摘要:
Outer code words can span multiple data blocks, multiple die, or multiple chips of a memory device to protect against errors in the data stored in the blocks, die and/or chips. A solid state memory device is arranged in multiple data blocks, each block including an array of memory cells arranged in a plurality of pages. The data is encoded into inner code words and symbol-based outer code words. The inner code words and the symbol-based outer code words are stored in the memory cells of the multiple blocks. One or more inner code words are stored in each page of each block and one or more symbols of each outer code word are stored in at least one page of each block. The inner code words and the outer code words are read from the memory device and are used to correct the errors in the data.
摘要:
A storage medium includes at least one data unit defining a plurality of symbol-based inner code words and a plurality of symbol-based outer code words. Each symbol included in one of the inner code words is also included in one of the outer code words. A processor is configured to perform a first iteration of inner code error correction on the plurality of symbol-based inner code words, a first iteration of outer code error correction on the plurality of symbol-based outer code words and a second iteration of inner code error correction on the plurality of symbol-based inner code words. In the first iteration of outer code error corrections, at least one of the outer code words is correctable. In the second iteration of inner code error correction, at least one of the inner code words is correctable.
摘要:
A nominal reference read operation compares analog voltages of the memory cells to at least one nominal reference voltage. A shifted reference read operation compares the analog voltages of the memory cells to at least one shifted reference voltage that is shifted from the nominal reference voltage to compensate for an expected change in the analog voltages of the memory cells. Data stored in the memory cells is decoded by a first decoding process that uses the information from either the nominal reference read operation or the shifted reference read operation. The data stored in the memory cells is decoded by a second decoding process that uses the information from both the nominal reference read operation and the shifted reference read operation.
摘要:
This disclosure is related to systems and methods for low wear operation of solid state memory, such as a flash memory. In one example, a controller is coupled to a memory and adapted to dynamically adjust programming thresholds over the course of usage of the data storage device such that a signal-to-noise ratio from reading data stored in the data storage cells is no less than a minimum amount needed to recover the data using an enhanced error detection capability.
摘要:
A method and apparatus for bandwidth balancing of data transfer operations between a computer and a storage subsystem are disclosed. The storage subsystem contains a number of storage devices such as magnetic disk drives. Data to be stored is supplied by the computer to the storage subsystem in the form of a transfer unit through a communication channel. The storage subsystem divides the transfer unit into a number of stripes of a pre-determined size. Each stripe is allocated to a separate disk drive whose disk surfaces are formatted into a number of track bands. Each track band is composed of several contiguous tracks associated with the same data transfer rate. Each stripe is then stored on its disk drive within a selected track band. Both data storage and retrieval from each disk drive occur at the data transfer rate associated with the accessed track band. Since all the stripes in the transfer unit are transferred to their disk drives simultaneously, the transfer operation occurs at an aggregate transfer rate equal to the sum of the individual track band transfer rates. The storage subsystem selects the track bands on each disk drive in such a manner as to ensure that the data transfer operation occurs at an aggregate transfer rate within a pre-determined bandwidth range of the communication channel bandwidth.
摘要:
Multiple logical pages are jointly encoded into a single code word and are stored in the same physical page of a solid state non-volatile memory (NVM) device having multi-level memory cells. A first logical page of the multiple logical pages is stored in the memory device as first bits of the multi-level memory cells while a second logical page of the multiple logical pages is temporarily cached. After the first logical page is stored as the first bits of the memory cell, the second logical page is stored as second bits of the memory cells.
摘要:
Methods and systems for accessing encoded data stored in a solid state non-volatile memory device include iteratively demodulating and decoding the data. The memory device includes memory cells arranged to store multiple bits of data per memory cell. The memory cells are capable of storing multiple pages of data. Each bit stored in a memory cell is associated with a page of data that is different from other pages associated with other bits stored in the memory cell. The multiple pages are demodulated responsive to sensed voltage levels of the memory cells, and a demodulated output is provided for each page of the multiple pages. A decoded output for each page of the multiple pages is generated. Decoding the page and demodulating the multiple pages proceeds iteratively, including an exchange of information between the decoder and the demodulator.
摘要:
Momentary contact with a defect site of a data storage disk or free particle by a magnetoresistive read element of a flying head causes momentary heating and unwanted increase in element resistance (thermal asperity) which can disrupt hard disk drive data reading operations. Since the disk carries a predetermined data format, the disk drive controller correlates location of a thermal asperity to the format and thereupon selects from several available thermal asperity recovery methods a method most likely to minimize thermal asperity effect upon disk drive operation during rereading of data at the thermal asperity location.
摘要:
Methodology and circuitry for providing adaptable dynamic prioritization of a plurality of requestors for a shared resource with a plurality of prioritization commands selected according to the winning request of each arbitrage operation.
摘要:
A disk in a disk drive has radial spokes wherein servo bursts are recorded, and multiple concentric bands holding data blocks in pre-defined block frames. To maximize data density, the data rate in each band is proportional to the band radius, and the ratio of block frames to spokes in a given band may be non-integral. In such bands, some data blocks are split by a spoke. A disk controller in the disk drive uses a byte position accumulator (BPA) when splitting a data block. During the transfer of a data block, the BPA counts at the nominal data transfer rate to continually identify by its position in the data block a byte therein to be transferred shortly. The BPA output feeds a latch which is normally open to receive the BPA output. A timer within the disk controller establishes the rotational time at which the data transfer must be suspended to avoid a spoke. The timer generates an early warning signal in advance of this time which closes the latch. The value in the closed latch is the position of the last data byte to be transferred before the split. A comparator indicates when a count of bytes transferred has reached the value in the latch; the data transfer is then suspended until the spoke has passed.