J. W.-S. Liu, K.-J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of 8th IEEE Real-Time Systems Symposium, December 1987.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....sharing characteristics at the multicast server. In addition to the metrics mentioned above for an adaptor, we propose an extended Quality of Service specification mechanism to specify the Adaptive Quality of Service desired by the application. We introduce the Imprecise Computational Model [4], that suits the QoS requirements of flexible tasks in flexible applications. It is possible to design a wide range of multimedia real time applications so that their tasks are flexible. The output quality of these applications improves while the provided Quality of Service improves. For example, ....

....be composed of a series of flexible tasks, which carry different parts of the responsibilities of the application, and may have their own specific Quality of Service demands. In order to model the QoS demands of these flexible applications or tasks, we apply the Imprecise Computation Model [4] [12] 5] 13] which originated from the research of hard real time scheduling for computational tasks. The essence of the Imprecise Computation Model is to make the scheduling of real time systems easier by dividing the processing of each task and its result in the system into two parts: a ....

J.Y. Chung, J. W.S. Liu, and K. J. Lin. Scheduling Real-Time, Periodic Jobs Using Imprecise Results. IEEE Transactions on Computers, September 1990.

....sharing characteristics at the multicast server. In addition to the metrics mentioned above for an adaptor, we propose an extended Quality of Service specification mechanism to specify the Adaptive Quality of Service desired by the application. We introduce the Imprecise Computational Model [4], that suits the QoS requirements of flexible tasks in flexible applications. It is possible to design a wide range of multimedia real time applications so that their tasks are flexible. The output quality of these applications improves while the provided Quality of Service improves. For example, ....

....be composed of a series of flexible tasks, which carry different parts of the responsibilities of the application, and may have their own specific Quality of Service demands. In order to model the QoS demands of these flexible applications or tasks, we apply the Imprecise Computation Model [4] [12] 5] 13] which originated from the research of hard real time scheduling for computational tasks. The essence of the Imprecise Computation Model is to make the scheduling of real time systems easier by dividing the processing of each task and its result in the system into two parts: a ....

J.Y. Chung, J. W.S. Liu, and K. J. Lin. Scheduling Real-Time, Periodic Jobs Using Imprecise Results. IEEE Transactions on Computers, September 1990.

....processes on different nodes may generate tasks to be executed upon a particular processor. Often, neither the number of tasks to be executed on the processor nor the characteristics of these tasks are known a priori. The method of imprecise computation,introduced by Lin, Liu and Natarajan [4, 5, 6], is a flexible technique for the design of such decentralized real time systems that are subject to occasional overload. In the imprecise computation model, each task is logically decomposed into a mandatory portion followed by an optional portion. The entire mandatory portion must be executed in ....

K. Lin, J. Liu, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of the Real-Time Systems Symposium, San Fransisco, CA, December 1987.

....will beget a better schedule, none of the algorithms display a consistent advantage over the others. This reinforces our approach to address overload scheduling from a structural point of view, rather than simply relying on algorithms, which have limited scope. Imprecise computation technique [10, 1] partitions each task into two sub tasks, a mandatory sub task 1 CPU time given to a task is quantified by a specified amount of CPU cycles allocated at fixed intervals which must be executed at every cycle and a optional sub task which can be discarded under overloaded conditions. The mandatory ....

....some form of compromise is needed to reduce the demand on the CPU. Some of the considerations we have are: ffl Task Criticality. A task often has to perform a series of actions and not all of these actions are equally important. This awareness is highlighted also in imprecise scheduling technique [10, 1]. The task should be as important as the most critical operation it performs, but the other non critical operations within the task should not share the same level of service. ffl Operation Importance. Non crucial operations, when discarded too often, may become critical. In a video conferencing ....

K. J. Lin, S. Natarajan, and J. W. S. Liu. Scheduling real-time, periodic jobs using imprecise results. In Proc. IEEE Real-Time System Symp., 1987.

....more execution time to certain tasks. One use of this extra time is to allow a task to provide higher quality results and still meet their deadlines. These ideas and goals have been extended to the general problem of scheduling periodic jobs using imprecise results by Liu, Lin, and Natarajan in [Liu 87] A well understood scheduling algorithm for guaranteeing the hard deadlines of periodic tasks in a multiprogrammed real time system is Liu and Layland s rate monotonic scheduling algorithm [Liu 73] Under this algorithm, fixed priorities are assigned to tasks based upon the rate of their ....

Jane W. S. Liu, Kwei-Jay Lin, and Swaminathan Natarajan. Scheduling Real-Time, Periodic Jobs Using Imprecise Results. In Proceedings of the 8th Real-Time Systems Symposium, pages 252-260. IEEE, San Jose, California, December, 1987.

....used admits transactions into the system with the absolute guarantee that either the primary task will successfully commit or the compensating task safely terminate. There have been a number of similar models suggested in the literature. These are contrasted to our model below. Liu et al. [23] developed the imprecise computation model which decomposes each task into two subtasks, a mandatory part and an optional part. Others employing this model include Audsley et al. 3] and Davis et al. 11] Our model differs from the imprecise computation model in that the WCET requirements for the ....

....decomposes each task into two subtasks, a mandatory part and an optional part. Others employing this model include Audsley et al. 3] and Davis et al. 11] Our model differs from the imprecise computation model in that the WCET requirements for the mandatory and optional parts are assumed in [23, 3, 11], whereas they are assumed only for the compensating tasks in our model. Also, unlike the imprecise computation model, we start off with the execution of the optional component (the primary task) leaving the mandatory component (the compensating task) to a later time (if needed) In a sense, our ....

J. W.-S. Liu, K. J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of the 8th IEEE Real-time Systems Symposium, December 1987.

....used admits transactions into the system with the absolute guarantee that either the primary task will successfully commit or the compensating task safely terminate. There have been a number of similar models suggested in the literature. These are contrasted to our model below. Liu et al. [27] developed the imprecise computation model which decomposes each task into two subtasks, a mandatory part and an optional part. Others employing this model include Audsley et al. 5] and Davis et al. 14] Our model differs from the imprecise computation model in that the WCET requirements for ....

....decomposes each task into two subtasks, a mandatory part and an optional part. Others employing this model include Audsley et al. 5] and Davis et al. 14] Our model differs from the imprecise computation model in that the WCET requirements for the mandatory and optional parts are assumed in [27, 5, 14], whereas they are assumed only for the compensating tasks in our model. Also, unlike the imprecise computation model, we start off with the execution of the optional component (the primary task) leaving the mandatory component (the compensating task) to a later time (if needed) In a sense, our ....

J. W.-S. Liu, K. J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of the 8th IEEE Real-time Systems Symposium, December 1987.

....movies to homes over an ATM based network may unexpectedly encounter network congestion, potentially causing some deadlines to be missed. Under such an overload condition, the real time system must remain robust and maintain an acceptable level of performance. The imprecisecomputation technique [25, 29, 30] is a way to deal with these transient overloads. 1.1 Motivation The imprecise computation technique is motivated by the fact that one can often trade off precision for timeliness. During transient overloads, it prevents missed deadlines (i.e. timing faults) and provides graceful degradation ....

J. W.-S. Liu, K.-J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of 8th IEEE Real-Time Systems Symposium, December 1987.

....Our work differs from previous research in that our transaction model incorporates not only primary tasks, with unknown WCET, but also compensating tasks. There have been a number of similar transaction models suggested in the literature, and these are contrasted with our model below. Liu et al. [9] developed the imprecise computation model which decomposes each task into two subtasks, a mandatory part and an optional part. Others employing this model include Audsley et al. 1] and Davis et al. 5] Our model differs from the imprecise computation model in that the WCET requirements for ....

....decomposes each task into two subtasks, a mandatory part and an optional part. Others employing this model include Audsley et al. 1] and Davis et al. 5] Our model differs from the imprecise computation model in that the WCET requirements for the mandatory and optional parts are assumed in [9, 1, 5], whereas they are assumed only for the compensating tasks in our model. Also, unlike the imprecise computation model, we start off with the execution of the optional component (the primary task) leaving the mandatory component (the compensating task) to a later time (if needed) In a sense, our ....

J. W.-S. Liu, K. J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of the 8th IEEE Real-time Systems Symposium, December 1987.

....used admits transactions into the system with the absolute guarantee that either the primary task will successfully commit or the compensating task safely terminate. There have been a number of similar models suggested in the literature. These are contrasted to our model below. Liu et al. [23, 22, 25] describe the imprecise computation model which decomposes each task into two subtasks, a mandatory part and an optional part. The mandatory part, which has a hard deadline, must be completed in order for the task to produce an acceptable result. The optional part, which has a soft deadline and ....

J. W.-S. Liu, K. J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of the 8th IEEE Real-time Systems Symposium, December 1987.

No context found.

J. W.-S. Liu, K.-J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of 8th IEEE Real-Time Systems Symposium, December 1987.

No context found.

J. W.-S. Liu, K.-J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of 8th IEEE Real-Time Systems Symposium, December 1987.

....each task and there are usually multiple tasks in a system, there arises a problem of scheduling all requests of the tasks properly so that their deadlines are met. The development of scheduling algorithms for periodic task systems has been a major focus in the area of real time scheduling theory [1, 16, 19, 20, 24, 28, 40, 42, 43, 46, 47, 60, 64, 68, 70]. Since current technology is incapable of producing hardware components which never fail or software programs which are free of errors, a task might miss its deadline because of processor failures or task errors. To tolerate hardware failures or software errors, hardware and software redundancy ....

J.W.S. Liu, K.-J. Lin, and S. Natarajan, Scheduling Real-time, Periodic Jobs Using 195 Imprecise Results, IEEE Real-Time Systems Symposium, 1987, 252-260.

No context found.

J.W.-S. Liu, K.-J. Lin, and S. Natarajan, Scheduling Real-Time, Periodic Jobs Using Imprecise Results, IEEE Real-Time Systems Symposium 1987, pp. 252260.

....or increase the error. Finally a scheduling algorithm, based on these constraints is presented. Key words. real time systems, multiprocessors, scheduling algorithms, imprecise computations. AMS subject classifications. 68M20, 68N25, 68Q22 1. Introduction. The Imprecise Computation model [2] provides a framework for incorporating graceful degradation in real time applications. The technique is based on the premise that, in some cases, producing less that perfect results on time is better than producing no results at all. This premise is particularly useful for interactive multimedia ....

....at the output device. Because the period of a job is defined as the time between two consecutive deadlines, all the jobs will have the same period, namely ff k;j 1 Gamma ff k;j where ff k;j is the start time of task T k;j . 3.1. The Imprecise Computation model. In a seminal paper, Chung et.al [2] describe a technique for evaluating monotone processes using a model for imprecise computations. A monotone process is one that is guaranteed to produce increasingly accurate results as it is allowed to execute longer. The Imprecise Computation model partitions a task into a mandatory part and an ....

[Article contains additional citation context not shown here]

J. Y. Chung, J. W. S Liu, and K. J. Lin, Scheduling Real-time, Periodic Jobs Using Imprecise Results, Proc. IEEE RTS, (1987), pp. 252--260.

....the dependencies between the timing constraints and result qualities of the tasks that generate utterances. We then extend the imprecise computation model to capture these dependencies and discuss the general applicability of the extended model. 1 Introduction The imprecise computation technique [3] is a way to improve the scheduling feasibility of applications where results of poorer quality are better than late results. The imprecise computation model assumes that the deadline of each task is given and that the quality of a task s result is solely dependent on the time and resources spent ....

....dependencies and discuss the general applicability of the extended model. This work addresses many of the issues raised in [1] While the emphasis of [1] is on the use of the anytime approach for time dependent planning [2] we focus on extending the imprecise computation technique, developed in [3], in order to model the tasks in a real time speech application. 2 A Real Time Speech Application We refer to the two persons in the conversation and the tasks that emulate them as Alice and Bob. For concreteness, we may think of Alice and Bob in the following scenario: A graduate student named ....

J. W. S. Liu, K.-J Lin, and S. Natarajan. Scheduling Real-Time, Periodic Jobs Using Imprecise Results. Proceedings of the 8th Real-Time Systems Symposium (1987).

....worst case load level (e.g. unexpected network congestion) a transient overload occurs, potentially causing some deadlines to be missed. The real time system must remain robust and maintain an acceptable level of performance under a transient overload. The imprecise computation 1 technique [1 5] was introduced as a way to deal with transient overloads. The technique is motivated by the fact that one can often trade off precision for timeliness. It prevents missed deadlines and provides graceful degradation during a transient overload by ensuring that an approximate result of acceptable ....

....work and F i = i Gamma oe i i = p i Gamma OE i i for i OE i p i the fraction of discarded work 1 . Since OE i is never in the range [0; i ) the value of F i in this range is irrelevant; it is assumed to have the value 1 for the sake of convenience. Most existing algorithms [3 5, 7 15] for scheduling tasks with optional parts assume that the tasks are monotone. As a monotone task executes longer, the quality of its results improves. Hence, these algorithms seek schedules in which the fraction of discarded work (or some function of this fraction) of each task is as small as ....

J. W.-S. Liu, K.-J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of 8th IEEE Real-Time Systems Symposium, December 1987.

....the uncomputed portions. 1 Introduction In a hard real time system, a timing fault is said to occur when a real time task fails to complete before its deadline. A new approach, called the imprecise computation approach, has been proposed as a means to avoid these timing faults of real time tasks [1, 2, 3, 9]. This approach makes available results of poorer, but acceptable, quality when the desired quality result may not be available in time. We assume that the realtime processes are monotone, i.e. the error function is a non increasing function of time. As more time is spent on the task, the ....

....In a system that supports imprecise computations, run time support is provided to record intermediate results produced by each real time process at appropriate instances of the job s execution. There have been a number of results in scheduling uniprocessor systems for imprecise computations [1,2,3,9]. In this paper, we are concerned with the problem of scheduling periodic tasks on multiprocessors for imprecise computation approach. A monotone process that may be terminated any time after it has produced an acceptable result is modelled as a task that is logically decomposed into a mandatory ....

J.W.S. Liu, K.J. Lin, and S. Natarajan, Scheduling Real-Time, Periodic Jobs Using Imprecise Results, Proc. IEEE Real-Time Systems Symp. 1987.

No context found.

J. W.-S. Liu, K.-J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of 8th IEEE RealTime Systems Symposium, December 1987.

No context found.

J. W.-S. Liu, K. J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of the 8th IEEE Real-time Systems Symposium, December 1987.

No context found.

J. W. -S. Liu, K.-J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of 8th IEEE Real-Time Systems Symposium, December 1987. 25

No context found.

J.W.S. Liu, K.J. Lin, and S. Natarajan. Scheduling real-time, periodic jobs using imprecise results. In Proceedings of the IEEE Real-Time Systems Symposium, San Jose, California, December 1987.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC