NON-VOLATILE MEMORY WITH ERROR DETECTION

Abstract

Data move operations in a memory device are described that enable identification of data errors. Error detection circuitry in the memory device can be operated using parity data or ECC data stored in the memory. Results of the error detection can be accessed by a memory controller for data repair operations by the controller.

Description

FIELD OF THE INVENTION

The present invention relates to memory devices and more particularly to non-volatile memory internal data move operations.

BACKGROUND

Error detection and correction (ECC) engines are well known to those skilled in the art. An ECC engine is a device which performs a process of detecting for error and correcting errors to ensure the accuracy and integrity of data during a data transmission. Different ECC engines are based on Hamming Codes, Reed-Solomon Codes or other techniques to correct for data errors.

In memory systems a memory controller typically writes data and ECC data to a memory device. The ECC data is used by the controller during a read operation to identify and correct errors that may have occurred since the data was written to the memory.

Memory devices can be categorized in two broad areas as volatile and non-volatile. Volatile memory devices require power to maintain data, while non-volatile memories are capable of maintaining data in the absence of a power supply.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram of a memory system according to an embodiment of the invention.

FIG. 2 is a flow chart illustrating embodiments of the present invention.

FIG. 3 is a flow chart illustrating additional embodiments of the present invention.

DESCRIPTION

In the following detailed description of the invention, reference is made to the accompanying drawings which form a part hereof, and in which is shown, by way of illustration, different embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. Other embodiments may be utilized and structural, logical, and electrical changes may be made without departing from the scope of the present invention.

The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims, along with the full scope of equivalents to which such claims are entitled.

Embodiments of the present invention can include a semiconductor memory device having an array of memory cells. The memory cells are non-volatile, and can be charge trapping cells such as floating gate transistors or NROM cells, phase-change memory cells such as chalcogenide cells, programmable conductor random access memory (PCRAM), latching cells such as SRAM, or magnetic random access memories (MRAM's). In addition, the memory cells can store one or more bits per cell.

FIG. 1 is a simplified block diagram of an integrated circuit dynamic memory device 100 in accordance with an embodiment of the invention. The memory device 100 includes an array of non-volatile memory cells 102, an address circuitry 104, and Input/Output (I/O) circuitry 110. In one embodiment the memory array is a NAND Flash memory array. In another embodiment, the memory array is a NOR Flash memory array.

A control circuit 108 is provided to manage memory operations, such as read, write and erase operations. As explained below, one memory operation performed by the memory control circuitry includes an internal data move operation.

The memory device 100 can be coupled to a controller 114 for accessing the memory array 102. The memory device 100 receives control signals across control lines 116 from the controller 114 to control access to the memory array 102. Access to the memory array 102 is directed to one or more target memory cells in response to address signals received across address lines 118. Once accessed in response to the control signals and the address signals, data is written to or read from the memory cells across data, DQ, lines 120.

It will be appreciated by those skilled in the art that additional circuitry and control signals can be provided, and that the memory device of FIG. 1 has been simplified to help focus on the invention. It will be understood that the above description of a memory device is intended to provide a general understanding of the memory and is not a complete description of all the elements and features of a typical memory device.

The non-volatile memory also includes an error detecting code (EDC) circuit 140. As described below, the EDC in one embodiment uses parity bits to detect errors, and in another embodiment uses ECC data provided by the controller 114.

Non-volatile memory devices, such as FLASH memories, often perform an internal data move operation. This operation is performed as part of “house keeping.” That is, data stored in a first memory array location is moved to a second memory array location so that memory operations, such as memory cell erasing, can be performed on the first location.

In prior art memory devices, the data is not read by the controller during the move operation. As such, the ECC circuitry of the controller is not employed during the move to determine if an error exists in the memory data.

In one embodiment, the EDC circuit 140 of the non-volatile memory device 100 uses a parity technique for identifying single bit errors. As such, when data is written to the memory array parity is also stored in the memory. The parity data can be internally generated and stored for later use. The parity data can be stored in the array or in an overhead location. For example, in one embodiment a 512 bit array sector has 16 bits of overhead reserved for the parity data. The parity data can be restricted from external access.

During an internal data move the parity bit is used to detect single bit errors. The memory controller 114 can check the status of an error register 150 to determine if an error was detected while executing the internal move. If an error is detected, the controller can read the data from the memory into a buffer of the controller, perform an ECC operation to correct the error, and write the corrected data back into the memory. The error register can be one or multiple bits long. That is, a simple status flag can be used in one embodiment to indicate that an error was detected.

In another embodiment, the memory device 100 includes an ECC register 160 for storing ECC information provided by the controller. The register can store an indication of the ECC scheme employed by the controller, for example Hamming, BCH or Reed-Solomon coded. In addition to the type of ECC used by the controller, register 160 can store an address, or offset, of the location of the ECC data bytes associated with array data. ECC techniques are well know in the art and are not listed or described in detail herein. It will be understood that embodiments of the present invention can be implemented without limitation to a specific ECC code(s).

The EDC circuit 140 detects errors during internal data move operations using the ECC register 160 information. That is, the EDC uses the identified ECC code and ECC data to detect errors. The memory controller 114 can check the status of an error register 150 to determine if an error was detected while executing the internal move. The error register can be one or multiple bits long. That is, a simple status flag can be used in one embodiment to indicate that an error was detected.

If an error is detected, the controller can read the data from the memory into a buffer of the controller, perform an ECC operation to correct the error, and write the corrected data back into the memory. To reduce the time needed by the controller to correct the error, the error register, in one embodiment, contains multi-bit repair solution data. As such, the controller only needs to execute the repair solution prior to re-writing the data to the memory.

It will be appreciated that there are a wide variety of ECC schemes available for use by the controller. Implementing each of these schemes on the memory device would be cost prohibitive. As such, the memory device may be limited to implementing an EDC technique based on one, or a select few, ECC scheme(s).

FIG. 2 is a flow chart illustrating embodiments of the present invention. The memory controller instructs the non-volatile memory to perform an internal data move operation 200. The memory moves data from a first location to a second location within the memory array 210. An error detection operation is performed 220 using parity data stored in the memory. In response to the error detection operation, an error register is set 230 accordingly. Upon completion of the data move, the controller reads the error register 240 to determine if an error was detected. If an error was detected, the controller reads the moved data 250, applies an ECC operation 260 and re-writes the corrected data to the memory 270.

FIG. 3 is a flow chart illustrating additional embodiments of the present invention. The memory controller instructs the non-volatile memory to perform an internal data move operation 300. The memory moves data from a first location to a second location within the memory array 310. The controller provides an indication of the ECC technique implemented by the controller and a location identifier of the ECC data corresponding to the moved data 320. An error detection operation is performed 330 using the ECC data stored in the memory. In response to the error detection operation, an error register is set 340 indicating an error status, and optionally a repair solution for the moved data. Upon completion of the data move, the controller reads the error register 350 to determine if an error was detected, and the repair solution. If an error was detected, the controller reads the moved data 360, applies the repair solution 370 and re-writes the corrected data to the memory 380.

Embodiments of the present invention allow internal data move operations in a non-volatile memory while identifying data errors. The error detection can be implemented by using parity data or ECC data stored in the memory. Results of the error detection can be accessed by a memory controller for data repair operations by the controller.

Claims

1. A memory device comprising: an array of memory cells;control circuitry to perform an internal data move operation such that memory data is moved from a first array location to a second array location;an error detection circuit to detect an error in the memory data as part of the internal data move operation; andan error register to indicate an error state of the memory data corresponding to detection of an error in the memory data during the internal data move operation.

2. The memory device of claim 1, wherein the memory device is arranged to store parity data for use in error detection during the internal data move operation.

3. The memory device of claim 2, wherein the memory device is configured to restrict external access to the parity data.

4. The memory device of claim 1, wherein the memory device comprises an error correction code (ECC) register to store ECC data such that the error correction code register is configured to provide the ECC data to detect an error in the memory data as part of the internal data move operation.

5. The memory device of claim 4, wherein the error correction code register is arranged to store an indication of an ECC scheme used by an external memory controller to correct a detected an error in the memory data as part of the internal data move operation.

6. The memory device of claim 5, wherein the memory device is arranged to implement one or more ECC schemes selected from a group including a Hamming scheme, a BCH scheme, and a Reed-Solomon scheme.

7. The memory device of claim 4, wherein the error correction code (ECC) register is arranged to store an address of a location of ECC data bytes associated with the memory data.

8. A system comprising: a memory controller;a memory device coupled to communicate with the memory controller, wherein the memory device includes: an array of memory cells;control circuitry to perform an internal data move operation such that memory data is moved from a first memory array location to a second memory array location in response to a data move command from the memory controller,an error detection circuit to detect an error in the memory data as part of the internal data move operation; andan error register to indicate an error state of the memory data corresponding to detection of an error in the memory data during the internal data move operation.

9. The system of claim 8, wherein the error register is configured to be read by the memory controller.

10. The system of claim 8, wherein the memory controller, upon determination of an error in the memory data during the internal data move operation, is operable to: read the memory data from the memory device into a buffer of the memory controller;perform an error correction code (ECC) operation to correct the error; andwrite the corrected memory data back into the memory device.

11. The system of claim 8, wherein the determination of an error in the memory data during the internal data move operation is based on parity stored in the memory device.

12. The system of claim 8, wherein the error register contains repair solution data readable by the memory controller, the memory controller operable to execute a repair solution of the error in the memory data and to write the corrected memory data back into the memory device

13. A method of operating a memory device, the method comprising: receiving, in a memory device, a command to perform an internal data move operation of data in the memory device;controlling the implementation of the command using control circuitry to move the data from a first storage location in the memory device to a second storage location in the memory device;evaluating, as part of the internal data move operation, the data to determine if an error is present in the data using an error detection circuit of the memory device; andsetting an indicator in an error register to indicate an error state of the data corresponding to detection of an error in the data during the internal data move operation.

14. The method of claim 13, wherein evaluating the data comprises performing a parity check operation on the data using parity data stored in the memory device.

15. The method of claim 13, wherein evaluating the data comprises performing an error detection operation using error correction code (ECC) data stored in the memory device.

16. The method of claim 15, the method further comprises storing the ECC data in the memory device using an external memory controller.

17. A method of operating a memory device, the method comprising: sending a command from a memory controller to a memory device, the command arranged to initiate an internal data move operation of data in the memory device as a organizing operation, the internal data move operation including moving the data from the first storage location in the memory device to a second storage location in the memory device;evaluating the data to determine if an error is present in the data, the evaluation using an error detection circuit of the memory device in the internal data move operation such that the error detection circuit uses error correction code (ECC) data in the memory device corresponding to the data;setting a indicator in an error register to indicate an error status based upon the evaluation; andcorrecting the error using the memory controller based on the indicator.

18. The method of claim 17, wherein the method includes: reading the data from the memory device into a buffer of the memory controller;performing an error correction code (ECC) operation to correct the error; andwriting the corrected memory data back into the memory device.

19. The method of claim 17, wherein the method includes storing, in the error register, data indicating a repair solution for detected errors.

20. The method of claim 17, wherein the method includes selecting one or more error correction code (ECC) schemes to correct the error present in the data.