Static priority scheduling is widely used in real-time systems. But its schedulab.lity will be reduced if priority levels of the system are insufficient. A task set may require more priority levels than the system can...
详细信息
Static priority scheduling is widely used in real-time systems. But its schedulab.lity will be reduced if priority levels of the system are insufficient. A task set may require more priority levels than the system can support. In this case, more than one task must be grouped into the same priority. This paper presents necessary and sufficient conditions for analyzing the schedulab.lity of static priority algorithms on resources with limited priority levels. A static priority assignment algorithm (AGP) with limited priority levels is developed. As it turns out, AGP is optimal for the basic task set in the sense that the number of priority levels required by AGP is minimal and no other static priority rule can schedule a basic task set which cannot scheduled by AGP. Simulation results show that the schedulab.lity of AGP is much higher than that of Constant Ratio Grid algorithm. AGP is significant for solving the problem of assigning priorities of tasks in embedded real-time systems.
This paper describes an object-oriented framework for solving comp.tational fluid dynamics problems on parallelcomp.ters. The design and comp.nents of the framework are discussed related to design patterns methodolog...
详细信息
ISBN:
(纸本)1892512459
This paper describes an object-oriented framework for solving comp.tational fluid dynamics problems on parallelcomp.ters. The design and comp.nents of the framework are discussed related to design patterns methodology. The proposed framework offers higher-level programming abstractions for parallelization and improves the overall efficiency of implementation.
In this paper, we introduce an easy-to-use, platform senseless task parallel programming model called Lily Task, as well as its implementations on SMP and Cluster. Lily Task programming model reflects directly the hum...
详细信息
ISBN:
(纸本)088986392X
In this paper, we introduce an easy-to-use, platform senseless task parallel programming model called Lily Task, as well as its implementations on SMP and Cluster. Lily Task programming model reflects directly the human thoughts in the parallelism process of a problem. LilyTask supports both data and function parallelisms, as well as dynamic task creation and scheduling. It is very suitable for solving irregular problems. And its performance is satisfying.
An extended architecture of recurrent neural networks is proposed. It is based on ignoring unimportant input information using a register of latches as the input layer of the network. The latch is implemented with a m...
详细信息
An extended architecture of recurrent neural networks is proposed. It is based on ignoring unimportant input information using a register of latches as the input layer of the network. The latch is implemented with a multiplexer 2/1 whose output is differentiable with respect to all of its inputs, thus enabling the derivatives to be propagated through the network. The relevance of input vectors is learned together with the weights of the network using a gradient-based algorithm.
Most preconditioned iterative methods apply to both real- and comp.ex-valued linear systems. At the same time, most iterative linear solver packages availab.e today focus exclusively on real-valued systems or deal wit...
详细信息
Most preconditioned iterative methods apply to both real- and comp.ex-valued linear systems. At the same time, most iterative linear solver packages availab.e today focus exclusively on real-valued systems or deal with comp.ex-valued systems as an afterthought. By recasting the comp.ex problem in a real formulation, a real-valued solver can be applied to the equivalent real system. On one hand, real formulations have been dismissed due to their unfavorable spectral properties. On the other hand, using an equivalent preconditioned real formulation can be very effective. We give theoretical and experimental evidence that an equivalent real formulation is useful in a number of practical situations. Furthermore, we show how to use the advanced features of modern solver packages to formulate equivalent real preconditioners that are comp.tationally efficient and mathematically identical to their comp.ex counterparts. The effectiveness of equivalent real formulations is demonstrated by solving ill-conditioned comp.ex-valued linear systems for a variety of large scale applications. Moreover, the circumstances under which certain equivalent real formulations are comp.titive is more clearly delineated.
This paper proposes a novel real-time adaptive admission control (AAC) scheme with a desired quality of service (QoS) guarantee and high network utilization in high-speed networks. The QoS is given in terms of service...
详细信息
This paper proposes a novel real-time adaptive admission control (AAC) scheme with a desired quality of service (QoS) guarantee and high network utilization in high-speed networks. The QoS is given in terms of service delay, which is defined as the time it takes for a source to get admitted into the network after it initiates its intended request, packet/cell losses, and transmission delay (time taken to comp.ete transmission from its initiation). AAC uses the following information- the availab.e capacity from a novel adaptive bandwidth estimation scheme, a congestion indicator derived from a congestion controller, Peak Cell Rate (PCR) estimate from new sources, along with the desired QoS metrics, and outputs an 'admit' or 'reject' decision signal to the new sources while guaranteeing QoS and network utilization. Simulation results are presented by streaming ON/OFF and video data into the network. Results show that the proposed AAC admits significantly more traffic comp.red to other availab.e admission control schemes thereby guaranteeing high network utilization while maintaining the desired QoS.
Many per-flow scheduling algorithms have been proposed to provide rate and delay guarantees to flows. It is often argued that the need for maintaining per-flow state and performing per-packet classification seriously ...
详细信息
Many per-flow scheduling algorithms have been proposed to provide rate and delay guarantees to flows. It is often argued that the need for maintaining per-flow state and performing per-packet classification seriously limits the scalab.lity of routers that employ such per-flow scheduling algorithms. Consequently, design of algorithms that can provide per-flow rate and delay guarantees without requiring per-flow functionality in the network core routers has become an active area of research. In this paper, we propose a methodology to transform any Guaranteed Rate (GR) per-flow scheduling algorithm into a version that does not require per-flow state to be maintained in the core routers. We prove that a network of such core-stateless servers provides the same delay guarantee as a corresponding network of GR servers.
A lattice Bhatnagar-Gross-Krook (LBGK) model for reaction-diffusion systems is presented. This model provides a mesoscopic approach to the dynamics of spatially-distributed reacting systems. Pure diffusion phenomena a...
详细信息
A lattice Bhatnagar-Gross-Krook (LBGK) model for reaction-diffusion systems is presented. This model provides a mesoscopic approach to the dynamics of spatially-distributed reacting systems. Pure diffusion phenomena are comp.ted and the results are agreement with the theoretical predictions. This method is also applied to formation of Turing patterns in chloride-iodide-malonic acid (CIMA) reactive model. We get hexagonal structures and stripes which are agreement with other numerical results and experimental results.
Resource reservation is an important means to guarantee the QoS of distributed multimedia applications. In this paper, an application level QoS negotiation protocol is proposed. It has two merits. One is globalizing t...
详细信息
Resource reservation is an important means to guarantee the QoS of distributed multimedia applications. In this paper, an application level QoS negotiation protocol is proposed. It has two merits. One is globalizing the local QoS parameters so that the reservation becomes more flexible and users can reserve resources using the parameters they concern. The other is localizing the global reservation to make reservation simpler and to facilitate the implementation of optimal delay allocation.
In this paper, we propose a multi-level abstraction mechanism for capturing the spatial and temporal semantics associated with various objects in an input image or in a sequence of video frames. This abstraction can m...
详细信息
In this paper, we propose a multi-level abstraction mechanism for capturing the spatial and temporal semantics associated with various objects in an input image or in a sequence of video frames. This abstraction can manifest itself effectively in conceptualizing events and views in multimedia data as perceived by individual users. The objective is to provide an efficient mechanism for handling content-based queries, with the minimum amount of processing performed on raw data during query evaluation. We introduce a multi-level architecture for video data management at different levels of abstraction. The architecture facilitates a multi-level indexing/searching mechanism. At the finest level of granularity, video data can be indexed based on mere appearance of objects and faces. For management of information at higher levels of abstractions, an object-oriented paradigm is proposed which is capable of supporting domain specific views.
暂无评论