Simulating the transient processes in complex water transmission system is time-consuming, and improving computational efficiency by means of parallelization on CPU clusters or even faster GPU platform is demanded. Th...
详细信息
Simulating the transient processes in complex water transmission system is time-consuming, and improving computational efficiency by means of parallelization on CPU clusters or even faster GPU platform is demanded. This paper proposes an approach to accelerate the transient simulations of open channel and pipe combined flows on single GPU chip. The Saint-Venant equations for open channel flows is solved by using the method of characteristics (MOC), whose inherent parallelism can be well exploited by GPU implementations in the thread-level parallelism structure of Compute Unified Device Architecture (CUDA). The sub-processes, including open channel computation, pipe flow computation and connecting boundary treatment, are implemented by different kernels. The procedures are first verified by analyzing the parallel computation efficiency of hydraulic transient processes in an open channel. Then the transient processes of a practical engineering project, which involves both open channel flow and pressurized pipe flow, are simulated. The GPU kernels are found to be memory bandwidth bounded, and the proposed single chip GPU parallel can achieve up to hundreds of speedup ratios compared to the sequential counterpart on single CPU chip.
Average (mean) voter is one of the commonest voting methods suitable for decision making in highly-available and long-missions applications where the availability and the speed of the system are *** this paper, a new ...
详细信息
Average (mean) voter is one of the commonest voting methods suitable for decision making in highly-available and long-missions applications where the availability and the speed of the system are *** this paper, a new generation of average voter based on parallel algorithms and parallel random access machine (PRAM) structure are *** analysis shows that this algorithm is optimal due to its improved time complexity, speed-up, and efficiency and is especially appropriate for applications where the size of input space is large.
The temperature profile and infrared radiance of a tank were calculated by combining Domain Decomposition Method with Monte Carlo method in this paper. When the radiative energy transfer coefficient (RETC) was calcula...
详细信息
The temperature profile and infrared radiance of a tank were calculated by combining Domain Decomposition Method with Monte Carlo method in this paper. When the radiative energy transfer coefficient (RETC) was calculated by means of Monte Carlo method, the complication of surface radiative characteristic, for example, specular reflecting, anisotropy emitting, anisotropy reflecting, ect., could be taken into account, and the influence of complex shapes, such as geometry barrier and the projecting area of the sun radiation, could also be considered directly. By application of the RETC, a complicated calculation has been divided into several relatively easy sub-calculations in time-zone (computing steps) so that it can be solved in parallel. In space-zone (computing zones), the tank was divided into a number of domains, then several computer processors were used simultaneously. At the same time, the Monte Carlo procedures were able to be compiled easily in some extent, and the computing time was reduced as well.
In power system analysis, the alternating current optimal power flow (ACOPF) problem is modeled to minimize the total cost of generation while ensuring balance in the electrical network and addressing security conside...
详细信息
In power system analysis, the alternating current optimal power flow (ACOPF) problem is modeled to minimize the total cost of generation while ensuring balance in the electrical network and addressing security considerations in which scenarios of partial network failure may occur. The ACOPF can be formulated as a nonconvex quadratically constrained quadratic optimization problem, which is well known to be challenging because of nonlinearity and nonconvexity. We present a decomposable reformulation of the ACOPF, in which variables are copied and linear consensus constraints are added. This decomposability is realized once the consensus constraints are relaxed, thus leading to a particular Lagrangian dual of the ACOPF. We apply a recently developed scalable dual solution approach to the ACOPF based on an augmented Lagrangian method (ALM) that integrates the proximal bundle method with the simplicial decomposition method (SDM) and a Gauss-Seidel method, called SDM-ALM, which is used to solve a primal, convexified characterization of the Lagrangian dual of the ACOPF. We provide computational results demonstrating the scalability of our dual solution approach.
＜正＞While high throughput screening（HTS） and combinational chemistry（CC） become mature, the need of processing jillion chemical structure data is growing *** is a great challenge to a chemical database search en...
详细信息
＜正＞While high throughput screening（HTS） and combinational chemistry（CC） become mature, the need of processing jillion chemical structure data is growing *** is a great challenge to a chemical database search engine when it searches on a database with millions of chemical structures. Most of chemical substructure search engines were published before the year *** recent years, high performance computing and personal computing have experienced dramatic improvements.
This article considers up-to-date problems of parallel computing systems development in Russia. The study describes an engineering of an interface for organization of high-performance system with programmable structur...
详细信息
ISBN:
(纸本)9781509040704
This article considers up-to-date problems of parallel computing systems development in Russia. The study describes an engineering of an interface for organization of high-performance system with programmable structure and for its partition to specific subsystems focused on applied tasks. The solution is based on the concept of homogeneous computing systems (HCS) relying on the model of collective of calculators. HCS concept was formulated in the Institute of Mathematics of the USSR under the leadership of E.V. Evreinov in 1962 [1]. The approach is particularly relevant in terms of growing popularity of information networks which combining numerous personal computers (PCs). It's obviously necessary to develop software tools to integrate disparate calculators into the system and identify the required number of sub-systems for specific problem solving. An interference into the hardware and software parts of the calculators must be avoided during the software development process. Programmable structure of the computer system is provided at the stage of unification of calculators into software subsystem interface called an agent of DCS PS. The experience of the development of the Interface organization of distributed computing systems with programmable structure and allocation of subsystems for specific applications. The software described in the present document has been tested while an experimental organization of the DCS PS at the department of the computer engineering of NSTU.
In this paper we consider a method for finding several eigenvalues and corresponding eigenvectors of large-scale generalized eigenvalue problems. In this method, a small matrix pencil that has only the desired eigenva...
详细信息
暂无评论