CN111586144A - Computer group construction method with OODA fractal mechanism - Google Patents

Computer group construction method with OODA fractal mechanism Download PDF

Info

Publication number
CN111586144A
CN111586144A CN202010363691.7A CN202010363691A CN111586144A CN 111586144 A CN111586144 A CN 111586144A CN 202010363691 A CN202010363691 A CN 202010363691A CN 111586144 A CN111586144 A CN 111586144A
Authority
CN
China
Prior art keywords
ooda
partition
fractal
computing
computer cluster
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
Application number
CN202010363691.7A
Other languages
Chinese (zh)
Inventor
谭光明
邵恩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Western Institute Of Advanced Technology Institute Of Computing Chinese Academy Of Sciences
Original Assignee
Western Institute Of Advanced Technology Institute Of Computing Chinese Academy Of Sciences
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Western Institute Of Advanced Technology Institute Of Computing Chinese Academy Of Sciences filed Critical Western Institute Of Advanced Technology Institute Of Computing Chinese Academy Of Sciences
Priority to CN202010363691.7A priority Critical patent/CN111586144A/en
Priority to CN202010866765.9A priority patent/CN111866188B/en
Publication of CN111586144A publication Critical patent/CN111586144A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/104—Peer-to-peer [P2P] networks
    • H04L67/1042—Peer-to-peer [P2P] networks using topology management mechanisms
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/104—Peer-to-peer [P2P] networks
    • H04L67/1059—Inter-group management mechanisms, e.g. splitting, merging or interconnection of groups
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Multi Processors (AREA)
  • Computer And Data Communications (AREA)

Abstract

The invention provides a computer group construction method with an OODA fractal mechanism, which is characterized in that: the method specifically comprises the following steps: sequentially constructing a computer group system according to the sequence of a processor, a computing card, a server host and a computer group by a fractal mechanism; the fractal mechanism comprises a strong fractal mechanism and a weak fractal mechanism; the strong fractal mechanism completely utilizes an OODA operator, and is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode, namely each part of the computer cluster system has an OODA fractal structure; the weak fractal mechanism is characterized in that at least 1 operator in OODA operators in the strong fractal mechanism is replaced by a general operator, and the weak fractal mechanism is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode.

Description

Computer group construction method with OODA fractal mechanism
Technical Field
The invention relates to a computer system architecture, in particular to a computer group construction method with an OODA fractal mechanism
Background
As workflows with OODA and fractal features gradually become the main computational load for large-scale data centers and supercomputer clusters, the structural design for computer clusters gradually extends toward a "multi-level" design concept. However, the existing computer cluster structure design often integrates the same type of server node mode into the cluster system, and improves the computing power of the whole cluster system through a horizontal expansion mode. In addition, it is difficult for the existing computer cluster system to ensure that each organization level of the computer cluster system can schedule various computing resources for the sub-computing tasks of each level in an efficient manner according to the load characteristics of the OODA workflow.
Therefore, a method for constructing a computer cluster with an OODA fractal mechanism is needed.
Disclosure of Invention
In view of this, the present invention provides a method for constructing a computer cluster with an OODA fractal mechanism.
The invention provides a computer group construction method with an OODA fractal mechanism, which is characterized by comprising the following steps: the method specifically comprises the following steps: sequentially constructing a computer group system according to the sequence of a processor, a computing card, a server host and a computer group by a fractal mechanism;
the fractal mechanism comprises a strong fractal mechanism and a weak fractal mechanism;
the strong fractal mechanism completely utilizes an OODA operator, and is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode, namely each part of the computer cluster system has an OODA fractal structure;
the weak fractal mechanism is characterized in that at least 1 operator in OODA operators in the strong fractal mechanism is replaced by a general operator, and the weak fractal mechanism is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode.
Further, the OODA operator includes OODA four independent compute partitions, namely a 01 compute partition, an O2 compute partition, a D3 compute partition, and an a4 compute partition;
each job occupies a calculation partition according to the sequence of O1- > O2- > D3- > A4, and executes calculation tasks in a circular mode of O1- > O2- > D3- > A4- > O1;
each job occupies some or all of the computational resources of the four partitions of the OODA.
Further, the method for constructing the computer cluster by the strong fractal mechanism comprises the following steps:
s1: constructing an OODA partition processor, and calculating a Group partition by using an OODA operator to obtain OODA partition processors, namely an O1 partition processor, an O2 partition processor, a D3 partition processor and an A4 partition processor;
s2: constructing an OODA partition calculation card, taking an O1 partition processor, an O2 partition processor, a D3 partition processor and an A4 partition processor as OODA operators for constructing the OODA partition calculation card, and constructing the OODA partition calculation card by a fractal mode by using a design method same as that of a processor structure;
s3: an OODA computing server host is constructed, an OODA partition computing card is used as an OODA operator for constructing the OODA computing server host, the OODA partition computing card is used as a computing card of an IO resource pool of the server host, namely the computing card of an O1IO resource pool is an O1 computing card, the computing card of an O2IO resource pool is an O2 computing card, the computing card of a D3IO resource pool is a D3 computing card, the computing card of an A4IO resource pool is an A4 computing card, and the server host comprises four OODA IO resource pools and a scheduling controller in a fractal mode;
s4: an OODA fractal computer cluster system is constructed, an OODAA calculation server host is used as an OODA operator for constructing the OODA fractal computer cluster system, the OODA calculation server host is used as a node server of each calculation partition, and the computer cluster system comprises an O1 calculation partition, an O2 calculation partition, a D3 calculation partition, an A4 calculation partition and a resource management partition with a scheduler function in a fractal mode.
Further, the OODA compute partitions described in step S4 each include one or more node servers corresponding thereto, that is, the O1 compute partition includes one or more O1 node servers, the O2 compute partition includes one or more O2 node servers, the D3 compute partition includes one or more D3 node servers, and the a4 compute partition includes one or more a4 node servers.
Further, the functions and structures of the node servers corresponding to the respective computing partitions in the four OODA computing partitions are the same.
Further, the computer cluster system also includes a storage partition, a network device partition, and a resource management partition, the storage partition, the network device partition, the resource management partition, and the OODA computing partition being connected via a high performance interconnection network.
Further, the method for constructing the computer cluster by the weak fractal mechanism further comprises the following steps: the system is characterized in that an OODA operator is partially utilized, a general operator is partially utilized, the system is divided into three layers from small to large, a processor, a computing card, a server host and a computer cluster are sequentially arranged, and computing components of each layer of the computer cluster system are sequentially built layer by layer.
The invention has the beneficial technical effects that: the computer cluster construction method with OODA fractal mechanism provided by the invention can avoid the mode of horizontal extension to continuously improve the speed of the Computer (CPU) of the whole cluster system for calculating the hash function output; in addition, the efficiency of scheduling various computing resources by calling sub-computing tasks of various levels by various organizational layers of the cluster system is improved. The OODA fractal computer group constructed by the method is more suitable for OODA fractal computing load corresponding to the architecture. The OODA fractal calculation load is composed of four calculation steps of OODA, wherein the four calculation steps have a front-back dependency relationship. In addition, each calculation step can be divided into four OODA calculation steps.
Drawings
The invention is further described below with reference to the following figures and examples:
FIG. 1 is a diagram of a computer cluster architecture with OODA multi-partitions.
FIG. 2 illustrates a strongly fractal computer cluster constructed using a three-layer OODA fractal mechanism.
Fig. 3 illustrates an embodiment of constructing a weakly fractal computer cluster using a three-layer OODA fractal mechanism.
Fig. 4 constructs an embodiment of an OODA fractal computer cluster system.
Detailed Description
The invention is further described with reference to the accompanying drawings in which:
the invention provides a computer group construction method with an OODA fractal mechanism, which is characterized by comprising the following steps: the method specifically comprises the following steps: sequentially constructing a computer group system according to the sequence of a processor, a computing card, a server host and a computer group by a fractal mechanism;
the fractal mechanism comprises a strong fractal mechanism and a weak fractal mechanism;
the strong fractal mechanism completely utilizes an OODA operator, and is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode, namely each part of the computer cluster system has an OODA fractal structure; because each part forming the computer cluster has an OODA fractal structure, the constructed computer cluster has a strong fractal characteristic, as shown in FIG. 2.
The weak fractal mechanism is characterized in that at least 1 operator in OODA operators in the strong fractal mechanism is replaced by a general operator, and the weak fractal mechanism is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode. The constructed computer cluster has a 'weak fractal' characteristic, as shown in fig. 3.
The computer cluster construction method with OODA fractal mechanism provided by the invention can avoid the mode of horizontal extension to continuously improve the speed of the Computer (CPU) of the whole cluster system for calculating the hash function output; in addition, the efficiency of scheduling various computing resources by calling sub-computing tasks of various levels by various organizational layers of the cluster system is improved. The OODA fractal computer group constructed by the method is more suitable for OODA fractal computing load corresponding to the architecture. The OODA fractal calculation load is composed of four calculation steps of OODA, wherein the four calculation steps have a front-back dependency relationship. In addition, each calculation step can be divided into four OODA calculation steps.
In the present embodiment, the OODA operator includes four independent compute partitions, i.e., a 01 compute partition, an O2 compute partition, a D3 compute partition, and an a4 compute partition;
each job occupies a calculation partition according to the sequence of O1- > O2- > D3- > A4, and executes calculation tasks in a circular mode of O1- > O2- > D3- > A4- > O1;
each job occupies some or all of the computational resources of the four partitions of the OODA. The OODA fractal calculation load is composed of four calculation steps of OODA, wherein the four calculation steps have a front-back dependency relationship. In addition, each calculation step can be divided into four OODA calculation steps.
In this embodiment, the method for constructing a computer cluster by the strong fractal mechanism is as follows:
s1: constructing an OODA partition processor, and calculating a Group partition by using an OODA operator to obtain OODA partition processors, namely an O1 partition processor, an O2 partition processor, a D3 partition processor and an A4 partition processor;
s2: constructing an OODA partition calculation card, taking an O1 partition processor, an O2 partition processor, a D3 partition processor and an A4 partition processor as OODA operators for constructing the OODA partition calculation card, and constructing the OODA partition calculation card by a fractal mode by using a design method same as that of a processor structure;
s3: an OODA computing server host is constructed, an OODA partition computing card is used as an OODA operator for constructing the OODA computing server host, the OODA partition computing card is used as a computing card of an IO resource pool of the server host, namely the computing card of an O1IO resource pool is an O1 computing card, the computing card of an O2IO resource pool is an O2 computing card, the computing card of a D3IO resource pool is a D3 computing card, the computing card of an A4IO resource pool is an A4 computing card, and the server host comprises four OODA IO resource pools and a scheduling controller in a fractal mode;
s4: an OODA fractal computer cluster system is constructed, an OODAA calculation server host is used as an OODA operator for constructing the OODA fractal computer cluster system, the OODA calculation server host is used as a node server of each calculation partition, and the computer cluster system comprises an O1 calculation partition, an O2 calculation partition, a D3 calculation partition, an A4 calculation partition and a resource management partition with a scheduler function in a fractal mode. As shown in fig. 4.
In this embodiment, the OODA compute partitions described in step S4 respectively include one or more node servers corresponding thereto, that is, the O1 compute partition includes one or more O1 node servers, the O2 compute partition includes one or more O2 node servers, the D3 compute partition includes one or more D3 node servers, and the a4 compute partition includes one or more a4 node servers.
In this embodiment, the functions and structures of the node servers corresponding to the respective computing partitions in the four OODA computing partitions are the same. That is, the functions and structures of the node servers corresponding to the O1 calculation partitions are the same, the functions and structures of the node servers corresponding to the O2 calculation partitions are the same, the functions and structures of the node servers corresponding to the D3 calculation partitions are the same, and the functions and structures of the node servers corresponding to the a4 calculation partitions are the same. The number of node servers of an OODA computing partition is set by the actual needs of the computer cluster. And simultaneously, the expandability of the computer cluster is increased.
In this embodiment, the computer cluster system further includes a storage partition, a network device partition, and a resource management partition, where the storage partition, the network device partition, the resource management partition, and the OODA computing partition are connected via a high performance interconnection network. As shown in fig. 1, the storage partition includes a plurality of storage nodes, the network device partition includes a plurality of routing switch nodes, and the resource management partition includes a master control node and a plurality of backup master control nodes, as shown in fig. 1.
In this embodiment, the method for constructing a computer cluster by using the weak fractal mechanism further includes: the system is characterized in that an OODA operator is partially utilized, a general operator is partially utilized, the system is divided into three layers from small to large, a processor, a computing card, a server host and a computer cluster are sequentially arranged, and computing components of each layer of the computer cluster system are sequentially built layer by layer. As shown in fig. 3.
The invention combines OODA four types of computing partitions, and distributes the computing resources of each computing partition to each operating load running on the cluster by the resource management partition. In addition, the computer cluster is built layer by layer through a fractal mechanism. And building each layer of computing components of the computer group system by using an OODA operator with OODA partition characteristics and a three-layer fractal mode. And according to the processor, the computing card, the server host and the computer cluster, sequentially constructing a computer cluster system layer by layer.
The method for constructing the computer cluster on the basis of OODA multi-partition and the method for constructing the computer cluster layer by layer on the basis of a fractal mechanism.
This patent provides a method for building a computer cluster based on OODA multiple partitions. Its characteristics are as shown in fig. 1, have following 3 characteristics:
the method is characterized in that: the OODA fractal computer cluster system comprises four computing partitions, including four independent "OODA" computing partitions, wherein each computing partition is composed of a plurality of node servers with the same functions and structures.
And (2) feature: and each job running in the cluster system occupies the server nodes of each computing partition in turn according to the sequence of O1- > O2- > D3- > A4- > O1, and executes computing tasks in a circulating manner.
And (3) feature: each job of the cluster system occupies part or all of the computing resources of the four OODA partitions. The number of resources of each partition occupied by each job is managed by the resource management partition, and the computing resources of the whole cluster are uniformly managed by the resource management partition.
The patent provides a method for constructing a computer cluster layer by layer based on a fractal mechanism, which is characterized in that as shown in fig. 2, the method has the following 4 characteristics:
and (4) feature: the operator unit constructed by the characteristics 1-3 is called an OODA operator, and is shown in FIG. 2. And (4) building each layer of computing components of the computer group system by completely utilizing an OODA operator and in a three-layer fractal mode. And the system is constructed layer by layer in sequence according to the processor, the computing card, the server host and the computer cluster. Because each part forming the computer cluster has an OODA fractal structure, the constructed computer cluster has a 'strong fractal' characteristic, as shown in FIG. 2.
And (5) feature: and partially utilizing an OODA operator and partially utilizing a general operator to construct each layer of computing components of the computer group system in a three-layer fractal mode. And the system is constructed layer by layer in sequence according to the processor, the computing card, the server host and the computer cluster. The constructed computer cluster has a 'weak fractal' characteristic, as shown in fig. 3.
And (6) feature: full fractal cluster architecture: the OODA operator is the primary computing component that makes up the OODA fractal computer cluster system. Each layer of OODA operators forming the OODA fractal computer group system is divided into three layers from large to small: namely a calculation server host, a calculation board card and a processor. And the OODA operators constructed on each layer are constructed by an OODA quaternary structure in a fractal mode. The OODA quaternary structure means that the computing unit of each layer of the structure comprises: an O1 operator, an O2 operator, a D3 operator, an A4 operator, and a scheduler.
And (7) feature: the full fractal cluster system is constructed and completed through an OODA fractal three-step rule, and the steps are as follows.
The method comprises the following steps: corresponding to the first layer fractal of fig. 4. Group partitions are calculated by using four OODA, and an OODA partition processor is formed. The OODA partition handler is used as an OODA operator for constructing an OODA partitioned computing card. And constructing the OODA partition calculation card by a design method which is the same as the structure of the processor and a fractal mode.
Step two: corresponding to the second layer fractal of fig. 4. And taking the OODA partition calculation board card as an OODA operator for constructing an OODA calculation server host. And using the OODA partition calculation board card as a calculation card of each IO resource pool. And constructing an OODA computing server host by four OODA IO resource pools and a scheduling controller in a fractal mode.
Step three: corresponding to the third layer fractal of fig. 4. And taking the OODA computing server host as an OODA operator for constructing an OODA fractal computer group system. An OODA compute server host is utilized as a node server for each compute partition. An OODA fractal computer group system is constructed by four OODA computing partitions and a resource management partition with a scheduler function in a fractal mode.
The OODA Loop theory was first proposed by the united states air force school John Boyd in 1966 and is the main model framework for describing the military command decision process. The OODA ring is composed of: observation (observer), adjustment (origin), idea (Decide), action (Act), and military decisions in a round-robin fashion in four internal steps. The OODA ring theory completes the thinking process of decision or complex problem, and is the thinking set of human brain rational thinking. Nowadays, the OODA ring theory has not only been applied to military decisions, but has gradually become a modeling means for solving key problems in various industries. However, as the business problem is complicated, solving a certain key problem needs to be accomplished by using multiple "repetitions" and "iterations". The fractal thinking is the thinking in the way of repeated thinking and iterative thinking.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.

Claims (7)

1. A computer group construction method with an OODA fractal mechanism is characterized in that: the method specifically comprises the following steps: sequentially constructing a computer group system according to the sequence of a processor, a computing card, a server host and a computer group by a fractal mechanism;
the fractal mechanism comprises a strong fractal mechanism and a weak fractal mechanism;
the strong fractal mechanism completely utilizes an OODA operator, and is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode, namely each part of the computer cluster system has an OODA fractal structure;
the weak fractal mechanism is characterized in that at least 1 operator in OODA operators in the strong fractal mechanism is replaced by a general operator, and the weak fractal mechanism is constructed layer by layer in sequence according to a processor, a computing card, a server host and a computer cluster in a three-layer fractal mode.
2. The method of claim 1 for constructing a computer cluster with an OODA fractal mechanism, wherein: the OODA operators comprise OODA four independent compute partitions, namely a 01 compute partition, an O2 compute partition, a D3 compute partition, and an A4 compute partition;
each job occupies a calculation partition according to the sequence of O1- > O2- > D3- > A4, and executes calculation tasks in a circular mode of O1- > O2- > D3- > A4- > O1;
each job occupies some or all of the computational resources of the four partitions of the OODA.
3. The method for constructing a computer cluster with an OODA fractal mechanism as claimed in claim 2, wherein: the method for constructing the computer cluster by the strong fractal mechanism comprises the following steps:
s1: constructing an OODA partition processor, and calculating a Group partition by using an OODA operator to obtain OODA partition processors, namely an O1 partition processor, an O2 partition processor, a D3 partition processor and an A4 partition processor;
s2: constructing an OODA partition calculation card, taking an O1 partition processor, an O2 partition processor, a D3 partition processor and an A4 partition processor as OODA operators for constructing the OODA partition calculation card, and constructing the OODA partition calculation card by a fractal mode by using a design method same as that of a processor structure;
s3: an OODA computing server host is constructed, an OODA partition computing card is used as an OODA operator for constructing the OODA computing server host, the OODA partition computing card is used as a computing card of an IO resource pool of the server host, namely the computing card of an O1IO resource pool is an O1 computing card, the computing card of an O2IO resource pool is an O2 computing card, the computing card of a D3IO resource pool is a D3 computing card, the computing card of an A4IO resource pool is an A4 computing card, and the server host comprises four OODA IO resource pools and a scheduling controller in a fractal mode;
s4: an OODA fractal computer cluster system is constructed, an OODAA calculation server host is used as an OODA operator for constructing the OODA fractal computer cluster system, the OODA calculation server host is used as a node server of each calculation partition, and the computer cluster system comprises an O1 calculation partition, an O2 calculation partition, a D3 calculation partition, an A4 calculation partition and a resource management partition with a scheduler function in a fractal mode.
4. The method for constructing a computer cluster with an OODA fractal mechanism as claimed in claim 3, wherein: the OODA compute partitions described in step S4 each include one or more node servers corresponding thereto, i.e., the O1 compute partition includes one or more O1 node servers, the O2 compute partition includes one or more O2 node servers, the D3 compute partition includes one or more D3 node servers, and the a4 compute partition includes one or more a4 node servers.
5. The method for constructing a computer cluster with an OODA fractal mechanism as in claim 4, wherein: and the functions and structures of the node servers corresponding to the computing partitions in the four OODA computing partitions are the same.
6. The method for constructing a computer cluster with an OODA fractal mechanism as claimed in claim 5, wherein: the computer cluster system also includes a storage partition, a network device partition, and a resource management partition, the storage partition, the network device partition, the resource management partition, and the OODA computing partition being connected via a high performance interconnection network.
7. The method for constructing a computer cluster with an OODA fractal mechanism as claimed in claim 2, wherein: the method for constructing the computer cluster by the weak fractal mechanism further comprises the following steps: the system is characterized in that an OODA operator is partially utilized, a general operator is partially utilized, the system is divided into three layers from small to large, a processor, a computing card, a server host and a computer cluster are sequentially arranged, and computing components of each layer of the computer cluster system are sequentially built layer by layer.
CN202010363691.7A 2020-04-30 2020-04-30 Computer group construction method with OODA fractal mechanism Pending CN111586144A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202010363691.7A CN111586144A (en) 2020-04-30 2020-04-30 Computer group construction method with OODA fractal mechanism
CN202010866765.9A CN111866188B (en) 2020-04-30 2020-08-25 Computer group construction method with OODA fractal mechanism

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010363691.7A CN111586144A (en) 2020-04-30 2020-04-30 Computer group construction method with OODA fractal mechanism

Publications (1)

Publication Number Publication Date
CN111586144A true CN111586144A (en) 2020-08-25

Family

ID=72126530

Family Applications (2)

Application Number Title Priority Date Filing Date
CN202010363691.7A Pending CN111586144A (en) 2020-04-30 2020-04-30 Computer group construction method with OODA fractal mechanism
CN202010866765.9A Active CN111866188B (en) 2020-04-30 2020-08-25 Computer group construction method with OODA fractal mechanism

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN202010866765.9A Active CN111866188B (en) 2020-04-30 2020-08-25 Computer group construction method with OODA fractal mechanism

Country Status (1)

Country Link
CN (2) CN111586144A (en)

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1302412C (en) * 2003-11-11 2007-02-28 联想(北京)有限公司 Computer group system and its operation managing method
CN100451970C (en) * 2005-09-27 2009-01-14 浪潮电子信息产业股份有限公司 Method for realizing dynamic layout of high-performance server based on group structure
CN102902592B (en) * 2012-09-10 2016-04-20 曙光信息产业(北京)有限公司 A kind of subregion schedule management method of PC cluster resource
CN103068058B (en) * 2012-12-24 2015-08-26 中国人民解放军总参谋部第六十一研究所 A kind of scheduling method for wireless resource based on double-layer loop model
US8549001B1 (en) * 2013-03-15 2013-10-01 DLZTX, Inc. Method and system for gathering and providing consumer intelligence
US10521747B2 (en) * 2014-04-08 2019-12-31 Northrop Grumman Systems Corporation System and method for providing a scalable semantic mechanism for policy-driven assessment and effective action taking on dynamically changing data
CN108920412B (en) * 2018-06-20 2020-12-29 中国科学院计算技术研究所 Algorithm automatic tuning method for heterogeneous computer system structure
CN109491760B (en) * 2018-10-29 2021-10-19 中国科学院重庆绿色智能技术研究院 High-performance data center cloud server resource autonomous management method
CN110059948B (en) * 2019-04-10 2023-01-06 重庆邮电大学 Hierarchical network analysis method of OODA (optical on-off digital data acquisition) ring
CN110034961B (en) * 2019-04-11 2022-02-15 重庆邮电大学 Seepage rate calculation method taking OODA chain as element

Also Published As

Publication number Publication date
CN111866188B (en) 2022-05-17
CN111866188A (en) 2020-10-30

Similar Documents

Publication Publication Date Title
Hosseinzadeh et al. Multi-objective task and workflow scheduling approaches in cloud computing: a comprehensive review
US9116181B2 (en) Method, apparatus, and system for virtual cluster integration
WO2008025761A2 (en) Parallel application load balancing and distributed work management
US20100241884A1 (en) Power Adjustment Based on Completion Times in a Parallel Computing System
CN107463442B (en) Satellite-borne multi-core SoC task level load balancing parallel scheduling method
CN114610474B (en) Multi-strategy job scheduling method and system under heterogeneous supercomputing environment
Deng et al. A data and task co-scheduling algorithm for scientific cloud workflows
Rashidi et al. Themis: A network bandwidth-aware collective scheduling policy for distributed training of dl models
Shojaee et al. A new cat swarm optimization based algorithm for reliability-oriented task allocation in distributed systems
Yu et al. Algorithms for divisible load scheduling of data-intensive applications
Zhang et al. Data-aware task scheduling for all-to-all comparison problems in heterogeneous distributed systems
US20120059938A1 (en) Dimension-ordered application placement in a multiprocessor computer
CN111866188B (en) Computer group construction method with OODA fractal mechanism
Lo Algorithms for static task assignment and symmetric contraction in distributed computing systems
Shah et al. Modified least cost method for grid resource allocation
Ding et al. Data locality-aware and QoS-aware dynamic cloud workflow scheduling in Hadoop for heterogeneous environment
Meddeber et al. Tasks assignment for Grid computing
Fan et al. A survey on task scheduling method in heterogeneous computing system
Zhou et al. Improving batch scheduling on blue Gene/Q by relaxing network allocation constraints
CN111813562B (en) Server host with OODA multi-partition IO resource pool mechanism
Wang et al. Spatial data dependence graph simulator for convolutional neural network accelerators
Yang et al. Versa-DNN: A Versatile Architecture Enabling High-Performance and Energy-Efficient Multi-DNN Acceleration
Zeng et al. Distributed scheduling strategy for divisible loads on arbitrarily configured distributed networks using load balancing via virtual routing
Chauhan et al. Resource based optimized decentralized grid scheduling algorithm
Tallent et al. Modeling the impact of silicon photonics on graph analytics

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200825