CN106095725A - A kind of concordance catalogue construction method, system and multiprocessor computer system - Google Patents
A kind of concordance catalogue construction method, system and multiprocessor computer system Download PDFInfo
- Publication number
- CN106095725A CN106095725A CN201610375476.2A CN201610375476A CN106095725A CN 106095725 A CN106095725 A CN 106095725A CN 201610375476 A CN201610375476 A CN 201610375476A CN 106095725 A CN106095725 A CN 106095725A
- Authority
- CN
- China
- Prior art keywords
- processor
- group
- bit vector
- concordance
- data block
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
- G06F15/177—Initialisation or configuration control
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
This application discloses a kind of concordance catalogue construction method, system and multiprocessor computer system, the method is applied to comprise the multiprocessor computer system of N number of processor;The method includes: be grouped above-mentioned N number of processor, obtains T group processor, and wherein, often group processor all includes n processor;Utilizing Bloom filter, data sharing situation is mapped to T group bit vector by T group processor one to one, obtain corresponding share directory vector, wherein, often group bit vector all includes m position, and m is less than n.Visible, on the one hand the application carries out mapping process based on Bloom filter, which ensure that concordance catalogue is taken up space relatively low;On the other hand, the processor of the difference group bit vector from different groups is carried out mapping pair by the application should, so be equivalent to so that often organizing the state of isolating that is between bit vector, it is to avoid between them, produce mutual impact, so that mapping conflict will not be produced between different group bit vector.
Description
Technical field
The present invention relates to multiprocessor computer technology field, particularly to a kind of concordance catalogue construction method, system
And multiprocessor computer system.
Background technology
Currently, in multiprocessor computer system, in order to safeguard that the privately owned Cache of different processor (i.e. deposit by speed buffering
Reservoir) in the concordance of data, need to use Cache coherence protocol.Cache concordance based on catalogue is good due to it
Autgmentability, is widely used in modern mainframe computer system.
At present, the way of realization of the concordance catalogue in multiprocessor computer system have full mapping directory and by cloth grand
The concordance catalogue that filter produces.Wherein, the implementation of full mapping directory is simple, but the storage sky that catalogue itself is shared
Between bigger.And the concordance catalogue produced by Bloom filter can be compressed catalogue significantly and be taken up space, but different disposal
Device may produce mapping conflict between the mapped bits in catalogue, thus causes pseudo-sharing, namely causes some not have number
Be mistaken for comprising corresponding data trnascription according to the processor of copy, in this case, misjudged processor would have to by
Compel to carry out communication with the external world, thereby produce redundancy message.
In sum it can be seen that how ensure concordance catalogue taken up space relatively low on the premise of, minimizing is owing to reflecting
Penetrating the produced redundancy message of conflict is to have problem to be solved at present.
Summary of the invention
In view of this, it is an object of the invention to provide a kind of concordance catalogue construction method, system and multiprocessor meter
Calculation machine system, ensure concordance catalogue taken up space relatively low on the premise of, decrease due to map conflict produced by redundancy
Message.Its concrete scheme is as follows:
A kind of concordance catalogue construction method, is applied to comprise the multiprocessor computer system of N number of processor, wherein, N
For the integer not less than 2;Described method includes:
Being grouped described N number of processor, obtain T group processor, wherein, often group processor all includes n processor;
Utilize Bloom filter, data sharing situation mapped to by described T group processor one to one T group bit vector,
Obtaining corresponding share directory vector, wherein, often group bit vector all includes m position, and m is less than n.
Preferably, described utilize Bloom filter, data sharing situation is mapped to by described T group processor one to one
The process of T group bit vector, including:
In advance described T group bit vector is initialized, so that each in described T group bit vector is all set to 0;
Processor is performed both by k Hash operation, will often organize processor to described data sharing situation often organizing respectively
All mapping to the one group bit vector corresponding with this group processor, wherein, k is less than m.
Preferably, often organizing the Hash operation used between processor is identical Hash operation or the Hash fortune differed
Calculate.
Preferably, any processor is mapped to data sharing situation process in one group of bit vector of correspondence, including:
If this processor needs to read target data block, then corresponding data block copy is sent to this processor, and will
The mapping position in one group of bit vector that this processor is corresponding is 1;
If this processor needs target data block is carried out write operation, then find out all data block pairs with correspondence
This processor, sends for indicating the invalid command that this data block copy is invalid to all processors found out, and to phase
The mapped bits answered is updated, and then allows this to need the processor carrying out write operation to carry out corresponding write operation.
Preferably, described in find out the process of processor of all data block copies with correspondence, including:
By combine current each processor mapping situation in the bit vector of self correspondence and presently described share
The concrete numerical value of each on catalogue vector, finds out the processor of all data block copies with correspondence.
The invention also discloses a kind of concordance catalogue constructing system, be applied to comprise the multiprocessor meter of N number of processor
Calculation machine system, wherein, N is the integer not less than 2;Described constructing system includes:
Processor grouping module, for being grouped described N number of processor, obtains T group processor, wherein, often at group
Reason device all includes n processor;
Share situation mapping block, be used for utilizing Bloom filter, by described T group processor to data sharing situation a pair
One ground maps to T group bit vector, obtains corresponding share directory vector, and wherein, often group bit vector all includes m position, and m is less than n.
Preferably, described shared situation mapping block, including:
Initialization unit, in advance described T group bit vector being initialized, every with by described T group bit vector
One is all set to 0;
Mapping submodule, for being performed both by k Hash operation, will often organize processor to institute often organizing respectively in processor
Stating data sharing situation and all map to the one group bit vector corresponding with this group processor, wherein, k is less than m.
Preferably, described mapping submodule includes:
First mapping submodule, for needing to read target data block, then when any processor in described N number of processor
Corresponding data block copy is sent to this processor, and is 1 by the mapping position in one group of corresponding for this processor bit vector;
Second mapping submodule, for needing to carry out target data block when any processor in described N number of processor
Write operation, then find out the processor of all data block copies with correspondence, sends to all processors found out and uses
In indicating the invalid command that this data block copy is invalid, and corresponding mapped bits is updated, then allows these needs to carry out
The processor of write operation carries out corresponding write operation.
Preferably, described second mapping submodule includes:
Unit searched by processor, for needing to carry out target data block when any processor in described N number of processor
Write operation, then by combining current each processor mapping situation in the bit vector of self correspondence and presently described common
Enjoy the concrete numerical value of each on catalogue vector, find out the processor of all data block copies with correspondence.
The present invention further discloses a kind of multiprocessor computer system, build system including aforesaid concordance catalogue
System.
In the present invention, concordance catalogue construction method, it is applied to comprise the multiprocessor computer system of N number of processor;
The method includes: be grouped above-mentioned N number of processor, obtains T group processor, and wherein, often group processor all includes n process
Device;Utilize Bloom filter, data sharing situation is mapped to by T group processor one to one T group bit vector, obtain corresponding
Share directory vector, wherein, often group bit vector all includes m position, and m is less than n.Visible, the present invention is utilizing Bloom filter logarithm
Before mapping according to shared situation, first all processors in multiprocessor computer system are grouped, the most again
Utilize Bloom filter, data sharing situation is mapped to by T group processor one to one T group bit vector, that is, the most originally
Invention carries out mapping process based on Bloom filter, which ensure that concordance catalogue is taken up space relatively low;On the other hand,
The present invention processor of the difference group bit vector from different groups is carried out mapping pair should, be so equivalent to so that often organize bit vector it
Between be in the state of isolating, it is to avoid produce mutual impact between them, so that will not produce between different group bit vector
Map conflict, thereby reduce owing to mapping the produced redundancy message of conflict.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Inventive embodiment, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to
The accompanying drawing provided obtains other accompanying drawing.
Fig. 1 is a kind of concordance catalogue construction method flow chart disclosed in the embodiment of the present invention;
Fig. 2 is a kind of concordance catalogue constructing system structural representation disclosed in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under not making creative work premise
Embodiment, broadly falls into the scope of protection of the invention.
The embodiment of the invention discloses a kind of concordance catalogue construction method, be applied to comprise the multiprocessing of N number of processor
Device computer system, wherein, N is the integer not less than 2;Shown in Figure 1, the method includes:
Step S11: be grouped N number of processor, obtains T group processor, and wherein, often group processor all includes at n
Reason device.
It is pointed out that above-mentioned grouping process is a kind of grouping process not repeated and do not omit, that is, based on not weighing
Group forming criterion that is multiple and that do not omit, is grouped above-mentioned N number of processor, is correspondingly made available T group processor, and the most often group processes
Device all includes n processor, it can be seen that, N=T × n.It addition, can be according to the concrete numerical value of N value and the actual need of user
Want, T value is set, T value is not carried out at this concrete restriction numerically.
Step S12: utilize Bloom filter, data sharing situation is mapped to by T group processor one to one T group position to
Amount, obtains corresponding share directory vector, and wherein, often group bit vector all includes m position, and m is less than n.
It should be noted that above-mentioned often group bit vector all includes m position, namely refer to m position binary system.Above-mentioned m value needs little
In the processor number often organized in processor, that is, m needs less than n.
It addition, above-mentioned so-called data sharing situation is the finger processor shared situation to Cache data.
In the embodiment of the present invention, concordance catalogue construction method, it is applied to comprise the multiprocessor computer of N number of processor
System;The method includes: be grouped above-mentioned N number of processor, obtains T group processor, and wherein, often group processor all includes n
Individual processor;Utilize Bloom filter, data sharing situation is mapped to by T group processor one to one T group bit vector, obtains
Corresponding share directory vector, wherein, often group bit vector all includes m position, and m is less than n.Visible, the embodiment of the present invention is utilizing cloth
Before data sharing situation is mapped by grand filter, first all processors in multiprocessor computer system are carried out
Packet, then recycles Bloom filter, T group processor maps to T group bit vector to data sharing situation, also one to one
I.e., on the one hand, the embodiment of the present invention carries out mapping process based on Bloom filter, which ensure that shared by concordance catalogue
Space is relatively low;On the other hand, the embodiment of the present invention processor of the difference group bit vector from different groups is carried out mapping pair should, this
Sample is equivalent to so that often organizing the state of isolating that is between bit vector, it is to avoid produce mutual impact between them, so that
Mapping conflict will not be produced between different group bit vectors, thereby reduce owing to mapping the produced redundancy message of conflict.
The embodiment of the invention discloses a kind of concrete concordance catalogue construction method, relative to a upper embodiment, this reality
Execute example and technical scheme has been made further instruction and optimization.Concrete:
In upper embodiment step S12, utilize Bloom filter, by T group processor to data sharing situation one to one
Map to the process of T group bit vector, including:
Step S121: initialize T group bit vector in advance, to be all set to 0 by each in T group bit vector;
Step S122: be performed both by k Hash operation in processor, will often organize processor to data sharing often organizing respectively
Situation all maps to the one group bit vector corresponding with this group processor, and wherein, k is less than m.
Wherein, often organizing the Hash operation used between processor is identical Hash operation or the Hash fortune differed
Calculate, that is, often organizing the hash function used between processor can be identical hash function, it is also possible to be different Hash
Function.
Further, in above-mentioned steps S122, any processor is mapped to data sharing situation one group of correspondence
Process in bit vector, including:
If this processor needs to read target data block, then corresponding data block copy is sent to this processor, and will
The mapping position in one group of bit vector that this processor is corresponding is 1;If this processor needs target data block carries out write behaviour
Make, then find out the processor of all data block copies with correspondence, send for indicating to all processors found out
The invalid command that this data block copy is invalid, and corresponding mapped bits is updated, then allow these needs to carry out write behaviour
The processor made carries out corresponding write operation.That is, before target data block is carried out write operation (i.e. changing data),
First pass through invalid command and the data block copy in respective processor is carried out invalidation, the most just carry out data write behaviour
Make.It is understood that above-mentioned data block copy refers to be stored in the data trnascription of the target data block in Cache buffer.
It addition, the process of the above-mentioned processor finding out all data block copies with correspondence, specifically include: by knot
Before being fated on each processor mapping situation in the bit vector of self correspondence and current shared catalogue vector each
Concrete numerical value, finds out the processor of all data block copies with correspondence.That is, by by current each processor from
On concrete numerical value in the bit vector that body is corresponding and current shared catalogue vector, the concrete data value of each carries out numeric ratio pair,
Find out the processor that storage has the data block copy of correspondence.
Accordingly, the embodiment of the invention discloses a kind of concordance catalogue constructing system, be applied to comprise N number of processor
Multiprocessor computer system, wherein, N is the integer not less than 2;Shown in Figure 2, above-mentioned constructing system includes:
Processor grouping module 21, for being grouped N number of processor, obtains T group processor, and wherein, often group processes
Device all includes n processor;
Share situation mapping block 22, be used for utilizing Bloom filter, by T group processor to data sharing situation one to one
Map to T group bit vector, obtain corresponding share directory vector, wherein, often group bit vector all include m position, m be less than n.
It is pointed out that above-mentioned grouping process is a kind of grouping process not repeated and do not omit, that is, based on not weighing
Group forming criterion that is multiple and that do not omit, is grouped above-mentioned N number of processor, is correspondingly made available T group processor, and the most often group processes
Device all includes n processor, it can be seen that, N=T × n.It addition, can be according to the concrete numerical value of N value and the actual need of user
Want, T value is set, T value is not carried out at this concrete restriction numerically.
Visible, the embodiment of the present invention is before utilizing Bloom filter to map data sharing situation, first to many places
All processors in reason device computer system are grouped, and then recycle Bloom filter, by T group processor to data
Shared situation maps to T group bit vector one to one, that is, on the one hand the embodiment of the present invention is to reflect based on Bloom filter
Penetrate process, which ensure that concordance catalogue is taken up space relatively low;On the other hand, the embodiment of the present invention is by the process of difference group
The device bit vector from different groups carries out mapping pair and answers, and is so equivalent to so that often organizing the state of isolating that is between bit vector, it is to avoid
Produce mutual impact between them, so that mapping conflict will not be produced between different group bit vector, thereby reduce
Owing to mapping the produced redundancy message of conflict.
The embodiment of the invention discloses a kind of concrete concordance catalogue constructing system, relative to a upper embodiment, this reality
Execute example and technical scheme has been made further instruction and optimization.Concrete:
Shared situation mapping block in a upper embodiment, specifically can include initialization unit and mapping submodule;Its
In,
Initialization unit, for initializing T group bit vector in advance, each in T group bit vector all to be put
It is 0;
Mapping submodule, for being performed both by k Hash operation, will often organize processor logarithm often organizing respectively in processor
All mapping to the one group bit vector corresponding with this group processor according to shared situation, wherein, k is less than m.
Concrete, above-mentioned mapping submodule includes the first mapping submodule and the second mapping submodule;Wherein,
First mapping submodule, for needing to read target data block, then by phase when any processor in N number of processor
The data block copy answered sends to this processor, and is 1 by the mapping position in one group of corresponding for this processor bit vector;
Second mapping submodule, for needing to write target data block when any processor in N number of processor
Operation, then find out the processor of all data block copies with correspondence, send for referring to all processors found out
Show the invalid command that this data block copy is invalid, and corresponding mapped bits is updated, then allow these needs to write
The processor of operation carries out corresponding write operation.
Wherein, the second mapping submodule includes: unit searched by processor, for when any processor in N number of processor
Need target data block is carried out write operation, then by combining current each processor reflecting in the bit vector of self correspondence
Penetrate the concrete numerical value of each on situation and current shared catalogue vector, find out all data block copies with correspondence
Processor.
Further, the embodiment of the invention also discloses a kind of multiprocessor computer system, including in previous embodiment
Disclosed concordance catalogue constructing system, the particular content about this constructing system refers to the corresponding portion in previous embodiment
Point, do not repeat them here.
Finally, in addition it is also necessary to explanation, in this article, the relational terms of such as first and second or the like be used merely to by
One entity or operation separate with another entity or operating space, and not necessarily require or imply these entities or operation
Between exist any this reality relation or order.And, term " includes ", " comprising " or its any other variant meaning
Containing comprising of nonexcludability, so that include that the process of a series of key element, method, article or equipment not only include that
A little key elements, but also include other key elements being not expressly set out, or also include for this process, method, article or
The key element that equipment is intrinsic.In the case of there is no more restriction, statement " including ... " key element limited, do not arrange
Except there is also other identical element in including the process of described key element, method, article or equipment.
Above a kind of concordance catalogue construction method provided by the present invention, system and multiprocessor computer system are entered
Having gone and be discussed in detail, principle and the embodiment of the present invention are set forth by specific case used herein, above enforcement
The explanation of example is only intended to help to understand method and the core concept thereof of the present invention;General technology people simultaneously for this area
Member, according to the thought of the present invention, the most all will change, in sum, and this explanation
Book content should not be construed as limitation of the present invention.
Claims (10)
1. a concordance catalogue construction method, it is characterised in that be applied to comprise the multi-processor computer of N number of processor
System, wherein, N is the integer not less than 2;Described method includes:
Being grouped described N number of processor, obtain T group processor, wherein, often group processor all includes n processor;
Utilize Bloom filter, described T group processor is mapped to T group bit vector one to one to data sharing situation, obtains
Corresponding share directory vector, wherein, often group bit vector all includes m position, and m is less than n.
Concordance catalogue construction method the most according to claim 1, it is characterised in that the described Bloom filter that utilizes, will
Described T group processor maps to the process of T group bit vector one to one to data sharing situation, including:
In advance described T group bit vector is initialized, so that each in described T group bit vector is all set to 0;
Processor is performed both by k Hash operation, described data sharing situation all to be reflected by often organizing processor often organizing respectively
Being incident upon the one group bit vector corresponding with this group processor, wherein, k is less than m.
Concordance catalogue construction method the most according to claim 2, it is characterised in that often used between group processor
Hash operation is identical Hash operation or the Hash operation differed.
Concordance catalogue construction method the most according to claim 2, it is characterised in that by any processor to data sharing
Situation maps to process in one group of bit vector of correspondence, including:
If this processor needs to read target data block, then corresponding data block copy is sent to this processor, and by this
The mapping position in one group of bit vector that reason device is corresponding is 1;
If this processor needs target data block is carried out write operation, then find out all data block copies with correspondence
Processor, sends for indicating the invalid command that this data block copy is invalid to all processors found out, and to accordingly
Mapped bits is updated, and then allows this to need the processor carrying out write operation to carry out corresponding write operation.
Concordance catalogue construction method the most according to claim 4, it is characterised in that described in find out and all there is correspondence
The process of processor of data block copy, including:
By combining current each processor mapping situation in the bit vector of self correspondence and presently described share directory
The concrete numerical value of each on vector, finds out the processor of all data block copies with correspondence.
6. a concordance catalogue constructing system, it is characterised in that be applied to comprise the multi-processor computer of N number of processor
System, wherein, N is the integer not less than 2;Described constructing system includes:
Processor grouping module, for being grouped described N number of processor, obtains T group processor, wherein, often organizes processor
All include n processor;
Share situation mapping block, be used for utilizing Bloom filter, by described T group processor to data sharing situation one to one
Mapping to T group bit vector, obtain corresponding share directory vector, wherein, often group bit vector all includes m position, and m is less than n.
Concordance catalogue constructing system the most according to claim 6, it is characterised in that described shared situation mapping block,
Including:
Initialization unit, for initializing described T group bit vector in advance, with by each in described T group bit vector
All it is set to 0;
Mapping submodule, for being performed both by k Hash operation, will often organize processor to described number often organizing respectively in processor
All mapping to the one group bit vector corresponding with this group processor according to shared situation, wherein, k is less than m.
Concordance catalogue constructing system the most according to claim 7, it is characterised in that described mapping submodule includes:
First mapping submodule, for needing to read target data block, then by phase when any processor in described N number of processor
The data block copy answered sends to this processor, and is 1 by the mapping position in one group of corresponding for this processor bit vector;
Second mapping submodule, for needing to write target data block when any processor in described N number of processor
Operation, then find out the processor of all data block copies with correspondence, send for referring to all processors found out
Show the invalid command that this data block copy is invalid, and corresponding mapped bits is updated, then allow these needs to write
The processor of operation carries out corresponding write operation.
Concordance catalogue constructing system the most according to claim 8, it is characterised in that described second mapping submodule bag
Include:
Unit searched by processor, for needing to write target data block when any processor in described N number of processor
Operation, then by combining current each processor mapping situation in the bit vector of self correspondence and presently described shared mesh
The concrete numerical value of each on record vector, finds out the processor of all data block copies with correspondence.
10. a multiprocessor computer system, it is characterised in that include the concordance as described in any one of claim 6 to 9
Catalogue constructing system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610375476.2A CN106095725A (en) | 2016-05-31 | 2016-05-31 | A kind of concordance catalogue construction method, system and multiprocessor computer system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610375476.2A CN106095725A (en) | 2016-05-31 | 2016-05-31 | A kind of concordance catalogue construction method, system and multiprocessor computer system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106095725A true CN106095725A (en) | 2016-11-09 |
Family
ID=57230410
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610375476.2A Pending CN106095725A (en) | 2016-05-31 | 2016-05-31 | A kind of concordance catalogue construction method, system and multiprocessor computer system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106095725A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108566388A (en) * | 2018-03-27 | 2018-09-21 | 西安电子科技大学 | SDN stream rule conflict detection methods based on Bloom Filter and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103729309A (en) * | 2014-01-15 | 2014-04-16 | 浪潮电子信息产业股份有限公司 | Method for cataloging Cache consistency |
CN104133785A (en) * | 2014-07-30 | 2014-11-05 | 浪潮集团有限公司 | Method for achieving cache coherency of double-control storage server with mixed catalogs |
CN104239270A (en) * | 2014-07-25 | 2014-12-24 | 浪潮(北京)电子信息产业有限公司 | High-speed cache synchronization method and high-speed cache synchronization device |
CN104408069A (en) * | 2014-10-30 | 2015-03-11 | 浪潮电子信息产业股份有限公司 | Consistency content design method based on Bloom filter thought |
CN104714901A (en) * | 2015-03-13 | 2015-06-17 | 浪潮集团有限公司 | Coarse structure catalog design method based on counters |
CN104778132A (en) * | 2015-04-08 | 2015-07-15 | 浪潮电子信息产业股份有限公司 | Multi-core processor directory cache replacement method |
-
2016
- 2016-05-31 CN CN201610375476.2A patent/CN106095725A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103729309A (en) * | 2014-01-15 | 2014-04-16 | 浪潮电子信息产业股份有限公司 | Method for cataloging Cache consistency |
CN104239270A (en) * | 2014-07-25 | 2014-12-24 | 浪潮(北京)电子信息产业有限公司 | High-speed cache synchronization method and high-speed cache synchronization device |
CN104133785A (en) * | 2014-07-30 | 2014-11-05 | 浪潮集团有限公司 | Method for achieving cache coherency of double-control storage server with mixed catalogs |
CN104408069A (en) * | 2014-10-30 | 2015-03-11 | 浪潮电子信息产业股份有限公司 | Consistency content design method based on Bloom filter thought |
CN104714901A (en) * | 2015-03-13 | 2015-06-17 | 浪潮集团有限公司 | Coarse structure catalog design method based on counters |
CN104778132A (en) * | 2015-04-08 | 2015-07-15 | 浪潮电子信息产业股份有限公司 | Multi-core processor directory cache replacement method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108566388A (en) * | 2018-03-27 | 2018-09-21 | 西安电子科技大学 | SDN stream rule conflict detection methods based on Bloom Filter and system |
CN108566388B (en) * | 2018-03-27 | 2020-10-16 | 西安电子科技大学 | SDN flow rule conflict detection method and system based on bloom filter |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lv et al. | BIM big data storage in WebVRGIS | |
US10810179B2 (en) | Distributed graph database | |
CN110457319B (en) | Block chain state data storage method and device and electronic equipment | |
Lindstrom et al. | An integrated global GIS and visual simulation system | |
CN107533518A (en) | Distributed index for fault tolerant object memory construction | |
CN107924371A (en) | Infinite memory constructional hardware implementation with router | |
US11327900B2 (en) | Securing memory accesses in a virtualized environment | |
CN107402958A (en) | A kind of establishment in GKF three-dimensional space datas storehouse and access method | |
Xuan et al. | Voronoi-based multi-level range search in mobile navigation | |
CN108885604A (en) | Memory construction software implement scheme | |
EP2437462B1 (en) | Data access processing method and device | |
CN1710607A (en) | 3-D scene organization method facing to virtual reality 3-D picture engine | |
CN109690522B (en) | Data updating method and device based on B+ tree index and storage device | |
CN101976468A (en) | Method and system for visualizing multiresolution dynamic landform | |
CN109358974A (en) | A kind of method and relevant apparatus of interprocess communication | |
CN114244595B (en) | Authority information acquisition method and device, computer equipment and storage medium | |
Wang et al. | Retrieving and indexing spatial data in the cloud computing environment | |
JP2018513454A (en) | Efficient performance of insert and point query operations in the column store | |
US20230385353A1 (en) | Spatial search using key-value store | |
CN105677252B (en) | Read method, data processing method and the associated storage device of data | |
CN111651424A (en) | Data processing method and device, data node and storage medium | |
CN108093024A (en) | A kind of classification method for routing and device based on data frequency | |
CN106095725A (en) | A kind of concordance catalogue construction method, system and multiprocessor computer system | |
Glatter et al. | Scalable data servers for large multivariate volume visualization | |
Li et al. | An improved distributed storage model of remote sensing images based on the HDFS and pyramid structure |
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: 20161109 |
|
RJ01 | Rejection of invention patent application after publication |