CN105355233B - Efficient data wiring method based on PCM reversion error correction algorithms - Google Patents
Efficient data wiring method based on PCM reversion error correction algorithms Download PDFInfo
- Publication number
- CN105355233B CN105355233B CN201510819072.3A CN201510819072A CN105355233B CN 105355233 B CN105355233 B CN 105355233B CN 201510819072 A CN201510819072 A CN 201510819072A CN 105355233 B CN105355233 B CN 105355233B
- Authority
- CN
- China
- Prior art keywords
- group
- area
- mistake
- address
- pointer
- 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.)
- Active
Links
Abstract
The invention discloses a kind of efficient data wiring method based on PCM reversion error correction algorithms, comprise the following steps：Data block is divided into multiple groups, and the group comprising mistake in multiple groups and the group not comprising mistake are distinguished by mark；The group of predetermined number is formed into a data segment, and each data segment is divided into first area and second area, wherein, the quantity of the group comprising mistake in first area is not more than the quantity for the group for not including mistake in second area；Each group comprising mistake in first area is replaced with to a group for not including mistake in second area, so that the group in first area is the group not comprising mistake；New data block is separately constituted in first area and second area, and data are write to new data block.Method according to embodiments of the present invention, it can effectively lift the write performance of storage device.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of efficient data based on PCM reversion error correction algorithms is write
Enter method.
Background technology
NVRAM (the Non-Volatile Random such as such as PCM (Phase Change Memory, phase transition storage)
Access Memory, nonvolatile random access memory) because with storage density is big, readwrite performance is high and long lifespan etc.
Advantage and be widely used.
PCM can often run into a kind of stuck-at fault (stuck-at fault) class mistake during data are write, and
Error correction mainly is carried out by inverting error correction algorithm when running into this kind of wrong, i.e., will be write again after data reversal, by continuous
Attempt to find correct data write mode.But this kind of algorithm can cause storage device PCM write performance degradation,
Specific reason is as follows：(1) by write-in can cause write latency to double again after data reversal；(2) PCM Wear leveling algorithms
Data to be written is evenly distributed in each data block, and the mistake of the above-mentioned type can increase over time and constantly tire out
Product, therefore, with the use of equipment, the data block comprising mistake in PCM will be more and more；(3) continuously without above-mentioned wrong
The length of data block constantly shortens, and causes the probability increase for running into the data block comprising mistake；(4) above-mentioned error correction in correlation technique
The design mechanism of method so that at most only have a mistake in each group, this undoubtedly accelerates the scattered of mistake；(5) PCM writes
Enter that expense is larger, cause influence of the write latency to PCM also larger.
Therefore, in view of the above-mentioned problems, up for proposing a kind of data write-in side that can improve storage device write performance
Method.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.Therefore, the present invention
Purpose is to propose a kind of efficient data wiring method based on PCM reversion error correction algorithms, can effectively lift storage device
Write performance.
Efficient data wiring method based on PCM reversion error correction algorithms according to embodiments of the present invention, comprises the following steps：
Data block is divided into multiple groups, and distinguished by mark in the multiple group comprising wrong group and not comprising mistake
Group by mistake；The group of predetermined number is formed into a data segment, and each data segment is divided into first area and second
Region, wherein, the quantity of the group comprising mistake in the first area, which is not more than in the second area, does not include mistake
The quantity of group；Each group comprising mistake in the first area is replaced with into one in the second area not wrap
Group containing mistake, so that the group in the first area is the group not comprising mistake；In the first area and institute
State and new data block is separately constituted in second area, and data are write to the new data block.
The efficient data wiring method based on PCM reversion error correction algorithms according to embodiments of the present invention, by by data block
Multiple groups are divided into, and the group of predetermined number is formed into a data segment, each data segment is then divided into Liang Ge areas
Domain, then the group for including mistake in one of region is replaced with another region and does not include wrong group, with
A region for not including mistake is formed, finally when writing data, mistake will not be run into the region not comprising mistake.By
This, can effectively reduce the situation that mistake is run into during data write-in, compared with correlation technique, before data are write, by only accounting for
The step of with expense is read, to avoid taking write-in expense writing data again when running into mistake, it make use of storage device
Reading rate is much larger than the characteristics of writing rate, effectively improves the write performance of storage device.
In addition, the efficient data wiring method according to the above embodiment of the present invention based on PCM reversion error correction algorithms may be used also
With with technical characteristic additional as follows：
According to one embodiment of present invention, it is described that the group that mistake is included in the multiple group is distinguished by mark
Specifically included with the group not comprising mistake：Match somebody with somebody bit " 1 " for each small component comprising mistake, and for each not
Small component comprising mistake matches somebody with somebody bit " 0 ".
According to one embodiment of present invention, the predetermined number is 512.
According to one embodiment of present invention, it is described that each data segment is divided into first area and second area bag
Include：The group that address in the data segment is less than to default value is divided to the first area, and by the data segment
The group that location is more than or equal to default value is divided to the second area, so as to include the group of mistake in the first area
Quantity be not more than the second area in do not include mistake group quantity.
Further, each group comprising mistake in the first area is replaced with into the second area described
In one do not include mistake group before, in addition to：If mistake is included in the first area or the second area
Group increase, and cause in the first area comprising mistake quantity be more than the second area in do not include mistake it is small
The quantity of group, then select new default value, and each data segment is divided into first area with the new default value
And second area, so that the quantity of the group comprising mistake in the first area, which is not more than in the second area, does not include mistake
The quantity of group by mistake.
Further, the new default value of the selection specifically includes：Selected first pointer points to the minimum group in address,
And selected second pointer points to address highest group, and first pointer is gradually moved to the higher group in address, make
Second pointer gradually moves to the relatively low group in address, in the process that first pointer and second pointer move
In, it is always ensured that the quantity for the group comprising mistake that first pointer accesses is not wrapped no more than what second pointer accessed
The quantity of group containing mistake, until when first pointer and second pointer point to identical group, will be described identical
Group address as the new default value.
According to one embodiment of present invention, it is described to replace with each group comprising mistake in the first area
A group for not including mistake in the second area specifically includes：In the first area by it is described comprising mistake
Group is arranged in order by the order of address from low to high, and presses ground by the group for not including mistake in the second area
The order of location from high to low is arranged in order, and i-th in the first area is included into the group of mistake and the second area
In i-th of group for not including mistake swap, wherein, i is positive integer, and i is less than or equal in the first area
The quantity of group comprising mistake.
According to one embodiment of present invention, methods described also includes：High address is evenly distributed to each data
Section, polymerize the second area in the multiple group, so that the first area composition in multiple data segments is described new
Data block there is continuous address space.
Brief description of the drawings
Fig. 1 is the stream according to the efficient data wiring method that error correction algorithm is inverted based on PCM of one embodiment of the invention
Cheng Tu；
Fig. 2 is the schematic diagram according to the data segment of one embodiment of the invention；
Fig. 3 is the schematic diagram that group replaces in the data segment according to one embodiment of the invention；
Fig. 4 is the schematic diagram of continuous dispensing address in multiple data segments according to one embodiment of the invention；
Fig. 5 is the schematic diagram that high address is evenly distributed in multiple data segments according to one embodiment of the invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
The efficient data wiring method based on PCM reversion error correction algorithms of the embodiment of the present invention is described below in conjunction with the accompanying drawings.
Fig. 1 is the stream according to the efficient data wiring method that error correction algorithm is inverted based on PCM of one embodiment of the invention
Cheng Tu.
As shown in figure 1, the efficient data wiring method based on PCM reversion error correction algorithms of the embodiment of the present invention, including with
Lower step：
S101, data block is divided into multiple groups, and the group that mistake is included in multiple groups is distinguished by mark
With the group not comprising mistake.
The mistake that will occur in embodiments of the invention in using the stuck-at fault in PCM as data block.To
When database is divided into multiple groups, mistake may be included in each group, it is also possible to not comprising mistake.At one of the present invention
Can be that each small component matches somebody with somebody bit in embodiment, wherein, can be that each small component comprising mistake enters with one two
Position " 1 " processed, and can be that each small component for not including mistake matches somebody with somebody bit " 0 ".
S102, the group of predetermined number is formed into a data segment, and each data segment is divided into first area and second
Region, wherein, the quantity of the group comprising mistake in first area is not more than the number for the group for not including mistake in second area
Amount.
Due in one embodiment of the invention, reading the metadata speed of 512, in subsequent steps,
For that can read the metadata of data segment simultaneously, the digit that can make each data segment is 512.Therefore, 512 groups can be formed
One data segment.
In one embodiment of the invention, each group has corresponding address, can be by segment register by number
The group for being less than default value according to address in section is divided to first area, and address in data segment is more than or equal into default value
Group be divided to second area so that in first area comprising mistake group quantity be not more than second area in do not include
The quantity of the group of mistake.
For example, can be by segment register by its stroke as shown in Fig. 2 in some data segment for including 512 groups
It is divided into two regions.For ease of understand, in fig. 2 can by the order of address from low to high by the group in the data segment from a left side to
The right side is arranged in order.It should be appreciated that the size of default value will influence the group that binary digit " 1 " in first area includes mistake
Quantity and second area in binary digit " 0 " i.e. do not include mistake group quantity.
In one embodiment of the invention, if the group comprising mistake in first area or second area increases, and
Cause the quantity comprising mistake in first area to be more than the quantity for the group for not including mistake in second area, then select new pre-
If numerical value, and each data segment is divided into by first area and second area with new default value, so as to be included in first area
The quantity of the group of mistake is not more than the quantity for the group for not including mistake in second area.
Specifically, the first pointer can be selected and point to the minimum group in address, and selected second pointer points to address highest
Group, and the first pointer is gradually moved to the higher group in address, the second pointer is gradually moved to the relatively low group in address,
During the first pointer and the second pointer move, the quantity for the group comprising mistake that the first pointer accesses is always ensured that not
The quantity of the group for not including mistake accessed more than the second pointer, until the first pointer and the second pointer point to identical group
When, using the address of identical group as new default value.
The process of new default value is selected to cause the abrasion of storage device, therefore in the first region comprising mistake
, can be all the time with original default value by each data when quantity is not more than the quantity for the group for not including mistake in second area
Section is divided into first area and second area.Thereby, it is possible to reduce the abrasion to storage device.
S103, each group comprising mistake in first area is replaced with one in second area and does not include mistake
Group so that the group in first area be not comprising mistake group.
Specifically, the group comprising mistake can be arranged in order by the order of address from low to high in the first region, and
The group not comprising mistake is arranged in order by the order of address from high to low in the second area, by i-th in first area
I-th of group for not including mistake in individual group and second area comprising mistake swaps, wherein, i is positive integer, and
I is less than or equal to the quantity of the group comprising mistake in first area.And the group and second of mistake is not included in first area
The position that group comprising mistake in region then retains its original is constant.
For example, as shown in figure 3, in the data segment that Fig. 2 is arranged, due to being arranged group from low to high by address
Array from left to right, can be by the right number first in left several bits " 1 " in first area and second area
Individual binary digit " 0 " swaps, and by the right number in second binary digit " 1 " of left number in first area and second area
Second binary digit " 0 " swaps ... until the group in first area is binary digit " 0 ".
In one embodiment of the invention, in step s 102, the firstth area can be made by selecting suitable default value
The quantity of group of the quantity of group comprising mistake in domain with not including mistake in second area is equal, or only compares second area
In do not include mistake group quantity it is small by 1.Thus, after the completion of step S103 replacement, first area can be made as far as possible
Ground is big.
S104, new data block is separately constituted in first area and second area, and data are write to new data block.
In one embodiment of the invention, high address can be evenly distributed to each data segment, made in multiple groups
Second area polymerize, so that the new data block that the first area in multiple data segments is formed has continuous address space.
Because each data segment is each divided into first area and second area, if in each data segment, Duo Ge little
The address of group is continuous or is more or less the same, then when writing data by address, the first areas of multiple data segments will by its second
Separate in region.The digit of each data segment in the embodiment of the present invention is 512, and this causes the firstth area being each separated
Domain is smaller, so as to influence writing rate.In one embodiment of the invention, high address can be evenly distributed to each data
Section.
As shown in Figure 4 and Figure 5, six groups in figure per a line form a data segment, each data segment in Fig. 4
In 6 groups address it is continuous in the case of, if (operating system carries out pipe by page table using 18 addresses as one page
Reason), then it is middle by 4-5,10-11,15-17 and 21-23 tetra- the in 0-3,6-9,12-14,18-20 and 24-26 one page
Separate in two regions.And in the case that high address is evenly distributed to each data segment in Figure 5, specifically, if one
Data segment includes n group, then the address matched somebody with somebody for j-th of small component of i-th of data segment can be i+j*n.Thus, can be by 6
Second area polymerization in group, the group included in 0-17 one page can be the group of first area, i.e. 0-17's
One page can have continuous address space.Thus, number can rapidly be write to the new data block with continuous address space
According to.
The efficient data wiring method based on PCM reversion error correction algorithms according to embodiments of the present invention, by by data block
Multiple groups are divided into, and the group of predetermined number is formed into a data segment, each data segment is then divided into Liang Ge areas
Domain, then the group for including mistake in one of region is replaced with another region and does not include wrong group, with
A region for not including mistake is formed, finally when writing data, mistake will not be run into the region not comprising mistake.By
This, can effectively reduce the situation that mistake is run into during data write-in, compared with correlation technique, before data are write, by only accounting for
The step of with expense is read, to avoid taking write-in expense writing data again when running into mistake, it make use of storage device
Reading rate is much larger than the characteristics of writing rate, effectively improves the write performance of storage device.
In the description of the invention, it is to be understood that term " " center ", " longitudinal direction ", " transverse direction ", " length ", " width ",
" thickness ", " on ", " under ", "front", "rear", "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ", " outer ", " up time
The orientation or position relationship of the instruction such as pin ", " counterclockwise ", " axial direction ", " radial direction ", " circumference " be based on orientation shown in the drawings or
Position relationship, it is for only for ease of and describes the present invention and simplify description, rather than indicates or imply that signified device or element must
There must be specific orientation, with specific azimuth configuration and operation, therefore be not considered as limiting the invention.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include one or more this feature.In the description of the invention, " multiple " are meant that two or more,
Unless otherwise specifically defined.
In the present invention, unless otherwise clearly defined and limited, term " installation ", " connected ", " connection ", " fixation " etc.
Term should be interpreted broadly, for example, it may be fixedly connected or be detachably connected, or integrally；Can be that machinery connects
Connect or electrically connect；Can be joined directly together, can also be indirectly connected by intermediary, can be in two elements
The connection in portion or the interaction relationship of two elements.For the ordinary skill in the art, can be according to specific feelings
Condition understands the concrete meaning of above-mentioned term in the present invention.
In the present invention, unless otherwise clearly defined and limited, fisrt feature can be with "above" or "below" second feature
It is that the first and second features directly contact, or the first and second features pass through intermediary mediate contact.Moreover, fisrt feature exists
Second feature " on ", " top " and " above " but fisrt feature are directly over second feature or oblique upper, or be merely representative of
Fisrt feature level height is higher than second feature.Fisrt feature second feature " under ", " lower section " and " below " can be
One feature is immediately below second feature or obliquely downward, or is merely representative of fisrt feature level height and is less than second feature.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the different embodiments or example and the feature of different embodiments or example described in this specification
Close and combine.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changed, replacing and modification.
Claims (5)
1. a kind of efficient data wiring method based on PCM reversion error correction algorithms, it is characterised in that comprise the following steps：
Data block is divided into multiple groups, and the group comprising mistake in the multiple group is distinguished by mark and not wrapped
Group containing mistake；
The group of predetermined number is formed into a data segment, and each data segment is divided into first area and second area,
Wherein, the quantity of the group comprising mistake in the first area, which is not more than in the second area, does not include wrong group
Quantity；
Each group comprising mistake in the first area is replaced with one in the second area and does not include mistake
Group so that the group in the first area be not comprising mistake group；
New data block is separately constituted in the first area and the second area, and number is write to the new data block
According to,
Wherein, it is described each data segment is divided into first area and second area to include：
The group that address in the data segment is less than to default value is divided to the first area, and by the data segment
The group that location is more than or equal to default value is divided to the second area, so as to include the group of mistake in the first area
Quantity be not more than the second area in do not include mistake group quantity,
One in the group by the first area each comprising mistake replaces with the second area is not wrapped
Before group containing mistake, in addition to：
If group's increase comprising mistake in the first area or the second area, and would cause the first area Zhong Bao
Quantity containing mistake is more than the quantity for the group for not including mistake in the second area, then selects new default value, and with
Each data segment is divided into first area and second area by the new default value, so as to be included in the first area
The quantity of the group of mistake is not more than the quantity for the group for not including mistake in the second area.
2. the efficient data wiring method according to claim 1 based on PCM reversion error correction algorithms, it is characterised in that institute
The group distinguished in the multiple group comprising wrong group and not comprising mistake by mark is stated to specifically include：
Match somebody with somebody bit " 1 " for each small component comprising mistake, and match somebody with somebody one for each small component for not including mistake
Binary digit " 0 ".
3. the efficient data wiring method according to claim 1 based on PCM reversion error correction algorithms, it is characterised in that institute
Predetermined number is stated as 512.
4. the efficient data wiring method according to claim 1 based on PCM reversion error correction algorithms, it is characterised in that institute
State and select new default value to specifically include：
Selected first pointer points to the minimum group in address, and selected second pointer points to address highest group, and makes described
First pointer gradually moves to the higher group in address, second pointer is gradually moved to the relatively low group in address, in institute
During stating the first pointer and second pointer movement, the group for including mistake that first pointer accesses is always ensured that
Quantity no more than the group for not including mistake that second pointer accesses quantity, until first pointer and described the
When two pointers point to identical group, using the address of the identical group as the new default value.
5. the efficient data wiring method according to claim 1 based on PCM reversion error correction algorithms, it is characterised in that institute
State one replaced with the group in the first area each comprising mistake in the second area and do not include mistake
Group specifically includes：
The group comprising mistake is arranged in order by the order of address from low to high in the first area, and described
The group for not including mistake is arranged in order by the order of address from high to low in second area, by the first area
I-th group and i-th in the second area comprising mistake do not include wrong group and swap, wherein, i is
Positive integer, and i is less than or equal to the quantity of the group comprising mistake in the first area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510819072.3A CN105355233B (en) | 2015-11-23 | 2015-11-23 | Efficient data wiring method based on PCM reversion error correction algorithms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510819072.3A CN105355233B (en) | 2015-11-23 | 2015-11-23 | Efficient data wiring method based on PCM reversion error correction algorithms |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105355233A CN105355233A (en) | 2016-02-24 |
| CN105355233B true CN105355233B (en) | 2018-04-10 |
Family
ID=55331190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510819072.3A Active CN105355233B (en) | 2015-11-23 | 2015-11-23 | Efficient data wiring method based on PCM reversion error correction algorithms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105355233B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109933424B (en) * | 2019-01-22 | 2020-11-13 | 浙江工商大学 | PCM memory line multiplexing method based on data cyclic shift |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1178989A (en) * | 1996-10-08 | 1998-04-15 | 三星电子株式会社 | Semiconductor capable of imaging bad block |
| US6137735A (en) * | 1998-10-30 | 2000-10-24 | Mosaid Technologies Incorporated | Column redundancy circuit with reduced signal path delay |
| CN1849671A (en) * | 2003-09-10 | 2006-10-18 | 海珀斯通股份公司 | Management of defective blocks in flash memories |
| CN101388255A (en) * | 2008-10-31 | 2009-03-18 | 成都市华为赛门铁克科技有限公司 | Solid hard disk using method and apparatus |
| CN102842341A (en) * | 2011-06-23 | 2012-12-26 | 旺宏电子股份有限公司 | High-endurance phase change memory devices and methods for operating the same |
| CN103164343A (en) * | 2013-02-27 | 2013-06-19 | 山东大学 | Paging, error correction code (ECC) verifying and multidigit prefetching method based on phase transition storer and structure thereof |
| CN104380262A (en) * | 2012-06-29 | 2015-02-25 | 英特尔公司 | Bad block management mechanism |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9875810B2 (en) * | 2013-07-24 | 2018-01-23 | Microsoft Technology Licensing, Llc | Self-identifying memory errors |
-
2015
- 2015-11-23 CN CN201510819072.3A patent/CN105355233B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1178989A (en) * | 1996-10-08 | 1998-04-15 | 三星电子株式会社 | Semiconductor capable of imaging bad block |
| US6137735A (en) * | 1998-10-30 | 2000-10-24 | Mosaid Technologies Incorporated | Column redundancy circuit with reduced signal path delay |
| CN1849671A (en) * | 2003-09-10 | 2006-10-18 | 海珀斯通股份公司 | Management of defective blocks in flash memories |
| CN101388255A (en) * | 2008-10-31 | 2009-03-18 | 成都市华为赛门铁克科技有限公司 | Solid hard disk using method and apparatus |
| CN102842341A (en) * | 2011-06-23 | 2012-12-26 | 旺宏电子股份有限公司 | High-endurance phase change memory devices and methods for operating the same |
| CN104380262A (en) * | 2012-06-29 | 2015-02-25 | 英特尔公司 | Bad block management mechanism |
| CN103164343A (en) * | 2013-02-27 | 2013-06-19 | 山东大学 | Paging, error correction code (ECC) verifying and multidigit prefetching method based on phase transition storer and structure thereof |
Non-Patent Citations (1)
| Title |
|---|
| 基于相变存储器的存储系统与技术综述;张鸿斌 等;《计算机研究与发展》;20141230;第51卷(第8期);第1647-1662页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105355233A (en) | 2016-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9436609B2 (en) | Block addressing for parallel memory arrays | |
| US11704025B2 (en) | Solid state storage device with variable logical capacity based on memory lifecycle | |
| TWI775122B (en) | Circuit for accessing at least one non-volatile memory | |
| US8412987B2 (en) | Non-volatile memory to store memory remap information | |
| US7386655B2 (en) | Non-volatile memory and method with improved indexing for scratch pad and update blocks | |
| US7366826B2 (en) | Non-volatile memory and method with multi-stream update tracking | |
| KR101139534B1 (en) | Semiconductor memory device | |
| US7412560B2 (en) | Non-volatile memory and method with multi-stream updating | |
| US8478796B2 (en) | Uncorrectable error handling schemes for non-volatile memories | |
| US8259498B2 (en) | Continuous address space in non-volatile-memories (NVM) using efficient management methods for array deficiencies | |
| US20050015557A1 (en) | Nonvolatile memory unit with specific cache | |
| US20100332950A1 (en) | Bit error threshold and content addressable memory to address a remapped memory device | |
| US8656090B2 (en) | Method for performing block management, and associated memory device and controller thereof | |
| US20140115416A1 (en) | Non-volatile memory error correction | |
| KR20110001881A (en) | Bit error threshold and remapping a memory device | |
| US20060271729A1 (en) | Memory card, nonvolatile semiconductor memory, and method of controlling semiconductor memory | |
| US11003587B2 (en) | Memory system with configurable NAND to DRAM ratio and method of configuring and using such memory system | |
| US20100146239A1 (en) | Continuous address space in non-volatile-memories (nvm) using efficient embedded management of array deficiencies | |
| US20100287329A1 (en) | Partial Page Operations for Non-Volatile Memory Systems | |
| CN103890856A (en) | Shiftable memory supporting in-memory data structures | |
| US20190243772A1 (en) | Word type/boundary propagation with memory performance applications | |
| CN105355233B (en) | Efficient data wiring method based on PCM reversion error correction algorithms | |
| CN103514098B (en) | For reclaiming the method and system of memory space | |
| CN107402890A (en) | A kind of data processing method and system based on Solid-state disc array and caching | |
| WO2021021652A1 (en) | Selecting read voltage using write transaction data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |