CN102411517A - Access method and access device for volatile memory - Google Patents
Access method and access device for volatile memory Download PDFInfo
- Publication number
- CN102411517A CN102411517A CN2010102981795A CN201010298179A CN102411517A CN 102411517 A CN102411517 A CN 102411517A CN 2010102981795 A CN2010102981795 A CN 2010102981795A CN 201010298179 A CN201010298179 A CN 201010298179A CN 102411517 A CN102411517 A CN 102411517A
- Authority
- CN
- China
- Prior art keywords
- block
- volatile memory
- bad
- blocks
- error correction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Techniques For Improving Reliability Of Storages (AREA)
- For Increasing The Reliability Of Semiconductor Memories (AREA)
Abstract
The invention discloses an access method and an access device for a volatile memory. The access method is applied to the volatile memory, and is used for accessing the volatile memory in a block access way. The volatile memory comprises a plurality of blocks. The access method comprises the following steps of: executing reading operation for one, with at least one known bad memory cell, of the plurality of blocks, wherein the reading operation comprises the reading of block data and error correction code data which correspond to the block; and correcting data, read from the at least one known bad memory cell, in the block data by using the error correction code data to generate corrected block data.
Description
Technical field
The present invention is relevant to a kind of access method of volatile memory and relevant apparatus, but refer to especially a kind of access have bad memory cell the access method and the relevant apparatus of a volatile memory.
Background technology
General volatile memory on using, in case when finding wherein to include bad or impaired memory cell, can exclude the memory cell that contains bad/impaired (downgrade) memory block and only use remaining memory block.Yet, in the prior art, tend in order to get rid of the bad/impaired memory cell of a little, and given up a large amount of storage space, thus, can cause the whole effective utilization of system to descend.
Summary of the invention
In view of this, but the purpose of this invention is to provide a kind of access have bad memory cell the access method and the relevant apparatus of a volatile memory, in the hope of making full use of storage space and elevator system usefulness.
According to one aspect of the present invention a kind of access method that is applied to a volatile memory is provided; Come this volatile memory of access in order to the mode of application area block access; This volatile memory includes a plurality of blocks; This access method includes: an onblock executing one read operation to having at least one known bad memory cell in these a plurality of blocks includes: read a pairing block data of this block and an error correction code data; And use this error correction code data and correct in this block data from the data that should at least one known bad memory cell institute be read, produce one and correct block data afterwards.
According to the present invention a kind of access method that is applied to a volatile memory is provided on the other hand; Come this volatile memory of access in order to the mode of application area block access; This volatile memory includes a plurality of blocks; This access method includes: to an onblock executing one write operation that has at least one known bad memory cell (bad cell) in these a plurality of blocks; Include: produce an error correcting code (error correction code, ECC) data according to original block data; And this error correction code data write to this volatile memory, and these original block data are write to this block, wherein these original block section data data write this at least one known bad memory cell.
According to another aspect of the invention a kind of access device that is applied to a volatile memory is provided; Come this volatile memory of access in order to the mode of application area block access; This volatile memory includes a plurality of blocks; This access device includes: a read element, in order to a block that has at least one known bad memory cell in these a plurality of blocks, read a pairing block data of this block and an error correction code data; And an error correction controller, be coupled to this read element, correct in this block data from the data that should at least one known bad memory cell institute be read in order to use this error correction code data, produce one and correct block data afterwards.
According to further aspect of the present invention a kind of access device that is applied to a volatile memory is provided; Come this volatile memory of access in order to the mode of application area block access; This volatile memory includes a plurality of blocks; This access method includes: a positive element more, in order to produce an error correction code data according to original block data; An and write element; Be coupled to this more positive element; In order to this error correction code data is write to this volatile memory; And with these original block data write to have in these a plurality of blocks at least one known bad memory cell block, wherein these original block section data data write this at least one known bad memory cell.
Useful technique effect of the present invention is: but access of the present invention has the access method and the relevant apparatus of a volatile memory of bad memory cell; Each block is arrived in address through redistributing bad memory cell; Application error corrigendum sign indicating number is revised block data wherein, just can make full use of storage space and elevator system usefulness thus.
Description of drawings
Fig. 1 is the synoptic diagram according to the access device that one embodiment of the invention realized.
Fig. 2 is for to use the synoptic diagram that access device reads a volatile memory according to one embodiment of the invention.
Fig. 3 is the synoptic diagram according to the access device that one embodiment of the invention realized.
Fig. 4 is for to use the synoptic diagram that access device writes to a volatile memory according to one embodiment of the invention.
Fig. 5 is the synoptic diagram according to the access device that one embodiment of the invention realized.
Embodiment
Please with reference to Fig. 1, it is the synoptic diagram according to the access device 100 that one embodiment of the invention realized.Access device 100 is applied to a volatile memory (volatile memory); For example: a dynamic RAM (dynamic random access memory; DRAM) or a static RAM (static random access memory; SRAM)), come this volatile memory of access through the mode of application area block access (block access).Access device 100 includes (but a being not limited to) read element 110 and an error correction controller 120, and wherein this volatile memory includes a plurality of blocks (block).Before the formal running of access device 100 and this volatile memory (execution read or write-in program before); The distribution situation and the number of bad memory cell in this volatile memory detects in the chamber of commerce of manufacturing plant of this volatile memory; And when the detected a plurality of bad memory cells of a faulty blocks in these a plurality of blocks outnumber an error correction threshold value TH time; Storage address to detected these a plurality of bad memory cells is redistributed (remapping) and is distributed with at least one bad memory cell in will these a plurality of bad memory cells and give the target block outside this faulty blocks; Redistribute setting ADD_remap to produce a storage address; Wherein in redistributing this faulty blocks after the storage address of detected these a plurality of bad memory cells, the number of the known bad memory cell that this target block had surpasses error correction threshold value TH.And read element 110 is in order to a block that has at least one known bad memory cell (bad cell) in these a plurality of blocks; Read the pairing block data of this block and an error correcting code (error correction code, ECC) data after redistributing.Error correction controller 120 then uses this error correction code data to correct oneself these at least one known data that bad memory cell read in this block data, produces a corrigendum back block data.
Please refer again to Fig. 2, it is for to use the synoptic diagram that access device 100 reads a volatile memory 200 according to one embodiment of the invention.For instance; If m block B1～Bm arranged in volatile memory 200; Wherein only have in the one first block B1 (that is have this block of at least one known bad memory cell) and include N1 bad memory cell;, and other block (bad memory cell that all has no among the B2～Bm).Therefore manufacturer is before read operation begins; Can detect earlier and include N1 bad memory cell in the first block B1; Then, whether the chamber of commerce of manufacturing plant decides follow-up action above error correction threshold value TH according to the quantity N1 of bad memory cell.If the quantity N1 of bad memory cell less than error correction threshold value TH (N1＜TH), volatile memory 200 directly provides block data according to original storage address, just and access device 100 can directly begin read operation; Yet as (the N1＞TH) of the quantity N1 of bad memory cell during greater than error correction threshold value TH; The chamber of commerce of manufacturing plant redistributes the storage address of these bad memory cells of detect; Distribute other block of giving in these a plurality of blocks (that is block B2～Bm) with will be wherein at least one bad memory cell; Bad number of memory cells in all blocks is all less than error correction threshold value TH; And produce this storage address and redistribute and set the block that ADD_remap redistributes volatile memory 200, then access device just can begin read operation 100 this moments.
Likewise; As long as have arbitrary block to have bad memory cell in the volatile memory 200 above error correction threshold value TH quantity; Manufacturer just can redistribute the address of each memory cell according to the quantity of the bad memory cell that is contained in each block, and the quantity of the bad memory cell that in each block, is had all is no more than till the error correction threshold value TH.For instance; If include N1 bad memory cell in the first block B1; And include N2 bad memory cell in the second block B2; Wherein the quantity N2 of the bad memory cell of the second block B2 greater than error correction threshold value TH (N2＞TH), (N1=TH-1＜TH) is under this situation and the quantity N1 of the bad memory cell of the first block B1 is no more than error correction threshold value TH just; With the bad memory cell of the second block B2 be re-assigned to block outside the second block B2 in (that is block B1, B3～Bm); Bad number of memory cells in all blocks is all less than error correction threshold value TH, and produces storage address and redistribute and set the block that ADD_remap redistributes volatile memory 200, just can begin read operation after the access device 100.
After in guaranteeing all blocks, all not surpassing the bad memory cell of error correction threshold value TH quantity, read element 110 can read the pairing block data of each block one by one.At first, read element 110 reads the one first block data D1 of the first block B1 and an error correcting code (error correction code, ECC) the data ECC1 of the corresponding first block B1 earlier.Then, error correction controller 120 can application errors corrigendum code data ECC1 cooperate the first block data D1 with correct the first block data D1 in mistake, and produce one first corrigendum back block data.In this embodiment; Error correcting code ECC1 is the parity check code (parity) that determines out according to error correction threshold value TH; Therefore; The number of the application error corrigendum code data ECC1 and the first block data D1 institute recoverable error is TH; ((N1＜TH), so error correction controller 120 can be according to error correction code data ECC1 and the first block data D1 revises among the first block data D1 mistake that bad memory cell produced owing to the first block B1 easily and the first block B1 has N1 bad memory cell.Likewise; Block data D1～Dm that access device can read block B1～Bm respectively with and pairing error correction code data ECC1～EECm respectively; Because the quantity of the bad memory cell that is comprised in each block among block B1～Bm all is less than error correction threshold value TH, so the interior mistake that quantity caused owing to bad memory cell of each block all can be revised through error correction controller 120 among block B1～Bm.Thus; Even have bad memory cell in the volatile memory 200; Through redistributing the address of bad memory cell and the program of error correction, access device 100 still can fully use volatile memory 200 wherein effective storage space and need not give up the block that includes bad memory cell.
Please refer again to Fig. 3, it is the synoptic diagram according to the access device 300 that one embodiment of the invention realized.Access device 300 is that the mode of application area block access is come access one a volatile memory (dynamic RAM (dynamic random access memory; DRAM) or a static RAM (static random access memory; SRAM)), wherein this volatile memory includes a plurality of blocks.Access device 300 includes more positive element 320 of (but being not limited to) write element 310 and.Wherein before the formal running of access device 300 and this volatile memory (read or write-in program before); The chamber of commerce of manufacturing plant of this volatile memory detects the distribution situation and the number of bad memory cell in this volatile memory earlier; And to each particular block of bad number memory cells in these a plurality of blocks above an error correction threshold value TH; Manufacturer redistributes the storage address of the detected a plurality of bad memory cells of this particular block to distribute with at least one bad memory cell in will these a plurality of bad memory cells and gives other block in these a plurality of blocks; Redistribute the block that setting ADD_remap redistributes volatile memory 200 to produce a storage address; Wherein after the storage address of the bad memory cell of redistributing all particular block, the number of the bad memory cell that each block had does not surpass error correction threshold value TH in these a plurality of blocks.Then, when using access device 300 to carry out this volatile memory is write fashionable, more positive element 320 is in order to produce an error correction code data according to original block data.Write element 310 then can write to this volatile memory with this error correction code data, and these original block data are write to the block that has at least one known bad memory cell in these a plurality of blocks.
Please refer again to Fig. 4, it wherein includes m block B1～Bm for to use the synoptic diagram that access device 300 writes to a volatile memory 200 according to one embodiment of the invention in the volatile memory 200.Likewise; Manufacturer does not all surpass the bad memory cell of error correction threshold value TH quantity in guaranteeing all blocks after; Can produce a storage address and redistribute the block that setting ADD_remap redistributes volatile memory 200, more positive element 320 can produce an error correcting code ECCin according to a block data Din.And write element 310 is coupled to more positive element 320; In order to error correction code data ECCin is write among the volatile memory 200; And with block data Din write block B1～Bm one of them; In this embodiment, write element 310 can write to block data Din in the middle of the block B1 with at least one known bad memory cell.Thus, even include known bad memory cell among the block B1, the block data Din of the middle storage of block B1 is follow-up still can be cooperated error correction code data ECCin and is correctly read out.
Above-mentioned example is merely and is used for explaining spirit of the present invention, is not to be used for limiting scope of the present invention, and for instance, access device 100 also can be integrated into a single device with access device 300.Please with reference to Fig. 5, it is the synoptic diagram according to the access device 500 that one embodiment of the invention realized, access device 500 includes a read-write elements 510 and an error correction element 520.The address that the chamber of commerce of manufacturing plant redistributes bad memory cell to be guaranteeing all to surpass the bad memory cell of the quantity of error correction threshold value TH in all blocks, and produces a storage address and redistribute and set the block that ADD_remap redistributes volatile memory 200.The function of the write element 210 among the read element 110 of read-write elements 510 whiles in Fig. 1 and Fig. 3, the action of reading or writing in the different stages respectively.Error correction element 520 is the function of the more positive element 320 among the error correction controller 120 of while in Fig. 1 and Fig. 3 then; Carry out different runnings in the different stages respectively, produce the error correction data or use the error correction code data to come the modified block data.In addition; Storage address is redistributed setting ADD_remap and also only is not defined as and can be provided by manufacturer; Storage address redistribute set ADD_remap also can by access device 500 inside in a fixed cycle (for example: one month cycle) its pairing volatile memory is scanned to upgrade; Thus, even this volatile memory is passed through in time and produced new bad memory cell, access device 500 also can be got rid of these new influences that bad memory cell caused; And then prolonging the serviceable life of this volatile memory, the variation in this type design also belongs to category of the present invention.
In sum; But the invention provides access method and relevant apparatus that a kind of access has a volatile memory of bad memory cell; Each block is arrived in address through redistributing bad memory cell; Application error corrigendum sign indicating number is revised block data wherein, just can make full use of storage space and elevator system usefulness thus.
The above is merely preferred embodiment of the present invention, and all changes that is equal to or replacement that all schemes spiritual according to the present invention and that claims limit have been done all should belong to covering scope of the present invention.
Claims (12)
1. an access method that is applied to a volatile memory is come this volatile memory of access in order to the mode of application area block access, and this volatile memory includes a plurality of blocks, and this access method includes:
Onblock executing one read operation to having at least one known bad memory cell in these a plurality of blocks includes:
Read a pairing block data of this block and an error correction code data; And
Use this error correction code data and correct in this block data, produce one and correct block data afterwards from the data that should at least one known bad storage element institute be read.
2. access method according to claim 1 is characterized in that, includes:
Before carrying out this read operation, carry out an initialization allocator, wherein this initialization allocator includes:
Detect the distribution situation and the number of bad memory cell in this volatile memory; And
Each particular block that surpasses an error correction threshold value to bad number memory cells in these a plurality of blocks; The storage address of the detected a plurality of bad memory cells of this particular block redistributed to distribute with at least one bad memory cell in will these a plurality of bad memory cells give other block in these a plurality of blocks; Wherein after the storage address of the bad memory cell of redistributing all particular block, the number of the bad memory cell that each block had does not surpass this error correction threshold value in these a plurality of blocks.
3. access method according to claim 1 is characterized in that, this volatile memory is a dynamic RAM or a static RAM.
4. an access method that is applied to a volatile memory is come this volatile memory of access in order to the mode of application area block access, and this volatile memory includes a plurality of blocks, and this access method includes:
Onblock executing one write operation to having at least one known bad memory cell in these a plurality of blocks includes:
Produce an error correction code data according to original block data; And
This error correction code data is write to this volatile memory, and these original block data are write to this block, wherein these original block section data data write this at least one known bad memory cell.
5. access method according to claim 4 is characterized in that other includes:
Before carrying out this write operation, carry out an initialization allocator, wherein this initialization allocator includes:
Detect the distribution situation and the number of bad memory cell in this volatile memory; And
Each particular block that surpasses an error correction threshold value to bad number memory cells in these a plurality of blocks; The storage address of the detected a plurality of bad memory cells of this particular block redistributed to distribute with at least one bad memory cell in will these a plurality of bad memory cells give other block in these a plurality of blocks; Wherein after the storage address of the bad memory cell of redistributing all particular block, the number of the bad memory cell that each block had does not surpass this error correction threshold value in these a plurality of blocks.
6. access method according to claim 5 is characterized in that, this volatile memory is a dynamic RAM or a static RAM.
7. an access device that is applied to a volatile memory comes this volatile memory of access in order to the mode of application area block access, and this volatile memory includes a plurality of blocks, and this access device includes:
One read element in order to a block that has at least one known bad memory cell in these a plurality of blocks, reads a pairing block data of this block and an error correction code data; And
One error correction controller is coupled to this read element, corrects in this block data from the data that should at least one known bad memory cell institute be read in order to use this error correction code data, produces one and corrects block data afterwards.
8. access device according to claim 7; It is characterized in that; Other includes a storage address and redistributes setting; This storage address is redistributed setting and is redistributed in order to the storage address that bad number memory cells in will these a plurality of blocks surpasses a plurality of bad memory cells in each particular block of an error correction threshold value; So that other block in these a plurality of blocks is given at least one bad memory cell distribution in these a plurality of bad memory cells, and the number of the bad memory cell that each block had surpasses this error correction threshold value in these a plurality of blocks.
9. access device according to claim 7 is characterized in that, this volatile memory is a dynamic RAM or a static RAM.
10. an access device that is applied to a volatile memory comes this volatile memory of access in order to the mode of application area block access, and this volatile memory includes a plurality of blocks, and this access device includes:
One positive element more is in order to produce an error correction code data according to original block data; And
One write element; Be coupled to this more positive element; In order to this error correction code data is write to this volatile memory; And with these original block data write to have in these a plurality of blocks at least one known bad memory cell block, wherein this original block section data data system writes this at least one known bad memory cell.
11. access device according to claim 10; It is characterized in that; Other includes a storage address and redistributes setting; This storage address is redistributed setting and is redistributed in order to the storage address that bad number memory cells in will these a plurality of blocks surpasses a plurality of bad memory cells in each particular block of an error correction threshold value; So that other block in these a plurality of blocks is given at least one bad memory cell distribution in these a plurality of bad memory cells, and the number of the bad memory cell that each block had surpasses this error correction threshold value in these a plurality of blocks.
12. access device according to claim 10 is characterized in that, this volatile memory is a dynamic RAM or a static RAM.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010298179 CN102411517B (en) | 2010-09-21 | 2010-09-21 | Access method and access device for volatile memory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010298179 CN102411517B (en) | 2010-09-21 | 2010-09-21 | Access method and access device for volatile memory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102411517A true CN102411517A (en) | 2012-04-11 |
| CN102411517B CN102411517B (en) | 2013-09-11 |
Family
ID=45913603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010298179 Active CN102411517B (en) | 2010-09-21 | 2010-09-21 | Access method and access device for volatile memory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102411517B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824598A (en) * | 2012-11-19 | 2014-05-28 | 智微科技股份有限公司 | Error checking and correcting method and error checking and correcting circuit |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5848076A (en) * | 1996-06-10 | 1998-12-08 | Mitsubishi Denki Kabushiki Kaisha | Memory card with capability of error correction and error correction method therefore |
| CN1549121A (en) * | 2003-05-09 | 2004-11-24 | 台湾积体电路制造股份有限公司 | Hiding error detecting/correcting latency in dynamic random access memory (DRAM) |
| CN1864232A (en) * | 2003-06-12 | 2006-11-15 | 因芬尼昂技术股份公司 | Error detection and correction method and apparatus in a magnetoresistive random access memory |
-
2010
- 2010-09-21 CN CN 201010298179 patent/CN102411517B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5848076A (en) * | 1996-06-10 | 1998-12-08 | Mitsubishi Denki Kabushiki Kaisha | Memory card with capability of error correction and error correction method therefore |
| CN1549121A (en) * | 2003-05-09 | 2004-11-24 | 台湾积体电路制造股份有限公司 | Hiding error detecting/correcting latency in dynamic random access memory (DRAM) |
| CN1864232A (en) * | 2003-06-12 | 2006-11-15 | 因芬尼昂技术股份公司 | Error detection and correction method and apparatus in a magnetoresistive random access memory |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824598A (en) * | 2012-11-19 | 2014-05-28 | 智微科技股份有限公司 | Error checking and correcting method and error checking and correcting circuit |
| CN103824598B (en) * | 2012-11-19 | 2017-02-22 | 联芸科技（杭州）有限公司 | Error checking and correcting method and error checking and correcting circuit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102411517B (en) | 2013-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8732552B2 (en) | Block management method, memory controller and memory storage device thereof | |
| JP5221699B2 (en) | Semiconductor memory device | |
| JP5132687B2 (en) | Error detection and correction method and apparatus using cache in memory | |
| US20100199020A1 (en) | Non-volatile memory subsystem and a memory controller therefor | |
| US9361036B2 (en) | Correction of block errors for a system having non-volatile memory | |
| JP2016540288A (en) | Method and apparatus for non-volatile RAM error remapping | |
| CN104932951B (en) | A kind of nand flash memory occur ECC can not error correction when data reconstruction method | |
| US20090150747A1 (en) | Correction of errors in a memory array | |
| JP2013089082A (en) | Memory controller, semiconductor storage system and memory control method | |
| CN102969028A (en) | Method, system, and flash memory of ECC dynamic adjustment | |
| CN102929740A (en) | Method and device for detecting bad block of storage equipment | |
| US10275307B2 (en) | Detection of error patterns in memory dies | |
| CN103744744A (en) | Data storage device and data checking method of volatile storage | |
| CN103106148B (en) | Block management method, storage controller and storage storing device | |
| CN102411517B (en) | Access method and access device for volatile memory | |
| US20080068898A1 (en) | Data readout circuit of memory cells, memory circuit and method of reading out data from memory cells | |
| CN105718328A (en) | Data backup method and system for memory bad block | |
| US11494260B2 (en) | Memory with an error correction function and related memory system | |
| CN102141944B (en) | Method for reducing errors incapable of being corrected, memory device and controller thereof | |
| CN113342577A (en) | Storage device and data recovery method thereof | |
| US20120066560A1 (en) | Access method of volatile memory and access apparatus of volatile memory | |
| US20100153777A1 (en) | Program updating system having correction storage units and method thereof | |
| CN104111895A (en) | Method for utilizing DRAM defective products | |
| US20060117134A1 (en) | System and method for prolonging usage lifetime of a non-volatile memory | |
| US20230187012A1 (en) | Implementing fault isolation in dram |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |