dependence on the absolute value of the log likelihood ratio associated with the symbol node and the absolute value of the previous metric in the set, and generating log likelihood ratios to be propagated back to each symbol node in dependence on the updated sets of forward and backward difference metrics.
摘要:
An apparatus for providing dynamic equalizer optimization is disclosed. The present invention solves the above-described problems by providing equalizer coefficient updates that converge towards the same solution as the direct method without having to first write a known pattern to the disk or requiring any prior knowledge of the data already written on the disk. The adaptive cosine function may be used to modify only a DFIR tap set, only the j and k parameters of a cosine equalizer or to modify both the tap set for a DFIR filter and the j and k parameters of the cosine equalizer. Another algorithm, such as the LMS algorithm, may be used to modify parameters not modified by the cosine algorithm.
摘要:
An apparatus that uses a lengthened equalization target filter with a matched filter metric in a Viterbi detector is disclosed. The equalization target includes a base partial response component, i.e., (1−D2), a fractional coefficient polynomial component to whiten the noise, i.e., (1+p1D+p2D2), and a time-reversed replica of the noise-whitening component. Thus, the time-reversed replica of the noise-whitening component comes from what was formerly a matched filter component.
摘要:
In one embodiment, a data storage system includes a tape channel for reading data from a magnetic tape medium to produce a signal, a noise whitening filter positioned subsequent to the tape channel adapted for receiving the signal, wherein the noise whitening filter is adapted for minimizing variance of its output signal, a soft detector adapted for receiving output from the noise whitening filter, the soft detector adapted for calculating first soft information about each bit of the signal and sending the first soft information to a soft decoder, and the soft decoder positioned subsequent to the soft detector, the soft decoder being adapted for calculating second soft information about each bit of the signal and sending the second soft information to the soft detector. Other systems, methods, and computer program products are described according to more embodiments.