M. F. Wehner, J. J. Ambrosiano, J. C. Brown, W .P. Dannevik, P. G. Eltgroth, A. A. Mirin, J. D. Farrara, C. C. Ma, C. R. Mechoso and J. A. Spahr, "Toward a high performance distributed memory climate model," in Proc. 2nd Intern. Sympos. on High Performance Distributed Computing (HPDC2), Spokane, WA, July 20--23, 1993, pp. 102--113.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....was the resident memory on each node. The T340 problem could only be run on the two smallest size decompositions. 3 2 D models The 3 D UCLA Atmospheric General Circulation Model (AGCM) of Arakawa [1, 2] was recently ported into a 2 D latitude longitude decomposed form by Wehner and associates [26]. Integration is carried out along a vertical column, which shows little sign of parallelization possibilities at least for a small number of layers. They used the staggered mesh decomposition of Arakawa [3] with vorticity corrections at the poles and discrete Fourier filters to allow longer time ....

....since the vertical profiles are based on parameterized functions of the surface variables. Time updates in our model were performed using a two step Lax Wendroff scheme in order to minimize mesh drifting and eliminate the need for the expensive Fourier filtering step used by Wehner and associates [26]. For the ocean component of our model, we use the box model of Harvey and Schneider [11] This model assumes a 3 level vertical decomposition of the ocean into mixed, intermediate and bottom layers. The equations governing these 3 layers are: RM dTM dt = Q s L # L GammaH Gamma LE ....

M. F. Wehner, J. J. Ambrosiano, J. C. Brown, W .P. Dannevik, P. G. Eltgroth, A. A. Mirin, J. D. Farrara, C. C. Ma, C. R. Mechoso and J. A. Spahr, "Toward a high performance distributed memory climate model," in Proc. 2nd Intern. Sympos. on High Performance Distributed Computing (HPDC2), Spokane, WA, July 20--23, 1993, pp. 102--113.

.... fields with spherical basis functions, which have been widely used for modeling phenomena like weather prediction, global warming or global change of atmospheric constituents [2, 3] Spectral models have some advantages over the grid based models commonly parallelized in past and current work[4, 5, 6, 7]. For example, spectral models naturally conserve the area averaged mean square kinetic energy and the mean square vorticity of wind fields, whereas in grid based models these quantities are either not conserved or require additional computation when such conservation is important[8] Despite such ....

....and accessed locally by the processor to which this range of s has been assigned. As a result, no movement of grid data is necessary during model computation, whereas spectral data is shared frequently. 2.3. 1 Layer Parallelization Grid based global models are typically decomposed (e.g. see [4]) using a two dimensional latitude longitude domain decomposition, where each subdomain consists of several neighboring vertical columns extending from the earth s surface to the top layer of the atmosphere addressed by the model. This decomposition is used for a variety of reasons, including ....

M.F. Wehner, J.J. Ambrosiano, J.C. Brown, W.P. Dannevik, P.G. Eltgroth, A.A. Mirin, J.D. Farrara, C.C. Ma, C.R. Mechoso, and J.A. Spahr. Toward a high performance distributed memory climate model. IEEE, pages 102 -- 113, 1993.

.... machines [89, 31] Such work is motivated by the intended use of parallel machines for commercial, large scale data processing, by upcoming programs like NASA s EOS satellites which will generate Terabytes of data that have to be processed and re processed for use in earth science applications [252], and it is motivated by the recent convergence of high performance computing and networking technologies resulting in large scale, physically distributed, and heterogeneous parallel machines. Brief survey of multiprocessor hardware. Several current textbooks in parallel computing provide good ....

M. Wehner, J. Ambrosiano, J. Brown, W. Dannevik, P. Eltgroth, and A. Mirin. Toward a high performance distributed memory climate model. In Proceedings of the 2nd International Symposium on High Performance Distributed Computing, pages 102--113, July 1993.

....structure of the model and does not need to be decreased with increased horizontal resolution. Parallel Decomposition Parallelization of the UCLA AGCM has been a collaborative effort of researchers at the Lawrence Livermore National Laboratory and UCLA. For a more complete description see [3], which is the basis for the following discussion. The Parallel UCLA AGCM is designed for a distributed memory (message passing) MIMD computing environment. The basic domain decomposition is two dimensional over latitude and longitude, with each subdomain thus consisting of a number of contiguous ....

M. F. Wehner, J. J. Ambrosiano, J. C. Brown, W. P. Dannevik, P.G. Eltgroth, A.A. Mirin and J. D. Farrara, C.C Ma, C. R. Mechoso, J. R. Spahr, "Toward a High Performance Distributed Memory Climate Model", Second International Symposium on High Performance Distributed Computing (HPDC-2, 1992), Spokane, WA, IEEE Computer Society, 16-25.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC