CN110413409A - A kind of method and medium of the distribution of Multi probe star sensor multiple nucleus system task - Google Patents
A kind of method and medium of the distribution of Multi probe star sensor multiple nucleus system task Download PDFInfo
- Publication number
- CN110413409A CN110413409A CN201910636830.6A CN201910636830A CN110413409A CN 110413409 A CN110413409 A CN 110413409A CN 201910636830 A CN201910636830 A CN 201910636830A CN 110413409 A CN110413409 A CN 110413409A
- Authority
- CN
- China
- Prior art keywords
- core
- main
- period
- task
- remained capacity
- 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.)
- Granted
Links
Classifications
-
- 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
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4812—Task transfer initiation or dispatching by interrupt, e.g. masked
-
- 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
- G06F9/505—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 considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/48—Indexing scheme relating to G06F9/48
- G06F2209/484—Precedence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/508—Monitor
Abstract
A kind of method of Multi probe star sensor multiple nucleus system task distribution, includes the following steps: S1, within any period, and main nuclear energy enough obtains all load numbers from core within next period, and sorts to all from core, subsequently into next period；S2, when it is any complete remained capacity task from core K1 after, main core obtains the remaining time in this period according to the time from core K1 interruption；S3, main core are according to the slave core sequence in S1, the remaining time in this period in S2, the remained capacity quantity M that can be completed in remaining time in this period from core K1 is obtained, then main core is distributed to from core K1 from the last M remained capacity task of core K2 by load number is highest；Finally main core updates all from core sequence in S1 according to the load number after redistributing；S4, S2~S3 is repeated, is completed until all from the remained capacity task of core.This method can be realized from core task load and maximize real time equaliser purpose.
Description
Technical field
The present invention relates to the methods and medium of a kind of distribution of Multi probe star sensor multiple nucleus system task, belong to Multi probe star
Sensor technical field.
Background technique
Multi probe star sensor can simultaneously identify the day area of multiple directions, each with multiple nucleus system parallel processing
The identification mission in its area；Use a core as main core again, the task of main core be to respectively from core forecast posture, will be each from the area He Tian
Recognition result merge；Since day area is directed toward difference, area's navigation star number difference leads to greatly the identification in each day area within each day
Matching workload difference is big, this results in respectively unbalanced from the task load of core；In a cycle, load weight can from the task of core
Can time-out, load it is light have a large amount of free times from core, seriously constrain Multi probe star sensor detection quality and application effect
Fruit.
Summary of the invention
The technical problem to be solved by the present invention is having overcome the deficiencies of the prior art and provide a kind of Multi probe star sensor
The method and medium of multiple nucleus system task distribution, using monitoring when main verification respectively from core task load situation, and load is heavy
The task of slave core distribute to the idle method from core, single probe identification time-out is reduced in each cycle to reach, respectively from core task
The purpose of load balancing.
The object of the invention is achieved by the following technical programs:
A kind of method of Multi probe star sensor multiple nucleus system task distribution, multiple nucleus system include a main core and it is multiple from
The measurement result of core, each probe is identified by one from core, is included the following steps:
S1, within any period, main nuclear energy enough obtains all load numbers from core within next period, and according to described
Load number sorts to all from core, subsequently into next period；
S2, when it is any complete remained capacity task from core K1 after by triggering the main core of interrupt notification of main core, main core according to
The time interrupted from core K1 obtains the remaining time in this period；
S3, main core are according to the slave core sequence in S1, the remaining time in this period in S2, when obtaining the residue in this period
In the remained capacity quantity M that can be completed from core K1, then main core is loaded from last M of core K2 by load number is highest
Identification mission is distributed to from core K1；Finally main core updates all from core sequence in S1 according to the load number after redistributing；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, it is sent to from core K1 by recognition result from core K2；
S4, S2~S3 is repeated, is completed until all from the remained capacity task of core.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, in S1, main core each cycle is in fixed time
All postures from core in next period are estimated, while retrieving all nautical star numbers from core in the case where currently pointing to；Each from
The corresponding nautical star number of core is the load number from core.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, main core each cycle are exposed in the period star chart
Moment estimate it is all from core next period posture.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution in S2, completes remained capacity task from core K1
Afterwards by triggering the main core of interrupt notification of main core highest priority, the first complement mark amount then is sent to main core from core K1, is accused
Know that this enters idle state from core K1.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, the main core are recorded every by mask register
At the beginning of a period, any the current time of remained capacity task, the time in each period are completed from core K1.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, main core described in S3 are highest by load number
The method from core K1 is distributed to from the last M remained capacity task of core K2 are as follows:
Then main core triggering will be distributed from the highest priority interrupt of core K1 from the last M remained capacity task of core K2
To from core K1；Meanwhile main core record is corresponding relationship from core K1 and from core K2；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, again by the main core highest priority of triggering
It is open close to know main core, then the second complement mark amount and remained capacity result are sent to main core from core K1；Main core is logical according to described the
Two complement mark amounts, corresponding relationship will be sent to from the remained capacity result of core K1 from core K2；Pass through cyclic query side from core K2
Formula obtains the remained capacity result completed from core K1.
A kind of method of Multi probe star sensor multiple nucleus system task distribution, multiple nucleus system include a main core and it is multiple from
The measurement result of core, each probe is identified by one from core, is included the following steps:
S11, within any period, main nuclear energy enough obtains all load numbers from core within next period, and according to institute
Load number is stated tentatively to be sorted to all from core；
S12, in the slave core of all sequences, the load number and load number of the most slave core of load number it is least from
The ratio between load number of core is more than or equal to 3, and the load number of the slave core of load number at most is more than or equal to default basic load
When quantity, by at least one third of the remained capacity task of the most slave core of load number distribute to load number it is least from
Core；
S13, other least from other than core of the most slave core of load number and load number are ranked up from core, so
S12 is repeated afterwards, is less than or equal to 1 until participating in the quantity of slave core of sequence, main verification is according to each from the load number of core to institute
Have from core and finally sorted, subsequently into next period；
S14, when it is any complete remained capacity task from core K1 after by triggering the main core of interrupt notification of main core, main core according to
The time interrupted from core K1 obtains the remaining time in this period；
S15, main core are obtained in this period and are born according to the final sequence in S13, the remaining time in this period in S12
The quantity for carrying the highest maximum load identification that can be completed within this period from core K2 of quantity, judges load number in this period
The highest all remained capacity tasks that whether can be completed within this period from core K2 from core K2, if can be complete from core K2
At being then transferred to S17；Otherwise, the slave core K2 remained capacity task that main core will exceed maximum load identification quantity distribute to from
Core K1；Finally main core updates all final sequences from core in S13 according to the load number after redistributing；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, it is sent to from core K1 by recognition result from core K2；
S16, S14~S15 is repeated；It is transferred to S17；
S7, it is all from the remained capacity task of core complete.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, in S11, main core each cycle is in fixed time
All postures from core in next period are estimated, while retrieving all nautical star numbers from core in the case where currently pointing to；Each from
The corresponding nautical star number of core is the load number from core.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, main core each cycle are exposed in the period star chart
Moment estimate it is all from core next period posture.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, will exceed the maximum load described in S15
The slave core K2 remained capacity task of identification quantity distributes to the method from core K1 are as follows:
Then main core triggering will exceed the slave core K2 of the maximum load identification quantity from the highest priority interrupt of core K1
Remained capacity task is distributed to from core K1；Meanwhile main core record is corresponding relationship from core K1 and from core K2；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, again by the main core highest priority of triggering
It is open close to know main core, then the second complement mark amount and remained capacity result are sent to main core from core K1；Main core is logical according to described the
Two complement mark amounts, corresponding relationship will be sent to from the remained capacity result of core K1 from core K2；Pass through cyclic query side from core K2
Formula obtains the remained capacity result completed from core K1.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution in S14, completes remained capacity task from core K1
Afterwards by triggering the main core of interrupt notification of main core highest priority, the first complement mark amount then is sent to main core from core K1, is accused
Know that this enters idle state from core K1.
The method of above-mentioned Multi probe star sensor multiple nucleus system task distribution, the main core are recorded every by mask register
At the beginning of a period, any the current time of remained capacity task, the time in each period are completed from core K1.
A kind of computer storage readable medium, is stored thereon with computer program, when which is executed by processor, realizes
The step of method of above-mentioned Multi probe star sensor multiple nucleus system task distribution.
The present invention has the following beneficial effects: compared with the prior art
(1) present invention can be substantially reduced from vouching probe identification mission time-out probability；
(2) present invention will be respectively in a basic balance from vouching probe identification mission load, and each cycle recognition time is almost the same,
So as to improve Multi probe star sensor entirety attitude data renewal frequency；
(3) present invention realizes that the method that multicore task is distributed in real time is to interrupt using chip interior, opens without extra resource
Pin；
(4) the method for the present invention principle is simple, does not increase algoritic module newly, realizes convenient for the quick program of star.
Detailed description of the invention
Fig. 1 is the step flow chart of the embodiment of the present invention 1；
Fig. 2 is the step flow chart of the embodiment of the present invention 4.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to implementation of the invention
Mode is described in further detail.
Embodiment 1:
A kind of method of Multi probe star sensor multiple nucleus system task distribution, multiple nucleus system include a main core and it is multiple from
The measurement result of core, each probe is identified by one from core, as shown in Figure 1, including the following steps:
S1, within any period, main core the star chart time of exposure in period estimate it is all from core next period appearance
State, while retrieving all nautical star numbers from core in the case where currently pointing to；Main core obtains all negative within next period from core
Quantity is carried, and is sorted to all from core according to the load number, subsequently into next period.
S2, pass through the interrupt notification master of the main core highest priority of triggering after any completion remained capacity task from core K1
Then core sends the first complement mark amount to main core from core K1, idle state should be entered from core K1 by informing；Main core according to it is described from
The time that core K1 is interrupted obtains the remaining time in this period.
S3, S3, main core obtain the surplus of this period according to the slave core sequence in S1, the remaining time in this period in S2
The remained capacity quantity M that can be completed in the remaining time from core K1, then main core is by load number the highest last M from core K2
Remained capacity task is distributed to from core K1；Finally main core updates all from core row in S1 according to the load number after redistributing
Sequence；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, it is sent to from core K1 by recognition result from core K2.
Main core distributes to the method from core K1 from the last M remained capacity task of core K2 for load number is highest are as follows:
Then main core triggering will be distributed from the highest priority interrupt of core K1 from the last M remained capacity task of core K2
To from core K1；Meanwhile main core record is corresponding relationship from core K1 and from core K2；
When from core K1 by the last M remained capacity task from core K2 after the completion of, again by triggering main core highest
Then the main core of the interrupt notification of priority sends the second complement mark amount and remained capacity result to main core from core K1；Main core is logical
According to the second complement mark amount, corresponding relationship, will be sent to from the remained capacity result of core K1 from core K2；Pass through from core K2
Cyclic query mode obtains the remained capacity result completed from core K1.
S4, S2~S3 is repeated, is completed until all from the remained capacity task of core.
The main core each period is recorded by mask register at the beginning of, it is any from core K1 complete remained capacity appoint
The current time of business, the time in each period.
Embodiment 2:
A kind of method of Multi probe star sensor multiple nucleus system task distribution, multiple nucleus system include a main core and it is multiple from
The measurement result of core, each probe is identified by one from core, is included the following steps:
S11, within any period, main core in the star chart time of exposure in period all postures from core in next period,
All nautical star numbers from core in the case where currently pointing to are retrieved simultaneously；Main core obtains all load numbers from core within next period
Amount, and tentatively sorted to all from core according to the load number.
S12, in the slave core of all sequences, the load number and load number of the most slave core of load number it is least from
The ratio between load number of core is more than or equal to 3, and the load number of the slave core of load number at most is more than or equal to default basic load
When quantity, by at least one third of the remained capacity task of the most slave core of load number distribute to load number it is least from
Core.
S13, other least from other than core of the most slave core of load number and load number are ranked up from core, so
S12 is repeated afterwards, is less than or equal to 1 until participating in the quantity of slave core of sequence, main verification is according to each from the load number of core to institute
Have from core and finally sorted, subsequently into next period.
S14, pass through the interrupt notification master of the main core highest priority of triggering after any completion remained capacity task from core K1
Then core sends the first complement mark amount to main core from core K1, idle state should be entered from core K1 by informing；Main core according to it is described from
The time that core K1 is interrupted obtains the remaining time in this period.
S15, main core are obtained in this period and are born according to the final sequence in S13, the remaining time in this period in S12
The quantity for carrying the highest maximum load identification that can be completed within this period from core K2 of quantity, judges load number in this period
The highest all remained capacity tasks that whether can be completed within this period from core K2 from core K2, if can be complete from core K2
At being then transferred to S17；Otherwise, the slave core K2 remained capacity task that main core will exceed maximum load identification quantity distribute to from
Core K1；Finally main core updates all final sequences from core in S13 according to the load number after redistributing；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, it is sent to from core K1 by recognition result from core K2.
It will exceed the maximum load and identify that the slave core K2 remained capacity task of quantity distributes to the method from core K1 are as follows:
Then main core triggering will exceed the slave core K2 of the maximum load identification quantity from the highest priority interrupt of core K1
Remained capacity task is distributed to from core K1；Meanwhile main core record is corresponding relationship from core K1 and from core K2；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, again by the main core highest priority of triggering
It is open close to know main core, then the second complement mark amount and remained capacity result are sent to main core from core K1；Main core is logical according to described the
Two complement mark amounts, corresponding relationship will be sent to from the remained capacity result of core K1 from core K2；Pass through cyclic query side from core K2
Formula obtains the remained capacity result completed from core K1.
S16, S14~S15 is repeated；It is transferred to S17；
S17, it is all from the remained capacity task of core complete.
The main core each period is recorded by mask register at the beginning of, it is any from core K1 complete remained capacity appoint
The current time of business, the time in each period.
Embodiment 3:
A kind of computer storage readable medium, is stored thereon with computer program, when which is executed by processor, realizes
The step of above-mentioned Multi probe star sensor multiple nucleus system method for allocating tasks.
Embodiment 4:
A method of it is distributed for Multi probe star sensor multiple nucleus system task, as shown in Fig. 2, including the following steps:
(1) in Multi probe star sensor multiple nucleus system, main core each cycle is in fixed time (when the period star chart exposes
Carve) to the posture for respectively estimating next period from core, when estimating posture, needs are retrieved the current optical axis that should should pop one's head in from verification and are directed toward
Under nautical star, the nautical star number of retrieval can reflect the loading condition from the lower Periodic identification task of core, nautical star number
It is more more, it should need to be observed star from a core lower period and the number of nautical star template matching is more, be loaded from core heavier；This
When record each nautical star number that day area is currently pointed to from core, and by will sort from high to low from core；
(2) it respectively starts to work (after each cycle star chart end exposure) in the same time from core and main core each cycle, main core each cycle
The time of reading processor mask register record period start time when start-up operation；Identification mission respectively is carried out simultaneously from core,
When certain is completed from core identification mission, the interruption of the main core highest priority of its forced-triggered is enabled, and main core is notified by mark amount
Idle state should be entered from core；
Elder generation's reading processor mask register obtains current time when main core enters interrupt service routine, before being subtracted with it
Time start time in period of record obtains current period time-consuming, and it is surplus to subtract the time-consuming acquisition period with frame cycle time
The remaining time acquires in the period remaining time and the ratio of time-consuming；
(3) main core reads pack heaviest (forecast navigation star number is most) core and currently identifies matching times, due to each from core
Identification matching is time-consuming identical (identification matching is the well-known technique that triangle map algorithm is those skilled in the art) every time, by this
Matching times are time that at most may be matched the remaining time in period asked multiplied by remaining time and the ratio of time-consuming
Number；The number is subtracted into certain surplus and obtains times N, is that can also be identified within remaining time in this period from core the free time
The n times backmost that the slave core of pack heaviest is carrying out matching sequence are dumped to a new matching sequence, newly by matched number
Matching sequence will be distributed to idle from core processing；
New matching sequence from the highest priority interrupt of core, is passed to this from core, is somebody's turn to do from core by the main core forced-triggered free time
Match cognization task is done in its interrupt service routine；The two cores are done corresponding relationship record by main core at this time, and by before
Load sequence is set to the most heavy task of present load in second task；Main core exits interrupt service routine；
The slave core for the task of being assigned triggers main core highest priority interrupt after finishing match cognization task again, and by not
Main core is notified with mark amount；Interrupt service routine is exited from core；What main core recorded before reading will identify from internuclear corresponding relationship
As a result another is passed to from core, should obtain required recognition result from core by cyclic query mode；
(4) task of load sequence before second is set to load sequence highest by main core, other from core completion one when having
Identification mission notifies main core to continue by step (2), (3) by present load highest when interrupting by way of interruption in period
Business, which is distributed to, currently to be triggered the free time that main core interrupts and is handled from core；
It is actually passed through embedded system test, the present invention can be reduced largely from the operating condition of vouching Periodic identification task time-out.
The content that description in the present invention is not described in detail belongs to the well-known technique of those skilled in the art.
Claims (13)
1. a kind of method of Multi probe star sensor multiple nucleus system task distribution, multiple nucleus system include a main core and it is multiple from
The measurement result of core, each probe is identified by one from core, characterized by the following steps:
S1, within any period, main nuclear energy enough obtains all load numbers from core within next period, and according to the load
Quantity sorts to all from core, subsequently into next period；
S2, pass through the interrupt notification main core for triggering main core after any completion remained capacity task from core K1, main core is according to
The time interrupted from core K1 obtains the remaining time in this period；
S3, main core obtain in the remaining time in this period according to the slave core sequence in S1, the remaining time in this period in S2
The remained capacity quantity M that can be completed from core K1, then main core is by the highest last M remained capacity from core K2 of load number
Task is distributed to from core K1；Finally main core updates all from core sequence in S1 according to the load number after redistributing；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, it is sent to from core K1 by recognition result from core K2；
S4, S2~S3 is repeated, is completed until all from the remained capacity task of core.
2. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 1, it is characterised in that:
In S1, main core each cycle estimates all postures from core in next period in fixed time, while retrieving and all working as from core
Nautical star number under preceding direction；It is each the load number from core from the corresponding nautical star number of core.
3. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 2, it is characterised in that:
Main core each cycle the star chart time of exposure in period estimate it is all from core next period posture.
4. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 1, it is characterised in that:
In S2, pass through the main core of interrupt notification for triggering main core highest priority after completing remained capacity task from core K1, then from core K1
The first complement mark amount is sent to main core, idle state should be entered from core K1 by informing.
5. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 1, it is characterised in that:
The main core each period is recorded by mask register at the beginning of, it is any from core K1 complete remained capacity task it is current
Time, each period time.
6. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 4, it is characterised in that:
Main core described in S3 distributes to the method from core K1 from the last M remained capacity task of core K2 for load number is highest are as follows:
The triggering of main core from the highest priority interrupt of core K1, then by from the last M remained capacity task of core K2 distribute to from
Core K1；Meanwhile main core record is corresponding relationship from core K1 and from core K2；
When from core K1 by the last M remained capacity task from core K2 after the completion of, again by triggering, main core highest is preferential
Then the main core of interrupt notification of grade sends the second complement mark amount and remained capacity result to main core from core K1；Main core leads to basis
The second complement mark amount, corresponding relationship will be sent to from the remained capacity result of core K1 from core K2；Pass through circulation from core K2
Inquiry mode obtains the remained capacity result completed from core K1.
7. a kind of method of Multi probe star sensor multiple nucleus system task distribution, multiple nucleus system include a main core and it is multiple from
The measurement result of core, each probe is identified by one from core, characterized by the following steps:
S11, within any period, main nuclear energy enough obtains all load numbers from core within next period, and according to described negative
Quantity is carried tentatively to be sorted to all from core；
S12, in the slave core of all sequences, the load number and load number of the most slave core of load number are least from core
The ratio between load number is more than or equal to 3, and the load number of the slave core of load number at most is more than or equal to default basic load quantity
When, it is least from core that at least one third of the remained capacity task of the most slave core of load number is distributed into load number；
S13, other least from other than core of the most slave core of load number and load number are ranked up from core, are then weighed
Multiple S12 is less than or equal to 1 until participating in the quantity of slave core of sequence, main verification basis each from the load number of core to it is all from
Core is finally sorted, subsequently into next period；
S14, pass through the interrupt notification main core for triggering main core after any completion remained capacity task from core K1, main core is according to
The time interrupted from core K1 obtains the remaining time in this period；
S15, main core obtain according to the final sequence in S13, the remaining time in this period in S12 and load number in this period
The quantity for measuring the highest maximum load identification that can be completed within this period from core K2, judges load number highest in this period
Slave core K2 all remained capacity tasks from core K2 whether can be completed within this period, if can be completed from core K2,
It is transferred to S17；Otherwise, the slave core K2 remained capacity task that main core will exceed the maximum load identification quantity is distributed to from core K1；
Finally main core updates all final sequences from core in S13 according to the load number after redistributing；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, it is sent to from core K1 by recognition result from core K2；
S16, S14~S15 is repeated；It is transferred to S17；
S17, it is all from the remained capacity task of core complete.
8. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 7, it is characterised in that:
In S11, main core each cycle estimates all postures from core in next period in fixed time, while retrieving and all working as from core
Nautical star number under preceding direction；It is each the load number from core from the corresponding nautical star number of core.
9. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 8, it is characterised in that:
Main core each cycle the star chart time of exposure in period estimate it is all from core next period posture.
10. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 7, feature exist
In: it will exceed the maximum load described in S15 and identify that the slave core K2 remained capacity task of quantity distributes to the method from core K1
Are as follows:
Then main core triggering will exceed the slave core K2 load of the maximum load identification quantity from the highest priority interrupt of core K1
Identification mission is distributed to from core K1；Meanwhile main core record is corresponding relationship from core K1 and from core K2；
It is described after the completion of core K2 remained capacity task when being incited somebody to action from core K1, it is open close in main core highest priority again by triggering
Know main core, then sends the second complement mark amount and remained capacity result to main core from core K1；Main core is logical complete according to described second
At mark amount, corresponding relationship, will be sent to from the remained capacity result of core K1 from core K2；It is obtained from core K2 by cyclic query mode
Obtain the remained capacity result completed from core K1.
11. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 7, feature exist
In: in S14, from core K1 complete remained capacity task after by triggering the main core of interrupt notification of main core highest priority, then from
Core K1 sends the first complement mark amount to main core, and idle state should be entered from core K1 by informing.
12. a kind of method of Multi probe star sensor multiple nucleus system task distribution according to claim 7, feature exist
At the beginning of: the main core records each period by mask register, any remained capacity task is completed from core K1
Current time, the time in each period.
13. a kind of computer stores readable medium, it is stored thereon with computer program, it is characterised in that: the program is by processor
When execution, the step of realizing one of claim 1~12 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910636830.6A CN110413409B (en) | 2019-07-15 | 2019-07-15 | Method and medium for task allocation of multi-probe star sensor multi-core system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910636830.6A CN110413409B (en) | 2019-07-15 | 2019-07-15 | Method and medium for task allocation of multi-probe star sensor multi-core system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110413409A true CN110413409A (en) | 2019-11-05 |
| CN110413409B CN110413409B (en) | 2021-08-10 |
Family
ID=68361440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910636830.6A Active CN110413409B (en) | 2019-07-15 | 2019-07-15 | Method and medium for task allocation of multi-probe star sensor multi-core system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110413409B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011090776A1 (en) * | 2010-01-19 | 2011-07-28 | Mindspeed Technolgies, Inc. | Highly distributed parallel processing on multi-core device |
| CN102681902A (en) * | 2012-05-15 | 2012-09-19 | 浙江大学 | Load balancing method based on task distribution of multicore system |
| CN105700959A (en) * | 2016-01-13 | 2016-06-22 | 南京邮电大学 | Multi-core platform oriented multithreaded division and static balancing scheduling policy |
| CN106598731A (en) * | 2016-12-01 | 2017-04-26 | 上海交通大学 | Heterogeneous multi-core architecture-based runtime system and control method thereof |
-
2019
- 2019-07-15 CN CN201910636830.6A patent/CN110413409B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011090776A1 (en) * | 2010-01-19 | 2011-07-28 | Mindspeed Technolgies, Inc. | Highly distributed parallel processing on multi-core device |
| CN102681902A (en) * | 2012-05-15 | 2012-09-19 | 浙江大学 | Load balancing method based on task distribution of multicore system |
| CN105700959A (en) * | 2016-01-13 | 2016-06-22 | 南京邮电大学 | Multi-core platform oriented multithreaded division and static balancing scheduling policy |
| CN106598731A (en) * | 2016-12-01 | 2017-04-26 | 上海交通大学 | Heterogeneous multi-core architecture-based runtime system and control method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110413409B (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3847549B1 (en) | Minimizing impact of migrating virtual services | |
| CN112162865B (en) | Scheduling method and device of server and server | |
| CN103516536B (en) | Server service request parallel processing method based on thread number limit and system thereof | |
| CN109918198A (en) | A kind of emulation cloud platform load dispatch system and method based on user characteristics prediction | |
| CN108536592B (en) | Test task assignment method and device and server | |
| CN108829494A (en) | Container cloud platform intelligence method for optimizing resources based on load estimation | |
| CN110008024B (en) | Container scheduling method and device based on delay decision under multidimensional constraint | |
| CN110287245A (en) | Method and system for scheduling and executing distributed ETL (extract transform load) tasks | |
| CN103699433B (en) | One kind dynamically adjusts number of tasks purpose method and system in Hadoop platform | |
| CN110347602B (en) | Method and device for executing multitasking script, electronic equipment and readable storage medium | |
| CN108763093A (en) | A kind of automated testing method and system | |
| CN106844027A (en) | A kind of method for scheduling task based on node load | |
| CN110334157A (en) | A kind of cloud computing management system | |
| CN112052081A (en) | Task scheduling method and device and electronic equipment | |
| CN115220898A (en) | Task scheduling method, system, device and medium based on deep reinforcement learning | |
| CN104346220B (en) | A kind of method for scheduling task and system | |
| CN115237568A (en) | Mixed weight task scheduling method and system for edge heterogeneous equipment | |
| Ruan et al. | A comparative study of large-scale cluster workload traces via multiview analysis | |
| CN111367632B (en) | Container cloud scheduling method based on periodic characteristics | |
| CN110084507A (en) | The scientific workflow method for optimizing scheduling of perception is classified under cloud computing environment | |
| CN110413409A (en) | A kind of method and medium of the distribution of Multi probe star sensor multiple nucleus system task | |
| CN106686619B (en) | Performance evaluation method and equipment | |
| CN115185685B (en) | Task scheduling method, device, computer equipment and storage medium | |
| CN110716875A (en) | Concurrency test method based on feedback mechanism in domestic office environment | |
| CN107634978A (en) | A kind of resource regulating method and device |
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 |