CN103810113A - Fusion memory system of nonvolatile memory and dynamic random access memory - Google Patents
Fusion memory system of nonvolatile memory and dynamic random access memory Download PDFInfo
- Publication number
- CN103810113A CN103810113A CN201410041777.2A CN201410041777A CN103810113A CN 103810113 A CN103810113 A CN 103810113A CN 201410041777 A CN201410041777 A CN 201410041777A CN 103810113 A CN103810113 A CN 103810113A
- Authority
- CN
- China
- Prior art keywords
- memory
- nonvolatile memory
- dram
- fusion
- data
- 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)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The invention discloses a fusion memory system of a nonvolatile memory and a dynamic random access memory. The nonvolatile memory and the dynamic random access memory are fused together and are jointly used as a memory of a computer system for unified management, the dynamic random access memory can carry out unified addressing together with the nonvolatile memory, part capacity of the dynamic random access memory can be used as a high-speed cache of the nonvolatile memory, the capacity of cache space adapts to data load characteristics by itself and is dynamically matched, so that the access speed of the nonvolatile memory is improved, access frequency of a disk by an I/O can be lowered, and the overall performance of the computer system is improved.
Description
Technical field
The invention belongs to Computer Storage field, be specifically related to the fusion memory system of a kind of nonvolatile memory and dynamic RAM.
Background technology
The appearance of novel nonvolatile memory (Non-Volatile Memory, NVM) for expansion calculator memory provides new approach, has promoted the change of computing machine in system architecture simultaneously.Existing NVM has PCM(Phase Change Memory, phase transition storage), STT-RAM(Spin Transfer Torque Random Access Memory, spin-transfer torque random access memory), MRAM(Magnetic Random Access Memory, magnetic RAM device), FeRAM(Ferroelectric Random Access Memory, ferroelectric random storer) etc.The Ultrahigh of novel nonvolatile memory is no longer traditional flow of charge storage data that electronics forms utilized, but utilize magnetoresistance, resistive effect should, the such mechanism of cholesteric-nematic transition etc. realizes the storage of data, such characteristic makes them have the advantage that many legacy memory can not have, if phase transition storage is a kind of novel nonvolatile memory being made up of chalcogenide material, it utilizes the reversible phase transformation of material to carry out storage information, phase-change memory material can occur from non-crystal state to crystal state under certain condition, return to again the variation of non-crystal state, non-crystal state in this process and crystal state present different resistance characteristics and optical characteristics, therefore, can utilize amorphous state and crystalline state to represent that respectively " 0 " and " 1 " store data, it provides non-volatile, low energy consumption, the features such as random read-write speed is fast.Samsung and company of Micron Technology have released the PCM chip of 90nm and 45nm processing procedure successively at present.
Current novel nonvolatile memory is in the research in computer memory system field, main direction has two: the one, use as external equipment, the 2nd, adopt nonvolatile memory and DRAM as mixing internal memory (Hybrid Memory), DRAM is the cache of nonvolatile memory.
For DRAM, nonvolatile memory has non-volatile, can retain for a long time data, has high density characteristic simultaneously, and this provides support to further developing of memory techniques; But meanwhile nonvolatile memory has relatively large delay, and writing speed and DRAM also have gap, the life-span of part nonvolatile memory is also relatively limited, if think, it can substitute DRAM, just must overcome the problems such as himself, energy consumption and delay in life-span, but existing research is mostly all only for some the carrying out in these problems, do not consider and overcome many-sided restriction, therefore nonvolatile memory does separately internal memory and also has a lot of challenges and predicament, also cannot accomplish in a short time the complete replacer of DRAM.Generally only use at present the ROM part of nonvolatile memory replacement computer original system, or research is used DRAM and nonvolatile memory to build mixing internal memory, make the intermediate storage layer of computer memory system of nonvolatile memory, as: data storage is successively by disk, nonvolatile memory, dynamic RAM, Cache, CPU, data access level is too many, IO path is long, does not give full play of the feature of nonvolatile memory.
Summary of the invention
Given this, the object of the present invention is to provide the fusion memory system of a kind of nonvolatile memory and dynamic RAM, solution active computer internal memory power failure data is lost, starting up is slow, the low inferior series of problems of IO performance of Energy Intensity Reduction difficulty, frequent and disk swapping, simultaneously can be by dynamically adjusting the capacity that merges space, core buffer, the request of self-adaptation application load, improves internal memory service efficiency.
A kind of nonvolatile memory that the present invention proposes and the fusion memory system of dynamic RAM, comprising:
The nonvolatile memory (NVM) of unified addressing, unified management and dynamic RAM (DRAM), wherein DRAM comprises the DRAM cache part of the cache that serves as nonvolatile memory, its spatial content capable of dynamic is adjusted;
Protocol conversion module, for the protocol memory that the protocol conversion of nonvolatile memory phy chip package interface is adopted for memory interface;
Merge Memory Controller Hub, for according to the work schedule of nonvolatile memory and DRAM phy chip, upper strata call instruction and pin level signal condition, worker state machine is set to complete corresponding operation, and the software interface that drives memory chip is provided;
Merge memory management module, for carrying out unified management to merging internal memory, comprise that dram space capacity dynamically adjusts submodule, wherein, described dram space capacity is dynamically adjusted submodule for periodically monitoring the hit rate H of DRAM cache part, and detects read-write requests ratio R:
R=read request number ÷ write request number (1)
In the time of hit rate H < K and read-write requests ratio R<T, increase DRAM cache capacity, wherein, K, T are predetermined threshold, its value can be according to user's request and self-defined configuration, 0<K<1,0<T<1;
In the time of hit rate H >=K and read-write requests ratio R >=T, reduce DRAM cache capacity.
Compared with prior art, the present invention has following beneficial effect: the advantage of having given play to greatest extent nonvolatile memory and DRAM, by merging memory architecture, solve that existing memory system power failure data is lost, starting up is slow, the low inferior series of problems of IO performance of Energy Intensity Reduction difficulty, frequent and disk swapping.
Accompanying drawing explanation
Fig. 1 is the fusion memory system Organization Chart of the embodiment of the present invention;
Fig. 2 is the fusion memory system hardware platform architecture figure of the embodiment of the present invention;
Fig. 3 is the non-volatile fusion internal memory hardware structure figure of the embodiment of the present invention;
Fig. 4 is the fusion memory management module figure of the embodiment of the present invention;
Fig. 5 is that parallel framework merges memory modules figure;
Fig. 6 is that vertical framework merges memory modules figure.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing and exemplary embodiment, the present invention is further elaborated.Should be appreciated that exemplary embodiment described herein is only in order to explain the present invention, the scope of application being not intended to limit the present invention.
The fusion memory system of the embodiment of the present invention is described below: merge memory system overall architecture, merge memory system hardware platform and merge memory management module from three aspects.
One, merge memory system overall architecture
As shown in Figure 1, in the fusion memory system of the embodiment of the present invention, adopt nonvolatile memory (NVM) and dynamic RAM (DRAM) to build internal memory, CPU visits fusion memory system by merging Memory Controller Hub, so-called fusion, the reflection in system level is addressing and the allocation manager scheme of the memory system that is made up of nonvolatile memory and dynamic RAM.
According to DRAM device residing position in this framework, DRAM device is divided into two parts:
The status of part DRAM and nonvolatile memory is equal, and they carry out unified addressing, unified management, and both form traditional internal memory jointly.According to the feature of CPU access memory data, can directly deposit data be arrived to the dynamic RAM part of internal memory or the nonvolatile memory part of internal memory;
Another part DRAM serves as the cache of nonvolatile memory, for covering and alleviating the nonvolatile memory delay performance poor with respect to DRAM, is called DRAM cache.The amount of capacity of this part dram space dynamically can be joined, and can, according to the information such as characteristic and access frequency of upper layer data load, dynamically adjust adaptively amount of capacity.
For whole fusion memory system, it is to DRAM and nonvolatile memory unified addressing, unified management, and the scope of its address is 0~n, can regard as a whole internal memory as to upper strata, and concrete device type is invisible.Wherein, the part that the address of nonvolatile memory part is unified addressing, this part address immobilizes; The address of DRAM is another part of unified addressing, can dynamic change.Notice that the address realm A of cache DRAM is 0~X herein, the maximum address that X is DRAM, address realm A dynamically adjusts according to the characteristic of upper strata request.For example, if request is to read to write few type more, A will diminish, and directly allows read request occur on nonvolatile memory; On the contrary, if request is to read to write less many types, A can become greatly, also utilizes more DRAM to serve as the cache of nonvolatile memory, to cover its writing rate, and improves the life-span.
Two, merge memory system hardware platform
Employing includes but not limited to the embedded-development environment of the processor such as ARM, FPGA, merge memory system in these platform deploy, make processor identify and access fusion internal memory in the mode of internal memory, realize the fusion memory system based on nonvolatile memory and DRAM.
(1) hardware platform overall architecture
As shown in Figure 2, hardware platform overall architecture comprises with next several parts:
Processor module, includes but not limited to the processor such as ARM, FPGA;
Multiple internal memory physical interfaces, for providing the signaling protocol that meets memory techniques standard.Above-mentioned memory interface technical standard can be existing memory interface technical standard, as DDR2, and DDR3 etc.In these internal memory physical interfaces, reserve the memory interface that design system must be used, the I/O mouths that used as the corresponding internal memory of processor control etc., also will reserve and merge nonvolatile memory and the needed memory interface of DRAM device in memory system.
SD card interface module, is configured and is started processor system by SD card;
Universal serial port turns usb interface module, and debugging serial port function is provided;
PCIe interface module, according to user's request and self-defined, supports PCIe series (comprising a PCIe generation, multiple passage configuration under two generations) physical layer protocol, and this hardware platform is communicated with host interface with the PCIe interface (PCIe2.0X8) of definition;
Power supply adaptor module, supporting with ATX power interface, multiple adaptive I/O mouth level can be provided, as 1.2V, 1.5V, 1.8V, 2.5V, 3.3V etc. are provided;
Clock management module, for generation of the needed clock of corresponding module.
(2) nonvolatile memory merges internal memory hardware
Nonvolatile memory merges the concrete framework of internal memory hardware as shown in Figure 3, its mentality of designing is as follows: take certain serial nonvolatile memory chip as basis, design and make nonvolatile memory and merge internal memory, this internal memory hardware interface type is followed the memory standard signaling protocol that mainboard internal memory physical interface adopts, corresponding standard physical interface is provided, can be connected in memory interface with set form, support the DRAM internal memory hardware of same standard agreement simultaneously, by the work of merging memory management and merging Memory Controller Hub, make processor to access nonvolatile memory storer and DRAM storer according to the access mode of internal memory, realize the fusion memory system based on nonvolatile memory and dynamic randon access.
Wherein, because the interface protocol of internal storage access is standard agreement, and current nonvolatile memory phy chip on the market has not all adopted the communication protocol consistent with memory standard.Therefore,, in order to realize memorymodel access nonvolatile memory, need between the protocol memory that memory interface module adopts in nonvolatile memory chip package interface protocol and hardware plan overall architecture, change, or complete compatibility.For this reason, this fusion internal memory hardware comprises a protocol conversion module, for the protocol memory that the protocol conversion of nonvolatile memory phy chip package interface is adopted for memory interface.
Meanwhile, level between distinct interface agreement need to be isolated and be changed (if the support level of the LPDDR2 of Micron Technology Series PC M chip is 1.2V, P8P series is 3.3V, and the level of DDR3 agreement support is 1.5V, the level of DDR2 agreement support is 1.8V), therefore, preferably, this fusion internal memory hardware also comprises a level switch module, completes level isolation and conversion between distinct interface agreement.
The concrete form of non-volatile memory hardware can be memory bar, selected nonvolatile memory chip according to demand, composition storage array; Also can be the form of inserting subcard in master card, on each subcard, can adopt multi-disc, formed certain capacity solid-state storage space, in subcard, each nonvolatile memory chip is an independent passage, and the operation such as the read-write between multiple subcards can complete parallel.
(3) merge Memory Controller Hub
As traditional Memory Controller Hub, merge Memory Controller Hub according to the work schedule of nonvolatile memory and DRAM phy chip, upper strata call instruction and pin level signal condition, worker state machine is set to complete corresponding operation, and the software interface that drives memory chip is provided.The hardware aspect of Memory Controller Hub, according to merging the state machine of memory chip work and the order that call on current upper strata, completes corresponding operating; The software aspect of Memory Controller Hub, provides the function interface to merging each orders such as memory system read-write.In Memory Controller Hub, the specific design of state machine is the state of the art, does not repeat them here.
Three, merge memory management module
For nonvolatile memory and the different internal memory of DRAM two classes, merge memory management module and need to consider layout and the migration of data, according to the relative merits of two class storeies, rationally place data, make the internal storage data of depositing in nonvolatile memory and DRAM have certain difference, very fast to embody DRAM access rate, the feature that PCM is non-volatile, to crucial data consistent metadata information reliably as high in needs, start and need configuration information fast, read-only system information is directly placed in nonvolatile memory.Rationally utilize both storage spaces simultaneously, internal memory Cache using part DRAM as nonvolatile memory, often the data placement of access is in DRAM, nonvolatile memory is as the rear end storage of DRAM, utilize the fast feature of DRAM access speed, cover the long shortcoming of write delay of nonvolatile memory, and reduced the number of times of writing of nonvolatile memory, be beneficial to non-volatile storage life and the restriction of writing energy consumption.Also given play to the non-volatile characteristic of nonvolatile memory power down, data consistency is good, persistence internal storage data simultaneously.
As shown in Figure 4, in the embodiment of the present invention, merge memory management module and carry out unified management to merging internal memory, comprise cold and hot data identification submodule, Data Migration submodule, initialization submodule, read-write requests scheduling sublayer module, address mapping submodule, wear leveling submodule etc.
Cold and hot data identification submodule: the cold and hot property that judges visit data according to access frequency and access time.Wherein, consider the temperature of data itself, the many factors such as the principle of locality while considering routine access again, for nonvolatile memory used, dispose cold and hot data identification mechanism;
Data Migration submodule: according to the recognition result of cold and hot data, the data of cold data will be identified as in DRAM, move in DRAM cache or NVM and (specifically decide according to the characteristic of selected NVM the Data Migration direction that is identified as cold data by DRAM), by be identified as the data of dsc data in DRAM cache, move in DRAM.Such advantage is, make full use of the fast advantage of read-write speed of DRAM, reduce the time of Data Migration operation and postpone expense, simultaneously in the time that data are moved in succession between the two, do not have real being written in nonvolatile memory, reduce writing of redundancy in nonvolatile memory device or unnecessary data, be conducive to the life-span of nonvolatile memory;
Initialization submodule: when system initialization for the first time, predetermined critical data (as system starts required information, needs high consistent metadata information reliably) is imported in nonvolatile memory.In the time of follow-up operation, critical data also leaves in nonvolatile memory, is like this started and carried out fast the next time that makes system, and no longer need again to import log-on message.
Read-write requests scheduling sublayer module: after upper strata request is assigned, determine the address that issues of request according to request characteristic, then request command is issued to fusion Memory Controller Hub, finally arrive the corresponding internal memory that merges.Described request characteristic comprises read-write type ratio, request load characteristic etc.
Address mapping submodule: maintain unified address mapping table for merging memory system.This table leaves in nonvolatile memory, and the logical address and the physical address that merge internal memory are separated, and is convenient to carry out abrasion equilibrium and the read-write requests scheduling of nonvolatile memory device.
Abrasion equilibrium submodule: the read-write number of times of monitoring nonvolatile memory, divides timing to utilize Address Mapping to realize the abrasion equilibrium of nonvolatile memory carrying out upper strata request.Preferably, can also take into account in nonvolatile memory region Mobile state abrasion equilibrium, as periodically read and write the exchange of thermal region address.Be specially: what the each region of statistics nonvolatile memory occurred reads number of times and write number of times, between the frequent read operation region that I/O occurs and write operation region, carry out data, address displacement.
Preferably, merge memory management module and also comprise performance optimization submodule: carry out optimisation strategy according to the characteristic of nonvolatile memory, comprise reduction write delay, write time-out and write cancellation etc.Wherein, because nonvolatile memory is larger with respect to the write delay of DRAM, and the life-span of nonvolatile memory is limited, therefore to merging the performance optimization mechanism of memory system mainly for write performance optimization, the energy optimization etc. of nonvolatile memory device, and solving to greatest extent the restriction of nonvolatile memory at aspects such as life-span, write operation delay and energy consumptions, Integral lifting merges the performance of memory system.
Further, merge memory management module and also comprise that dram space capacity dynamically adjusts submodule: periodically monitor the hit rate H of DRAM cache part, and detect read-write requests ratio R:
R=read request number ÷ write request number (1)
When hit rate H < K(K is a predetermined threshold, its value can be according to user's request and self-defined configuration, 0<K<1) and (T is a predetermined threshold when read-write requests ratio R<T, its value can be according to user's request and self-defined configuration, 0<T<1), increase DRAM cache capacity.Concrete operations are that the DRAM of unified addressing is rejected to space, subregion, and be addressed in DRAM cache, the amount of capacity increasing is that doubly (γ is the volume change factor for the γ of former DRAM cache capacity, 0< γ <1, this value can also be configured by User Defined);
In the time of hit rate H >=K and read-write requests ratio R >=T, reduce DRAM cache capacity.Concrete operations are that the segment space in DRAM cache is addressed in the unified addressing that merges internal memory, the amount of capacity reducing is that doubly (θ is the volume change factor for the θ of former DRAM cache capacity, 0< θ <1, this value can also be configured by User Defined).
As can be seen here, this memory system is emphasized the fusion of nonvolatile memory and DRAM, the status and the effect that are both are no longer the memory architecture that simple mixed architecture or individual course exist, but " fusion architecture ", be that nonvolatile memory and DRAM form unified internal memory jointly, wherein DRAM will unify space addressing with nonvolatile memory, meanwhile in DRAM, mark off segment space and be the buffer memory cache of nonvolatile memory; According to the difference of the factors such as data payload feature, the capacity that serves as the cache segment space of nonvolatile memory in DRAM is dynamically configurable; Load characteristic is had to perception, flexible configuration DRAM cache amount of capacity, to improve the hit rate of DRAM cache, improves the performance that merges memory system.
It is pointed out that the adjustment of DRAM capacity likely become two extreme: 1. parallel construction: all DRAM all with nonvolatile memory unified addressing, no longer serve as the cache of nonvolatile memory, as shown in Figure 5; 2. vertical stratification: all DRAM have served as the cache of nonvolatile memory, nonvolatile memory is as the rear end exented memory of DRAM, as shown in Figure 6.
Finally it may be noted that the nonvolatile memory that merges memory system in the embodiment of the present invention can be the storer based on phase transition storage, can be also that storer based on NAND FLASH or other can be as the nonvolatile memorys of internal memory.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. a fusion memory system for nonvolatile memory and dynamic RAM, comprising:
The nonvolatile memory (NVM) of unified addressing, unified management and dynamic RAM (DRAM), wherein DRAM comprises the DRAM cache part of the cache that serves as nonvolatile memory, its spatial content capable of dynamic is adjusted;
Protocol conversion module, for the protocol memory that the protocol conversion of nonvolatile memory phy chip package interface is adopted for memory interface;
Merge Memory Controller Hub, for according to the work schedule of nonvolatile memory and DRAM phy chip, upper strata call instruction and pin level signal condition, worker state machine is set to complete corresponding operation, and the software interface that drives memory chip is provided;
Merge memory management module, for carrying out unified management to merging internal memory, comprise that dram space capacity dynamically adjusts submodule, wherein, described dram space capacity is dynamically adjusted submodule for periodically monitoring the hit rate H of DRAM cache part, and detects read-write requests ratio R:
R=read request number ÷ write request number (1)
In the time of hit rate H < K and read-write requests ratio R<T, increase DRAM cache capacity, wherein, K, T are predetermined threshold, its value can be according to user's request and self-defined configuration, 0<K<1,0<T<1;
In the time of hit rate H >=K and read-write requests ratio R >=T, reduce DRAM cache capacity.
2. fusion memory system according to claim 1, also comprises level switch module, for completing level isolation and the conversion between distinct interface agreement.
3. fusion memory system according to claim 1, wherein, described fusion memory management module also comprises cold and hot data identification submodule and Data Migration submodule, and described cold and hot data identification submodule is for judging the cold and hot property of visit data according to access frequency and access time; Described Data Migration submodule, for according to the recognition result of cold and hot data, will be identified as the data of cold data in DRAM, moves in DRAM cache or NVM, by be identified as the data of dsc data in DRAM cache, moves in DRAM.
4. fusion memory system according to claim 1, wherein, described fusion memory management module also comprises initialization submodule, for predetermined critical data (as system starts required information, needs high consistent metadata information reliably) being imported to nonvolatile memory when the system initialization for the first time.
5. fusion memory system according to claim 1, wherein, described fusion memory management module also comprises read-write requests scheduling sublayer module: after upper strata request is assigned, determine the address that issues of request according to request characteristic, then request command is issued to fusion Memory Controller Hub, finally arrives the corresponding internal memory that merges.
6. fusion memory system according to claim 1, wherein, described fusion memory management module also comprises address mapping submodule, is used to fusion memory system to maintain unified address mapping table.
7. fusion memory system according to claim 1, wherein, described fusion memory management module also comprises abrasion equilibrium submodule, for monitoring the read-write number of times of nonvolatile memory, divides timing to utilize Address Mapping to realize the abrasion equilibrium of nonvolatile memory carrying out upper strata request.
8. fusion memory system according to claim 7, wherein, described abrasion equilibrium submodule is also for adding up the each region of nonvolatile memory occurs read number of times and write number of times, between the frequent read operation region that I/O occurs and write operation region, carries out data, address displacement.
9. fusion memory system according to claim 1, wherein, described fusion memory management module also comprises performance optimization submodule, for carrying out optimisation strategy according to the characteristic of nonvolatile memory, comprises reduction write delay, writes time-out and write cancellation.
10. fusion memory system according to claim 1, wherein, described nonvolatile memory is that the storer based on phase transition storage (PCM), the storer based on NAND FLASH or other can be as the nonvolatile memorys of internal memory.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410041777.2A CN103810113B (en) | 2014-01-28 | 2014-01-28 | A kind of fusion memory system of nonvolatile storage and dynamic random access memory |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410041777.2A CN103810113B (en) | 2014-01-28 | 2014-01-28 | A kind of fusion memory system of nonvolatile storage and dynamic random access memory |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103810113A true CN103810113A (en) | 2014-05-21 |
CN103810113B CN103810113B (en) | 2016-07-06 |
Family
ID=50706907
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410041777.2A Active CN103810113B (en) | 2014-01-28 | 2014-01-28 | A kind of fusion memory system of nonvolatile storage and dynamic random access memory |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103810113B (en) |
Cited By (51)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104077084A (en) * | 2014-07-22 | 2014-10-01 | 中国科学院上海微系统与信息技术研究所 | Distributed random file accessing system and accessing control method thereof |
CN104090852A (en) * | 2014-07-03 | 2014-10-08 | 华为技术有限公司 | Method and equipment for managing hybrid cache |
CN104102590A (en) * | 2014-07-22 | 2014-10-15 | 浪潮(北京)电子信息产业有限公司 | Heterogeneous memory management method and device |
CN104111898A (en) * | 2014-05-26 | 2014-10-22 | 中国能源建设集团广东省电力设计研究院 | Hybrid storage system based on multidimensional data similarity and data management method |
CN104135514A (en) * | 2014-07-25 | 2014-11-05 | 英业达科技有限公司 | Integrated virtualized storing system |
CN104360963A (en) * | 2014-11-26 | 2015-02-18 | 浪潮(北京)电子信息产业有限公司 | Heterogeneous hybrid memory method and device oriented to memory computing |
CN104360825A (en) * | 2014-11-21 | 2015-02-18 | 浪潮(北京)电子信息产业有限公司 | Hybrid internal memory system and management method thereof |
CN104834608A (en) * | 2015-05-12 | 2015-08-12 | 华中科技大学 | Cache replacement method under heterogeneous memory environment |
CN104834606A (en) * | 2015-01-07 | 2015-08-12 | 浪潮(北京)电子信息产业有限公司 | Heterogeneous confusion hierarchical memory device |
CN105117285A (en) * | 2015-09-09 | 2015-12-02 | 重庆大学 | Non-volatile memory schedule optimization method based on mobile virtualization system |
CN105279113A (en) * | 2014-07-03 | 2016-01-27 | 中国科学院声学研究所 | Method, apparatus and system for reducing access to DRAM Cache in missing condition |
CN105405465A (en) * | 2015-12-29 | 2016-03-16 | 中北大学 | Data storing and processing circuit |
CN105573660A (en) * | 2014-09-30 | 2016-05-11 | 伊姆西公司 | Method and device for improving performance of declustered disk array |
CN105786716A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Computer system of heterogeneous hybrid memory architecture, control method of computer system and memory detection system |
CN105786400A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Heterogeneous hybrid memory module, system and storage method |
CN105786721A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Memory address mapping management method and processor |
CN105786643A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Data backup method and system based on heterogeneous hybrid memory |
CN105938458A (en) * | 2016-04-13 | 2016-09-14 | 上海交通大学 | Software-defined heterogeneous hybrid memory management method |
CN106326135A (en) * | 2015-06-30 | 2017-01-11 | 华为技术有限公司 | Method and device for translating data of non-volatile memory NVM |
CN106569964A (en) * | 2015-10-13 | 2017-04-19 | 中兴通讯股份有限公司 | Power-off protection method, power-off protection device, power-off protection system and memory |
CN106776360A (en) * | 2017-02-28 | 2017-05-31 | 建荣半导体(深圳)有限公司 | A kind of chip and electronic equipment |
CN106775476A (en) * | 2016-12-19 | 2017-05-31 | 中国人民解放军理工大学 | Mixing memory system and its management method |
CN106897026A (en) * | 2016-10-07 | 2017-06-27 | 威盛电子股份有限公司 | Nonvolatile memory device and address classification method thereof |
WO2017107164A1 (en) * | 2015-12-25 | 2017-06-29 | 研祥智能科技股份有限公司 | Computer system of heterogeneous hybrid memory architecture and control method therefor, and memory detection system |
CN107562806A (en) * | 2017-08-08 | 2018-01-09 | 上海交通大学 | Mix the adaptive perception accelerated method and system of memory file system |
CN107797944A (en) * | 2017-10-24 | 2018-03-13 | 郑州云海信息技术有限公司 | A kind of hierarchy type isomery mixing memory system |
CN108153538A (en) * | 2017-12-26 | 2018-06-12 | 郑州云海信息技术有限公司 | A kind of isomery storage device and method based on phase transition storage |
CN108268220A (en) * | 2018-02-08 | 2018-07-10 | 重庆邮电大学 | Optimization method for software based on non-volatile hybrid memory in real time embedded system |
CN105045730B (en) * | 2015-06-26 | 2018-10-23 | 上海新储集成电路有限公司 | Mixing memory carries out the moving method of data in a kind of multi-core processor system |
CN108932111A (en) * | 2018-06-15 | 2018-12-04 | 深圳市华傲数据技术有限公司 | A kind of optimization method, medium and the equipment of reading and writing data performance |
WO2019033239A1 (en) * | 2017-08-14 | 2019-02-21 | 北京盛和大地数据科技有限公司 | Method and device for reading file data |
CN109376094A (en) * | 2018-09-27 | 2019-02-22 | 郑州云海信息技术有限公司 | A kind of method of the cold and hot Data Migration of garbage reclamation in storage system |
CN109582599A (en) * | 2017-09-29 | 2019-04-05 | 上海宝存信息科技有限公司 | Data memory device and non-volatile formula memory operating method |
CN110096452A (en) * | 2018-01-31 | 2019-08-06 | 北京忆恒创源科技有限公司 | Non-volatile random access memory and its providing method |
CN110287128A (en) * | 2019-05-21 | 2019-09-27 | 北京微密科技发展有限公司 | CPU virtual DRAM controller fusing flash memory |
CN110781107A (en) * | 2019-09-16 | 2020-02-11 | 北京领芯迅飞科技有限公司 | Low-delay fusion IO control method and device based on DRAM interface |
CN110851273A (en) * | 2019-10-31 | 2020-02-28 | 山东省计算中心(国家超级计算济南中心) | Program processing method based on hybrid memory and device based on hybrid memory |
WO2020082449A1 (en) * | 2018-10-24 | 2020-04-30 | 江苏华存电子科技有限公司 | Method for mapping table corresponding to logical position of management host in flash memory storage |
CN111176584A (en) * | 2019-12-31 | 2020-05-19 | 曙光信息产业(北京)有限公司 | Data processing method and device based on hybrid memory |
CN111208948A (en) * | 2020-01-13 | 2020-05-29 | 华东师范大学 | Request distribution method based on hybrid storage |
CN111444113A (en) * | 2019-01-16 | 2020-07-24 | 阿里巴巴集团控股有限公司 | Non-volatile storage medium sharing method and device, electronic equipment and storage equipment |
US10733107B2 (en) | 2016-10-07 | 2020-08-04 | Via Technologies, Inc. | Non-volatile memory apparatus and address classification method thereof |
CN111627475A (en) * | 2019-04-04 | 2020-09-04 | 前海晶云(深圳)存储技术有限公司 | Memory, electronic device thereof, test system, test method and application method thereof |
CN111722804A (en) * | 2020-06-12 | 2020-09-29 | 浪潮电子信息产业股份有限公司 | Method, system and equipment for scheduling nonvolatile memory and readable storage medium |
WO2020224662A1 (en) * | 2019-05-09 | 2020-11-12 | 北京忆芯科技有限公司 | Storage device that provides open channel by means of cmb |
CN112099733A (en) * | 2020-08-26 | 2020-12-18 | 瑞芯微电子股份有限公司 | DRAM memory time sequence configuration method and device |
CN113608698A (en) * | 2021-08-05 | 2021-11-05 | 上海理工大学 | Heterogeneous memory page migration system and method based on DRAM (dynamic random Access memory) sacrificial Cache |
CN113703690A (en) * | 2021-10-28 | 2021-11-26 | 北京微核芯科技有限公司 | Processor unit, method for accessing memory, computer mainboard and computer system |
CN114038491A (en) * | 2021-10-14 | 2022-02-11 | 西安紫光国芯半导体有限公司 | 3D dynamic storage device, data reading method, data writing method and memory equipment |
CN115686372A (en) * | 2022-11-07 | 2023-02-03 | 武汉麓谷科技有限公司 | ZNS solid state disk ZRWA function-based data management method |
CN116737604A (en) * | 2023-08-15 | 2023-09-12 | 苏州浪潮智能科技有限公司 | Memory control chip, memory module of server and server |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0359923A2 (en) * | 1988-09-15 | 1990-03-28 | International Business Machines Corporation | Multiuser dynamic cache |
CN101989183A (en) * | 2010-10-15 | 2011-03-23 | 浙江大学 | Method for realizing energy-saving storing of hybrid main storage |
US20120144092A1 (en) * | 2010-12-02 | 2012-06-07 | Microsoft Corporation | Efficient cache management |
CN102831087A (en) * | 2012-07-27 | 2012-12-19 | 国家超级计算深圳中心(深圳云计算中心) | Data reading-writing processing method and device based on mixing memory |
CN103207799A (en) * | 2013-04-23 | 2013-07-17 | 中国科学院微电子研究所 | Computer system shutdown method, computer system startup method, computer system shutdown device and computer system startup device |
-
2014
- 2014-01-28 CN CN201410041777.2A patent/CN103810113B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0359923A2 (en) * | 1988-09-15 | 1990-03-28 | International Business Machines Corporation | Multiuser dynamic cache |
CN101989183A (en) * | 2010-10-15 | 2011-03-23 | 浙江大学 | Method for realizing energy-saving storing of hybrid main storage |
US20120144092A1 (en) * | 2010-12-02 | 2012-06-07 | Microsoft Corporation | Efficient cache management |
CN102831087A (en) * | 2012-07-27 | 2012-12-19 | 国家超级计算深圳中心(深圳云计算中心) | Data reading-writing processing method and device based on mixing memory |
CN103207799A (en) * | 2013-04-23 | 2013-07-17 | 中国科学院微电子研究所 | Computer system shutdown method, computer system startup method, computer system shutdown device and computer system startup device |
Cited By (79)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104111898A (en) * | 2014-05-26 | 2014-10-22 | 中国能源建设集团广东省电力设计研究院 | Hybrid storage system based on multidimensional data similarity and data management method |
CN104090852A (en) * | 2014-07-03 | 2014-10-08 | 华为技术有限公司 | Method and equipment for managing hybrid cache |
CN105279113B (en) * | 2014-07-03 | 2018-01-30 | 中国科学院声学研究所 | Reduce the methods, devices and systems that DRAM Cache missings access |
CN104090852B (en) * | 2014-07-03 | 2017-04-05 | 华为技术有限公司 | The method and apparatus of management hybrid cache |
CN105279113A (en) * | 2014-07-03 | 2016-01-27 | 中国科学院声学研究所 | Method, apparatus and system for reducing access to DRAM Cache in missing condition |
CN104102590A (en) * | 2014-07-22 | 2014-10-15 | 浪潮(北京)电子信息产业有限公司 | Heterogeneous memory management method and device |
CN104077084B (en) * | 2014-07-22 | 2017-07-21 | 中国科学院上海微系统与信息技术研究所 | Distributed random access file system and its access control method |
CN104077084A (en) * | 2014-07-22 | 2014-10-01 | 中国科学院上海微系统与信息技术研究所 | Distributed random file accessing system and accessing control method thereof |
CN104135514A (en) * | 2014-07-25 | 2014-11-05 | 英业达科技有限公司 | Integrated virtualized storing system |
CN104135514B (en) * | 2014-07-25 | 2017-10-17 | 英业达科技有限公司 | Fusion type virtual storage system |
CN105573660A (en) * | 2014-09-30 | 2016-05-11 | 伊姆西公司 | Method and device for improving performance of declustered disk array |
CN105573660B (en) * | 2014-09-30 | 2019-05-17 | 伊姆西公司 | Method and apparatus for improving the performance of sub-clustering disk array |
CN104360825A (en) * | 2014-11-21 | 2015-02-18 | 浪潮(北京)电子信息产业有限公司 | Hybrid internal memory system and management method thereof |
CN104360825B (en) * | 2014-11-21 | 2018-02-06 | 浪潮(北京)电子信息产业有限公司 | One kind mixing memory system and its management method |
CN104360963B (en) * | 2014-11-26 | 2017-12-12 | 浪潮(北京)电子信息产业有限公司 | A kind of isomery mixing internal memory method and apparatus calculated towards internal memory |
CN104360963A (en) * | 2014-11-26 | 2015-02-18 | 浪潮(北京)电子信息产业有限公司 | Heterogeneous hybrid memory method and device oriented to memory computing |
CN105786716A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Computer system of heterogeneous hybrid memory architecture, control method of computer system and memory detection system |
CN105786400A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Heterogeneous hybrid memory module, system and storage method |
CN105786721A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Memory address mapping management method and processor |
CN105786643A (en) * | 2014-12-25 | 2016-07-20 | 研祥智能科技股份有限公司 | Data backup method and system based on heterogeneous hybrid memory |
CN105786643B (en) * | 2014-12-25 | 2021-05-18 | 研祥智能科技股份有限公司 | Data backup method and system based on heterogeneous hybrid memory |
CN104834606A (en) * | 2015-01-07 | 2015-08-12 | 浪潮(北京)电子信息产业有限公司 | Heterogeneous confusion hierarchical memory device |
CN104834608A (en) * | 2015-05-12 | 2015-08-12 | 华中科技大学 | Cache replacement method under heterogeneous memory environment |
CN104834608B (en) * | 2015-05-12 | 2017-09-29 | 华中科技大学 | A kind of buffer replacing method under isomery memory environment |
CN105045730B (en) * | 2015-06-26 | 2018-10-23 | 上海新储集成电路有限公司 | Mixing memory carries out the moving method of data in a kind of multi-core processor system |
CN106326135A (en) * | 2015-06-30 | 2017-01-11 | 华为技术有限公司 | Method and device for translating data of non-volatile memory NVM |
CN105117285A (en) * | 2015-09-09 | 2015-12-02 | 重庆大学 | Non-volatile memory schedule optimization method based on mobile virtualization system |
CN105117285B (en) * | 2015-09-09 | 2019-03-19 | 重庆大学 | A kind of nonvolatile memory method for optimizing scheduling based on mobile virtual system |
CN106569964A (en) * | 2015-10-13 | 2017-04-19 | 中兴通讯股份有限公司 | Power-off protection method, power-off protection device, power-off protection system and memory |
WO2017107164A1 (en) * | 2015-12-25 | 2017-06-29 | 研祥智能科技股份有限公司 | Computer system of heterogeneous hybrid memory architecture and control method therefor, and memory detection system |
CN105405465A (en) * | 2015-12-29 | 2016-03-16 | 中北大学 | Data storing and processing circuit |
CN105405465B (en) * | 2015-12-29 | 2019-07-23 | 中北大学 | Data storage and processing circuit |
CN105938458B (en) * | 2016-04-13 | 2019-02-22 | 上海交通大学 | The isomery mixing EMS memory management process of software definition |
CN105938458A (en) * | 2016-04-13 | 2016-09-14 | 上海交通大学 | Software-defined heterogeneous hybrid memory management method |
US10733107B2 (en) | 2016-10-07 | 2020-08-04 | Via Technologies, Inc. | Non-volatile memory apparatus and address classification method thereof |
CN106897026A (en) * | 2016-10-07 | 2017-06-27 | 威盛电子股份有限公司 | Nonvolatile memory device and address classification method thereof |
CN106897026B (en) * | 2016-10-07 | 2020-02-07 | 威盛电子股份有限公司 | Nonvolatile memory device and address classification method thereof |
CN106775476A (en) * | 2016-12-19 | 2017-05-31 | 中国人民解放军理工大学 | Mixing memory system and its management method |
CN106776360B (en) * | 2017-02-28 | 2018-04-17 | 建荣半导体(深圳)有限公司 | A kind of chip and electronic equipment |
CN106776360A (en) * | 2017-02-28 | 2017-05-31 | 建荣半导体(深圳)有限公司 | A kind of chip and electronic equipment |
CN107562806B (en) * | 2017-08-08 | 2020-07-28 | 上海交通大学 | Self-adaptive sensing acceleration method and system of hybrid memory file system |
CN107562806A (en) * | 2017-08-08 | 2018-01-09 | 上海交通大学 | Mix the adaptive perception accelerated method and system of memory file system |
WO2019033239A1 (en) * | 2017-08-14 | 2019-02-21 | 北京盛和大地数据科技有限公司 | Method and device for reading file data |
CN109582599A (en) * | 2017-09-29 | 2019-04-05 | 上海宝存信息科技有限公司 | Data memory device and non-volatile formula memory operating method |
CN109582599B (en) * | 2017-09-29 | 2023-12-22 | 上海宝存信息科技有限公司 | Data storage device and non-volatile memory operation method |
CN107797944A (en) * | 2017-10-24 | 2018-03-13 | 郑州云海信息技术有限公司 | A kind of hierarchy type isomery mixing memory system |
CN108153538A (en) * | 2017-12-26 | 2018-06-12 | 郑州云海信息技术有限公司 | A kind of isomery storage device and method based on phase transition storage |
CN110096452B (en) * | 2018-01-31 | 2024-05-28 | 北京忆恒创源科技股份有限公司 | Nonvolatile random access memory and method for providing the same |
CN110096452A (en) * | 2018-01-31 | 2019-08-06 | 北京忆恒创源科技有限公司 | Non-volatile random access memory and its providing method |
CN108268220A (en) * | 2018-02-08 | 2018-07-10 | 重庆邮电大学 | Optimization method for software based on non-volatile hybrid memory in real time embedded system |
CN108268220B (en) * | 2018-02-08 | 2020-12-18 | 重庆邮电大学 | Software optimization method of non-volatile mixed memory in real-time embedded system |
CN108932111A (en) * | 2018-06-15 | 2018-12-04 | 深圳市华傲数据技术有限公司 | A kind of optimization method, medium and the equipment of reading and writing data performance |
CN109376094A (en) * | 2018-09-27 | 2019-02-22 | 郑州云海信息技术有限公司 | A kind of method of the cold and hot Data Migration of garbage reclamation in storage system |
WO2020082449A1 (en) * | 2018-10-24 | 2020-04-30 | 江苏华存电子科技有限公司 | Method for mapping table corresponding to logical position of management host in flash memory storage |
CN111444113A (en) * | 2019-01-16 | 2020-07-24 | 阿里巴巴集团控股有限公司 | Non-volatile storage medium sharing method and device, electronic equipment and storage equipment |
CN111444113B (en) * | 2019-01-16 | 2023-06-13 | 阿里巴巴集团控股有限公司 | Nonvolatile storage medium sharing method and device, electronic equipment and storage equipment |
CN111627475B (en) * | 2019-04-04 | 2022-12-13 | 深圳市晶凯电子技术有限公司 | Memory, electronic device thereof, test system, test method and application method thereof |
CN111627475A (en) * | 2019-04-04 | 2020-09-04 | 前海晶云(深圳)存储技术有限公司 | Memory, electronic device thereof, test system, test method and application method thereof |
WO2020224662A1 (en) * | 2019-05-09 | 2020-11-12 | 北京忆芯科技有限公司 | Storage device that provides open channel by means of cmb |
CN110287128B (en) * | 2019-05-21 | 2021-06-04 | 北京融芯微科技有限公司 | CPU virtual DRAM controller fusing flash memory |
CN110287128A (en) * | 2019-05-21 | 2019-09-27 | 北京微密科技发展有限公司 | CPU virtual DRAM controller fusing flash memory |
CN110781107A (en) * | 2019-09-16 | 2020-02-11 | 北京领芯迅飞科技有限公司 | Low-delay fusion IO control method and device based on DRAM interface |
CN110851273B (en) * | 2019-10-31 | 2022-07-15 | 山东省计算中心(国家超级计算济南中心) | Program processing method based on hybrid memory and device based on hybrid memory |
CN110851273A (en) * | 2019-10-31 | 2020-02-28 | 山东省计算中心(国家超级计算济南中心) | Program processing method based on hybrid memory and device based on hybrid memory |
CN111176584A (en) * | 2019-12-31 | 2020-05-19 | 曙光信息产业(北京)有限公司 | Data processing method and device based on hybrid memory |
CN111176584B (en) * | 2019-12-31 | 2023-10-31 | 曙光信息产业(北京)有限公司 | Data processing method and device based on hybrid memory |
CN111208948A (en) * | 2020-01-13 | 2020-05-29 | 华东师范大学 | Request distribution method based on hybrid storage |
US11789615B2 (en) | 2020-06-12 | 2023-10-17 | Inspur Electronic Information Industry Co., Ltd. | Nonvolatile memory scheduling method, system and device, and readable storage medium |
CN111722804B (en) * | 2020-06-12 | 2022-07-08 | 浪潮电子信息产业股份有限公司 | Method, system and equipment for scheduling nonvolatile memory and readable storage medium |
CN111722804A (en) * | 2020-06-12 | 2020-09-29 | 浪潮电子信息产业股份有限公司 | Method, system and equipment for scheduling nonvolatile memory and readable storage medium |
WO2021248935A1 (en) * | 2020-06-12 | 2021-12-16 | 浪潮电子信息产业股份有限公司 | Nonvolatile memory scheduling method, system and device, and readable storage medium |
CN112099733B (en) * | 2020-08-26 | 2022-05-13 | 瑞芯微电子股份有限公司 | DRAM memory time sequence configuration method and device |
CN112099733A (en) * | 2020-08-26 | 2020-12-18 | 瑞芯微电子股份有限公司 | DRAM memory time sequence configuration method and device |
CN113608698B (en) * | 2021-08-05 | 2024-02-23 | 上海理工大学 | Heterogeneous memory page migration system and method based on DRAM sacrificial Cache |
CN113608698A (en) * | 2021-08-05 | 2021-11-05 | 上海理工大学 | Heterogeneous memory page migration system and method based on DRAM (dynamic random Access memory) sacrificial Cache |
CN114038491A (en) * | 2021-10-14 | 2022-02-11 | 西安紫光国芯半导体有限公司 | 3D dynamic storage device, data reading method, data writing method and memory equipment |
CN113703690A (en) * | 2021-10-28 | 2021-11-26 | 北京微核芯科技有限公司 | Processor unit, method for accessing memory, computer mainboard and computer system |
CN115686372A (en) * | 2022-11-07 | 2023-02-03 | 武汉麓谷科技有限公司 | ZNS solid state disk ZRWA function-based data management method |
CN116737604A (en) * | 2023-08-15 | 2023-09-12 | 苏州浪潮智能科技有限公司 | Memory control chip, memory module of server and server |
Also Published As
Publication number | Publication date |
---|---|
CN103810113B (en) | 2016-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103810113B (en) | A kind of fusion memory system of nonvolatile storage and dynamic random access memory | |
US10725956B2 (en) | Memory device for a hierarchical memory architecture | |
US11366591B2 (en) | Data storage among a plurality of storage drives | |
EP2795470B1 (en) | Apparatus and method to provide cache move with non-volatile mass memory system | |
US8694719B2 (en) | Controller, storage device, and method for power throttling memory operations | |
CN103946811B (en) | Apparatus and method for realizing the multi-level store hierarchy with different operation modes | |
JP5453661B2 (en) | Memory system controller | |
US8195971B2 (en) | Solid state disk and method of managing power supply thereof and terminal including the same | |
US10949120B2 (en) | Host defined bandwidth allocation for SSD tasks | |
CN104011691A (en) | Non-volatile ram disk | |
CA2740511A1 (en) | A composite memory having a bridging device for connecting discrete memory devices to a system | |
US20220156000A1 (en) | Data Aggregation In ZNS Drive | |
TW201030746A (en) | A bridging device having a configurable virtual page size | |
US11372543B2 (en) | Zone-append command scheduling based on zone state | |
US10032494B2 (en) | Data processing systems and a plurality of memory modules | |
CN105808455A (en) | Memory access method, storage-class memory and computer system | |
CN110299159A (en) | The operating method and storage system of memory device, memory device | |
CN114253461A (en) | Mixed channel memory device | |
CN114253462A (en) | Method for providing mixed channel memory device | |
TW201535113A (en) | System and method of operation for high capacity solid-state drive | |
US20160334861A1 (en) | Power management for a data storage system | |
CN107885667A (en) | Reduce the method and apparatus of read command processing delay | |
CN213338708U (en) | Control unit and storage device | |
WO2021221725A1 (en) | Zone-based device with control level selected by the host | |
CN106155565A (en) | A kind of high speed hard-disk based on 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 |