Although research seems to address event and stream data processing as two separate topics, there are a number of similarities between them. For many advanced stream applications, both event and rule processing are ne...
详细信息
Although research seems to address event and stream data processing as two separate topics, there are a number of similarities between them. For many advanced stream applications, both event and rule processing are needed and are not currently well-supported. Extant event processing systems concentrate primarily on complex events and rules and stream processing systems concentrate on stream operators, scheduling, and quality of service issues. Synergistic integration of these models will be better than the sum of its parts. We propose an integrated model to combine the capabilities of both models for applications that need both of them. Specifically, we introduced a number of enhancements, including stream modifiers, semantic windows, event generators, and enhanced event and rule specifications, to couple two models seamlessly. We prototype our integrated system using the stream processing system (MavStream) with the event processing system (Snoop and Sentinel) and discuss the design and implementation issues of our prototype.
Deblocking filtering represents one of the most compute intensive tasks in an H.264/AVC standard video decoder due to its demanding memory accesses and irregular dataflow. For these reasons, an efficient implementati...
详细信息
ISBN:
(纸本)9783981080124
Deblocking filtering represents one of the most compute intensive tasks in an H.264/AVC standard video decoder due to its demanding memory accesses and irregular dataflow. For these reasons, an efficient implementation poses big challenges, especially for programmable platforms. In this sense, the mapping of this decoder's functionality onto a C-programmable coarse-grained reconfigurable architecture named ADRES (architecture for dynamically reconfigurable embedded systems) is presented in this paper, including results from the evaluation of different topologies. The results obtained show a considerable reduction in the number of cycles and memory accesses needed to perform the filtering as well as an increase in the degree of instruction parallelism (ILP) when compared with an implementation on a very long instruction word (VLIW) dedicated processor. This demonstrates that high ILP is achievable on the ADRES even for irregular, data-dependent kernels
We have developed Argus, a novel approach for providing low-cost, comprehensive error detection for simple cores. The key to Argus is that the operation of a von Neumann core consists of four fundamental tasks - contr...
详细信息
ISBN:
(纸本)9780769530475
We have developed Argus, a novel approach for providing low-cost, comprehensive error detection for simple cores. The key to Argus is that the operation of a von Neumann core consists of four fundamental tasks - control flow, dataflow, computation, and memory access - that can be checked separately. We prove that Argus can detect any error by observing whether any of these tasks are performed incorrectly. We describe a prototype implementation, Argus-1, based on a single-issue, 4-stage, in-order processor to illustrate the potential of our approach. Experiments show that Argus-1 detects transient and permanent errors in simple cores with much lower impact on performance (<4% average overhead) and chip area (<17% overhead) than previous techniques.
The ground truth labeling of an image dataset is a task that often requires a large amount of human time and labor. We present an infrastructure for distributed human labeling that can exploit the modularity of common...
详细信息
The ground truth labeling of an image dataset is a task that often requires a large amount of human time and labor. We present an infrastructure for distributed human labeling that can exploit the modularity of common vision problems involving segmentation and recognition. We present the different elements of this infrastructure in detail, in particular the different vision human computational tasks (HCTs) and machine computable tasks (MCTs). We also discuss the impact of such a system on Internet security vs. the current state of the art. Finally, we present our prototype implementation of such a system, named soylent grid, on typical problems.
Program slicing is a program-reduction technique for extracting statements that may influence other statements. While there exist efficient algorithms to slice sequential programs precisely, there are only two algorit...
详细信息
Program slicing is a program-reduction technique for extracting statements that may influence other statements. While there exist efficient algorithms to slice sequential programs precisely, there are only two algorithms for precise slicing of concurrent interprocedural programs with recursive procedures. We implemented both algorithms for Java, applied several new optimizations and examined their precision and runtime behavior. We compared these results with two further algorithms which trade precision for speed. We show that one algorithm may produce incorrect slices and that precise slicing of concurrent programs is very expensive in terms of computation time.
For aspect-oriented modular reconfigurable computing, we specify a notion of "aspect" in the context of modular reconfigurable computing systems. In our formal approach, an aspect is determined as a coalgebr...
详细信息
For aspect-oriented modular reconfigurable computing, we specify a notion of "aspect" in the context of modular reconfigurable computing systems. In our formal approach, an aspect is determined as a coalgebraic transformation on modular reconfigurable computing systems. Then, based on this fundamental concept of aspect, inheritance and super- imposition properties of aspects are studied. Specifically, the inheritance property is shown to be a bisimulation relation and the superimposition property is determined in the context of coalgebraic reconfiguration. Moreover, we also justify that our approach is sufficiently expressive to combine aspect-orientation and modular reconfigurable computing.
We have architected and evaluated a new kind of data resource, one that is composed of a logical collection of ephemeral data streams that could be viewed as a collection of publish-subscribe "channels" over...
详细信息
ISBN:
(纸本)0769525857
We have architected and evaluated a new kind of data resource, one that is composed of a logical collection of ephemeral data streams that could be viewed as a collection of publish-subscribe "channels" over which rich data-access and semantic operations can be performed. This paper contributes new insight to stream processing under the highly asynchronous stream workloads often found in data-driven scientific applications, and presents insights gained through porting a distributed stream processing system to a Grid services framework. Experimental results reveal limits on stream processing rates that are directly tied to differences in stream rates.
Unlike their hard realtime counterparts, soft realtime applications are only expected to guarantee their "expected delay" over input data space. This paradigm shaft calls for customized statistical design te...
详细信息
ISBN:
(纸本)0769525237
Unlike their hard realtime counterparts, soft realtime applications are only expected to guarantee their "expected delay" over input data space. This paradigm shaft calls for customized statistical design techniques to replace the conventional pessimistic worst case analysis methodologies. Statistical design methods can provide a realistic assessment of design space, and improve the design quality by exploiting its stochastic behavior We present a novel probabilistic time budgeting algorithm that translates the application expected delay constraint into its components delay constraints. Our algorithm which is based on mathematical properties of the problem, determines the optimal maximum weighted timing relaxation of an application under expected delay constraint. Experimental results on core-based synthesis of several multimedia applications on FPGAs show about 20% and 19% average energy and area improvement, respectively.
Our current research into programming models for parallel web services composition is targeted at providing mechanisms for obtaining higher throughput for large scale compute and data intensive programs that delegate ...
详细信息
ISBN:
(纸本)0769525857
Our current research into programming models for parallel web services composition is targeted at providing mechanisms for obtaining higher throughput for large scale compute and data intensive programs that delegate part of their computation to services, and making it easier to develop such applications. The ability to invoke multiple service calls at one time on different machines enables different portions of the program to be executed concurrently. We are addressing this through an implementation of an existing functional language, XSLT Our implementation uses a dataflow execution model, and includes a compiler to build dataflow graphs from XSLT source code. This paper describes the execution model used to obtain parallelism and compose web services, as well as the compilation process used to create the dataflow graphs. Our aim with this paper is to present the design of our system and demonstrate that XSLT provides a suitable model for distributed execution and parallel composition of web services.
The processing capabilities of wireless sensor nodes enable to aggregate redundant data to limit total dataflow over the network. The main property of a good aggregation algorithm is to extract the most representativ...
详细信息
The processing capabilities of wireless sensor nodes enable to aggregate redundant data to limit total dataflow over the network. The main property of a good aggregation algorithm is to extract the most representative data by using minimum resources. From this point of view, sampling is a promising aggregation method, that acts as surrogate for the whole data, and once extracted can be used to answer multiple kinds of queries (such as AVG, MEDIAN, SUM, COUNT, etc.), at no extra cost. Additionally, sampling also preserves the correlation info within multi-dimensional data, which is quite valuable for further data mining. In this paper, we propose a novel, distributed, weighted sampling algorithm to sample sensor network data and compare to an existing random sampling algorithm, which to the best of our knowledge is the only algorithm to work in this kind of setting
暂无评论