Numerical Weather Prediction (NWP) and Parallel Computing

Numerical Weather Prediction (NWP) NOOR NASHUHA BINTI AZMAN 2013837386 MUHAMMAD IKHWAN BIN AZMAN 2013638218

INTRODUCTION Numerical weather prediction (NWP) uses mathematical models of the atmosphere and oceans to predict the weather based on current weather conditions Numerical weather prediction has emerged as one of the important discipline requiring increasing computing power. Climate and weather modelers were among the first users of parallel computers. In parallel processing different parts of application code are computed at the same time by different processors working in parallel. There are worldwide efforts to port weather forecasting codes on parallel computers.

BACKGROUND 1950s :Numerical weather prediction and climate simulation have been among the computationally most demanding applications of high performance computing. 1980s : The most powerful computers have featured an ever larger number of processors. 2000s : This number is often several thousand. An operational weather model must use all these processors in a highly coordinated fashion.

PURPOSE To illustrate the application of parallel network processing computing system to an important class of problem in hydrodynamics.

Domain Area Regional models allow for the use of finer grid spacing than global models because the available computational resources are focused on a specific area instead of being spread over the globe. This allows regional models to resolve explicitly smaller-scale meteorological phenomena that cannot be represented on the coarser grid of a global model.

PARALLEL ARCHITECTURE USED The present study is an attempt to explore and examine the computational time required for the highly complex numerical simulations of weather and ocean models with multi core processors and variable RAM/processor speeds. Since multiple instructions multiple data streams (MIMD) is the most flexible architecture, NWP probably need this.

PARALLEL PLATFORM I/O also has been a problem in data-intensive parallel applications. To address this problem, high performance I/O libraries or systems, such as the MPIIO, HPIO, etc. have been designed and implemented To allow file decomposition that matches array decomposition, a structured file format that facilitates efficient storage and access of multi- dimensional arrays is needed. The PIC, a parallel I/O library for clusters, was developed at the SRL using the netCDF. PIC provides two main operations: the Scatter and the Gather

ADVANTAGES NWP The programmer can take the maximum advantage of mode control, neighbouring connection, variables geometry and simultaneous operation of network processing. The numerical solution elliptic partial differential equations by the parallel processing network.

CONCLUSION A parallel processing system of the type will give significant increase in computational speed over that sequentially organized computing system in the field of fluid dynamics as well as in other scientific field.

REFERENCES Numerical weather prediction. (n.d.). Retrieved October 30, 2016, from https://en.wikipedia.org/wiki/Numerical_weather_prediction Kothari, S. C., Cho, J., & Deng, Y. (2002, January). Software Tools and Parallel Computing for Numerical ... Retrieved October 30, 2016, from https://www.researchgate.net/publication/220950154_Software_Tools_an d_Parallel_Computing_for_Numerical_Weather_Prediction_Models Granma, A., Gupta, A., Karypis, G., & Kumar, V. (2003). Introduction to Parallel Computing (Second ed.). Addison Wesley. Numerical Weather Prediction. (n.d.). Retrieved October 30, 2016, from https://www.ncdc.noaa.gov/data-access/model-data/model- datasets/numerical-weather-prediction Navarro, C. A., Kahler, N. H., & Mateu, L. (2013, September 10). A Survey on Parallel Computing and its Applications in Data-Parallel Problems Using GPU Architectures [Review]. 300-303.