Flash EEPROM system with simultaneous multiple data sector programming and storage of physical block characteristics in other designated blocks

• US 20060109712A1
• Filed: 12/29/2005
• Published: 05/25/2006
• Est. Priority Date: 02/17/2000
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: Jeffrey G. Craig, John S. Mangan, Kevin M. Conley
• Inventors: Conley, Kevin M., Mangan, John S., Craig, Jeffrey G.
• Granted Patent: US 7,184,306 B2
• Time in Patent Office: Days
• US Class Current: 365/185.110
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 2212/7203 Temporary buffering, e.g. using volatile buffer or dedicated buffer blocks
• CPC Class Codes: G06F 2212/7207 management of metadata or control data
• CPC Class Codes: G06F 2212/7208 Multiple device management, e.g. distributing data over multiple flash devices
• CPC Class Codes: G11C 16/10 Programming or data input circuits
• CPC Class Codes: G11C 16/107 Programming all cells in an array, sector or block to the same state prior to flash erasing
• CPC Class Codes: G11C 16/3459 Circuits or methods to verify correct programming of nonvolatile memory cells
• CPC Class Codes: G11C 2216/14 Circuits or methods to write a page or sector of information simultaneously into a nonvolatile memory, typically a complete row or word line in flash memory
• CPC Class Codes: G11C 29/82 for EEPROMs

Abstract

A non-volatile memory system is formed of floating gate memory cells arranged in blocks as the smallest unit of memory cells that are erasable together. The system includes a number of features that may be implemented individually or in various cooperative combinations. One feature is the storage in separate blocks of the characteristics of a large number of blocks of cells in which user data is stored. These characteristics for user data blocks being accessed may, during operation of the memory system by its controller, be stored in a random access memory for ease of access and updating. According to another feature, multiple sectors of user data are stored at one time by alternately streaming chunks of data from the sectors to multiple memory blocks. Bytes of data in the stream may be shifted to avoid defective locations in the memory such as bad columns. Error correction codes may also be generated from the streaming data with a single generation circuit for the multiple sectors of data. The stream of data may further be transformed in order to tend to even out the wear among the blocks of memory. Yet another feature, for memory systems having multiple memory integrated circuit chips, provides a single system record that includes the capacity of each of the chips and assigned contiguous logical address ranges of user data blocks within the chips which the memory controller accesses when addressing a block, making it easier to manufacture a memory system with memory chips having different capacities. A typical form of the memory system is as a card that is removably connectable with a host system but may alternatively be implemented in a memory embedded in a host system. The memory cells may be operated with multiple states in order to store more than one bit of data per cell.

Claims

1. A method of operating a re-programmable non-volatile memory system having floating gate memory cells organized into distinct blocks of a number of simultaneously erasable cells capable of storing a given quantity of data, the blocks of cells being further organized into a plurality of units, comprising:

receiving and temporarily storing in a buffer memory at least a given number of sectors of user data to be programmed into the memory system,

moving data in a stream from one of the given number of sectors of user data in the buffer at a time to a respective one of a given number of storage registers at a time, and

thereafter moving the user data from the given number of storage registers in parallel to respective ones of a given number of memory cell blocks that are located within different ones of a given number of said units.

2. The method according to claim 1, wherein moving data from the storage registers to the memory cell blocks includes moving one chunk of a sector of user data from each of the given number of registers, wherein the amount of data in a chunk is equal to one half or less of the amount of data in a sector.

3. The method according to claim 2, wherein moving data from the buffer memory to the storage registers includes moving one chunk at a time alternatively from the given number of sectors of user data stored in the buffer memory.

4. The method according to claim 1, wherein moving data from the storage registers to the memory cell blocks includes moving a full user data sector from each of the given number of registers.

5. The method according to claim 4, wherein moving data from the buffer memory to the storage registers includes moving data from one sector at a time in sequence from the given number of sectors of user data stored in the buffer memory.

6. The method according to claim 1, which additionally comprises, prior to commencing moving the stream of data, generating a data transformation bit field for each sector of user data and using that bit field to transform the user data that is moved in a stream, and further comprising inserting the generated transformation bit field into each of the given number of sectors of user data at its beginning.

7. The method according to claim 1, wherein moving data in a stream includes generating a redundancy code from the stream of user data of the individual sectors and appending the generated code to the ends of the user data from which they are generated.

8. The method according to claim 3, wherein moving data in a stream includes generating a redundancy code from the stream of user data of the individual sectors and appending the generated code to the ends of the user data from which they are generated, the redundancy code generation including separately storing intermediate results of the redundancy code generations in a separate code register for each of the given number of sectors of data and combining the stored intermediate results of one sector of data with a new quantity of data for the same sector.

9. The method according to claim 1, wherein moving data in a stream includes inserting bits into the data stream for storage within cells in any defective columns of the memory blocks, the inserted bits shifting the user data thereafter.

10. The method according to claim 3, wherein moving data in a stream includes inserting bits into the data stream for storage within cells in any defective columns of the memory blocks, the inserted bits shifting the user data thereafter, the bit insertion including referencing addresses of any defective columns within each of the given number of memory cell blocks into which user data is moved from the storage registers.

11. The method of any one of claims 1-6, wherein the memory cells within at least a plurality of said blocks are individually operated with more than two storage states in order to store more than one bit of data per memory cell.

12. The method of any one of claims 1-6, wherein the memory cells within at least a plurality of said blocks are individually operated with exactly two storage states in order to store exactly one bit of data per memory cell.

13. The method of any one of claims 1-6, wherein the memory cells within a first group of a plurality of said blocks are individually operated with more than two storage states in order to store more than one bit of data per memory cell, and wherein the memory cells within a second group of a plurality of said blocks different from said first group are individually operated with exactly two storage states in order to store exactly one bit of data per memory cell.