This paper describes the work of an objectual framework designed to be used in the parallelization of a set of related algorithms. As a concrete application a parallel Ant Colony Optimization algorithm (ACO) for the T...
详细信息
ISBN:
(纸本)0769522106
This paper describes the work of an objectual framework designed to be used in the parallelization of a set of related algorithms. As a concrete application a parallel Ant Colony Optimization algorithm (ACO) for the Travelling Salesman Problem (TSP) is presented. The idea behind the system we are describing is to have a re-usable framework for running several sequential algorithms in a parallel environment. The algorithms that the framework can he used with have several things in common: they have to run in cycles and the work should be possible to be split between several "processing units". The parallel framework uses the message-passing communication paradigm and is organized as a master-slave system. The ACO for TSP implemented by means of the parallel framework proves to have good performances: approximatively linear speedup and low communication cost.
The proceedings contain 142 papers from the 18th International parallel and distributedprocessingsymposium: IPDPS 2004. The topics discussed include: distributing data in composite grid applications for grid computi...
详细信息
ISBN:
(纸本)0769521320
The proceedings contain 142 papers from the 18th International parallel and distributedprocessingsymposium: IPDPS 2004. The topics discussed include: distributing data in composite grid applications for grid computing;benchmark performance on cluster grid with NGB;evaluating the information power grid using the NAS grid benchmarks;benchmark probes for grid assessment;Boltzmann algorithms to partition and map software for computational grids;application partitionability in computational grids;and on partitioning FEM graphs using diffusion.
Over the past decades, distributed computing has been gaining popularity. It provides more computing power and memory space for parallel applications. On the other hand, such applications fight back and challenge the ...
详细信息
ISBN:
(纸本)0769522424
Over the past decades, distributed computing has been gaining popularity. It provides more computing power and memory space for parallel applications. On the other hand, such applications fight back and challenge the architectures of the distributed systems for more efficiency. To face the challenge, a Key Messaging (KM) scheme was proposed to realize the optimization of communication at a system architecture level in our previous papers. The contribution of KM is that it performs the optimization in both the underlying communication system and high level application model. The performance of an application is always determined by its critical path. Currently, messages along the critical path can be easily blocked by non-critical path messages, which degrades the performance. To solve this problem, KM provides an algorithm to identify the critical-path messages and optimizes them by introducing a prioritized protocol layer Thus, these messages will be served first before any low priority messages. Shorter processing time for the messages results in faster completion time of the critical path.
Two parallel Computational Geometry Algorithms are presented: One to calculate a Discrete Voronoi Diagram when one of the seeds is removed and one to calculate the convex hull in two dimensions. The model of parallel ...
详细信息
ISBN:
(纸本)0769521320
Two parallel Computational Geometry Algorithms are presented: One to calculate a Discrete Voronoi Diagram when one of the seeds is removed and one to calculate the convex hull in two dimensions. The model of parallelprocessing used for these algorithms assumes the availability of one processor per pixel. The recent growth in the capacity of FPGAs and Systems-on-a-chip makes these algorithms interesting again.
An ad hoc grid is a heterogeneous computing system composed of mobile devices. The problem studied here is to statically assign resources to the subtasks of an application, which has an execution time constraint, when...
详细信息
One of the important issues facing the development of the grid its the computational framework of the future is availability of grid-enabled software. In this context, we discuss possible approaches to constructing it...
详细信息
ISBN:
(纸本)0769522106
One of the important issues facing the development of the grid its the computational framework of the future is availability of grid-enabled software. In this context, we discuss possible approaches to constructing it grid-enabled version of it computer algebra system. Our case study involves Maple: the proposed Maple2g package allows the connection between Maple and the computational grids based on the Globus Toolkit. We present the design of the Maple2g package and follow with a thorough discussion of its implementation.
As the first geographically distributed supercomputer on the Top 500 list, the AVIDD facility of Indiana University ranked 50th in June of 2003. It achieved 1.169 tera-flops running the UNPACK benchmark. In this paper...
详细信息
ISBN:
(纸本)0769521320
As the first geographically distributed supercomputer on the Top 500 list, the AVIDD facility of Indiana University ranked 50th in June of 2003. It achieved 1.169 tera-flops running the UNPACK benchmark. In this paper, our work of improving UNPACK performance is reported, and the impact of math kernel, UNPACK problem size and network tuning is analyzed based on the performance model of LINPACK.
作者：
Sohier, DevanBui, AlainLICA
Dept. de Mathématiques Univ. de Reims Champagne Ardenne BP1039 F-51687 Reims Cedex France LRIA
EPHE rue G. Lussac F-75005 Paris France
This paper presents a generalization of the results about the link between resistances and random walks on a graph. An efficient method to compute hitting times on a graph is also described. These results are to be us...
详细信息
ISBN:
(纸本)0769521320
This paper presents a generalization of the results about the link between resistances and random walks on a graph. An efficient method to compute hitting times on a graph is also described. These results are to be used in comparisons between distributed randomized and deterministic procedures, including, but not limited to, peer-to-peer networks and GRID computing.
In this paper, we propose an approach for the real-time performance analysis of distributed software with reliability constraints, called Athena. The approach is based on the principle of distributed program real-time...
详细信息
ISBN:
(纸本)0769521320
In this paper, we propose an approach for the real-time performance analysis of distributed software with reliability constraints, called Athena. The approach is based on the principle of distributed program real-time performance analysis. In Athena, we design some algorithms, count the transmission time for all the transmission paths of each data file, and then calculate response time of each data file with reliability constraint. So the real-time performance of distributed software with reliability-constrained can be evaluated.
This paper proposes a distributed stream multiplexing architecture for CODEC LSIs with multi-chip configuration, and demonstrates its scalability and usefulness. It consists of each media multiplexing unit with an ext...
详细信息
This paper proposes a distributed stream multiplexing architecture for CODEC LSIs with multi-chip configuration, and demonstrates its scalability and usefulness. It consists of each media multiplexing unit with an external stream input and inter-chip communication interfaces. parallel protocol processing, with an autonomous inter-chip control mechanism to mix and concatenate packets through daisy-chained transfer paths, provides a complete multi-chip output at the end of the chain. Dispensing with external stream handling devices contributes to both high throughput and downsizing. It is configurable for parallel encoding of super high-resolution video, multi-view/-angled HDTV vision and multiple HDTV channels. The architecture was implemented in a fabricated single-chip MPEG-2 422P@HL CODEC LSI and showed a good performance on an evaluation board system.
暂无评论