This paper presents a novel approach to writing TOSCA templates for application reusability and portability in a modular auto-scaling and orchestration framework (MiCADO). The approach defines cloud resources as well ...
详细信息
Thispaper examines the real time speed of the conservative parallel simulation of a telecommunications network Real time speed isdefinedas the ratio ofthe simulatedtime to the execution time. A generic simulation mode...
详细信息
parallel and distributed systems engineers are always looking for a way to speed-up their programs. They sometimes forget that well-structured programs are more flexible, and therefore easier to modify or restructure ...
详细信息
Atmospheric waves at the interface between two flowing layers of air are studied in this paper. The lower layer is assumed to be incompressible and to flow irrotationally, and its motion might be the result of a dista...
详细信息
Atmospheric waves at the interface between two flowing layers of air are studied in this paper. The lower layer is assumed to be incompressible and to flow irrotationally, and its motion might be the result of a distant thunderstorm, for example. The upper layer is modeled as a compressible isothermal atmosphere, so that if it were stationary, its density and pressure would both decrease exponentially with height. The equations of motion in the upper layer are linearized under the assumption that the lower layer of incompressible fluid is ''thin'' (its weight is a small fraction of the total), but the possibility of large-amplitude disturbances at the interface is nevertheless allowed. A linearized theory of wave propagation in this system is discussed, and a numerical scheme is outlined for the solution of the nonlinear equations. The results confirm the predictions of a model of Forbes and Belward [Phys. Fluids A 4, 2222 (1992)], in which the upper atmosphere was assumed stationary, and demonstrate that this simpler model gives results that are likely to be useful over most of the range of values of the speed in the upper layer encountered in practice. Nonlinear waves near the limiting height are discussed, and a very significant qualitative difference between the predictions of the linearized theory and the nonlinear results concerning progressive waves is analyzed, and may be of importance in meteorology.
A second and revised version of the parallel Prolog Abstract Machine (PPAM) is described in the paper. PPAM-2 is suitable for implementing Prolog on communicating process architecture-type, highly parallel computers w...
详细信息
A second and revised version of the parallel Prolog Abstract Machine (PPAM) is described in the paper. PPAM-2 is suitable for implementing Prolog on communicating process architecture-type, highly parallel computers with regular interconnection network. The parallel computational model behind PPAM-2 is an extended cellular-dataflow model, whose main features have been published elsewhere.16 Based on the model, Prolog programs are transformed into a dataflow search graph representing the static structure of the program. The paper explains in detail how the Prolog programs can be transformed into the dataflow graph form. The dynamic behaviour of the program is determined by the extended transition functions of the operators. By modifying the extended transition functions different kinds of parallelism can be achieved during the execution of the PPAM-2 code. In the paper an informal description is given of the transition functions realising OR-parallelism and pipelined AND-parallelism. A multi-transputer implementation of PPAM-2 has been investigated in the paper. First the chosen interconnection topology of the multi-transputer-based machine is described, then the method for mapping the dataflow search graph of Prolog programs on to the chosen topology. Finally, the realisation techniques of the dataflow operations on transputers are overviewed.
In 1959 Varga [14] presented the interpretation ofp-cyclic matrices as the generalization of Young's “Property A” [17]. Since then many interesting results have been given when the SOR method is applied to the l...
详细信息
In 1959 Varga [14] presented the interpretation ofp-cyclic matrices as the generalization of Young's “Property A” [17]. Since then many interesting results have been given when the SOR method is applied to the linear system (1. 1) withAp-cyclic and called the SOR-pmethod. In this paper, a repartitioning of the p-cyclic matrix A is given, which leads to a block SOR-2 scheme. It is shown that the SOR-2 scheme is faster than the SOR-pmethod under some conditions.
Waves at the interface of a two-layer fluid are considered. The fluid in the lower layer is incompressible with constant density and is flowing irrotationally. In the upper layer, the fluid is stationary but compressi...
Waves at the interface of a two-layer fluid are considered. The fluid in the lower layer is incompressible with constant density and is flowing irrotationally. In the upper layer, the fluid is stationary but compressible, and corresponds to an isothermal atmosphere with a density profile that decreases exponentially with height. The interface between the two fluids is assumed sharp. The formation of waves at the interface would come about typically as a result of the interaction of the moving lower layer of fluid with local topographical features, as with the classical problem of the generation of waves on the lee side of a mountain range. It is shown that the present model is capable of supporting the formation of interfacial waves that are similar in many respects to the classical gravity wave of Stokes, and that are ultimately limited in every case by the formation of a 120-degrees angle at the wave crest. The highly nonlinear wave profiles are computed numerically and compared with the predictions of linearized theory. An extended perturbation analysis is given near the point at which the inter-facial waves break down as a result of the Kelvin-Helmholtz instability.
The United Kingdom Meteorological Office's routine which models the advection of tracers in the atmosphere suffers from a large load imbalance which can be as large as 30:1 in global forecasting runs. By dynamical...
详细信息
Staff scheduling is a complex problem encountered in almost all large businesses. Available manpower and skills must be deployed as effectively as possible, while being flexible enough to cope with the unexpected. Thi...
详细信息
This paper presents a parallel FFT algorithm suitable for MIMD machines. It has the properties of uniform granularity, the dominance of computation, and suitability to large data matrices. The algorithm has been imple...
详细信息
This paper presents a parallel FFT algorithm suitable for MIMD machines. It has the properties of uniform granularity, the dominance of computation, and suitability to large data matrices. The algorithm has been implemented for a tree and cubic types of transputer network in Occam language. A set of performance figures has been derived for different size of networks and initial matrices.
暂无评论