CN104317739A - Hybrid memory paging method and device - Google Patents
Hybrid memory paging method and device Download PDFInfo
- Publication number
- CN104317739A CN104317739A CN201410589880.0A CN201410589880A CN104317739A CN 104317739 A CN104317739 A CN 104317739A CN 201410589880 A CN201410589880 A CN 201410589880A CN 104317739 A CN104317739 A CN 104317739A
- Authority
- CN
- China
- Prior art keywords
- page
- current accessed
- dram
- pcm
- access type
- 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.)
- Pending
Links
Abstract
The invention provides a hybrid memory paging method and device. The method includes the steps: 1, a unified memory address is converted into a PCD (page cache disable) or DRAM (dynamic random access memory) memory address; 2, if a currently accessed memory page is in the DRAM, a corresponding flag bit is set according to an access type currently accessed and the fact if the currently accessed memory page and a last visited page is an adjacent page; 3, if the currently accessed memory page is in the PCD, a corresponding flag bit is set according to an access type currently accessed and the fact if the currently accessed memory page and the last visited page is an adjacent page, and whether the currently accessed memory page needs to be moved to the DRAM is determined. With the hybrid memory paging method and device, memory pages needing frequent read operation is placed in the PCM as much as possible, and memory pages needing frequent write operation is placed in the DRAM as much as possible, and thus, writing operation of the PCM is reduced, and service life of the PCM is prolonged.
Description
Technical field
The present invention relates to field of computer technology, be specifically related to a kind of mixing memory pages dispatching method and device.
Background technology
Along with the development of computer technology, the requirement of system to internal memory is more and more higher.Conventional primary memory DRAM is due to the restriction of himself manufacturing process, and unit area memory capacity is difficult to increase, and causes the extendability of primary memory to meet with bottleneck.In addition, the energy consumption problem of DRAM also becomes a problem that can not be ignored of computer system day by day.In order to make up the deficiency of DRAM, a kind of novel memory technology-phase transition internal memory PCM grows up just gradually.The advantage such as PCM has that energy consumption is low, density is large, non-volatile, and there is good extendability.
But PCM also exists unit writes the limited shortcoming of number of times, therefore, use the mixing internal memory of PCM and DRAM, by write operation frequently page be placed in DRAM as far as possible, by read operation frequently page be placed in PCM as far as possible, significantly can reduce the write operation number of times of PCM, thus improve the serviceable life of PCM.Visible, use the mixing internal memory of PCM and DRAM, the advantage of DRAM and PCM can be made full use of.
In existing PCM and DRAM mixing memory pages dispatching method, Problems existing is, when dispatching page, the factor of consideration is the temporal locality of page, and such as, the use position of CLOCK algorithm use page and dirty position are as the foundation of dispatching page.The spatial locality of adjacent memory page is left in the basket in scheduling memory.Cause the efficiency of scheduling memory method and accuracy to reduce thus, produce a large amount of mistakes that skips leaf.
Summary of the invention
For defect of the prior art, the invention provides a kind of mixing memory pages dispatching method and device, by read operation frequently page be placed in PCM as far as possible, by write operation frequently page be placed in DRAM as far as possible, improve efficiency and the accuracy of scheduling memory method.
First aspect, the invention provides a kind of mixing memory pages dispatching method, comprising:
S1. internal memory is unified address and convert phase transition internal memory PCM or dynamic RAM DRAM memory address to;
If S2. the page of current accessed is in DRAM, then the access type being whether adjacent page and current accessed according to the page of the page of current accessed and last access arranges corresponding zone bit;
If S3. the page of current accessed is in PCM, then corresponding zone bit is set according to the access type of the page of current accessed, and determines whether the page of current accessed to move in DRAM.
Wherein, described mixing memory pages dispatching method also comprises:
If S4. skip leaf mistake, when the access type of the page of current accessed is read operation, the page of current accessed is placed in PCM; When the access type of the page of current accessed is write operation, the page of current accessed is placed in DRAM.
Wherein, described step S2 comprises:
S21. judge whether the page of current accessed and the page of last access are space adjacent page;
S22: if the access type of the page of current accessed is read operation, and the page of current accessed is adjacent page with last page of accessing, then the backward reference counter of the page of current accessed adds 1, and the forward reference counter of the page of last access adds 1;
S23: if the access type of the page of current accessed is write operation, then arrange the dirty position of the page of current accessed.
Wherein, described step S21 comprises:
If the page of current accessed is less than default adjacent threshold value with the distance of last page of accessing, then the page of current accessed is adjacent page with last page of accessing, otherwise the page of current accessed is not adjacent page with last page of accessing.
Wherein, described step S3 comprises:
S31: if the access type of the page of current accessed is read operation, then arrange the use position of the page of current accessed;
S32: if the access type of the page of current accessed is write operation, then from DRAM, obtain a free page, the page of current accessed is moved in DRAM, and the dirty position of the page of current accessed in DRAM is set, the backward reference counter of the page of current accessed is set to 0, the forward reference counter decrement 1 of the page of last access.
Wherein, described step S4 comprises:
S41: if the access type of the page of current accessed is read operation, then obtain a free page from PCM, and the page of current accessed is loaded into described from the free page that PCM obtains;
S42: if the access type of the page of current accessed is write operation, then obtain a free page from DRAM, and the page of current accessed is loaded into described from the free page that DRAM obtains, and arrange the dirty position of the page of current accessed.
Wherein, from PCM, obtain a free page in described step S41 specifically to comprise:
S411: if available free page in PCM, then return a free page in PCM;
S412: if do not have free page in PCM, then by CLOCK algorithm, according to the use position of page and the value of dirty position, find nearest untapped clean page, dispatched out PCM internal memory, and returned as free page by this nearest untapped clean page.
Wherein, from DRAM, obtain a free page in described step S32 or S42 specifically to comprise:
S421: if available free page in DRAM, then return a free page in DRAM;
S422: if do not have free page in DRAM, then searching loop DRAM page table, if first page is clean page in DRAM page table, and the value of the forward reference counter of this clean page and backward reference counter is all less than default spatial locality threshold value, then this page is moved in PCM, and this page is returned as free page;
Otherwise, if first page in described DRAM page table is not clean page, then by the dirty bit clear of this page, arranging this page is clean page, and the backward reference counter arranging this page successively decreases 1, the forward reference counter decrement 1 of the page of last access, to continue to check in DRAM page table that next page is until finding clean page and till the value of the forward reference counter of this clean page and backward reference counter is all less than default spatial locality threshold value.
Second aspect, the invention provides a kind of mixing memory pages dispatching device, comprising:
Unified address conversioning unit, converts phase transition internal memory PCM or dynamic RAM DRAM memory address to for internal memory being unified address;
Whether DRAM memory management unit, for being that the access type of adjacent page and current accessed arranges corresponding zone bit according to the page of the page of current accessed and last access;
PCM memory management unit, the access type for the page according to current accessed arranges corresponding zone bit, and determines whether the page of current accessed to move in DRAM;
Mixing memory management unit, after determining that at PCM memory management unit the page of current accessed is moved to DRAM, moves to the page of current accessed in DRAM.
Wherein, described mixing memory management unit, also for when skipping leaf mistake, if the access type of current accessed page is read operation, is placed in PCM by the page of current accessed; If the access type of current accessed page is write operation, the page of current accessed is placed in DRAM.
As shown from the above technical solution, mixing memory pages dispatching method of the present invention, according to spatial locality and the temporal locality of current accessed page, by read operation frequently page be placed in PCM as far as possible, by write operation frequently page be placed in DRAM as far as possible, improve efficiency and the accuracy of scheduling memory method, decrease simultaneously and number of times is write to PCM, optimize the wearing and tearing progress of PCM, improve the life-span of PCM.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of the mixing memory pages dispatching method that the embodiment of the present invention one provides;
Fig. 2 is the structural representation of the mixing memory pages dispatching device that the embodiment of the present invention two provides.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, clear, complete description is carried out to the technical scheme in the embodiment of the present invention, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 shows the process flow diagram of the mixing memory pages dispatching method that the embodiment of the present invention one provides, and the mixing memory pages dispatching method described in the embodiment of the present invention one comprises:
Step 101: internal memory is unified address and convert phase transition internal memory PCM or dynamic RAM DRAM memory address to.
In this step, by phase transition internal memory PCM (Phase-Change Memory) and DRAM internal memory unified addressing, PCM is in low address district, and DRAM is in high address district.
Step 102: if the page of current accessed is in DRAM, then the access type being whether adjacent page and current accessed according to the page of the page of current accessed and last access arranges corresponding zone bit.
In this step, first, judge whether the page of current accessed and the page of last access are space adjacent page; If the page of current accessed is less than default adjacent threshold value with the distance of last page of accessing, then the page of current accessed is adjacent page with last page of accessing, otherwise the page of current accessed is not adjacent page with last page of accessing.It is 2 ~ 4 more suitable that described adjacent threshold value is generally got.
Then the action type of current accessed is judged, if the type of current accessed is read operation, and the page of current accessed is adjacent page with last page of accessing, then the backward reference counter of the page of current accessed adds 1, and the forward reference counter of the page of last access adds 1;
If the type of current accessed is write operation, then the dirty position of the page of current accessed is set.
Step 103: if the page of current accessed is in PCM, then corresponding zone bit is set according to the access type of the page of current accessed, and determine whether the page of current accessed to move in DRAM.
In this step, if the access type of the page of current accessed is read operation, then the use position of the page of current accessed is set;
If the access type of the page of current accessed is write operation, then from DRAM, obtain a free page, the page of current accessed is moved in DRAM, and the dirty position of the page of current accessed in DRAM is set, the backward reference counter of the page of current accessed is set to 0, the forward reference counter decrement 1 of the page of last access.
Mixing memory pages dispatching method described in the present embodiment, according to spatial locality and the temporal locality of current accessed page, by read operation frequently page be placed in PCM as far as possible, by write operation frequently page be placed in DRAM as far as possible, improve efficiency and the accuracy of scheduling memory method, decrease simultaneously and number of times is write to PCM, optimize the wearing and tearing progress of PCM, improve the life-span of PCM.
Wherein, described mixing memory pages dispatching method also comprises:
If the mistake of skipping leaf, when the access type of the page of current accessed is read operation, the page of current accessed is placed in PCM; When the access type of the page of current accessed is write operation, the page of current accessed is placed in DRAM.
Particularly, if the access type of the page of current accessed is read operation, then from PCM, obtain a free page, and the page of current accessed is loaded into described from the free page that PCM obtains;
If the access type of the page of current accessed is write operation, then from DRAM, obtain a free page, and the page of current accessed is loaded into described from the free page that DRAM obtains, and the dirty position of the page of current accessed is set.
Wherein, described from PCM obtain a free page specifically comprise:
If available free page in PCM, then return a free page in PCM;
If there is no free page in PCM, then by CLOCK algorithm, according to the use position of page and the value of dirty position, find nearest untapped clean page, dispatched out PCM internal memory, and this nearest untapped clean page is returned as free page.
Wherein, described from DRAM obtain a free page specifically comprise:
If available free page in DRAM, then return a free page in DRAM;
If there is no free page in DRAM, then searching loop DRAM page table, if first page is clean page in DRAM page table, and the value of the forward reference counter of this clean page and backward reference counter is all less than default spatial locality threshold value, then this page is moved in PCM, and this page is returned as free page;
Otherwise, if first page in described DRAM page table is not clean page, then by the dirty bit clear of this page, arranging this page is clean page, and the backward reference counter arranging this page successively decreases 1, the forward reference counter decrement 1 of the page of last access, to continue to check in DRAM page table that next page is until finding clean page and till the value of the forward reference counter of this clean page and backward reference counter is all less than default spatial locality threshold value.
Here, whether the described page is the short period locality that clean page embodies the page, and the forward reference counter of the page embodies the spatial locality of the page together with the value of backward reference counter.When this page is not clean page, illustrate that this page was modified recently, namely this page has stronger temporal locality, therefore this page can not be moved in PCM.Meanwhile, if when the forward reference counter of this page and the value of backward reference counter had one to exceed preset spatial locality threshold value, then illustrate that this page has stronger spatial locality, even if this page is clean page, this page can not be moved in PCM.Therefore only have meet simultaneously this page for clean page and the value of the forward reference counter of this page and backward reference counter be all less than default spatial locality threshold value time, could this page be moved in PCM, by temporal locality and the more weak page movement of spatial locality in PCM.
Described default spatial locality threshold value is the spatial locality threshold value judging page forward-backward correlation, and it depends on the size of DRAM and the number percent of shared overall memory size, and through test of many times, this spatial locality threshold value is got 4 proper.
Fig. 2 shows the structural representation of the mixing memory pages dispatching device that the embodiment of the present invention two provides, and the mixing memory pages dispatching device described in the embodiment of the present invention two comprises:
Unified address conversioning unit 21, converts phase transition internal memory PCM or dynamic RAM DRAM memory address to for internal memory being unified address;
Whether DRAM memory management unit 22, for being that the access type of adjacent page and current accessed arranges corresponding zone bit according to the page of the page of current accessed and last access;
PCM memory management unit 23, the access type for the page according to current accessed arranges corresponding zone bit, and determines whether the page of current accessed to move in DRAM;
Mixing memory management unit 24, after determining that at PCM memory management unit the page of current accessed is moved to DRAM, moves to the page of current accessed in DRAM.
Wherein, described mixing memory management unit 24, also for when skipping leaf mistake, if the access type of the page of current accessed is read operation, is placed in PCM by the page of current accessed; If the access type of the page of current accessed is write operation, the page of current accessed is placed in DRAM.
Mixing memory pages dispatching device described in the present embodiment, can be used for the method described in embodiment one of performing, its know-why and technique effect and embodiment one similar, do not repeat them here.
Above embodiment only for illustration of technical scheme of the present invention, is not intended to limit; Although with reference to previous embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. mix a memory pages dispatching method, it is characterized in that, comprising:
S1. internal memory is unified address and convert phase transition internal memory PCM or dynamic RAM DRAM memory address to;
If S2. the page of current accessed is in DRAM, then the access type being whether adjacent page and current accessed according to the page of the page of current accessed and last access arranges corresponding zone bit;
If S3. the page of current accessed is in PCM, then corresponding zone bit is set according to the access type of the page of current accessed, and determines whether the page of current accessed to move in DRAM.
2. method according to claim 1, is characterized in that, also comprises:
If S4. skip leaf mistake, when the access type of the page of current accessed is read operation, the page of current accessed is placed in PCM; When the access type of the page of current accessed is write operation, the page of current accessed is placed in DRAM.
3. method according to claim 1, is characterized in that, described step S2 comprises:
S21. judge whether the page of current accessed and the page of last access are space adjacent page;
S22: if the access type of the page of current accessed is read operation, and the page of current accessed is adjacent page with last page of accessing, then the backward reference counter of the page of current accessed adds 1, and the forward reference counter of the page of last access adds 1;
S23: if the access type of the page of current accessed is write operation, then arrange the dirty position of the page of current accessed.
4. method according to claim 3, is characterized in that, described step S21 comprises:
If the page of current accessed is less than default adjacent threshold value with the distance of last page of accessing, then the page of current accessed is adjacent page with last page of accessing, otherwise the page of current accessed is not adjacent page with last page of accessing.
5. method according to claim 1, is characterized in that, described step S3 comprises:
S31: if the access type of the page of current accessed is read operation, then arrange the use position of the page of current accessed;
S32: if the access type of the page of current accessed is write operation, then from DRAM, obtain a free page, the page of current accessed is moved in DRAM, and the dirty position of the page of current accessed in DRAM is set, the backward reference counter of the page of current accessed is set to 0, the forward reference counter decrement 1 of the page of last access.
6. method according to claim 2, is characterized in that, described step S4 comprises:
S41: if the access type of the page of current accessed is read operation, then obtain a free page from PCM, and the page of current accessed is loaded into described from the free page that PCM obtains;
S42: if the access type of the page of current accessed is write operation, then obtain a free page from DRAM, and the page of current accessed is loaded into described from the free page that DRAM obtains, and arrange the dirty position of the page of current accessed.
7. method according to claim 6, is characterized in that, obtains a free page and specifically comprise in described step S41 from PCM:
S411: if available free page in PCM, then return a free page in PCM;
S412: if do not have free page in PCM, then by CLOCK algorithm, according to the use position of page and the value of dirty position, find nearest untapped clean page, dispatched out PCM internal memory, and returned as free page by this nearest untapped clean page.
8. the method according to claim 5 or 6, is characterized in that, obtains a free page and specifically comprise in described step S32 or S42 from DRAM:
S421: if available free page in DRAM, then return a free page in DRAM;
S422: if do not have free page in DRAM, then searching loop DRAM page table, if first page is clean page in DRAM page table, and the value of the forward reference counter of this clean page and backward reference counter is all less than default spatial locality threshold value, then this page is moved in PCM, and this page is returned as free page;
Otherwise, if first page in described DRAM page table is not clean page, then by the dirty bit clear of this page, arranging this page is clean page, and the backward reference counter arranging this page successively decreases 1, the forward reference counter decrement 1 of the page of last access, to continue to check in DRAM page table that next page is until finding clean page and till the value of the forward reference counter of this clean page and backward reference counter is all less than default spatial locality threshold value.
9. mix a memory pages dispatching device, it is characterized in that, comprising:
Unified address conversioning unit, converts phase transition internal memory PCM or dynamic RAM DRAM memory address to for internal memory being unified address;
Whether DRAM memory management unit, for being that the access type of adjacent page and current accessed arranges corresponding zone bit according to the page of the page of current accessed and last access;
PCM memory management unit, the access type for the page according to current accessed arranges corresponding zone bit, and determines whether the page of current accessed to move in DRAM;
Mixing memory management unit, after determining that at PCM memory management unit the page of current accessed is moved to DRAM, moves to the page of current accessed in DRAM.
10. device according to claim 9, is characterized in that, described mixing memory management unit, also for when skipping leaf mistake, if the access type of current accessed page is read operation, is placed in PCM by the page of current accessed; If the access type of current accessed page is write operation, the page of current accessed is placed in DRAM.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410589880.0A CN104317739A (en) | 2014-10-28 | 2014-10-28 | Hybrid memory paging method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410589880.0A CN104317739A (en) | 2014-10-28 | 2014-10-28 | Hybrid memory paging method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104317739A true CN104317739A (en) | 2015-01-28 |
Family
ID=52372974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410589880.0A Pending CN104317739A (en) | 2014-10-28 | 2014-10-28 | Hybrid memory paging method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104317739A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834608A (en) * | 2015-05-12 | 2015-08-12 | 华中科技大学 | Cache replacement method under heterogeneous memory environment |
| CN104899154A (en) * | 2015-06-10 | 2015-09-09 | 山东大学 | Page management method based on embedded system mixed main memory |
| CN106155938A (en) * | 2016-06-23 | 2016-11-23 | 清华大学 | Postpone cache replacement method and the device in PCM internal memory service life |
| CN106909323A (en) * | 2017-03-02 | 2017-06-30 | 山东大学 | The caching of page method of framework is hosted suitable for DRAM/PRAM mixing and mixing hosts architecture system |
| CN107015865A (en) * | 2017-03-17 | 2017-08-04 | 华中科技大学 | A kind of DRAM cache management method and system based on temporal locality |
| CN107193646A (en) * | 2017-05-24 | 2017-09-22 | 中国人民解放军理工大学 | A kind of high-efficiency dynamic paging method that framework is hosted based on mixing |
| CN107480074A (en) * | 2017-08-31 | 2017-12-15 | 郑州云海信息技术有限公司 | A kind of caching method, device and electronic equipment |
| CN109328340A (en) * | 2017-09-30 | 2019-02-12 | 华为技术有限公司 | Detection method, device and the server of memory failure |
| CN109558093A (en) * | 2018-12-19 | 2019-04-02 | 哈尔滨工业大学 | A kind of mixing memory pages moving method for image processing type load |
| CN109656482A (en) * | 2018-12-19 | 2019-04-19 | 哈尔滨工业大学 | It is a kind of that hot Web page predicting method is write based on memory access |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7130968B2 (en) * | 2003-03-11 | 2006-10-31 | Pmc-Sierra, Inc. | Cache memory architecture and associated microprocessor design |
| CN102508787A (en) * | 2011-11-29 | 2012-06-20 | 清华大学 | System and method for memory allocation of composite memory |
-
2014
- 2014-10-28 CN CN201410589880.0A patent/CN104317739A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7130968B2 (en) * | 2003-03-11 | 2006-10-31 | Pmc-Sierra, Inc. | Cache memory architecture and associated microprocessor design |
| CN102508787A (en) * | 2011-11-29 | 2012-06-20 | 清华大学 | System and method for memory allocation of composite memory |
Non-Patent Citations (1)
| Title |
|---|
| 刘巍: ""基于空间局部性的PCM和DRAM混合内存页面调度算法"", 《中国科技论文》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834608B (en) * | 2015-05-12 | 2017-09-29 | 华中科技大学 | A kind of buffer replacing method under isomery memory environment |
| CN104834608A (en) * | 2015-05-12 | 2015-08-12 | 华中科技大学 | Cache replacement method under heterogeneous memory environment |
| CN104899154A (en) * | 2015-06-10 | 2015-09-09 | 山东大学 | Page management method based on embedded system mixed main memory |
| CN104899154B (en) * | 2015-06-10 | 2017-08-29 | 山东大学 | The page management method hosted is mixed based on embedded system |
| CN106155938A (en) * | 2016-06-23 | 2016-11-23 | 清华大学 | Postpone cache replacement method and the device in PCM internal memory service life |
| CN106155938B (en) * | 2016-06-23 | 2019-02-05 | 清华大学 | Postpone the cache replacement method and device of PCM memory service life |
| CN106909323B (en) * | 2017-03-02 | 2020-03-10 | 山东大学 | Page caching method suitable for DRAM/PRAM mixed main memory architecture and mixed main memory architecture system |
| CN106909323A (en) * | 2017-03-02 | 2017-06-30 | 山东大学 | The caching of page method of framework is hosted suitable for DRAM/PRAM mixing and mixing hosts architecture system |
| CN107015865B (en) * | 2017-03-17 | 2019-12-17 | 华中科技大学 | DRAM cache management method and system based on time locality |
| CN107015865A (en) * | 2017-03-17 | 2017-08-04 | 华中科技大学 | A kind of DRAM cache management method and system based on temporal locality |
| CN107193646B (en) * | 2017-05-24 | 2020-10-09 | 中国人民解放军理工大学 | High-efficiency dynamic page scheduling method based on mixed main memory architecture |
| CN107193646A (en) * | 2017-05-24 | 2017-09-22 | 中国人民解放军理工大学 | A kind of high-efficiency dynamic paging method that framework is hosted based on mixing |
| CN107480074B (en) * | 2017-08-31 | 2020-02-07 | 郑州云海信息技术有限公司 | Caching method and device and electronic equipment |
| CN107480074A (en) * | 2017-08-31 | 2017-12-15 | 郑州云海信息技术有限公司 | A kind of caching method, device and electronic equipment |
| CN109328340A (en) * | 2017-09-30 | 2019-02-12 | 华为技术有限公司 | Detection method, device and the server of memory failure |
| US11119874B2 (en) | 2017-09-30 | 2021-09-14 | Huawei Technologies Co., Ltd. | Memory fault detection |
| CN109558093A (en) * | 2018-12-19 | 2019-04-02 | 哈尔滨工业大学 | A kind of mixing memory pages moving method for image processing type load |
| CN109656482A (en) * | 2018-12-19 | 2019-04-19 | 哈尔滨工业大学 | It is a kind of that hot Web page predicting method is write based on memory access |
| CN109656482B (en) * | 2018-12-19 | 2022-03-25 | 哈尔滨工业大学 | Write hot page prediction method based on memory access |
| CN109558093B (en) * | 2018-12-19 | 2022-04-15 | 哈尔滨工业大学 | Hybrid memory page migration method for image processing type load |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104317739A (en) | Hybrid memory paging method and device | |
| TWI457932B (en) | Method and system to improve the performance of a multi-level cell (mlc) nand flash memory | |
| US8417872B2 (en) | Write and merge methods in memory card systems for reducing the number of page copies | |
| CN105843749B (en) | A kind of NAND Flash fault-tolerance approach based on FPGA | |
| CN103425595A (en) | Data storage device and method for flash block management | |
| CN101165659A (en) | Methods and apparatus for reallocating addressable spaces within memory devices | |
| CN101641679A (en) | Mlc selected multi-program for system management | |
| CN101625897B (en) | Data write-in method, storage system and controller used for quick flash memory | |
| CN101556555B (en) | Block managing method for flash memory as well as controller and storage system thereof | |
| US20110271032A1 (en) | Access device and memory controller | |
| CN102214143A (en) | Method and device for managing multilayer unit flash memory, and storage equipment | |
| CN109582593A (en) | A kind of FTL address mapping method and data read-write method based on calculating | |
| CN104011689A (en) | Nonvolatile memory wear management | |
| KR20120012056A (en) | Memory device | |
| CN105551522A (en) | Management method and management apparatus of flash memory storage device | |
| CN101308701A (en) | Apparatus and method of managing mapping table of non-volatile memory | |
| JP6178516B2 (en) | Refresh scheme for memory cells using next bit table | |
| CN104461917A (en) | Nor Flash-based regional cycle storage method | |
| US10324959B2 (en) | Garbage collection in storage system | |
| CN102789422B (en) | The method for writing data of solid state hard disc | |
| CN101458659A (en) | Flash memory system and method thereof | |
| CN105512047A (en) | Method and device for write operation and erasure operation of Flash memory | |
| CN102023845A (en) | Cache concurrent access management method based on state machine | |
| CN102981965A (en) | NAND FLASH file system | |
| CN1988039A (en) | Flash storage scattered writing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150128 |
|
| RJ01 | Rejection of invention patent application after publication |