CN106330494B - SoC resource arbitration method and device - Google Patents
SoC resource arbitration method and device Download PDFInfo
- Publication number
- CN106330494B CN106330494B CN201510350819.5A CN201510350819A CN106330494B CN 106330494 B CN106330494 B CN 106330494B CN 201510350819 A CN201510350819 A CN 201510350819A CN 106330494 B CN106330494 B CN 106330494B
- Authority
- CN
- China
- Prior art keywords
- service
- qos
- index
- adjustment
- soc
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method and a device for SoC resource arbitration, wherein the method comprises the following steps: presetting a default priority index of a service; acquiring QoS requirement information of a service from a QoS frame to form a real-time QoS index of the service; generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service; and distributing SoC resources according to the decision index after the service weighting. The invention can realize the self-adaptive dynamic scheduling and resource arbitration of each service requirement when the multi-service concurrent operation is carried out.
Description
Technical Field
The present invention relates to the technical field of multi-service concurrent operations, and in particular, to a method and an apparatus for SoC resource arbitration.
Background
With the development of technology, the integration level of chips is higher and higher, and the requirements on systems on Chip (SoC) are higher and higher. At present, mainstream communication SoC chips include protocols (IP, Internet Protocol) for interconnection among various networks, and the multi-mode and multi-system SoC communication chips become standard configurations of systems. The preemption and allocation of shared resources becomes especially critical because of the need to process multiple systems simultaneously, and the limited resources in the chip. Typical examples include: how to effectively process similar problems and ensure that each Service during multi-Service parallel Processing has required Quality of Service (QoS) makes the overall index optimization of the SoC chip during multi-Service parallel operation a problem which is always researched.
Currently, in SoC design, hardware-based arbitration schemes are mainly adopted, such schemes usually use hardware to arbitrate according to priority in services, and are generally simple in design, resulting in poor flexibility.
Disclosure of Invention
In order to solve the above technical problems, the present invention provides a method and a device for SoC resource arbitration, which can adaptively perform dynamic scheduling and resource arbitration on each service requirement during multi-service concurrent operation.
In order to achieve the object of the present invention, the present invention provides an SoC resource arbitration method, including: presetting a default priority index of a service; acquiring QoS requirement information of a service from a QoS frame to form a real-time QoS index of the service; generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service; and distributing SoC resources according to the decision index after the service weighting.
Further, the presetting of the default priority index of the service includes: and presetting a default priority index of the service according to the nature of the service to form a set Dn of the default priority index of the service, wherein the set Dn is { d1, d2 …. Dn }.
further, the QoS frame structure includes a command Control word Control, an adjustment policy Strategy, and an adjustment policy Content, where a Control field defines a frame format; the Strategy field defines the adjustment Strategy as an adjustment order and a QoS index respectively; the Content field defines the contents of the Strategy field.
Further, the acquiring QoS requirement information of the service from the QoS frame to form a real-time QoS index of the service includes: if the Content field of the QoS frame is the adjustment order at the adjustment stage, acquiring QoS requirement information of a service from a QoS frame sent by a service receiving end, wherein the QoS requirement information comprises the adjustment order qn of the service; if the Content field of the QoS frame is a QoS index in an adjustment stage, acquiring QoS demand information of a service from a QoS frame sent by a service receiving end, wherein the QoS demand information comprises the QoS index of the service, and mapping an adjustment order according to the QoS index to obtain an adjustment order qn of the service; and forming a real-time QoS index set Qn of the service according to the adjustment order of the service, wherein the set Qn is { q1, q2 …. Qn }.
Further, the generating a service weighted decision index according to the default priority index of the service and the real-time QoS index of the service includes: and carrying out vector operation of addition on the default priority index Dn of the service and the real-time QoS index Qn of the service, wherein the default priority index Dn of the service is { d1, d2 …. Dn } and the real-time QoS index Qn of the service is { q1, q2 …. Qn }, and generating a service weighted decision index Fn is { f1, f2 …. Fn }.
Further, the allocating SoC resources according to the decision index after the service weighting includes: and arbitrating the service resource request according to the decision index after the service weighting, and deciding the SoC resource to the service with the highest decision index Max (Fn).
further, the method further comprises: pre-establishing a resource request queue; and caching the received service in the resource request queue according to the decision index weighted by the service.
The invention also provides a device for arbitrating the SoC resources, which comprises:
Further, the setting module is used for presetting the default priority index of the service; the QoS index and adjustment module is used for acquiring QoS requirement information of the service from the QoS frame to form a real-time QoS index of the service; the QoS shaper is used for generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service; and the resource arbiter is used for allocating SoC resources according to the decision indexes after the service weighting.
further, the setting module is specifically configured to: and presetting a default priority index of the service according to the nature of the service to form a set Dn of the default priority index of the service, wherein the set Dn is { d1, d2 …. Dn }.
Further, the QoS frame structure includes a command Control word Control, an adjustment policy Strategy, and an adjustment policy Content, where a Control field defines a frame format; the Strategy field defines the adjustment Strategy as an adjustment order and a QoS index respectively; the Content field defines the contents of the Strategy field.
Further, the QoS indicator and adjustment module is specifically configured to: if the Content field of the QoS frame is the adjustment order at the adjustment stage, acquiring QoS requirement information of a service from a QoS frame sent by a service receiving end, wherein the QoS requirement information comprises the adjustment order qn of the service; if the Content field of the QoS frame is a QoS index in an adjustment stage, acquiring QoS demand information of a service from a QoS frame sent by a service receiving end, wherein the QoS demand information comprises the QoS index of the service, and mapping an adjustment order according to the QoS index to obtain an adjustment order qn of the service; and forming a real-time QoS index set Qn of the service according to the adjustment order of the service, wherein the set Qn is { q1, q2 …. Qn }.
Further, the QoS shaper is specifically configured to: and carrying out vector operation of addition on the default priority index Dn of the service and the real-time QoS index Qn of the service, wherein the default priority index Dn of the service is { d1, d2 …. Dn } and the real-time QoS index Qn of the service is { q1, q2 …. Qn }, and generating a service weighted decision index Fn is { f1, f2 …. Fn }.
Further, the resource arbiter is specifically configured to: and arbitrating the service resource request according to the decision index after the service weighting, and deciding the SoC resource to the service with the highest decision index (Max (Fn)) after the service weighting.
Further, the apparatus further comprises: and the buffer module is used for pre-establishing a resource request queue and caching the received service in the resource request queue according to the decision index after the service weighting.
Compared with the prior art, the method comprises the steps of presetting the default priority index of the service; acquiring QoS requirement information of a service from a QoS frame to form a real-time QoS index of the service; generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service; and distributing SoC resources according to the decision index after the service weighting. The invention defines the QoS frame and embeds the QoS frame into the frame format of each service, thereby transmitting the QoS index and the adjustment requirement in real time; defining different adjustment strategies, when in an adjustment stage, initiating by an opposite terminal, and when in a QoS index stage, performing local adjustment; and generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service, and deciding the SoC resource to the service with the highest decision index, so that the resources in the system can be dynamically arbitrated by utilizing the change of the QoS index to the greatest extent, and the aim of optimizing the QoS is fulfilled.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention and not to limit the invention.
fig. 1 is a flowchart illustrating an SoC resource arbitration method according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an SoC resource arbitration device according to an embodiment of the present invention.
fig. 3 is a diagram illustrating a dynamic QoS adjustment curve according to an embodiment of the present invention.
Detailed Description
in order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
the steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.
Usually inside a complex SoC, there is a need for parallel operation of multiple services, and a typical scenario includes: a plurality of services such as WiFi (Wireless Fidelity), BlueTooth (BlueTooth), Long Term Evolution (LTE), Global Positioning System (GPS) are simultaneously turned on, or a coexistence scene of services such as voice, image, and data. The QoS required by different services themselves may have certain requirements, and the QoS itself may be various indexes: such as bandwidth, delay, packet loss rate, congestion rate, etc. In the prior art, a fixed priority is often set based on hardware and according to the attribute of a service, so that the service with high priority is processed preferentially.
The SoC resource arbitration method and the SoC resource arbitration device can adaptively carry out dynamic scheduling and resource arbitration on each service requirement.
as shown in fig. 1, the present invention provides an SoC resource arbitration method, including:
Step 101, presetting a default priority index of a service.
in this step, a default priority index of the service is preset according to the nature of the service, for example, the default priority index of the nth service is denoted as Dn, so that a set Dn of the default priority indexes of the service is formed as { d1, d2 …, Dn }, and the setting of Dn is confirmed by a system designer, which is not described herein.
step 102, obtaining QoS requirement information of the service from the QoS frame to form a real-time QoS index of the service.
Compared with the prior art, the invention defines a QoS frame structure, and the QoS frame can be embedded into the frame format of each service, interpreted by an upper layer or directly analyzed by hardware.
The QoS frame structure shown in table 1 includes a command Control word (Control), an adjustment policy (Strategy), and an adjustment policy Content (Content).
TABLE 1
According to table 1, the Control field defines the frame formats, which are 00 Control frame, 01 data frame, and 10QoS frame, respectively; in addition, an 11 Reserved bit Reserved is also included;
The Strategy field defines the adjustment policy, which is 0: adjusting the order and the QoS Index (QoS _ Index) 1;
the Content field is the specific Content of the adjustment policy in the Strategy field:
when the Content field is When Strategy ═ 0, it indicates that the adjustment policy is in the adjustment phase.
At this time, the adjustment requirement is initiated by the service receiving end, specifically, the service receiving end sends out a QoS frame according to its QoS status, and locally (the QoS frame receiving end) acquires QoS requirement information of the service from the QoS frame, where the QoS requirement information includes an adjustment order qx (x is 1 to n) of the service; the qx (x is 1 to n) Index is obtained by mapping QoS indexes of each service, qx is Function (Index _ a, Index _ b, … Index _ m), and the setting of the mapping Function () is confirmed by a system designer, which is not described herein.
In addition, the QoS requirement information in the QoS frame may further include an order indicating up-regulation or down-regulation, so as to provide coarse and fine control, for example, for data traffic, the possible indexes _ a/b/. m thereof are bit error rate, delay, throughput rate, etc., and 1-31 is defined as an order adjusted upwards, and-1 to-31 is defined as an order adjusted downwards, and during the adjustment, fine regulation may be performed at +1or-1 each time, and coarse regulation may be performed at +4or-4 each time.
When the Content field is When Strategy ═ 1, it indicates that the adjustment policy is the QoS index stage.
at this time, the receiving end of the service does not initiate an adjustment requirement, but only sends out the current QoS Index, and locally determines an adjustment policy, that is, the receiving end of the service sends out a QoS frame, and locally acquires QoS requirement information of the service from the QoS frame, where the QoS requirement information includes the QoS Index of the service, and locally determines adjustment control, specifically, locally performs mapping from the QoS Index to an adjustment order according to the acquired QoS Index, so as to adjust a qn value, and complete a task of rearranging and arbitrating a priority, where the mapping from the QoS Index to the adjustment order is qx (Function (Index _ a, Index _ b, … Index _ m), and the setting of the mapping relation Function () is confirmed by a system designer, which is not described herein.
In this step, receiving a QoS frame from a service receiving end, and acquiring QoS requirement information of a service from the QoS frame; if the Content field in the QoS frame is When stripe 0, the adjustment order qx (x is 1 to n) of the traffic can be directly obtained from the QoS frame; if the Content field in the QoS frame is When Strategy 1, acquiring the QoS index of the service from the QoS frame, and mapping an adjustment order according to the QoS index to obtain an adjustment order qx (x is 1-n) of the service; thus, according to the adjustment order of the service, the real-time QoS index set Qn of the service is obtained as { q1, q2 …. Qn }.
and 103, generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service.
in this step, a vector operation of adding the default priority index Dn ═ { d1, d2 …. Dn } of the traffic and the real-time QoS index Qn ═ { q1, q2 …. Qn } of the traffic is performed, and a decision index Fn ═ { f1, f2 …. Fn } weighted by the traffic, that is, Fn ═ Dn + Qn, is generated.
And 104, distributing SoC resources according to the decision indexes after the service weighting.
In this step, each service resource request is arbitrated according to the decision index after service weighting, and SoC resources are decided to the service with the highest decision index, namely, Max (Fn) service, so that the QoS of the service is improved to a certain extent.
In addition, in this step, a resource request queue is established, and the service is cached according to the decision index.
Fig. 2 is an SoC resource arbitration device of the present invention, including:
A setting module (not shown) for presetting a default priority index of the service.
Specifically, according to the nature of the service, the default priority index of the service is preset, and the set Dn of the default priority index of the service is obtained as { d1, d2 …. Dn }.
And the QoS index and adjustment module is used for acquiring QoS requirement information of the service from the QoS frame to form a real-time QoS index of the service.
Specifically, QoS requirement information of a service is acquired according to a received QoS frame; if the Content field in the QoS frame is When stripe 0, the adjustment order qx (x is 1 to n) of the traffic can be directly obtained from the QoS frame; if the Content field in the QoS frame is When Strategy 1, acquiring the QoS index of the service from the QoS frame, and mapping an adjustment order according to the QoS index to obtain an adjustment order qx (x is 1-n) of the service; thus, according to the adjustment order of the service, the real-time QoS index set Qn of the service is obtained as { q1, q2 …. Qn }.
And the QoS shaper is used for generating a decision index after the service weighting according to the default priority index of the service preset by the setting module and the real-time QoS index of the service from the QoS index and adjustment module.
specifically, the default priority index Dn of the traffic is { d1, d2 …, Dn } and the real-time QoS index Qn of the traffic is { q1, q2 …, Qn } are added to perform vector operation, and a decision index Fn of the weighted traffic is generated, that is, Fn is { f1, f2 …, Fn }, that is, Fn is Dn + Qn.
and the Buffer module (Buffer) is used for establishing a resource request queue and caching the service according to the judgment index.
And the resource arbiter is used for allocating the SoC resources according to the decision indexes after the service weighting.
Specifically, according to the decision index after the service weighting, each service resource request is arbitrated, and the SoC resource is decided for the service with the highest decision index Max (Fn).
And the strategy control configuration file is used for predefining the rules and strategies of the QoS shaper and the resource arbiter.
An embodiment of the present invention will be described below, in which QoS is dynamically adjusted based on the SoC resource arbitration method and apparatus.
Fig. 3 is a diagram illustrating a dynamic QoS adjustment curve according to an embodiment of the present invention. As shown in figure 3 of the drawings,
The QoS range required by the sub-service is assumed to be a shadow interval in the figure, the upper limit is the optimal QoS, and the lower limit is the QoS bottom line, so that the sub-service can be accepted when the service runs in the QoS shadow interval, and the user experience is not influenced.
Assuming that the service starting point is point a, since it is lower than the minimum value, the chip/entity at the receiving end of the service sends out the QoS frame and puts forward the requirement of upward adjustment. Specifically, if an adjustment strategy at an adjustment stage is adopted, for example, the throughput rate of a receiving end of a service is too low, the local is informed through a Qos Frame that the throughput rate of the service needs to be increased, an adjustment order is specified in the Qos Frame, that is, a value of qn is included in a Qos Frame, and when the Qos Frame is received locally and a Qos adjustment order is extracted, the resource decision weight of the Qos adjustment order can be correspondingly increased; if the adjustment strategy of the QoS index is adopted, for example, 0-31 is the content of the QoS index, the higher the throughput rate is better, and if the return is 0, the throughput rate is very poor, and more resources are expected to be locally given, so that the throughput rate can be subsequently increased.
The QoS index and adjustment module outputs increasing data, and superimposes the default priority index of the service, so that the total decision index of the service in the arbiter is increased, thereby increasing the advantage of the service in resource preemption, if the QoS is increased slowly, a more aggressive increasing mode can be adopted, for example, the order of coarse adjustment is increased greatly, thereby ensuring that the service can gradually increase the QoS value within a certain time.
in order to solve the greedy problem, when the QoS value rises to exceed the intermediate value, as shown in the diagram as point B, the adjustment order of the QoS frame remains unchanged, and the main purpose is to ensure the smoothness of the service and to excessively seize resources. When for some reason the QoS value gradually increases and reaches the upper limit, as shown in point C, the adjustment order needs to be gradually decreased, so that the system has an opportunity to gradually allocate limited resources to other services. Similarly, when the QoS is decreased to the middle value, the adjustment order remains unchanged, as shown by the position of point D in the figure, unless the QoS index is decreased all the time and the lower limit is reached, as shown by the position of point E in the figure, the adjustment order starts to increase again, as the system is at point a, and the whole system is in the dynamic adaptive adjustment process all the time. The design aim is to ensure that each service can stably run in the range acceptable by QoS without losing fairness.
In the invention, the QoS frame is defined and embedded into the frame format of each service, so that the QoS index and the adjustment requirement can be transmitted in real time; defining different adjustment strategies, when in an adjustment stage, initiating by an opposite terminal, and when in a QoS index stage, performing local adjustment; and generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service, and deciding the SoC resource to the service with the highest decision index, so that the resources in the system can be dynamically arbitrated by utilizing the change of the QoS index to the greatest extent, and the aim of optimizing the QoS is fulfilled.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (14)
1. An SoC resource arbitration method, comprising:
presetting a default priority index of a service;
acquiring QoS demand information of a service from a QoS frame sent by a service receiving end to form a real-time QoS index of the service, wherein the QoS frame is embedded into a frame format of each service, the QoS frame defines two adjustment strategies, one adjustment strategy is used for initiating adjustment demand by the service receiving end, and the other adjustment strategy is used for locally determining the adjustment strategy;
Generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service;
And distributing SoC resources according to the decision index after the service weighting.
2. The SoC resource arbitration method according to claim 1, wherein the presetting of the default priority index of the traffic comprises:
And presetting a default priority index of the service according to the nature of the service to form a set Dn of the default priority index of the service, wherein the set Dn is { d1, d2 …. Dn }.
3. The SoC resource arbitration method of claim 2, wherein the QoS frame structure comprises a command Control word (Control), an adjustment policy Strategy, and an adjustment policy Content (Content), wherein,
the Control field defines the frame format;
The Strategy field defines the adjustment Strategy as an adjustment order and a QoS index respectively;
The Content field defines the contents of the Strategy field.
4. the SoC resource arbitration method according to claim 3, wherein the obtaining QoS requirement information of the service from the QoS frame sent by the service receiving end to form a real-time QoS index of the service comprises:
If the Content field of the QoS frame is the adjustment order at the adjustment stage, acquiring QoS requirement information of a service from a QoS frame sent by a service receiving end, wherein the QoS requirement information comprises the adjustment order qn of the service;
if the Content field of the QoS frame is a QoS index in an adjustment stage, acquiring QoS demand information of a service from a QoS frame sent by a service receiving end, wherein the QoS demand information comprises the QoS index of the service, and mapping an adjustment order according to the QoS index to obtain an adjustment order qn of the service;
And forming a real-time QoS index set Qn of the service according to the adjustment order of the service, wherein the set Qn is { q1, q2 …. Qn }.
5. The SoC resource arbitration method of claim 4, wherein the generating a service weighted decision index according to the service default priority index and the service real-time QoS index comprises:
and carrying out vector operation of addition on the default priority index Dn of the service and the real-time QoS index Qn of the service, wherein the default priority index Dn of the service is { d1, d2 …. Dn } and the real-time QoS index Qn of the service is { q1, q2 …. Qn }, and generating a service weighted decision index Fn is { f1, f2 …. Fn }.
6. The SoC resource arbitration method according to claim 5, wherein the allocating SoC resources according to the decision index after the service weighting includes:
and arbitrating the service resource request according to the decision index after the service weighting, and deciding the SoC resource to the service with the highest decision index Max (Fn).
7. The SoC resource arbitration method of claim 5, wherein the method further comprises: pre-establishing a resource request queue;
And caching the received service in the resource request queue according to the decision index weighted by the service.
8. An SoC resource arbitration apparatus, comprising:
The setting module is used for presetting the default priority index of the service;
The QoS index and adjustment module is used for acquiring QoS requirement information of a service from a QoS frame sent by a service receiving end to form a real-time QoS index of the service, wherein the QoS frame is embedded into a frame format of each service, the QoS frame defines two adjustment strategies, one adjustment strategy is used for initiating an adjustment requirement by the service receiving end, and the other adjustment strategy is used for locally determining an adjustment strategy;
The QoS shaper is used for generating a decision index after service weighting according to the default priority index of the service and the real-time QoS index of the service;
And the resource arbiter is used for allocating SoC resources according to the decision indexes after the service weighting.
9. The SoC resource arbitration device according to claim 8, wherein the setting module is specifically configured to:
and presetting a default priority index of the service according to the nature of the service to form a set Dn of the default priority index of the service, wherein the set Dn is { d1, d2 …. Dn }.
10. The SoC resource arbitration device of claim 9, wherein the QoS frame structure comprises a command Control word (Control), an adjustment policy Strategy, and an adjustment policy Content (Content), wherein,
The Control field defines the frame format;
the Strategy field defines the adjustment Strategy as an adjustment order and a QoS index respectively;
The Content field defines the contents of the Strategy field.
11. The SoC resource arbitration device of claim 10, wherein the QoS indicator and adjustment module is specifically configured to:
if the Content field of the QoS frame is the adjustment order at the adjustment stage, acquiring QoS requirement information of a service from a QoS frame sent by a service receiving end, wherein the QoS requirement information comprises the adjustment order qn of the service;
If the Content field of the QoS frame is a QoS index in an adjustment stage, acquiring QoS demand information of a service from a QoS frame sent by a service receiving end, wherein the QoS demand information comprises the QoS index of the service, and mapping an adjustment order according to the QoS index to obtain an adjustment order qn of the service;
and forming a real-time QoS index set Qn of the service according to the adjustment order of the service, wherein the set Qn is { q1, q2 …. Qn }.
12. The SoC resource arbitration device of claim 11, wherein the QoS shaper is specifically configured to:
And carrying out vector operation of addition on the default priority index Dn of the service and the real-time QoS index Qn of the service, wherein the default priority index Dn of the service is { d1, d2 …. Dn } and the real-time QoS index Qn of the service is { q1, q2 …. Qn }, and generating a service weighted decision index Fn is { f1, f2 …. Fn }.
13. The SoC resource arbitration device of claim 12, wherein the resource arbiter is specifically configured to:
And arbitrating the service resource request according to the decision index after the service weighting, and deciding the SoC resource to the service with the highest decision index (Max (Fn)) after the service weighting.
14. the SoC resource arbitration device of claim 12, wherein the device further comprises:
and the buffer module is used for pre-establishing a resource request queue and caching the received service in the resource request queue according to the decision index after the service weighting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510350819.5A CN106330494B (en) | 2015-06-23 | 2015-06-23 | SoC resource arbitration method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510350819.5A CN106330494B (en) | 2015-06-23 | 2015-06-23 | SoC resource arbitration method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106330494A CN106330494A (en) | 2017-01-11 |
| CN106330494B true CN106330494B (en) | 2019-12-13 |
Family
ID=57727757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510350819.5A Active CN106330494B (en) | 2015-06-23 | 2015-06-23 | SoC resource arbitration method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106330494B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112463673B (en) * | 2020-11-25 | 2023-03-21 | 海光信息技术股份有限公司 | On-chip bus, and service quality arbitration method and device for on-chip bus |
| WO2023159652A1 (en) * | 2022-02-28 | 2023-08-31 | 华为技术有限公司 | Ai system, memory access control method, and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101730236A (en) * | 2008-10-30 | 2010-06-09 | 中兴通讯股份有限公司 | Resource scheduling method and system, base station and terminal therefor |
| CN102256266A (en) * | 2011-07-04 | 2011-11-23 | 重庆邮电大学 | User application-oriented adaptive access network selection device and method |
| CN103826312A (en) * | 2014-01-20 | 2014-05-28 | 浙江工业大学 | Improved LTE (Long Term Evolution) scheduling method based on exponential rule |
-
2015
- 2015-06-23 CN CN201510350819.5A patent/CN106330494B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101730236A (en) * | 2008-10-30 | 2010-06-09 | 中兴通讯股份有限公司 | Resource scheduling method and system, base station and terminal therefor |
| CN102256266A (en) * | 2011-07-04 | 2011-11-23 | 重庆邮电大学 | User application-oriented adaptive access network selection device and method |
| CN103826312A (en) * | 2014-01-20 | 2014-05-28 | 浙江工业大学 | Improved LTE (Long Term Evolution) scheduling method based on exponential rule |
Non-Patent Citations (2)
| Title |
|---|
| 实时自适应调度任务的Qos确保;程小鸥;《中国优秀硕士学位论文全文数据库信息科技辑》;20091115;第2009卷(第11期);第20-50页 * |
| 片上网络通信性能分析与优化;王坚;《中国博士学位论文全文数据库信息科技辑》;20120615;第2012卷(第6期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106330494A (en) | 2017-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5840795B2 (en) | Method and system for rate adaptive allocation of resources | |
| EP3226604A1 (en) | Data multi streaming transmission method, apparatus, anchor point, and system | |
| US10313919B2 (en) | Method and device for providing transmission differentiation in mobile communication system | |
| WO2021147368A1 (en) | Method and apparatus for adjusting service level, device, system and storage medium | |
| WO2014139448A1 (en) | Systems and methods for quality of experience aware joint scheduling of buffered video on demand and best effort flows | |
| WO2011139462A2 (en) | Techniques for initiating communication in a wireless network | |
| US8837282B2 (en) | Method and apparatus for pooling bandwidth across disparate bandwidth reservations | |
| WO2015024158A1 (en) | Access control method and apparatus | |
| JP7106639B2 (en) | Uplink data packet resource allocation method and user terminal | |
| CN112637911A (en) | Resource allocation method and system for eMB and urllc in coexistence in 5G system | |
| US20160173408A1 (en) | Data transmission method using multiple wireless networks | |
| WO2021160113A1 (en) | Application example deploying and application example scheduling method and apparatus | |
| KR102219015B1 (en) | Use of network support protocols to improve network usage | |
| TWI572234B (en) | Central controller and resource allocation method thereof using in a cellular network | |
| CN106330494B (en) | SoC resource arbitration method and device | |
| WO2019214524A1 (en) | Resource allocation method and apparatus | |
| US10554368B2 (en) | Wireless data-acknowledgement communication using frame aggregation | |
| JP2007281541A (en) | Base station device and control method thereof | |
| JP2009284297A (en) | Multi-session enabled router and communication control method thereof | |
| CN111131061B (en) | Data transmission method and network equipment | |
| US10581750B2 (en) | Network access entity for providing access to a communication network | |
| WO2014142718A1 (en) | Preventing free-riding data traffic when scheduling uplink data | |
| CN107995312B (en) | Boundary network service flow distribution system and dynamic distribution method | |
| CN111131081A (en) | Method and device for supporting multi-process high-performance unidirectional transmission | |
| JP5564603B1 (en) | Relay node |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |