gridComputing is a kind of distributed computingcomputer science。It studies how to put a hugeComputing powerThe problem that can be solved is divided into many small parts, and then these parts are allocated to manycomputerFinally, these calculation results are combined to get the final result.currentDistributed ComputingThe project has been used by thousands of volunteers around the worldcomputer's idleComputing power, viaInternet, you can analyze the electrical signals from outer space, find hidden black holes, and explore possible extraterrestrial intelligent life;You can find more than 10 million digitsMasonPrime number;You can also find and find more effective drugs to fight HIV.It is used to complete a huge project that requires an astonishing amount of calculation.[1]
Distributed ComputingIs usinginternetOncomputerIt is a computing science that uses the idle processing power of CPU to solve large-scale computing problems.
Grid computing coverage
along withcomputerThe popularity of personal computers began to enter thousands of households.With it comes the use of computers.More and more computers are idle, and the potential of CPU is far from being fully utilized even when it is turned on.We can imagine a householdcomputerSpend most of your time "waiting".Even if users actually use theircomputerThe processor still consumes silently and waits countless times (waiting for input, but actually doing nothing).internetThe appearance of makes the connection call all those with idle computing resourcescomputer systemIt has become a reality.Then, some very complex problems that are suitable for dividing into a large number of smaller pieces of computing are proposed, and then a research organization develops the computing tools through a lot of hard workServerandclient。ServerBe responsible for dividing the computing problem into many small computing parts, and then distributing these parts to many networked computing participantscomputerconductparallel processing Finally, these calculation results are combined to get the final result.
Distributed computing means that applications are no longer "bound" to specific physical systems and platform software, and data and programs can "flow" between computing nodes.
Practical proof
Announce
edit
Of course, this seems primitive and difficult, but with the participants andcomputerWith the continuous increase of the number of, the calculation plan becomes very fast and has been proved to be feasible by practice.At present, some largerDistributed ComputingThe processing capacity of the project has reached or even exceeded the fastest giant in the worldcomputer。You can also choose to participate in some projects to donate CPU kernel processing time. You will find that the CPU kernel processing time you provide will appear in the project contribution statistics.You can compete with other participants to rank your contribution time. You can also join an existing computing group or form a computing group yourself.This approach is conducive to mobilizing the enthusiasm of participants.
Participate in calculation
Announce
edit
participate inDistributed Computing——One of the most meaningful choices that can give full play to the use value of your personal computer - just download the relevant program, and then the program will have the lowest priority incomputerThis has little impact on normal use of the computer.If you want to usecomputerDo something useful in your spare time, why hesitate?Take action at once. Your trivial efforts may make you leave a big mark in the history of human science!
Professional definition
Announce
edit
(ChinaThe Institute of Science and Technology InformationDistributed ComputingDefinition of)
Distributed ComputingIt is a new calculation method.so-calledDistributed ComputingIt means that two or more software share information with each other. These software can be used on the same computercomputerIt can also run on multiple computers connected through the network.
advantage
Announce
edit
Distributed ComputingCompared with other algorithms, it has the following advantages:
First, we need to find aComputing powerTo solve the problem.Such problems are generally interdisciplinary, challenging and urgent scientific research topics for human beings.The more famous ones are:
1. Solve more complex mathematical problems, such as GIMPSMersenne prime )。
2. Research and find the safestCryptosystem, such as RC-72 (password cracking).
3. Biological pathology research, such as:Folding@home(Research on protein folding, misunderstanding, polymerization and related diseases caused by them).
4. Drug research for various diseases, such as United Devices (searching for effective drugs against cancer).
5. Signal processing, such as:SETI@Home(Looking for extraterrestrial civilization at home).
From these practical examples, we can see that these projects are very large and require an astonishing amount of calculation. It is impossible to complete the calculation only by a single computer or individual in an acceptable time.In the past, these problems should be solved bySupercomputerTo solve the problem.But,SupercomputerIts cost and maintenance are very expensive, which is not affordable for an ordinary scientific research organization.With the development of science, a cheap, efficient and easy to maintaincomputing methodCome into being at the historic moment——Distributed Computing!
Grid computing advantages
gridThe purpose of the calculation is tocomputerCan provide unlimitedComputing power, you can access vast amounts of information.This environment will enable enterprises to solve previously difficult problems, use their systems most effectively, meet customer requirements and reduce theircomputerThe total cost of owning and managing resources.gridThe main purpose of calculation is to design a system that can provide the following functions:
Improve or expand the efficiency and utilization of all computing resources in the enterprise, meet the needs of end users, and solve the problems caused by computing, data orstorageProblems that cannot be solved due to the shortage of resources.
establishvirtual organization And cooperate on public issues by letting them share applications and data.
integrationComputing power、storageAnd other resources can make it possible to solve huge problems that require a lot of computing resources.
Through sharing, effective optimization and overall management of these resources, the total cost of computing can be reduced.
Grid computing environment
gridCalculations are mainly used by universities and research laboratoriesHigh performance computingItems for.These projects require hugeComputing power, or a large amount of data needs to be accessed.
gridThe purpose of calculation is to supportE-commerce application。For example, the production of complex products such as aircraft and automobiles requires that product design, product assembly andProduct lifecycle managementPerform compute intensive simulation.Other examples include the simulation of complex financial environment through Monte Carlo method and many projects in the field of life science.
gridThe ultimate goal of the environment is to develop from simple resource centralization to data sharing, and finally to collaborative processing and quality of service.
Resource concentration - enables corporate users to view the entire IT infrastructure of the company as onecomputerAnd can find the unused resources according to their needs.
Data sharing - enables companies to access remote data.This is particularly useful for some life science projects where companies need to share human genetic data with other companies.
adoptgridCooperation through computing - enables organizations widely dispersed in different places to cooperate on certain projects, integrate business processes, and share engineering blueprints and softwareapplication programAnd all other information,Collaborative processingProblems in the project.
Quality of Service (QoS) - refers to the ability to target different users or differentdata streamUse different priorities, orapplication programTo ensure that the performance of the data stream reaches a certain level.Provide quality guaranteed services for all nodes in the same network.
Difference from cloud computing
Announce
edit
Unlike grid computing, cloud computing is more of a set of technologies and standards led by the industry.Both cloud computing and grid computing can improve the utilization of IT resources.However, cloud computing focuses on the integration of IT resources, and provides IT resources on demand after integration;Grid computing focuses on the connection of computing power between different organizations.Cloud computing, relying on the flexibility of IT resource supply, has innovated the business model of IT industry and is a typical application of the business model of basic IT resource outsourcing.Grid computing is the spontaneous formation of a coalition of nodes with computing power to jointly solve problems involving large-scale computing. It is the application of the joint sharing mode of basic IT resources.