The Kernel Tool Kit (KTK) is an object-based operating system kernel andparallel programming library that offers explicit support for on- and off-line program configuration. Specifically, KTK allows the specification...
详细信息
The Kernel Tool Kit (KTK) is an object-based operating system kernel andparallel programming library that offers explicit support for on- and off-line program configuration. Specifically, KTK allows the specification of attributes for object classes, object instances, state variables, operations and object invocations. Attributes are interpreted by policy classes that may be varied separately from the abstractions with which they are associated. They can be used to vary object internal implementation and semantics without affecting the methods being invoked. In this paper, the runtime configuration of KTK attributes is shown to improve the runtime performance of multiprocessor applications. KTK is layered on a portable and configurable parallel programming substrate, a Mach Cthreads compatible runtime library/spl lsqb/22/spl rsqb/.< >
In numerical algorithms based on adaptive mesh refinement, the computational workload changes during their execution. In mapping such algorithms on to distributed memory architectures, it is necessary to balance the w...
详细信息
In numerical algorithms based on adaptive mesh refinement, the computational workload changes during their execution. In mapping such algorithms on to distributed memory architectures, it is necessary to balance the workload among the processors dynamically in order to obtain high performance. In this paper, we propose a dynamic processor allocation algorithm for a mesh architecture that reassigns the workload in an attempt to minimize both the computational and communication costs. Our algorithm is based on a heuristic for a 2D packing problem that gives provably close to optimal solutions for special cases of the problem. We also demonstrate through experiments how our algorithm provides good quality solutions in general.< >
In our earlier papers,we investigated the parallelization and implementation of Gauss-Seidel (G-S) and Successive Overrelaxation (SOR) power flow analysis on shared memory, (SM) anddistributed (DM) machines. For the ...
详细信息
In our earlier papers,we investigated the parallelization and implementation of Gauss-Seidel (G-S) and Successive Overrelaxation (SOR) power flow analysis on shared memory, (SM) anddistributed (DM) machines. For the SOR case, constant acceleration factors obtained from experiments are used to speedup convergence. In this paper, we introduce a new adaptive nonlinear SOR (ANSOR) algorithm which uses an approximated optimal acceleration factor obtained during the iteration process. The algorithm is shown to be faster due to the significant reduction in the number of iterations, and to converge robustly under heavily-loaded conditions on large power systems. We also implement parallel and sequential versions of our ANSOR algorithm on the nCUBE2 machine, and show that our algorithm is competitive with the fast decoupled load flow (FDLF) algorithm. Moreover, the portability of the parallel ANSOR code is demonstrated by porting the code to the Intel iPSC/860 hypercube and the Paragon mesh MIMD machines. However, our new algorithm is not a panacea for all problems, as we demonstrate with an example from transient stability analysis.< >
Replication Server is aforthcoming Sybase product that dynamically maintains subsets of data in a distributed environment, providing several transaction models to maintain loose consistency. Replication Server is cont...
The author has implemented a set of computational physics codes on a network of IBM RS/6000 workstations used as a distributedparallel computer. He compares the performance of the codes on this network, using both st...
详细信息
The authors present a block data decomposition algorithm for two-dimensional grid problems. Their method includes local balancing to accommodate heterogeneous processors, and they characterize the conditions that must...
详细信息
Requirements of emerging applications together with rapid changes in networking technology towards gigabit speeds require new adequate transport systems. Integrated designs of transport services, protocol architecture...
详细信息
Based on the Fornasini-Marchesini (FM) second local state-space (LSS) model, an efficient algorithm is developed to derive the characteristic polynomial and the inverse of the system matrix from the state-space parame...
详细信息
ISBN:
(纸本)0780312813
Based on the Fornasini-Marchesini (FM) second local state-space (LSS) model, an efficient algorithm is developed to derive the characteristic polynomial and the inverse of the system matrix from the state-space parameters. As a result, the external description of the FM second LSS model is clarified. The FM second LSS model is then used to design 2-D state-space digital filters in the frequency domain. The resulting filter approximates both magnitude and group delay specifications and its stability is always guaranteed.
A great variety of techniques has been developed to optimize and enhance query processing for relational, client/server, distributed, parallel, and heterogeneous database systems (DBS). Based on that work and experien...
详细信息
ISBN:
(纸本)0897916263
A great variety of techniques has been developed to optimize and enhance query processing for relational, client/server, distributed, parallel, and heterogeneous database systems (DBS). Based on that work and experience, we investigate how far those techniques are applicable to query processing in Knowledge Base Management Systems (KBMS). Our reference system is the KRISYS KBMS that consists of a knowledge-processing system at the client (client-based processing) and a data-processing system at the server (database backend). We describe a unifying framework for query processing incorporating both processing systems (as realized in KRISYS). This allows to distribute and balance the amount of work done in the client and in the server. Based on an evaluation of that framework, several approaches to further enhance knowledge processing are reported.
The centralized computation of a global state in a distributed system creates a performance bottleneck. In order to overcome this problem for a hypercube distributed system, we first develop the concept of nC-Tree and...
详细信息
ISBN:
(纸本)0780312813
The centralized computation of a global state in a distributed system creates a performance bottleneck. In order to overcome this problem for a hypercube distributed system, we first develop the concept of nC-Tree and define a revolving permutation on the nodes of the nC-Tree. We define a mapping of hypercube distributed system on a sequence of 2C-Tree with a logical hierarchical structure. The logical hierarchical structure in conjunction with the revolving permutation defines the revolving hierarchy of the hypercube system. The repeated centralized computation of a global state is performed with uniform loading thereby removing this performance bottleneck.
暂无评论