Electrical computers and digital processing systems: memory – Addressing combined with specific memory configuration or... – For multiple memory modules
Reexamination Certificate
1999-03-31
2002-06-04
Lane, Jack A. (Department: 2185)
Electrical computers and digital processing systems: memory
Addressing combined with specific memory configuration or...
For multiple memory modules
C711S103000, C711S170000
Reexamination Certificate
active
06401160
ABSTRACT:
FIELD OF THE INVENTION
This invention relates to the field of computer memory storage systems. In particular, this invention is drawn to method and apparatus for storing code and data in the same nonvolatile memory such that the code/data boundary is adjustable.
BACKGROUND OF THE INVENTION
Communications devices such as cellular telephones and pagers need the ability to store both data and code. In addition, these communications devices typically require some sort of working memory.
These communication devices generally need to store the code and at least some of the data in nonvolatile memory. For example, serial numbers, authorization codes, frequently dialed numbers, etc. are examples of data that might be stored in nonvolatile memory. Given that the code and data are updated at different frequencies, the communications devices often used different types of nonvolatile memory for storage of data and code. As a result, prior art communications devices typically included one type of nonvolatile memory for code storage, another nonvolatile memory for data storage, and random access memory such as static random access memory for working memory.
One type of nonvolatile memory is a flash electrically erasable programmable read only memory (flash EEPROM). Flash EEPROM (hereinafter “flash memory”) is typically arranged as blocks of single transistor memory cells. Although flash memory is rewritable, the memory cells cannot be re-programmed unless they have first been erased. Moreover, the cells are erasable only in blocks. Thus in order to erase one cell, an entire block of cells must be erased. Updating the flash memory requires some form of media manager to handle copying of valid information out of the block, erasing the block, and writing the valid information as well as the update information to the same or another block. The process of erasing, writing, etc. is relatively time consuming.
Another type of nonvolatile memory is an electrically erasable programmable read only memory (EEPROM) having two-transistor memory cells. Although EEPROM may be arranged into erasable blocks similar to the flash memory, the two-transistor EEPROM is relatively easy to update and does not require the sophisticated media management that flash memory requires for updates. Writing a value to the two-transistor EEPROM cell, however, requires significantly greater time than does programming of an erased single transistor flash memory cell.
One prior art communications device memory architecture includes flash memory for code storage, EEPROM for data storage, and random access memory as working memory.
The use of a variety of nonvolatile memories tends to increase form factor size as well as design and fabrication costs, Personal communications devices such as pagers and cellular telephones are often differentiated based on their size, features, cost, and rate of power consumption.
Moreover as new features are constantly being added, the ratio of code to data may need to change. Providing excess storage for both types of nonvolatile memory increases the cost of the device and is wasteful, unless the storage requirements for both the code and the data are expected to grow. By storing code and data into different types of nonvolatile memory, excess storage capacity in the nonvolatile memory used for code is unavailable for storing data. Similarly, excess storage capacity in the nonvolatile memory used for data is unavailable for storing code. Thus the design is unable to easily accommodate changes in the ratio of nonvolatile memory allocated to code versus that allocated to data.
SUMMARY OF THE INVENTION
A method of moving a boundary in a nonvolatile memory is disclosed. The method comprises identifying a boundary location in the nonvolatile memory. The boundary location comprises a position between a first block of a first type and a second block of a second type. The method also comprises allocating objects from a last block of the first type to a second block of the first type. Additionally, the method comprises erasing the last block of the first type.
Other features and advantages of the present invention will be apparent from the accompanying drawings and from the detailed description that follows below.
REFERENCES:
patent: 5592669 (1997-01-01), Robinson et al.
patent: 5963980 (1999-10-01), Coulier et al.
patent: 2 251 324 (1992-07-01), None
patent: 97/08619 (1997-03-01), None
International Search Report mailed Jun. 5, 2000 in counterpart PCT application No. PCT/US00/06241.
Hasbun Robert N.
See Deborah L.
Blakely , Sokoloff, Taylor & Zafman LLP
Intel Corporation
Lane Jack A.
LandOfFree
Method and apparatus to permit adjustable code/data boundary... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus to permit adjustable code/data boundary..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus to permit adjustable code/data boundary... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2920659