摘要:
A nonvolatile memory device includes a plurality of memory controllers. Each of the memory controllers has an aggregation processing part and an aggregation synchronization part. Based on a signal from the aggregation synchronization part, the aggregation processing part aggregates valid data of a temporary physical block into another physical block. When one of the memory controllers requires an aggregation process, the aggregation synchronization part sends a synchronization signal to the other memory controller, so that the aggregation process is simultaneously carried out by the other memory controller. Thus, in the nonvolatile memory device having a plurality of memory controllers, it is possible to reduce the time required for the aggregation process and carry out a high-speed writing process.
摘要:
In a storage having a nonvolatile RAM of destructive read type, the number of restorations attributed to data read from the nonvolatile RAM is decreased, and the overall life of the storage is prolonged. In a storage having a nonvolatile RAM of destructive read type and a volatile RAM and holding the same data in the nonvolatile and volatile RAMs, data is read out of the volatile RAM in reading and data is written in both volatile and nonvolatile RAMs in writing.
摘要:
A physical area management table (105) and a pointer table (106) are stored in a nonvolatile auxiliary storage memory (107). When a logical-physical conversion table (108) is updated (restored) in a main storage memory (140), the restored area is determined in a re-arrangement way by the pointer table to avoid rewrite concentration on the main storage memory (140). Immediately after data is written in the main storage memory (140), the state of the physical block on the physical area management table (105) is updated. Consequently, even if power interruption occurs, it is possible to reliably judge if the data is valid or not.
摘要:
In a storage having a nonvolatile RAM of destructive read type, the number of restorations attributed to data read from the nonvolatile RAM is decreased, and the overall life of the storage is prolonged. In a storage having a nonvolatile RAM of destructive read type and a volatile RAM and holding the same data in the nonvolatile and volatile RAMs, data is read out of the volatile RAM in reading and data is written in both volatile and nonvolatile RAMs in writing.
摘要:
Used is a nonvolatile memory such as a multi-level NAND flash memory having memory cells for holding data of a plurality of pages. When the data is to be written in the nonvolatile memory 110, a physical unit is consisted in units of a plurality of paired pages. When all the physical units cannot be written, the data is copied from an old physical block holding an already written effective data, and is written in a new physical block till the written, from the first section of a new physical unit, so that an error can be prevented.
摘要:
It is possible to accurately detect a physical block which has caused a fixture defect in a flash memory so as to limit the use of the physical block. By recording a history of generation of a physical block error and a history of physical erasing in an ECC error record, it is judged whether the error which has occurred is accidental or caused by a fixture defect. When no error is caused in the data written by physical erasing after a first read error occurrence, the first error is accidental and if another error is caused, the error is judged to be caused by a fixture defect. By using such an ECC error record, it is possible to accurately judge whether the error is accidental or caused by a fixture defect. By eliminating use of the physical block judged to have a fixture defect, it is possible to reduce read errors.
摘要:
It is possible to accurately detect a physical block which has caused a fixture defect in a flash memory so as to limit the use of the physical block. By recording a history of generation of a physical block error and a history of physical erasing in an ECC error record, it is judged whether the error which has occurred is accidental or caused by a fixture defect. When no error is caused in the data written by physical erasing after a first read error occurrence, the first error is accidental and if another error is caused, the error is judged to be caused by a fixture defect. By using such an ECC error record, it is possible to accurately judge whether the error is accidental or caused by a fixture defect. By eliminating use of the physical block judged to have a fixture defect, it is possible to reduce read errors.