摘要:
Host system data files are written directly to a large erase block flash memory system with a unique identification of each file and offsets of data within the file but without the use of any intermediate logical addresses or a virtual address space for the memory. Directory information of where the files are stored in the memory is maintained within the memory system by its controller, rather than by the host. The file based interface between the host and memory systems allows the memory system controller to utilize the data storage blocks within the memory with increased efficiency.
摘要:
In sensing a page of nonvolatile memory cells with a corresponding group of sense modules in parallel, as each high current cell is identified, it is locked out from further sensing while others in the page continued to be sensed. The sense module involved in the locked out is then in a lockout mode and becomes inactive. A noise source from the sense module becomes significant when in the lockout mode. The noise is liable to interfere with the sensing of neighboring cells by coupling through its bit line to neighboring ones. The noise can also couple through the common source line of the page to affect the accuracy of ongoing sensing of the cells in the page. Improved sense modules and method isolate the noise from the lockout sense module from affecting the other sense modules still active in sensing memory cell in the page.
摘要:
Shifts in the apparent charge stored on a floating gate (or other charge storing element) of a non-volatile memory cell can occur because of the coupling of an electric field based on the charge stored in adjacent floating gates (or other adjacent charge storing elements). To compensate for this coupling, the read or programming process for a given memory cell can take into account the programmed state of an adjacent memory cell. To determine whether compensation is needed, a process can be performed that includes sensing information about the programmed state of an adjacent memory cell (e.g., on an adjacent bit line or other location).
摘要:
A semiconductor package having a low profile is disclosed. In embodiments, a surface mounted component may be mounted directly to the core of the semiconductor package substrate, so that there is no conductive layer, plating layers or solder paste between the component and the substrate core. The surface mounted component may be any type of component which may be surface mounted on a substrate according to an SMT process, including for example passive components and various packaged semiconductors.
摘要:
A method for repairing a neighborhood of rows in a memory array using a patch table is disclosed. First data to be stored in row N in a memory array of the memory device, second data, if any, stored in row N−1 in the memory array, and third data, if any, stored in row N+1 in the memory array are stored in a temporary storage area of a memory device. The first data is written in row N, and, in response to an error, the first data, the second data, if any, and the third data, if any, are written in respective rows in a repair area in the memory device. The addresses of rows N−1, N, and N+1 are added to a table stored in the memory device to indicate which rows in the repair area should be used instead of rows N−1, N, and N+1.
摘要:
Multiple copies of firmware code for controlling operation of a non-volatile flash memory system are stored at different suitable locations of the flash memory of a memory system. A map of addresses of these locations is also stored in the flash memory. Upon initialization of the memory system, boot code stored in the memory controller is executed by its microprocessor to reference the address map and load one copy of the firmware from the flash memory into a controller memory, from which it may then be executed by the microprocessor to operate the memory system to store and retrieve user data. An error correction code (ECC) is used to check the data but the best portions of the two or more firmware copies stored in the flash memory are used to reduce the need to use ECC. The firmware code may be stored in the flash memory in two-states when user data is stored in the same memory in more than two-states.
摘要:
Data stored in non-volatile storage is decoded using iterative probabilistic decoding and multiple read operations to achieve greater reliability. An error correcting code such as a low density parity check code may be used. In one approach, initial reliability metrics, such as logarithmic likelihood ratios, are used in decoding read data of a set of non-volatile storage element. The decoding attempts to converge by adjusting the reliability metrics for bits in code words which represent the sensed state. If convergence does not occur, e.g., within a set time period, the state of the non-volatile storage element is sensed again, current values of the reliability metrics in the decoder are adjusted, and the decoding again attempts to converge.
摘要:
Host system data files are written directly to a large erase block flash memory system with a unique identification of each file and offsets of data within the file but without the use of any intermediate logical addresses or a virtual address space for the memory. Directory information of where the files are stored in the memory is maintained within the memory system by its controller, rather than by the host. Each data file is uniquely identified in a file directory, which points to entries in a file index table (FIT) of data groups that make up the file and their physical storage locations in the memory.
摘要:
In a memory with block management system, program failure in a block during a time-critical memory operation is handled by continuing the programming operation in a breakout block. Later, at a less critical time, the data recorded in the failed block prior to the interruption is transferred to another block, which could also be the breakout block. The failed block can then be discarded. In this way, when a defective block is encountered during programming, it can be handled without loss of data and without exceeding a specified time limit by having to transfer the stored data in the defective block on the spot. This error handling is especially critical for a garbage collection operation so that the entire operation need not be repeated on a fresh block during a critical time. Subsequently, at an opportune time, the data from the defective block can be salvaged by relocation to another block.