摘要:
A memory system comprises a memory controller, an address RAM coupled to the memory controller, and a non-volatile memory coupled to the memory controller. The non-volatile memory has an address portion and a data portion. The address portion of the non-volatile memory provides data portion addresses and data portion addresses of valid data to the memory controller. The memory controller loads the data portion addresses and stores them in the address RAM at locations defined by the data portion addresses of valid data into the address RAM. The memory controller uses the data portion addresses, and locations of data blocks within the address RAM, to locate the data blocks within the data portion of non-volatile memory. The memory controller uses the data portion addresses, and locations of the data block addresses within the address RAM, to locate data blocks within the data portion of non-volatile memory
摘要:
A method and system wherein a volatile memory is partitioned to have a first percentage of address space dedicated to a first classification of data which is data that is expected to have greater than a predetermined number of times of being modified and a second percentage of address space dedicated to a second classification of data which is data that is expected to have less than the predetermined probability of being modified. Address assignment of data to be stored in the volatile memory is made on a basis of predicted change of the data. Memory addresses of the first and second percentages of address space are respectively assigned to first and second sections of nonvolatile memory. The memory addresses of the first percentage initially consume a smaller percentage of an address map of the first section than the memory addresses of the second percentage of the second section.
摘要:
Adaptive error correction for non-volatile memories is disclosed that dynamically adjusts sense amplifier read detection windows. Memory control circuitry uses error correction code (ECC) routines to detect bit errors that are non-correctable using these ECC routines. The memory control circuitry then dynamically adjusts sense amplifier read detection windows to allow for correct data to be determined. Corrected data can then be output to external circuitry. The corrected data can also be stored for later access when subsequent read operations attempt to access address locations that previously suffered bit failures. The adaptive error correction can also be used with respect to memories that are not non-volatile memories.
摘要:
Methods and systems are disclosed for adaptive error correction for non-volatile memories that dynamically adjust sense amplifier read detection windows. Memory control circuitry uses error correction code (ECC) routines to detect bit errors that are non-correctable using these ECC routines. The memory control circuitry then dynamically adjusts sense amplifier read detection windows to allow for correct data to be determined. Corrected data can then be output to external circuitry. The corrected data can also be stored for later access when subsequent read operations attempt to access address locations that previously suffered bit failures. The disclosed methods and systems can also be used with respect to memories that are not non-volatile memories.
摘要:
A method and system wherein a volatile memory is partitioned to have a first percentage of address space dedicated to a first classification of data which is data that is expected to have greater than a predetermined number of times of being modified and a second percentage of address space dedicated to a second classification of data which is data that is expected to have less than the predetermined probability of being modified. Address assignment of data to be stored in the volatile memory is made on a basis of predicted change of the data. Memory addresses of the first and second percentages of address space are respectively assigned to first and second sections of nonvolatile memory. The memory addresses of the first percentage initially consume a smaller percentage of an address map of the first section than the memory addresses of the second percentage of the second section.
摘要:
Methods and systems are disclosed for digital control for regulation of program voltages for non-volatile memory (NVM) systems. The disclosed embodiments dynamically adjust program voltages based upon parameters associated with the cells to be programmed in order to account for IR (current-resistance) voltage drops that occur within program voltage distribution lines. Other voltage variations can also be accounted for with these dynamic adjustments, as well. The parameters for cells to be programmed can include, for example, cell address locations for the cells to be programmed, the number of cells to be programmed, and/or other desired parameters associated with the cells to be programmed. The disclosed embodiments use digital control values obtained from lookup tables based upon the cell parameters to adjust output voltages generated by voltage generation circuit blocks used to program the selected cells thereby tuning the program output voltage level to a predetermined desired level.
摘要:
Methods and systems are disclosed for sector-based regulation of program voltages for non-volatile memory (NVM) systems. The disclosed embodiments regulate program voltages for NVM cells based upon feedback signals generated from sector return voltages that are associated with program voltage drivers that are driving program voltages to NVM cells within selected sectors an NVM array. As such, drops in program voltage levels due to IR (current-resistance) voltage losses in program voltage distribution lines are effectively addressed. This sector-based regulation of the program voltage effectively maintains the desired program voltage at the cells being programmed regardless of the sector being accessed for programming and the number of cells being programmed. Sector return voltages can also be used along with local program voltages to provide two-step feedback regulation for the voltage generation circuitry. Test mode configurations can also be provided using test input and/or output pads.
摘要:
Methods and systems are disclosed for sector-based regulation of program voltages for non-volatile memory (NVM) systems. The disclosed embodiments regulate program voltages for NVM cells based upon feedback signals generated from sector return voltages that are associated with program voltage drivers that are driving program voltages to NVM cells within selected sectors an NVM array. As such, drops in program voltage levels due to IR (current-resistance) voltage losses in program voltage distribution lines are effectively addressed. This sector-based regulation of the program voltage effectively maintains the desired program voltage at the cells being programmed regardless of the sector being accessed for programming and the number of cells being programmed. Sector return voltages can also be used along with local program voltages to provide two-step feedback regulation for the voltage generation circuitry. Test mode configurations can also be provided using test input and/or output pads.
摘要:
A semiconductor memory device includes a non-volatile memory, a memory controller, and a charge pump system. The memory controller establishes first parameters for a first programming cycle of a first plurality of memory cells of the non-volatile memory prior to the first programming cycle being performed. The charge pump system includes a plurality of charge pumps and provides a first programming pulse for use in performing the first program cycle. The first programming pulse is provided by selecting, according to the first parameters, which of the plurality of charge pumps are to be enabled during the first program cycle and which are to be disabled during the first program cycle.
摘要:
A system has an emulation memory having a plurality of sectors for storing information. A controller calculates a number of addresses used divided by a number of valid records in a predetermined address range of the emulation memory. An amount of remaining addresses in a currently used space of the emulation memory which have not been used to store information is calculated. A determination is made whether the calculation is greater than a first predetermined number and whether the amount of remaining addresses is greater than a second predetermined number. If both the fraction is greater than the first predetermined number and the amount of remaining addresses is greater than the second predetermined number, any subsequent update requests are responded to using the currently used space of the emulation memory. Otherwise a compression of the emulation memory is required by copying valid data to an available sector.