EP1997005A1 - Verfahren zur erstellung eines optimierten ablaufplans für ein zeitgesteuertes verteiltes rechnersystem - Google Patents
Verfahren zur erstellung eines optimierten ablaufplans für ein zeitgesteuertes verteiltes rechnersystemInfo
- Publication number
- EP1997005A1 EP1997005A1 EP07722970A EP07722970A EP1997005A1 EP 1997005 A1 EP1997005 A1 EP 1997005A1 EP 07722970 A EP07722970 A EP 07722970A EP 07722970 A EP07722970 A EP 07722970A EP 1997005 A1 EP1997005 A1 EP 1997005A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- elements
- class
- dependency
- ftcom
- coordinated
- 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.)
- Ceased
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
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- 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
Definitions
- the invention relates to a method for creating an optimized schedule for performing a functionality by means of a time-controlled distributed computer system, the distributed computer system and the functionality having a set of - in particular structural and functional - elements of at least one element class and the elements - at least partially - to be dependent.
- the invention further relates to a directed to the implementation of the method computer program.
- Data channel the extensibility in terms of architecture and functionality, the security or fault tolerance of the communication and the secure scheduling of the functionality implemented on the distributed computer system, but also with regard to the physical transmission medium of the data channel.
- various systems have emerged over time, which meet these requirements in very different degrees; Examples include LIN, CAN, TTCAN, MOST, Bluetooth, Byteflight, TTP and FlexRay.
- the computing nodes of the distributed computer system can be any technical units that are capable of performing calculations in the general sense by electronic means;
- the computing nodes may be control devices with connected sensors and actuators, as well as significantly less powerful field devices of a simple home installation system or extremely powerful modules of a simulation computer.
- time-controlled distributed computer systems such as TTCAN (time-triggered CAN), TTP (Time-Triggered Protocol) and FlexRay are used whose time response.
- TTCAN time-triggered CAN
- TTP Time-Triggered Protocol
- FlexRay FlexRay
- the communication over the data channel of a time-controlled distributed computer system can also happen at certain time intervals.
- be controlled that is, random events and processes can arbitrarily occupy the data channel at certain, well-defined time intervals (time slices, slots), the assignment of the data channel for information exchange between the computing nodes of the distributed computer system is firmly scheduled in the other time intervals.
- time-controlled distributed computer systems are particularly suitable for the realization of discrete-time sampling systems, which is based on the strictly periodic sequence of receiving current input values - in particular other computational nodes - the calculation of output values / signals and the output of the output values.
- the specification of the temporal behavior of a time-controlled computer system usually takes place by means of a schedule, in which it is precisely determined which elements of the distributed computer system execute which elements of the functionality to be performed by means of the computer system in which specific time sequence.
- Object of the present invention is to avoid - at least partially - the disadvantages shown in the creation of an optimized schedule for distributed computer systems.
- the object indicated is according to the invention initially and essentially in a method for creating an optimized flowchart for performing a functionality by means of a time-controlled distributed computer system, wherein the distributed computer system and the functionality have a set of elements of at least one element class and the elements - at least partially - in Dependence, solved by that the dependencies between the elements are recognized, classified and the elements are assigned to corresponding dependency classes and the flowchart is optimized by coordinating elements of at least one dependency class.
- the method according to the invention is preceded by an analysis of the elements of the distributed computer system and of the elements of the functionality to be performed on the distributed computer system.
- the elements of the distributed computer system are, for example, its computing node and possibly separate addressable subunits of the compute nodes, such. I / O groups, CPU, communication controllers and data channel interfaces.
- the elements of the functionality to be executed on the distributed time-controlled computer system are functional modules which, for example, relate to the calculation of an application - such as a control algorithm or the execution of time-controlled communication - time-controlled transmission and reception of messages - with other computing nodes of the distributed computer system.
- These structural and functional elements can be assigned to corresponding element classes; For example, all functional elements responsible for sending a signal form the element class of the transmit functions and all the elements responsible for computing an application on a compute node are the element class of the application functions.
- the inventive method is not fixed or limited to certain element classes, but the formation of very different and arbitrary element classes is possible, the definition of element classes is incumbent on the user of the method according to the invention.
- the elements of the element classes can be dependent on each other, ie in a certain - or none - relation to each other; this can apply to elements from the same element class as well as elements from different element classes.
- elements from the element class of application functions are dependent on each other when the output value calculated using a first application function serves as an input value of another application function. It is therefore possible to distinguish between the dependency class of the application functions which use as input value the output value of another application function and the dependency class of those application functions which are not dependent on any such input value.
- coordination of elements generally means the processes a) modification of a compilation / combination of elements, b) evaluation of the modification and c) selection of a modification (s).
- the modification of a collection of elements can only be a time - or local - resorting of elements represent, but this can also be the summary of compiled elements to a new element.
- the modification of a collection of elements per se is predetermined by the optimization method itself in the case of deterministic optimization methods.
- stochastic optimization methods and also genetic algorithms are used, several changes are made in the composition of elements by random event, whereupon the modifications obtained are obtained by applying a quality criterion. to be evaluated. Finally, the best optimization result or the best optimization results are successively improved in a further coordination step.
- quality criterion for optimizing a schedule by coordinating elements, and the selection of a corresponding quality criterion ultimately depends on the design goals that are considered relevant for the creation of an optimized schedule.
- Possible quality criteria can be based, for example, on the bus utilization, the period of the schedule, the number of messages to be transmitted, the number of computation nodes required and the worst-case execution time of the functionality to be executed on the computer system or of the computation node subfunctionalities.
- the method is carried out such that the elements of at least one dependency class are fully coordinated before the elements of another dependency class are coordinated.
- “Complete” is not to be understood as absolute, since it can happen that not all elements can actually be coordinated; is therefore fully understood in the sense of "complete, as far as practicable or as far as the problem allows”.
- the clarity of the flowchart optimization achieved by the method according to the invention is consistently continued by coordinating meaningful subsets of elements (dependency classes). If this procedure moves from the coordination of a dependency class to a new dependency class, then the elements of already coordinated dependency classes no longer have to be considered in the coordination; they are equally treated as fixpoints in the partially devised workflow.
- the elements originating from one and the same element class are coordinated separately.
- This approach has proven particularly advantageous for certain element classes, for example wise in the coordination of similar communication functions. It is useful when multiple transmit functions from identical nodes to identical nodes within overlapping time intervals send messages packed in messages. In this case, not every signal has to be sent separately with its own message via the data channel, but it offers the combination of several signals in a single message, which can be sent with a single send function, provided that the sum signal in one single message (frame).
- the method according to the invention is then to be carried out in a particularly clear manner if the optimization is carried out iteratively within at least one dependency class, wherein in each step only one selection - that is to say a subset - of elements of the dependency class is coordinated.
- so many iteration steps are carried out until all elements of the dependency class are coordinated or until no further elements of the dependency class can be more coordinated; it depends on the problem, whether all elements can be coordinated.
- Defining the first set of elements of the dependency class limits the theoretically achievable set of solutions, since it is not possible to coordinate - exchange, map, merge - elements of the first selection from the dependency class and elements of subsequent subsets from the dependency class .
- a larger number of solutions from the total solution set of an optimized schedule can be achieved if the coordination within an iteration step is carried out several times with a different element selection from a dependency class and the following iteration steps are continued with that coordinated element selection, which has achieved the best optimization result in the previous iteration steps.
- the final optimization result of the flowchart in this variant of the method according to the invention can be better than if only one single element selection is used in each iteration step; in return, correspondingly higher maturities for the implementation of the procedure can be expected.
- consistency checks are carried out with respect to the achieved (partial) result during the optimization of the flowchart, which are directed in particular at verifying compliance with predetermined and / or system-inherent boundary conditions. For example, it may be specified by the user that a specific application function is to be calculated on a specific computing node of the computer network, which may be useful, for example, if the result of the calculation of these application functions is via a specific I / O interface of the computer relevant computing node is to be output directly, for example because only this compute node has this I / O interface. If the consistency check fails, the preceding optimization or coordination step is discarded and replaced by a further, modified coordination step.
- the elements or a selection of the elements of the distributed time-controlled computer system or the functionality to be implemented on the computer system are assigned to the class of simple dependencies or the class of complex dependencies.
- a simple dependency there are all those elements that do not depend on one state or one output value of the other element. For example, if two application functions feed only a third application function, then the two application functions are in a simple dependency relationship. However, if a first application function indirectly feeds a third application function via a second application function, then the first and second application functions are in a complex dependency relationship.
- the method according to the invention is used with a distributed time-controlled computer system based on the FlexRay standard and comprising at least two computational nodes connected via a FlexRay bus, the element classes used for optimizing the flowchart including at least one of the classes FTCom, Transmission, application task, signals, messages and compute nodes, where the class of FTCom tasks is divided into the classes FTCom-Sender and FTCom-Receiver-Task.
- the terms used are common names of the hardware and software components of a FLEXRAY system.
- FTCom tasks are used to write / read messages from the node to / from the buffer of the communication controller, the one
- Compute node is assigned, whereas transmission tasks of Busseiti- transmission of messages.
- the term "task” here is not to be understood as meaning the task of an operating system, ie the smallest unit which can be planned and executed by the operating system, but rather can be understood here as an abstract function Planning individually as a task (an operating system) or several functions together - just after coordination - as a task (an operating system) are executed.
- each FlexRay system signal is assigned its own FlexRay message, which is linked to its own FTCom task to prepare coordination. Only then are maximum degrees of freedom for the optimization of the schedule guaranteed.
- FTCom tasks are assigned to the dependency class of the simple dependencies and coordinated if they are of the same type (FTCom transmitter or FTCom receiver), if they can be assigned to the same application node and if they are identical pairs have transmitting and receiving compute nodes or have identical transmitting and receiving nodes.
- FTCom tasks that have these properties are coordinated if their start times match
- FTCom tasks can be assigned to the dependency class of the complex dependencies and coordinated if they are of the same type (FTCom transmitter or FTCom receiver) as before, if they can be assigned to the same application node and if their startup Overlap time intervals.
- FTCom tasks are therefore only coordinated if their start times do not deviate from one another by a specific amount, wherein this amount can be specified, for example, by the user of the method; in the simplest case, the match of the start times is required.
- transmission tasks can be assigned to the dependency class of the simple dependencies and coordinated, if first their common signals do not exceed the maximum length of a FlexRay message; the length of a FlexRay message is not arbitrary, but rather predetermined by the FlexRay protocol, where in a FlexRay message multiple signals can be bundled, the FlexRay message so to speak a frame for several signals to be transmitted , An assignment to the dependency class of the simple dependencies takes place especially when the transmission tasks additionally have the same start times.
- transmission tasks can be assigned and coordinated to the dependency class of the complex dependencies if their common signals do not exceed the maximum length of a FlexRay message (frame), if they can be assigned to identical transmitting application nodes and if they have overlapping start time intervals ,
- the coordination of transmission tasks is also linked to their start times. In this case, transmission tasks are coordinated if their start times do not deviate from each other by more than an amount specified by the user, for example.
- the invention also relates to a computer program for carrying out the method steps described above when the program is executed on a data processing system.
- FIG. 2 is a schematic representation of a flowchart for a distributed time-controlled computer system
- Fig. 5 shows the optimization of a flow chart according to a last preferred embodiment of the method according to the invention.
- FIG. 1 shows a schematic overview of the essential components of the method according to the invention, which is usually carried out by a data processing system and with the aid of which an optimized sequence plan P for carrying out a functionality can be created by means of a time-controlled distributed computer system (not shown).
- the distributed computer system and the functionality have a set of structural and functional elements ej , ,, e 2) , which in the present case are associated with only two element classes Ei, E 2 .
- the elements ej jl5 e 2jl describe the distributed time-controlled computer systems and the functionality to be implemented by the computer systems.
- the elements e ⁇ , e 2i can be dependent on each other, whereby in the general case the dependencies can also exist between elements ei "e 2> , different element classes.
- the elements ej _ "e 2] I in the form of database entries in a database 1 a known.
- a first method step Ib the dependencies between the elements ei "e 2jl are recognized, the dependencies are classified, and the elements ei" e 2jl are assigned to corresponding dependency classes Ai, A 2 .
- element class E is the class of application functions-symbolized by triangles-and element class E 2 is the class of the computational nodes of the time-controlled distributed computer system-symbolized by squares.
- the optimization of the flowchart P is shown schematically, which takes place by coordinating elements ⁇ i , i > e 2, i of at least one dependency class A 1 ;
- the optimization in the second method step Ic takes place by coordinating the elements ej , "e 2i , which belong to the dependency class A].
- the coordination of elements essentially means the resorting, assigning and merging of elements e, wherein in the exemplary embodiment illustrated in FIG. 1 the coordination of the elements ei , i, e 2il is achieved by rearranging the elements e 1, (application Functions) from the dependency class Ai in the flowchart P 'and assigning these elements to the elements e 2jl (compute node ) consists of the dependency class Ai.
- the method illustrated in FIG. 1 is also configured such that the elements ei "e 2, of the dependency class Ai are fully coordinated, before the elements e ⁇ e ,, 2j, the further dependence class A 2 are coordinated.
- the coordination of the elements ei "e 2> 1 is effected by an optimization method which has both deterministic and stochastic elements.
- “Deterministic” because the determination of which elements are co-ordinate is tied to fixed rules or conditions, “stochastic", because, for example, the selection of elements that are checked for co-ordinability is one random selection is.
- Several acquired variants P 'of a flowchart P are then evaluated by a quality criterion, which, however, is not shown in detail.
- the optimization is completed or aborted, finally there is an optimized flow chart P as a result of the method used, see method step Id.
- the time bus utilization is used as a quality criterion for the calculation of an optimal solution.
- the quality criterion is based on the period of the schedule P, the number of messages to be transmitted, the number of required computational nodes and the worst-case execution time of the overall functionality or the partial functionality in other, not shown embodiments of the inventive method on the compute node.
- FIG. 2 For a better understanding of FIGS. 1, 3 and 5, a flowchart P is shown in FIG. 2, which is frequently used in time-controlled distributed computer systems.
- the time axis t is subdivided into time intervals S) -S 5 , wherein the extent of these time intervals SpS 5 is fixed or must be fixed.
- the ordinate is also subdivided into different sections B, ei i, ei i2, and ei > 3 , the lowest section B symbolizing the communication on the data channel of the time-controlled distributed computer system and the sections e ⁇ i, e 1> 2, and ei > 3 characterize the planned activity on other elements of the distributed computer system - that is, on the compute node.
- Fig. 2 is further shown that two application functions e 2i i, e 2 2 are performed on the node Q ⁇ j and a send function e 3 with a message that is prepared at the end of the time interval S 2 , in Time interval S 3 occupied the data channel B.
- the transmission function e 5 is responsible for the transmission of the message from the node ei j via the data channel B to the node e ] 3 .
- a receive function e 4 executed on the computation node ei ; 3 receives this message, which is then further used by an application function e 2> 3 accommodated on the same compute node.
- the elements e 2> i, e 2 2 and e 2> 3 in FIG. 2 are application tasks, in the elements e 3 and e 4 are FTCom tasks (more precisely a FTCom transmitter and an FTCom receiver task), which have the task to write a message to be sent / received by a computational node in the buffer of the communication controller of the computational node or to read from this buffer.
- Element e 5 is a transmission task responsible for transmitting a message via the timed FlexRay bus.
- the exemplary embodiment illustrated in FIG. 3 shows a similar starting situation to the exemplary embodiment in FIG. 1.
- the database 3 a has the elements ei "e 2i , which can be assigned to the element classes Ei, E 2 .
- a first method step 3b the dependencies between the elements ei "e 2jl are recognized, classified, and the elements ei" e 2, 1 are then assigned to the dependency classes Ai, A 2 .
- the method according to FIG. 3 differs from the method from FIG. 1 in the subsequent method step 3c.
- the method step 3c of FIG. 3 is characterized in that in the coordination of the elements e lil5 e 2 l of the dependency class Ai initially only the elements ei > ls e 2jl from one of the element classes Ei, E 2 , here element class El, separately coordinates before the elements of another element class are coordinated.
- the three elements C 1 from the dependency class A 1 coordinated, the coordination of the temporal rearrangement and summary (black filled triangles) of these elements e ⁇ includes.
- the elements e 2; (Squares) from the dependency class A) coordinated.
- the dependency classes Aj comprise at least the class of simple dependencies and the classes of complex dependencies, the coordination of the elements of the class of simple dependencies prior to the coordination of the Elements of the class of complex dependencies occurs.
- Fig. 4 illustrates the concept of simple and complex dependency.
- Fig. 4a shows three elements ei j , ei 2 and e ⁇ , which are related to each other, namely such that the elements ej j and ei 2 each apply a signal to the element e ⁇ .
- the elements e ]; i and ei 2 can be executed independently of each other because there is no compulsory processing order between them. Only if there is a deadline for the processing time of element e 1 3 , the elements ei i and e ⁇ must before this time (minus the worst-case execution time of element e ); 3 and the message transfer between e ⁇ , e ⁇ and e ⁇ ) are executed.
- Such elements are in the relationship of a simple dependency, because they are not dependent on one state or one output value of the other element.
- the elements ei j , e ⁇ and e 1> 3 shown in FIG. 4b are in a complex dependency, since their processing sequence necessarily results from the specified interaction of the elements: first element eu and subsequently element ei > 2 must be calculated before finally element e 1 3 can be calculated. In this case, the elements can not be arbitrarily coordinated.
- FIG. 5 shows a further exemplary embodiment of the method according to the invention.
- the boundary conditions R can, for example, fixed assignments of application functions to compute nodes, maximum periods for the re-execution of a specific functionality, absolute distances between the execution of certain (sub) functionalities and many other requirements are more.
- Other boundary conditions are none Specifications in the true sense, but simply based on given features of the time-controlled distributed computer system, such. As the ever-limited computing power of a computing node or the limited transmission capacity of the data channel over which messages between computational nodes are exchanged.
- a first method step 5b in FIG. 5 the elements e, in a known manner associated with dependency classes A 1 , in the case shown the class of the simple dependencies A] and the class of complex dependencies A 2 .
- a dependency class A 1 in the present case the elements of the class of simple dependencies Ai, are coordinated K (Ai).
- the coordination can be carried out in one step, or iteratively in several steps.
- each achieved partial solution P 1 of the optimized schedule P is examined for violation of the boundary conditions R. If there is a violation of the boundary conditions R, the conflicting partial solution P 1 is discarded and the process for coordinating K (A]) of the elements of the dependency class Ai returns via a loop 5h.
- the loop 5h is also used when a partial solution P 'for the flow chart P is free from conflict, but not all the desired elements e, the dependency class A
- the method according to FIG. 5 provides for the coordination of the elements of FIG Dependency class Ai to return via loop 5j, there to calculate a further partial solution P 1 of the flowchart P, which in turn as a starting position for calculating a solution of the flowchart P in the process steps 5e and 5f.
- Result of the method is a created and optimized flow chart P, which is stored in the illustrated embodiment in a database 5g.
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multi Processors (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102006010400.5A DE102006010400B4 (de) | 2006-03-03 | 2006-03-03 | Verfahren zur Erstellung eines optimierten Ablaufplans für ein zeitgesteuertes verteiltes Rechnersystem |
PCT/EP2007/001717 WO2007101590A1 (de) | 2006-03-03 | 2007-02-28 | Verfahren zur erstellung eines optimierten ablaufplans für ein zeitgesteuertes verteiltes rechnersystem |
Publications (1)
Publication Number | Publication Date |
---|---|
EP1997005A1 true EP1997005A1 (de) | 2008-12-03 |
Family
ID=38109158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP07722970A Ceased EP1997005A1 (de) | 2006-03-03 | 2007-02-28 | Verfahren zur erstellung eines optimierten ablaufplans für ein zeitgesteuertes verteiltes rechnersystem |
Country Status (5)
Country | Link |
---|---|
US (1) | US8271984B2 (de) |
EP (1) | EP1997005A1 (de) |
JP (1) | JP5404060B2 (de) |
DE (1) | DE102006010400B4 (de) |
WO (1) | WO2007101590A1 (de) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010089900A1 (en) * | 2009-02-05 | 2010-08-12 | Nec Corporation | Method, system and program for deadline constrained task admission control and scheduling using genetic approach |
US9069730B2 (en) * | 2009-06-29 | 2015-06-30 | Hewlett-Packard Development Company, L. P. | Coordinated reliability management of virtual machines in a virtualized system |
US8973010B2 (en) * | 2010-05-28 | 2015-03-03 | Varian Medical Systems International, AG | Scheduling image recognition tasks based on task dependency and phase |
WO2012146406A1 (en) | 2011-04-23 | 2012-11-01 | Deubzer Michael | Method for the design evaluation of a system |
DE102012005197B3 (de) | 2012-03-16 | 2013-06-13 | Iav Gmbh Ingenieurgesellschaft Auto Und Verkehr | Verfahren zur Optimierung einer Brennkraftmaschine |
US9483544B2 (en) | 2012-05-25 | 2016-11-01 | Crimson Hexagon, Inc. | Systems and methods for calculating category proportions |
US20170206184A9 (en) * | 2013-05-06 | 2017-07-20 | Sas Institute Inc. | Techniques to perform curve fitting for statistical tests |
EP3111600B1 (de) | 2014-02-24 | 2018-11-14 | TTTech Computertechnik AG | Verfahren und computernetzwerk zum übertragen von nachrichten |
FR3021108B1 (fr) * | 2014-05-16 | 2016-05-06 | Thales Sa | Procede d'execution de services en temps reel, notamment de gestion de vol et systeme temps reel mettant en oeuvre un tel procede |
DE102014215317A1 (de) * | 2014-08-04 | 2016-02-04 | Siemens Aktiengesellschaft | Verfahren und Serverarchitektur zur Steuerung von Diensten in einer Middleware für eine vereinfachte Kommunikation zwischen auf autonomen Rechnern verteilten, bei der Middleware registrierten oder zu registrierenden Anwendungen technischer Systeme |
EP3007111A1 (de) | 2014-10-10 | 2016-04-13 | Timing-Architects Embadded Systems GmbH | Optimierung Verfahren fur ein Computersystem |
CN110235114B (zh) * | 2017-02-07 | 2023-06-23 | 三菱电机株式会社 | 分散协调系统、设备行动监视装置和家电设备 |
CN113407319B (zh) * | 2021-06-15 | 2022-06-17 | 北京航空航天大学 | 基于Barrelfish的时间触发实时调度方法 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2776338B2 (ja) * | 1995-10-03 | 1998-07-16 | 日本電気株式会社 | ジョブスケジューリング方式 |
US20020087734A1 (en) * | 2000-12-29 | 2002-07-04 | Marshall Donald Brent | System and method for managing dependencies in a component-based system |
DE10291153D2 (de) | 2001-03-15 | 2004-04-15 | Bosch Gmbh Robert | Verfahren und Vorrichtung zur Erstellung eines Zeitplans der Übermittlung von Nachrichten auf einem Bussystem |
SE524201C2 (sv) * | 2002-12-17 | 2004-07-06 | Lars-Berno Fredriksson | Anordning vid distribuerat styr- och övervakningssystem |
US20050138625A1 (en) * | 2003-12-23 | 2005-06-23 | Carroll Timothy J. | Configuration management resource specification database design |
US8171481B2 (en) * | 2004-02-12 | 2012-05-01 | International Business Machines Corporation | Method and system for scheduling jobs based on resource relationships |
JP4401239B2 (ja) * | 2004-05-12 | 2010-01-20 | Necエレクトロニクス株式会社 | 通信メッセージ変換装置、通信方法及び通信システム |
DE602004027024D1 (de) * | 2004-08-05 | 2010-06-17 | Bosch Gmbh Robert | Kommunikationskontrolleur für FlexRay-Netze |
EP1739890A3 (de) * | 2005-06-28 | 2007-07-18 | Tttech Computertechnik AG | Verarbeitung von Datenrahmen, die mittels eines Kommunikationskontrollers über ein zeitgetriggertes System vermittelt werden |
US7548551B2 (en) * | 2005-08-19 | 2009-06-16 | Gm Global Technology Operations, Inc. | System and method of optimizing the bandwidth of a time triggered communication protocol with homogeneous slot sizes |
US7620694B2 (en) * | 2005-09-27 | 2009-11-17 | Intel Corporation | Early issue of transaction ID |
-
2006
- 2006-03-03 DE DE102006010400.5A patent/DE102006010400B4/de active Active
-
2007
- 2007-02-28 JP JP2008557634A patent/JP5404060B2/ja not_active Expired - Fee Related
- 2007-02-28 EP EP07722970A patent/EP1997005A1/de not_active Ceased
- 2007-02-28 WO PCT/EP2007/001717 patent/WO2007101590A1/de active Application Filing
- 2007-02-28 US US12/281,488 patent/US8271984B2/en active Active
Non-Patent Citations (5)
Title |
---|
FARCAS E ET AL: "Transparent distribution of real-time components based on logical execution time", 15 June 2005 (2005-06-15), pages 31 - 39, XP002602362, ISBN: 978-1-58113-527-0, Retrieved from the Internet <URL:http://delivery.acm.org/10.1145/1070000/1065915/p31-farcas.pdf?key1=1 065915&key2=7099855821&coll=GUIDE&dl=GUIDE&CFID=103428590&CFTOKEN=859909> [retrieved on 20100927] * |
FLEXRAY CONSORTIUM: "FlexRay Communications System Protocol Specification V 2.1 Revision A", INTERNET CITATION, 15 December 2005 (2005-12-15), pages 1 - 245, XP002521572 * |
GO: "FlexRay fuer verteilte Anwendungen im Fahrzeug", ELEKTRONIK AUTOMOTIVE, XX, XX, 1 May 2001 (2001-05-01), pages 40 - 43, XP002216067 * |
KOPETZ H ET AL: "MARS: EIN FEHLERTOLERANTES, VERTEILTES ECHTZEITSYSTEM. MARS: A FAULT-TOLERANT DISTRIBUTED REAL-TIME SYSTEM", INFORMATIONSTECHNIK IT, OLDENBOURG VERLAG. MUNCHEN, DE, vol. 30, no. 3, 1 January 1988 (1988-01-01), pages 197 - 208, XP000715968, ISSN: 0179-9738 * |
See also references of WO2007101590A1 * |
Also Published As
Publication number | Publication date |
---|---|
DE102006010400B4 (de) | 2023-04-13 |
JP5404060B2 (ja) | 2014-01-29 |
DE102006010400A1 (de) | 2007-09-06 |
JP2009528644A (ja) | 2009-08-06 |
WO2007101590A1 (de) | 2007-09-13 |
US8271984B2 (en) | 2012-09-18 |
US20100043001A1 (en) | 2010-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102006010400B4 (de) | Verfahren zur Erstellung eines optimierten Ablaufplans für ein zeitgesteuertes verteiltes Rechnersystem | |
Reif | Automobilelektronik | |
EP3538960B1 (de) | Ablaufsteuerung von programmmodulen | |
EP1723750B1 (de) | Verfahren zur Datenkommunikation | |
WO2007073862A1 (de) | Verfahren, kommunikationsnetzwerk und steuereinheit zum zyklischen übertragen von daten | |
DE102007050708A1 (de) | System zum Betreiben wenigstens eines nicht-sicherheitskritischen und wenigstens eines sicherheitskritischen Prozesses | |
EP3417373B1 (de) | Verfahren und vorrichtung zum betreiben eines steuergeräts | |
WO2020108998A1 (de) | Verteilerknoten, automatisierungsnetzwerk und verfahren zum übertragen von telegrammen | |
EP3176696A1 (de) | Verfahren zur realisierung und zum ausführen einer umfangreichen echtzeitcomputeranwendung | |
DE102019201231A1 (de) | Vorrichtung und Verfahren zur Erhöhung einer Verfügbarkeit einer Kommunikationsinfrastruktur | |
EP1428084A2 (de) | Verfahren und vorrichtung zur zeitbestimmung in einem bussystem und bussystem | |
EP1391086B1 (de) | Verfahren und vorrichtung zur erstellung eines zeitplans der übermittlung von nachrichten auf einem bussystem | |
DE102010023071B4 (de) | Verfahren und Netzknoten zur Übertragung ereignisgesteuerter Botschaften | |
EP3025458B1 (de) | Feldbuszugriffseinheit und verfahren zum betreiben derselben | |
WO2014071970A1 (de) | Kaskadiertes feldbussystem | |
EP1320047B1 (de) | Verfahren zur Analyse des Zeitverhaltens komplexer verteilter Systeme | |
EP2169485B1 (de) | Konfigurationseinrichtung zur Konfiguration eines zeitgesteuerten Bussystems | |
DE102008019287B4 (de) | Verfahren zum automatischen Erzeugen eines Zeitschemas für über einen zeitgesteuerten gemeinsamen Datenbus kommunizierende verteilte Anwendungen oder Prozesse eines digitalen Netzwerks | |
DE102004050293B3 (de) | Verfahren zur Simulation des Betriebs eines Netzwerks | |
DE60015032T2 (de) | Verteiltes Echtzeit-Betriebssystem | |
EP3575976A1 (de) | Verfahren zum bestimmen einer physikalischen verbindungstopologie eines für die steuergerätentwicklung eingerichteten, echtzeitfähigen testgeräts | |
EP2507974B1 (de) | Kommunikation zwischen elementen eines systems | |
DE102010038484A1 (de) | Verfahren und Vorrichtung zum Steuern einer Anlage | |
DE102008063276A1 (de) | Verfahren zum Einspielen von Updates in ein System | |
DE102016212291A1 (de) | Modulares gerät für ein modulares system und verfahren zur kommunikation in einem solchen modularen system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20080828 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC NL PL PT RO SE SI SK TR |
|
17Q | First examination report despatched |
Effective date: 20090303 |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: DSPACE DIGITAL SIGNAL PROCESSING AND CONTROL ENGIN |
|
DAX | Request for extension of the european patent (deleted) | ||
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
18R | Application refused |
Effective date: 20150703 |