CN113190498B - Frequency adjustment method and device and electronic equipment - Google Patents
Frequency adjustment method and device and electronic equipment Download PDFInfo
- Publication number
- CN113190498B CN113190498B CN202110383993.5A CN202110383993A CN113190498B CN 113190498 B CN113190498 B CN 113190498B CN 202110383993 A CN202110383993 A CN 202110383993A CN 113190498 B CN113190498 B CN 113190498B
- Authority
- CN
- China
- Prior art keywords
- node
- group
- frequency
- value
- nodes
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
- G06F15/7807—System on chip, i.e. computer system on a single chip; System in package, i.e. computer system on one or more chips in a single package
- G06F15/7825—Globally asynchronous, locally synchronous, e.g. network on chip
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
- G06F15/7807—System on chip, i.e. computer system on a single chip; System in package, i.e. computer system on one or more chips in a single package
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Power Sources (AREA)
- Transmitters (AREA)
Abstract
The application discloses a frequency adjustment method, a frequency adjustment device and electronic equipment, wherein the method comprises the steps of selecting a first node from a plurality of nodes; taking the first node as a starting point, and performing node searching to obtain a second node; grouping the first nodes and the second nodes into groups; the frequency of the group is adjusted. The method can carry out frequency adjustment on different nodes in a group mode so as to avoid local overheating of the chip or global performance degradation of the chip.
Description
Technical Field
The application relates to the technical field of processors, and further relates to a frequency adjustment method, a frequency adjustment device and electronic equipment.
Background
As chip fabrication reaches the limits of atomic scale circuitry and electronic physics, moore's law, once leading the development of the chip industry, is gradually moving toward end. The increase in chip performance is limited by three physical laws. With the increase of the number of transistors integrated in a chip and the increase of the flip speed of the transistors, the power consumption of the chip is increased sharply, and the heat dissipation requirement of the chip is met; as the transistors get smaller and faster, the delay of the interconnect becomes a factor restricting the speed increase of the chip; with the increase of the number of transistors, the design space, design complexity and verification difficulty of chip design are all greatly increased. Thus, the appearance of processors from single core to multi-core, many cores is the result of moore's law core physical law limiting interactions.
With the increase of the number of chip cores, the traditional bus-based interconnection communication mode gradually becomes the bottleneck of chip system performance, and the Network On Chip (NOC) technology has the advantages of supporting simultaneous access, high reliability, high reusability and the like, is considered to be a more ideal many-core interconnection technology, overcomes the defect of poor expandability of a bus structure, and provides a feasible system on chip communication mechanism for 10 hundred million transistor age. Meanwhile, the technical innovation also brings challenges, and the power consumption of the many-core chip is rapidly increased along with the continuous improvement of the integration scale and the overall performance of the many-core chip. The operating frequency or power consumption of the chip needs to be adjusted, subject to the effects of chip packaging, heat dissipation and external power supply capabilities.
Disclosure of Invention
One advantage of the present invention is to provide a frequency adjustment method, apparatus, and electronic device, where the method can perform frequency adjustment on different nodes in a group manner, so as to avoid chip local overheating or chip global performance degradation.
In a first aspect, an advantage of the present invention is to provide a frequency adjustment method, including:
selecting a first node from a plurality of nodes;
taking the first node as a starting point, and performing node searching to obtain a second node;
Grouping the first nodes and the second nodes into groups;
the frequency of the group is adjusted.
In one possible implementation manner, the selecting a first node from a plurality of nodes includes:
selecting a plurality of nodes in a random rule mode to obtain a first node;
and/or dividing the plurality of nodes into a plurality of areas, and selecting a first node from each area, wherein the first node comprises at least one of a center node and a four-corner node in the area.
In one possible implementation manner, the performing node search with the first node as a starting point to obtain a second node includes:
determining a search area based on the first node and a preset distance;
and searching nodes in the searching area to obtain a second node.
In one possible implementation manner, the search area includes a first search area and a second search area, and the determining the search area based on the first node and a preset distance includes:
determining the first search area within a range of a preset first distance from the first node;
and determining the second search area within a range which is a preset first distance away from the first node and a preset second distance away from the first node.
In one possible implementation manner, the performing node search with the first node as a starting point to obtain a second node includes:
a node in communication with the first node path is accessed to determine a second node.
In one possible implementation manner, the method further includes:
detecting whether an unaccessed node exists;
if the non-accessed node exists, the node communicated with the non-accessed node path is accessed to determine a second node.
In one possible implementation manner, the grouping the first node and the second node into a first group includes:
obtaining a first frequency quantized value of the first node according to the frequency of the first node and the ideal working frequency of the first node;
obtaining a second frequency quantized value of the second node according to the frequency of the second node and the ideal working frequency of the second node;
and if the difference value between the quantized value of the first frequency and the quantized value of the second frequency is smaller than a preset first threshold value, the first node and the second node are formed into a group.
In one possible implementation manner, the grouping the first node and the second node into a first group includes:
Detecting a temperature of the first node and a temperature of the second node;
and if the difference value between the temperature of the first node and the temperature of the second node is smaller than a preset second threshold value, the first node and the second node are combined into a group.
In one possible implementation manner, the group includes a first group and a second group, and the method further includes:
judging whether the same node exists in the first group and the second group, and whether the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value;
and if the same node exists in the first group and the second group and the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value, merging the first group and the second group.
In one possible implementation manner, the method further includes:
if the difference value between the frequency quantized value of a certain node in the group and the frequency quantized value of the group is larger than a preset third threshold value, the certain node is withdrawn from the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
In one possible implementation manner, the method further includes:
if the difference value between the frequency quantized value of a certain node outside the group and the frequency quantized value of the group is smaller than a preset fourth threshold value, adding the certain node into the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
In one possible implementation manner, the adjusting the frequency of the group includes:
if the frequency quantization value or the temperature of the group is larger than a preset fifth threshold value, controlling the frequency of the group to be reduced;
and if the frequency quantized value or the temperature of the group is smaller than a preset sixth threshold value, controlling the frequency of the group to rise, wherein the frequency quantized value or the temperature of the group is obtained according to the average value or the median value of the frequency quantized values or the temperatures of all the nodes in the group.
In a second aspect, the present application further provides a frequency adjustment device, including:
the selecting module is used for selecting a first node from a plurality of nodes;
the searching module is used for searching nodes by taking the first node as a starting point to obtain a second node;
A group management module, configured to group the first node and the second node;
and the adjusting module is used for adjusting the frequency of the group.
In a third aspect, another advantage of the present invention is to provide an electronic device, comprising:
one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions, which when executed by the device, cause the device to perform the method of the first aspect.
In a fourth aspect, another advantage of the present invention is to provide a computer readable storage medium having a computer program stored therein, which when run on a computer causes the computer to perform the method as described in the first aspect.
In a fifth aspect, the present application provides a computer program for performing the method of the first aspect when the computer program is executed by a computer.
In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged with the processor, or in part or in whole on a memory not packaged with the processor.
Drawings
Fig. 1 shows a method schematic diagram of an embodiment of the frequency adjustment method of the present invention.
Fig. 2 is a schematic diagram showing the structure of a chip in an embodiment of the frequency adjustment method of the present invention.
Fig. 3 is a schematic diagram of a structure of a plurality of adjacent nodes in an embodiment of the frequency adjustment method of the present invention.
Fig. 4A, 4B, and 4C are schematic diagrams respectively illustrating a structure of a first node in an embodiment of the frequency adjustment method according to the present invention.
Fig. 5A is a schematic structural diagram of a plurality of second nodes searched for in an embodiment of the frequency adjustment method according to the present invention.
Fig. 5B is a schematic structural diagram of a plurality of second nodes searched for in another embodiment of the frequency adjustment method according to the present invention.
Fig. 6 is a schematic diagram of a structure of a plurality of groups in an embodiment of the frequency adjustment method of the present invention.
Fig. 7 is a schematic diagram of a configuration of two groups combined in an embodiment of the frequency adjustment method of the present invention.
Fig. 8 is a schematic diagram showing the structure of an embodiment of the frequency adjustment device of the present invention.
Fig. 9 shows a schematic structural view of an embodiment of the electronic device of the invention.
Fig. 10 shows a schematic structural diagram of another embodiment of the electronic device of the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
It will be understood that the terms "a" and "an" should be interpreted as referring to "at least one" or "one or more," i.e., in one embodiment, the number of elements may be one, while in another embodiment, the number of elements may be plural, and the term "a" should not be interpreted as limiting the number.
Summary of the application
In the prior art, a temperature management method of a time dimension is provided, which achieves the purpose of reducing the chip temperature by slowing down the activity of a overheat operation node. In the method, the power adjustment is performed on the IP core of the processor by dynamically adjusting the frequency/voltage (DVFS) of the processor or closing an idle circuit (power gating) technology, and when the temperature of a certain node in the processor exceeds a threshold value, the frequency/voltage of the overheating node can be reduced or the whole overheating node can be stopped to achieve the purpose of cooling.
In the prior art, a temperature management method of space dimension is also provided, which achieves the purpose of cooling by transferring tasks of the overheat node, for example, the method can be adjusted by adopting a task scheduling or process migration mode.
However, the above two methods provided in the prior art have the following problems in managing network-on-chip power consumption: the adjustment granularity taking the IP core as a unit is small, the cost is high, the reaction is slow, and the practical application is not facilitated; the granularity of adjustment is large in the unit of chip, and the difference of each node or workload in the chip is not considered, so that the overall performance of the chip is affected. In addition, in the prior art, in order to acquire the load index of the IP core in the chip, a built-in sensor is required to acquire physical indexes such as voltage, temperature and the like in the chip, so that the deployment cost is increased.
Accordingly, the present application provides a frequency adjustment method, which may include: selecting a first node from a plurality of nodes; taking the first node as a starting point, and performing node searching to obtain a second node; grouping the first nodes and the second nodes into groups; the frequency of the group is adjusted. In the application, the method can carry out frequency adjustment on different nodes in a group (such as a dynamic group and the like) mode so as to avoid local overheating of a chip or global performance degradation of the chip and the like.
Exemplary frequency adjustment methods
Referring to fig. 1, a frequency adjustment method according to an embodiment of the present invention is applied to an electronic device (such as a computer, a mobile phone, a smart home, an automobile, etc.), where the electronic device may include a processor, such as a single-core, dual-core, multi-core or many-core processor, etc.
Further, the processor includes a chip (or wafer), or a microcircuit, or a microchip, or an integrated circuit, etc., which may communicate using Network On Chip (NOC) technology. Still further, the chip may include a plurality of nodes (e.g., operation nodes, etc.), for example, the plurality of nodes may form an nxm matrix, and each node may be connected to an adjacent node through a bidirectional channel.
Fig. 2 is a schematic diagram of a chip in the frequency adjustment method of the present application. As shown in fig. 2, the chip includes an n×m matrix formed by a plurality of nodes, wherein the node coordinates are (x, y), x is equal to or less than 0 and equal to or less than n, y is equal to or less than 0 and equal to or less than m, wherein two node coordinates (x 1, y 1), (x 2, y 2), if |x1-x2|=1, and y1=y2, are horizontally adjacent; if |y1-y2|=1, and x1=x2, then the two nodes are vertically adjacent, and if |x1-x2|=1, and |y1-y2|=1, then the two nodes are diagonally adjacent. Fig. 3 is a schematic diagram of a structure of a plurality of adjacent nodes in the frequency adjustment method of the present application, for example, node A1 is adjacent to node A2, node B1, node B2 and node B3 are adjacent, and node C1, node C2 and node C3 are adjacent.
It will be appreciated by those skilled in the art that the topology of the chip shown in fig. 2 is by way of example only, and in other possible embodiments, the topology of the chip may further include: one or more of star, ring, bus, tree, bus/star, and mesh topologies, as not limited herein.
As shown in fig. 1, the method may include:
s101, selecting a first node from a plurality of nodes.
That is, one or more first nodes are selected from all the nodes in the chip, where the selection method may include selecting according to a preset rule, such as random regularization selection, center selection, corner selection, and the like. As shown in fig. 4A, the node S1 is a first node obtained in a center selection manner. As shown in fig. 4B, the node S2 and the node S3 are first nodes obtained by corner selection. As shown in fig. 4C, the node S4 is a first node obtained by random regularized selection.
In one possible implementation manner, step S101 may include: the method comprises the steps of selecting a plurality of nodes in a random rule mode to obtain a first node, and/or dividing the plurality of nodes into a plurality of areas, and selecting the first node from each area.
For example, the nodes of the n×m matrix are divided into four areas, such as upper, lower, left, right areas, and the like, and then, selection is made in each area to obtain a plurality of first nodes. For example, the center node and/or the four corner nodes (e.g., upper left, lower left, upper right, lower right corner points, etc.) of each region may be selected as the first node, etc.
S102, performing node searching by taking the first node as a starting point to obtain a second node.
In this embodiment, step S102 may include, starting from the first node, searching for a node adjacent to the first node, so as to obtain a second node. Further, in step S102, starting from the searched second node, searching for a node adjacent to the second node may be continued to obtain other second nodes. That is, a first node may be adjacent to a second node, with multiple second nodes being adjacent to each other.
In this embodiment, step S102 may employ various algorithms to perform node searching to obtain the second node, such as a breadth-first algorithm or a depth-first algorithm. Fig. 5A is a schematic structural diagram of a plurality of second nodes searched in an embodiment of the frequency adjustment method of the present application, and as shown in fig. 5A, from the first node (1), a plurality of second nodes (2) (3) (4) (5) (6) are searched. Fig. 5B is a schematic structural diagram of a plurality of second nodes searched in another embodiment of the frequency adjustment method of the present application, and as shown in fig. 5B, from the first node (1), a plurality of second nodes (2) (3) (4) (5) (6) are searched.
In one possible implementation manner, step S102 may include:
s201, determining a search area based on the first node and a preset distance;
s202, searching nodes in the search area to obtain a second node.
In this embodiment, step S201 and step S202 may search for all nodes within a preset distance from the first node to obtain the second node, where the preset distance may be preset according to the distance between the adjacent nodes.
For example, taking the first node as a center, taking the preset distance as a searching radius, determining a circular or quasi-circular searching area, and searching to obtain all nodes in the searching area so as to obtain the second node.
In one possible implementation manner, the search area may include a first search area and a second search area, and step S201 may include:
s301, determining the first search area within a range with a preset first distance from the first node;
s302, determining the second search area within a range which is a preset first distance away from the first node and a preset second distance away from the first node.
That is, in the method, all nodes within a first distance (e.g., a search distance K) from a first node are searched first, and then all other nodes within a second distance (e.g., a search distance k+1) from the first node are searched to obtain a plurality of second nodes. It can be appreciated that the search distance may be gradually increased according to the number of searches, for example, the search distance may further include k+2, k+3, k+4..k+n, etc., so as to sequentially search for a plurality of second nodes in a plurality of search areas, until all the nodes in the chip are searched.
In one possible implementation manner, step S102 may include:
s401, accessing the node communicated with the first node path to determine a second node.
That is, from the first node, accessing the adjacent node in communication with the path of the first node, and then from the accessed node, continuing to access other non-accessed adjacent nodes until all the nodes in the chip in communication with the path of the first node are accessed, so as to obtain one or more second nodes.
In one possible implementation manner, step S102 may further include:
S402, detecting whether a node which is not accessed exists;
s403, if the non-accessed node exists, accessing the node communicated with the non-accessed node path to determine a second node.
That is, if it is detected that there is an unaccessed node in the chip, all nodes having paths communicating with the unaccessed node are accessed from the unaccessed node to obtain one or more second nodes.
Thus, through the above steps S401, S402 and S403, it is possible to access all nodes in the chip to search for one or more second nodes.
S103, the first nodes and the second nodes are combined into a group.
That is, after searching for the second node, the first node and the second node may form a group. Alternatively, for an existing group, after a second node is searched for that does not join the group, the second node may be added to the existing group to update the nodes within the group. One or more first nodes, one or more second nodes, etc. may be included in the group.
In this embodiment, step S103 may determine whether to group the first node and the second node or whether to join the second node that is not joined to the group to the existing group according to the judgment condition. Or, for the existing group, determining whether to exit a certain node in the group from the group according to the judging condition so as to update the node in the group. Or, for the existing groups, determining whether to combine the groups into one group according to the judging condition so as to update the nodes in the groups.
In one possible implementation manner, step S103 may include:
s501, obtaining a first frequency quantization value of the first node according to the frequency of the first node and the ideal working frequency of the first node;
s502, obtaining a second frequency quantized value of the second node according to the frequency of the second node and the ideal working frequency of the second node;
s503, if the difference value between the quantized value of the first frequency and the quantized value of the second frequency is smaller than a preset first threshold value, the first node and the second node are combined into a group.
In this embodiment, the ideal operating frequency of each node may be preset according to the operating frequency and power consumption of each node, for example, when the operating frequency of a node reaches the ideal operating frequency, the performance of the node is optimal, and the power consumption does not exceed the allowable maximum value, when the operating frequency of the node is lower than the ideal operating frequency, the power consumption of the node does not exceed the allowable maximum value, but the performance does not reach the optimal and has a lifting space, and when the operating frequency of the node is higher than the ideal operating frequency, the node is abnormal, the error rate increases, and the temperature exceeds a preset threshold.
Preferably, the frequency quantization value of each node may be obtained by quantizing the frequency of the node with the ideal operating frequency as a standard value, for example, each node may be obtained by quantizing (e.g., proportionally quantizing, etc.) the current frequency with the ideal operating frequency thereof as 100 as a standard value, so as to obtain the corresponding frequency quantization value.
More preferably, the frequency quantization value of each node may be obtained by converting the current frequency according to a preset conversion model, and the preset conversion module may be an ideal operating frequency-power consumption model of the chip operation node.
In step S503, the difference between the frequency quantization values of any two nodes in a group is smaller than a preset first threshold. That is, the frequency quantization values of all the nodes in a group can be in the same range, so that the frequencies of all the nodes in the group can be uniformly adjusted later, which is beneficial to avoiding local overheating of the chip or global performance degradation of the chip.
It is understood that if the difference between the quantized values of the first frequency and the quantized values of the second frequency is greater than or equal to a preset first threshold, the second node and the first node do not form a group.
In one possible implementation manner, step S103 may include:
s601, detecting the temperature of the first node and the temperature of the second node;
s602, if the difference value between the temperature of the first node and the temperature of the second node is smaller than a preset second threshold value, the first node and the second node are combined into a group.
That is, the temperature difference between any two nodes in a group is less than the preset second threshold. That is, the temperatures of all nodes in a group can be in the same range, so that the frequencies of all nodes in the group can be uniformly adjusted later, which is beneficial to avoiding local overheating of the chip or global performance degradation of the chip.
It is understood that if the difference between the temperature of the first node and the temperature of the second node is greater than or equal to a preset second threshold, the second node and the first node do not form a group.
In combination with the step S102 and the step S103, the first node is used as a starting point, and the nodes adjacent to the first node are searched to obtain the second node, and if the difference between the frequency quantization value or temperature of the first node and the frequency quantization value or temperature of the second node is smaller than the preset threshold, the first node and the second node are formed into a group. Then, with the group as a starting point, searching other nodes adjacent to each node in the group continuously, and judging whether the other nodes can be added into the group or not, so as to update the group. For example, if the difference between the frequency quantization value or temperature of the searched other node and the frequency quantization value or temperature of the node in the group is smaller than a preset threshold, the searched other node is added to the group, or if the difference between the frequency quantization value or temperature of the searched other node and the frequency quantization value or temperature of the group is smaller than a preset threshold, the searched other node is added to the group.
Preferably, the frequency quantization value or temperature of the group may be obtained according to an average value or median value of the frequency quantization values or temperatures of all nodes in the group, which is not limited herein.
In one possible implementation manner, the group includes a first group and a second group, and step S103 may further include:
s701, judging whether the same node exists in the first group and the second group, and whether the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value;
s702, if the same node exists in the first group and the second group, and the difference between the frequency quantization value of the first group and the frequency quantization value of the second group is smaller than a preset difference, merging the first group and the second group.
In this embodiment, the above step S102 and step S103 are performed according to different first nodes, so that different groups can be obtained. It is understood that the frequency quantization values or temperatures between different groups may be in different ranges, respectively.
That is, if there is the same node (or cross node) in both groups, and the difference of the frequency quantization value or the temperature between the two groups is smaller than the preset difference (or the difference of the frequency quantization value or the temperature between any two nodes in both groups is smaller than the preset threshold), the two groups may be combined into one group.
It should be noted that, the nodes in each group may be updated, such as adding a new node, or exiting a certain node in the group, or the two different groups may be combined or separated to implement a dynamic group.
As shown in fig. 6, the groups may include a first group Q1, a second group Q2, and a third group Q3, each including different nodes, and as the frequency or temperature of the nodes changes, the nodes in each group increase or decrease accordingly.
As shown in fig. 7, the group may include a fourth group Q4 and a fifth group Q5, and if the node D joins the fourth group Q4 and the node D4 joins the fifth group D5, and the difference between the frequency quantization value or temperature of the fourth group Q4 and the frequency quantization value or temperature of the fifth group Q5 is smaller than the preset difference, the node D, the fourth group D4 and the fifth group D5 are combined into one group.
In one possible implementation manner, step S103 may further include:
s703, if the difference value between the frequency quantized value of a certain node in the group and the frequency quantized value of the group is greater than a preset third threshold value, the certain node is withdrawn from the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
That is, if a large change in frequency or temperature of a certain node in the group is detected, for example, if a difference between the frequency quantized value or temperature of the node and the frequency quantized value or temperature of the group is detected to be greater than a preset third threshold, the node is withdrawn from the group to update the group, so that the difference between the frequency quantized value or temperature of any two nodes in the group is still kept within the preset range.
It is worth mentioning that, from the node that withdraws from the group, after a preset duration from the moment of withdrawing, judge whether the frequency quantization value or temperature of this node is less than the preset threshold value with the frequency quantization value or temperature difference of its adjacent node or group, if yes, combine this withdrawn node and its adjacent node into a group, or join this withdrawn node into the adjacent group again.
In one possible implementation manner, step S103 may further include:
s704, if the difference value between the frequency quantized value of a certain node outside the group and the frequency quantized value of the group is smaller than a preset fourth threshold value, adding the certain node into the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
That is, if it is detected that the difference between the frequency quantization value or temperature of the node not belonging to a certain group and the frequency quantization value or temperature of the group is smaller than the preset fourth threshold value, the node is added to the group, and the node may include a node adjacent to or in communication with any node in the group.
S104, adjusting the frequency of the group.
That is, the frequencies of all the nodes in the group are uniformly adjusted by taking the group as a unit, so that the adjustment efficiency is improved, the deployment cost of the chip is reduced, and the local overheating of the chip or the global performance degradation of the chip and the like are avoided.
In one possible implementation manner, step S104 may include:
s801, if the frequency quantized value or the temperature of the group is larger than a preset fifth threshold value, controlling the frequency of the group to be reduced;
s802, if the frequency quantized value or the temperature of the group is smaller than a preset sixth threshold value, controlling the frequency of the group to rise.
That is, if the frequency quantization value or the temperature of the group exceeds the fifth threshold (e.g., the normal range value, etc.), the frequencies of all the nodes in the group are reduced (e.g., the frequencies are reduced to the normal range value or the optimal value, etc.), so that the power consumption or the temperature of all the nodes in the group is reduced, which is beneficial to avoiding local overheating of the chip. If the frequency quantization value or the temperature of the group is lower than a sixth threshold (such as an allowable range value, etc.), the frequencies of all the nodes in the group are increased (such as the frequencies are increased to the allowable range value or the optimal value, etc.), so as to improve the operation frequency of all the nodes in the group, which is beneficial to improving the global performance of the chip.
It is to be understood that some or all of the steps or operations in the above embodiments are merely examples, and embodiments of the present application may also perform other operations or variations of various operations. Furthermore, the various steps may be performed in a different order presented in the above embodiments, and it is possible that not all of the operations in the above embodiments are performed.
Exemplary frequency adjustment device
As shown in fig. 8, one embodiment of the present application provides a frequency adjustment device 100, where the device 100 includes:
a selection module 10, configured to select a first node from a plurality of nodes;
the searching module 20 is configured to perform node searching with the first node as a starting point, so as to obtain a second node;
a group management module 30, configured to group the first node and the second node;
an adjustment module 40, configured to adjust the frequency of the group.
In one possible implementation manner, the selecting module 10 includes:
selecting a plurality of nodes in a random rule mode to obtain a first node;
and/or dividing the plurality of nodes into a plurality of areas, and selecting a first node from each area, wherein the first node comprises at least one of a center node and a four-corner node in the area.
In one possible implementation, the search module 20 includes:
determining a search area based on the first node and a preset distance;
and searching nodes in the searching area to obtain a second node.
In one possible implementation manner, the search area includes a first search area and a second search area, and the search module 20 further includes:
determining the first search area within a range of a preset first distance from the first node;
and determining the second search area within a range which is a preset first distance away from the first node and a preset second distance away from the first node.
In one possible implementation, the search module 20 further includes:
a node in communication with the first node path is accessed to determine a second node.
In one possible implementation manner, the method further includes:
detecting whether an unaccessed node exists;
if the non-accessed node exists, the node communicated with the non-accessed node path is accessed to determine a second node.
In one possible implementation, the group management module 30 includes:
Obtaining a first frequency quantized value of the first node according to the frequency of the first node and the ideal working frequency of the first node;
obtaining a second frequency quantized value of the second node according to the frequency of the second node and the ideal working frequency of the second node;
and if the difference value between the quantized value of the first frequency and the quantized value of the second frequency is smaller than a preset first threshold value, the first node and the second node are formed into a group.
In one possible implementation, the group pipe module 30 includes:
detecting a temperature of the first node and a temperature of the second node;
and if the difference value between the temperature of the first node and the temperature of the second node is smaller than a preset second threshold value, the first node and the second node are combined into a group.
In one possible implementation, the group includes a first group and a second group, and the group pipe module 30 further includes:
judging whether the same node exists in the first group and the second group, and whether the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value;
And if the same node exists in the first group and the second group and the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value, merging the first group and the second group.
In one possible implementation manner, the group management module 30 further includes:
if the difference value between the frequency quantized value of a certain node in the group and the frequency quantized value of the group is larger than a preset third threshold value, the certain node is withdrawn from the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
In one possible implementation manner, the group management module 30 further includes:
if the difference value between the frequency quantized value of a certain node outside the group and the frequency quantized value of the group is smaller than a preset fourth threshold value, adding the certain node into the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
In one possible implementation, the adjusting module 40 includes:
If the frequency quantization value or the temperature of the group is larger than a preset fifth threshold value, controlling the frequency of the group to be reduced;
and if the frequency quantized value or the temperature of the group is smaller than a preset sixth threshold value, controlling the frequency of the group to rise, wherein the frequency quantized value or the temperature of the group is obtained according to the average value or the median value of the frequency quantized values or the temperatures of all the nodes in the group.
It will be appreciated that the frequency adjustment device provided in the embodiment shown in fig. 8 may be used to implement the technical solution of the method embodiment shown in fig. 1 of the present application, and the principle and technical effects thereof may be further described with reference to the related descriptions in the method embodiment.
Exemplary electronic device
Fig. 9 is a schematic structural diagram of an embodiment of an electronic device, as shown in fig. 9, where the electronic device may include: one or more processors; a memory; and one or more computer programs.
The electronic device may be a mobile phone, a computer, a server, a mobile terminal (mobile phone), a cashing device, a computer, an intelligent screen, an unmanned aerial vehicle, an intelligent network vehicle (Intelligent Connected Vehicle; hereinafter abbreviated as ICV), an intelligent vehicle (smart/intelligent car) or a vehicle-mounted device.
Wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions that, when executed by the device, cause the device to perform the steps of:
selecting a first node from a plurality of nodes;
taking the first node as a starting point, and performing node searching to obtain a second node;
grouping the first nodes and the second nodes into groups;
the frequency of the group is adjusted.
In one possible implementation manner, the instructions, when executed by the device, cause the device to perform the selecting a first node from a plurality of nodes, include:
selecting a plurality of nodes in a random rule mode to obtain a first node;
and/or dividing the plurality of nodes into a plurality of areas, and selecting a first node from each area, wherein the first node comprises at least one of a center node and a four-corner node in the area.
In one possible implementation manner, when the instruction is executed by the device, the device is caused to perform the node searching with the first node as a starting point, to obtain a second node, and includes:
Determining a search area based on the first node and a preset distance;
and searching nodes in the searching area to obtain a second node.
In one possible implementation manner, the search area includes a first search area and a second search area, and when the instruction is executed by the device, the method includes causing the device to execute the determining the search area based on the first node and a preset distance, including:
determining the first search area within a range of a preset first distance from the first node;
and determining the second search area within a range which is a preset first distance away from the first node and a preset second distance away from the first node.
In one possible implementation manner, when the instruction is executed by the device, the device is caused to perform the node searching with the first node as a starting point, to obtain a second node, and includes:
a node in communication with the first node path is accessed to determine a second node.
In one possible implementation, the instructions, when executed by the apparatus, cause the apparatus to further perform:
Detecting whether an unaccessed node exists;
if the non-accessed node exists, the node communicated with the non-accessed node path is accessed to determine a second node.
In one possible implementation manner, the instructions, when executed by the device, cause the device to perform the grouping the first node and the second node into a first group, include:
obtaining a first frequency quantized value of the first node according to the frequency of the first node and the ideal working frequency of the first node;
obtaining a second frequency quantized value of the second node according to the frequency of the second node and the ideal working frequency of the second node;
and if the difference value between the quantized value of the first frequency and the quantized value of the second frequency is smaller than a preset first threshold value, the first node and the second node are formed into a group.
In one possible implementation manner, the instructions, when executed by the device, cause the device to perform the grouping the first node and the second node into a first group, include:
detecting a temperature of the first node and a temperature of the second node;
And if the difference value between the temperature of the first node and the temperature of the second node is smaller than a preset second threshold value, the first node and the second node are combined into a group.
In one possible implementation, the group includes a first group and a second group, which when executed by the apparatus, cause the apparatus to further perform:
judging whether the same node exists in the first group and the second group, and whether the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value;
and if the same node exists in the first group and the second group and the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value, merging the first group and the second group.
In one possible implementation, the instructions, when executed by the apparatus, cause the apparatus to further perform:
if the difference value between the frequency quantized value of a certain node in the group and the frequency quantized value of the group is larger than a preset third threshold value, the certain node is withdrawn from the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
In one possible implementation, the instructions, when executed by the apparatus, cause the apparatus to further perform:
if the difference value between the frequency quantized value of a certain node outside the group and the frequency quantized value of the group is smaller than a preset fourth threshold value, adding the certain node into the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
In one possible implementation, the instructions, when executed by the device, cause the device to perform the adjusting the frequency of the group, include:
if the frequency quantization value or the temperature of the group is larger than a preset fifth threshold value, controlling the frequency of the group to be reduced;
and if the frequency quantized value or the temperature of the group is smaller than a preset sixth threshold value, controlling the frequency of the group to rise, wherein the frequency quantized value or the temperature of the group is obtained according to the average value or the median value of the frequency quantized values or the temperatures of all the nodes in the group.
The electronic device shown in fig. 9 may be a terminal device or a server, or may be a circuit device built in the terminal device or the server. The apparatus may be used to perform the functions/steps in the frequency adjustment method provided in the embodiment shown in fig. 1 of the present application.
Fig. 10 is a schematic structural diagram of another embodiment of the electronic device of the present application. As shown in fig. 10, the electronic device may include a monitoring module 901, a refreshing module 902, a searching module 903, a group management module 904, a judging module 905, and a frequency adjusting module 906.
The monitoring module 901 is configured to monitor performance indexes of each node in the chip, such as temperature, frequency, or a frequency quantization value or temperature obtained by converting a preset conversion model, and send a monitoring result to the refreshing module 902.
The refresh module 902 is configured to activate node updates within a group at regular time or according to a judgment condition provided in the method embodiment shown in fig. 1, and send update events or requests to the search module 903 and the group management module 904. The refresh module 902 may periodically refresh nodes within the group, resulting in less system load. Optionally, the refresh module 902 may also actively refresh (in response to a user refresh operation, etc.) the nodes within the group to improve system performance, etc.
The searching module 903 is configured to, after receiving the update event or request sent by the refreshing module, perform a node search according to a method provided in the method embodiment shown in fig. 1 to find a new node joining a group, and send the found new node (or information) to the group management module 904.
The group management module 904 is configured to receive the new node searched by the search module 903, and manage addition or exit of the nodes in the group. The group management module 904 may include a group aggregation module 9041, a member data module 9042, a group separation module 9043, and a calculation module 9044. The calculating module 9044 is configured to calculate whether the new node searched by the searching module 903 can be added to a certain group (e.g. whether the difference between the temperature of the new node and the temperature of the group is less than a preset threshold), if so, the group aggregating module 9041 adds the new node to the group. The calculating module 9044 is further configured to calculate whether any node in the group exits the group (e.g. whether the difference between the temperature of a certain node and the temperature of the group is greater than or equal to a preset threshold), if so, the group aggregating module 9043 exits the node from the group. The membership data module 9042 is configured to record or store all the current nodes (e.g., node information, node coordinates, etc.) in the group in real time. The calculating module 9044 is further configured to calculate a temperature value or a frequency quantized value of all the nodes in each group (or an average value, a median value, etc. of the temperature values/the frequency quantized values of all the nodes) to obtain a temperature or a frequency (or a frequency quantized value) of the group, and send the calculation result to the determining module 905.
The determining module 905 is configured to determine whether the temperature or the frequency (or the frequency quantized value) of each group exceeds the normal range value, and if so, the adjusting module 906 decreases the operating frequency of all the nodes in the corresponding group to decrease the local temperature of the chip. The determining module 905 is further configured to determine whether the temperature or the frequency (or the frequency quantized value) of each group is lower than the allowable range value, if yes, the adjusting module 906 increases the operating frequency of all the nodes in the corresponding group, so as to improve the global performance of the chip, etc. In some embodiments, the adjustment module 906 may employ dynamic adjustment frequency/voltage technology (DVFS) to adjust the operating frequency of each node within a group, without limitation.
As shown in fig. 9, the electronic device 900 may also include a processor 910 and a memory 920. Wherein the processor 910 and the memory 920 may communicate with each other via an internal connection, and transfer control and/or data signals, the memory 920 is configured to store a computer program, and the processor 910 is configured to call and run the computer program from the memory 920.
The memory 920 may be a read-only memory (ROM), other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), a compact disc read-only memory (compact disc read-only memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, etc.
The processor 910 and the memory 920 may be combined into a single processing device, more commonly referred to as separate components, and the processor 910 is configured to execute program code stored in the memory 920 to perform the functions described above. In particular, the memory 920 may also be integrated into the processor 910 or may be separate from the processor 910.
It should be appreciated that the electronic device 900 shown in fig. 9 is capable of implementing the various processes of the method provided by the embodiment shown in fig. 1 of the present application. The operations and/or functions of the respective modules in the electronic device 900 are respectively for implementing the corresponding flows in the above-described method embodiments. Reference is specifically made to the description of the embodiment of the method shown in fig. 1 of the present application, and detailed descriptions thereof are omitted here as appropriate to avoid repetition.
In addition, in order to make the function of the electronic device 900 more complete, the electronic device 900 may further include one or more of a camera 930, a power supply 940, an input unit 950, and the like.
Optionally, a power supply 950 is used to provide power to various devices or circuits in the electronic device.
It should be understood that the processor 910 in the electronic device 900 shown in fig. 9 may be a system on a chip SOC, where the processor 910 may include a central processing unit (Central Processing Unit; hereinafter referred to as "CPU") and may further include other types of processors, such as: an image processor (Graphics Processing Unit; hereinafter referred to as GPU) and the like.
In general, portions of the processors or processing units within the processor 910 may cooperate to implement the preceding method flows, and corresponding software programs for the portions of the processors or processing units may be stored in the memory 920.
The present application also provides an electronic device, where the device includes a storage medium, which may be a nonvolatile storage medium, and a central processor, where the storage medium stores a computer executable program, and the central processor is connected to the nonvolatile storage medium and executes the computer executable program to implement the method provided by the embodiment shown in fig. 1 of the present application.
In the above embodiments, the processor may include, for example, a CPU, a DSP, a microcontroller, or a digital signal processor, and may further include a GPU, an embedded Neural Network Processor (NPU) and an image signal processor (Image Signal Processing; ISP), where the processor may further include a necessary hardware accelerator or a logic processing hardware circuit, such as an ASIC, or one or more integrated circuits for controlling the execution of the program in the technical solution of the present application, and so on. Further, the processor may have a function of operating one or more software programs, which may be stored in a storage medium.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored therein, which when run on a computer causes the computer to perform the method provided by the embodiment shown in fig. 1 of the present application.
Embodiments of the present application also provide a computer program product comprising a computer program which, when run on a computer, causes the computer to perform the method provided by the embodiment shown in fig. 1 of the present application.
Those of ordinary skill in the art will appreciate that the various elements and algorithm steps described in the embodiments disclosed herein can be implemented as a combination of electronic hardware, computer software, and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In several embodiments provided herein, any of the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (hereinafter referred to as ROM), a random access Memory (Random Access Memory) and various media capable of storing program codes such as a magnetic disk or an optical disk.
The foregoing is merely specific embodiments of the present application, and any person skilled in the art may easily conceive of changes or substitutions within the technical scope of the present application, which should be covered by the protection scope of the present application. The protection scope of the present application shall be subject to the protection scope of the claims.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are by way of example only and are not limiting. The advantages of the present invention have been fully and properly realized. The functional and structural principles of the present invention have been shown and described in the examples and embodiments of the invention may be modified or practiced without departing from the principles described.
Claims (11)
1. A method of frequency adjustment, comprising:
selecting a first node from a plurality of nodes;
taking the first node as a starting point, and performing node searching to obtain a second node;
grouping the first node and the second node, comprising:
obtaining a first frequency quantized value of the first node according to the frequency of the first node and the ideal working frequency of the first node; obtaining a second frequency quantized value of the second node according to the frequency of the second node and the ideal working frequency of the second node; if the difference value between the quantized value of the first frequency and the quantized value of the second frequency is smaller than a preset first threshold value, the first node and the second node are formed into a group; or (b)
Detecting a temperature of the first node and a temperature of the second node; if the difference value between the temperature of the first node and the temperature of the second node is smaller than a preset second threshold value, the first node and the second node are combined into a group;
Adjusting the frequency of the group;
if the difference value between the frequency quantized value or temperature of a certain node in the group and the frequency quantized value or temperature of the group is larger than a preset third threshold value, the certain node is withdrawn from the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group;
if the difference value between the frequency quantized value or temperature of a certain node outside the group and the frequency quantized value or temperature of the group is smaller than a preset fourth threshold value, adding the certain node into the group, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
2. The method of claim 1, wherein selecting a first node from a plurality of nodes comprises:
selecting a plurality of nodes in a random rule mode to obtain a first node;
and/or dividing the plurality of nodes into a plurality of areas, and selecting a first node from each area, wherein the first node comprises at least one of a center node and a four-corner node in the area.
3. The method of claim 1, wherein the performing a node search with the first node as a starting point to obtain a second node comprises:
determining a search area based on the first node and a preset distance;
and searching nodes in the searching area to obtain a second node.
4. The method of claim 3, wherein the search area comprises a first search area and a second search area, wherein the determining the search area based on the first node and a preset distance comprises:
determining the first search area within a range of a preset first distance from the first node;
and determining the second search area within a range which is a preset first distance away from the first node and a preset second distance away from the first node.
5. The method of claim 1, wherein the performing a node search with the first node as a starting point to obtain a second node comprises:
a node in communication with the first node path is accessed to determine a second node.
6. The method of claim 5, wherein the method further comprises:
Detecting whether an unaccessed node exists;
if the non-accessed node exists, the node communicated with the non-accessed node path is accessed to determine a second node.
7. The method of claim 1, wherein the group comprises a first group and a second group, the method further comprising:
judging whether the same node exists in the first group and the second group, and whether the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value;
and if the same node exists in the first group and the second group and the difference value between the frequency quantized value of the first group and the frequency quantized value of the second group is smaller than a preset difference value, merging the first group and the second group.
8. The method according to any one of claims 1 to 6, wherein said adjusting the frequency of the group comprises:
if the frequency quantization value or the temperature of the group is larger than a preset fifth threshold value, controlling the frequency of the group to be reduced;
and if the frequency quantized value or the temperature of the group is smaller than a preset sixth threshold value, controlling the frequency of the group to rise, wherein the frequency quantized value or the temperature of the group is obtained according to the average value or the median value of the frequency quantized values or the temperatures of all the nodes in the group.
9. A frequency adjustment device, comprising:
the selecting module is used for selecting a first node from a plurality of nodes;
the searching module is used for searching nodes by taking the first node as a starting point to obtain a second node;
a group management module, configured to group the first node and the second node, including:
obtaining a first frequency quantized value of the first node according to the frequency of the first node and the ideal working frequency of the first node; obtaining a second frequency quantized value of the second node according to the frequency of the second node and the ideal working frequency of the second node; if the difference value between the quantized value of the first frequency and the quantized value of the second frequency is smaller than a preset first threshold value, the first node and the second node are formed into a group; or (b)
Detecting a temperature of the first node and a temperature of the second node; if the difference value between the temperature of the first node and the temperature of the second node is smaller than a preset second threshold value, the first node and the second node are combined into a group;
the adjusting module is used for adjusting the frequency of the group;
The first judging module is used for exiting a certain node from the group if the difference value between the frequency quantized value or temperature of the certain node in the group and the frequency quantized value or temperature of the group is larger than a preset third threshold value, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group;
and the second judging module is used for adding a certain node into the group if the difference value between the frequency quantized value or temperature of the certain node outside the group and the frequency quantized value or temperature of the group is smaller than a preset fourth threshold value, wherein the frequency quantized value of the group is obtained according to the average value or the median value of the frequency quantized values of all the nodes in the group.
10. An electronic device, comprising:
one or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions, which when executed by the device, cause the device to perform the method of any of claims 1-8.
11. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when run on a computer, causes the computer to perform the method according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383993.5A CN113190498B (en) | 2021-04-09 | 2021-04-09 | Frequency adjustment method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110383993.5A CN113190498B (en) | 2021-04-09 | 2021-04-09 | Frequency adjustment method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113190498A CN113190498A (en) | 2021-07-30 |
| CN113190498B true CN113190498B (en) | 2023-04-28 |
Family
ID=76975428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110383993.5A Active CN113190498B (en) | 2021-04-09 | 2021-04-09 | Frequency adjustment method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190498B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112565035A (en) * | 2020-11-20 | 2021-03-26 | 珠海格力电器股份有限公司 | Data transmission method, device and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7506197B2 (en) * | 2005-02-07 | 2009-03-17 | International Business Machines Corporation | Multi-directional fault detection system |
| US10311014B2 (en) * | 2012-12-28 | 2019-06-04 | Iii Holdings 2, Llc | System, method and computer readable medium for offloaded computation of distributed application protocols within a cluster of data processing nodes |
| CN105580453B (en) * | 2013-09-18 | 2019-12-10 | 瑞典爱立信有限公司 | Carrier frequency processing in clusters |
| US9582012B2 (en) * | 2014-04-08 | 2017-02-28 | Qualcomm Incorporated | Energy efficiency aware thermal management in a multi-processor system on a chip |
| EP3188373B1 (en) * | 2015-12-30 | 2018-09-26 | Mitsubishi Electric R&D Centre Europe B.V. | Fast distributed clustering for cooperation in telecommunications networks |
| CN108055309B (en) * | 2017-12-07 | 2021-02-19 | 厦门集微科技有限公司 | Data transmission system and method |
| KR20200084987A (en) * | 2019-01-03 | 2020-07-14 | 삼성전자주식회사 | Electronic circuit for controlling power |
-
2021
- 2021-04-09 CN CN202110383993.5A patent/CN113190498B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112565035A (en) * | 2020-11-20 | 2021-03-26 | 珠海格力电器股份有限公司 | Data transmission method, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于模型预测控制的数据中心节能调度算法;赵小刚等;《软件学报》;20170215(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113190498A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11507430B2 (en) | Accelerated resource allocation techniques | |
| US20220036123A1 (en) | Machine learning model scaling system with energy efficient network data transfer for power aware hardware | |
| Sun et al. | Mobile data traffic prediction by exploiting time-evolving user mobility patterns | |
| US20220329522A1 (en) | Adaptive resilient network communication | |
| CN104798008B (en) | The configurable peak performance limit of control processor | |
| Ng et al. | Reputation-aware hedonic coalition formation for efficient serverless hierarchical federated learning | |
| CN113364603B (en) | Fault recovery method of ring network and physical node | |
| WO2022247880A1 (en) | Method for fusing operators of neural network, and related product | |
| KR20220149418A (en) | Methods and apparatus to automatically update artificial intelligence models for autonomous factories | |
| CN114945028A (en) | Information processing method based on Internet of things equipment, related equipment and storage medium | |
| Karthikeyan et al. | Saldeft: Self-adaptive learning differential evolution based optimal physical machine selection for fault tolerance problem in cloud | |
| CN113190498B (en) | Frequency adjustment method and device and electronic equipment | |
| US11915122B2 (en) | Gateway for distributing an artificial neural network among multiple processing nodes | |
| KR101672357B1 (en) | Performing frequency coordination in a multiprocessor system based on response timing optimization | |
| US11592889B2 (en) | Die-to-die dynamic clock and power gating | |
| CN117149382A (en) | Virtual machine scheduling method, device, computer equipment and storage medium | |
| US20220283951A1 (en) | Apparatus and method for intelligent memory page management | |
| Zhu et al. | Research on fog resource scheduling based on cloud-fog collaboration technology in the electric internet of things | |
| Fang et al. | A Scheduling Strategy for Reduced Power Consumption in Mobile Edge Computing | |
| Reza | Machine learning enabled solutions for design and optimization challenges in networks-on-chip based multi/many-core architectures | |
| Zhao et al. | Deep Reinforcement Learning‐Based Task Offloading for Parked Vehicle Cooperation in Vehicular Edge Computing | |
| CN113746873B (en) | Abnormal node processing method in ring network and related equipment | |
| Manihar et al. | Intelligent and Scalable IoT Edge-Cloud System | |
| Wang et al. | Container Scaling Strategy Based on Reinforcement Learning | |
| Chen et al. | Conflict‐Resilient Incremental Offloading of Deep Neural Networks to the Edge of Smart Environment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |