{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:31:52Z","timestamp":1781105512079,"version":"3.54.1"},"reference-count":35,"publisher":"IGI Global Scientific Publishing","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:p>Attempts to harness the big climate data that come from high-resolution model output and advanced sensors to provide more accurate and rapidly-updated weather prediction, call for innovations in the existing data assimilation systems. Matrix inversion is a key operation in a majority of data assimilation techniques. Hence, this article presents out-of-core CUDA implementation of an iterative method of matrix inversion. The results show significant speed up for even square matrices of size 1024 X 1024 and more, without sacrificing the accuracy of the results. In a similar test environment, the comparison of this approach with a direct method such as the Gauss-Jordan approach, modified to process large matrices that cannot be processed directly within a single kernel call shows that the former is twice as efficient as the latter. This acceleration is attributed to the division-free design and the embarrassingly parallel nature of every sub-task of the algorithm. The parallel algorithm has been designed to be highly scalable when implemented with multiple GPUs for handling large matrices.<\/jats:p>","DOI":"10.4018\/ijghpc.2018010105","type":"journal-article","created":{"date-parts":[[2017,12,26]],"date-time":"2017-12-26T10:37:55Z","timestamp":1514284675000},"page":"71-92","source":"Crossref","is-referenced-by-count":3,"title":["Embarrassingly Parallel GPU Based Matrix Inversion Algorithm for Big Climate Data Assimilation"],"prefix":"10.4018","volume":"10","author":[{"given":"M.","family":"Varalakshmi","sequence":"first","affiliation":[{"name":"VIT University, Vellore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amit Parashuram","family":"Kesarkar","sequence":"additional","affiliation":[{"name":"National Atmospheric Research Laboratory, Chittoor, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daphne","family":"Lopez","sequence":"additional","affiliation":[{"name":"School of Information Technology and Engineering, VIT University, Vellore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2432","reference":[{"issue":"1","key":"IJGHPC.2018010105-0","first-page":"90","article-title":"Review of matrix decomposition techniques for signal processing applications.","volume":"4","author":"M.Agarwal","year":"2014","journal-title":"Int. J. Eng. Res. Appl"},{"key":"IJGHPC.2018010105-1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSE.2012.6295141"},{"key":"IJGHPC.2018010105-2","doi-asserted-by":"crossref","unstructured":"Benner, P., Ezzatti, P., Quintana-Ort\u00ed, E. S., & Rem\u00f3n, A. (2009, August). Using hybrid CPU-GPU platforms to accelerate the computation of the matrix sign function. In Proceedings of theEuropean Conference on Parallel Processing (pp. 132-139). Springer Berlin Heidelberg.","DOI":"10.1007\/978-3-642-14122-5_17"},{"key":"IJGHPC.2018010105-3","doi-asserted-by":"publisher","DOI":"10.1109\/MAP.2015.2401792"},{"key":"IJGHPC.2018010105-4","unstructured":"Chrzeszczyk, A., & Chrzeszczyk, J. (2013). Matrix computations on the GPU CUBLAS and MAGMA by example. Retrieved 16.09. 2015 from https:\/\/developer.nvidia.com\/sites\/default\/files\/akamai\/cuda\/files\/Misc\/mygpu.pdf"},{"key":"IJGHPC.2018010105-5","doi-asserted-by":"publisher","DOI":"10.2528\/PIER11031607"},{"key":"IJGHPC.2018010105-6","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2011.66"},{"key":"IJGHPC.2018010105-7","doi-asserted-by":"crossref","unstructured":"Ezzatti, P., Quintana Ort\u00ed, E. S., & Rem\u00f3n G\u00f3mez, A. (2011a). Using graphics processors to accelerate the computation of the matrix inverse.","DOI":"10.1007\/s11227-011-0606-4"},{"key":"IJGHPC.2018010105-8","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2005.42"},{"key":"IJGHPC.2018010105-9","article-title":"Efficient CSR-Based Sparse Matrix-Vector Multiplication on GPU.","author":"J.Gao","year":"2016","journal-title":"Mathematical Problems in Engineering"},{"key":"IJGHPC.2018010105-10","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.57"},{"key":"IJGHPC.2018010105-11","doi-asserted-by":"publisher","DOI":"10.1145\/3038228.3038237"},{"key":"IJGHPC.2018010105-12","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014567546"},{"key":"IJGHPC.2018010105-13","unstructured":"Harris, M. (2012). How to overlap data transfers in cuda c\/c++. Retrieved from http:\/\/devblogs.nvidia.com\/parallelforall\/how-overlap-data-transfers-cuda-cc"},{"key":"IJGHPC.2018010105-14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2011.04.025"},{"key":"IJGHPC.2018010105-15","article-title":"Toward accelerating the matrix inversion computation of symmetric positive-definite matrices on heterogeneous GPU-based systems.","author":"H.Ibeid","year":"2011","journal-title":"Student Research Symposium, International High Performance Computing Conference (HiPC)"},{"issue":"2","key":"IJGHPC.2018010105-16","first-page":"310","article-title":"A comparison of direct and indirect solvers for linear systems of equations.","volume":"2","author":"N.Jamil","year":"2012","journal-title":"International Journal of Emerging Sciences"},{"key":"IJGHPC.2018010105-17","doi-asserted-by":"crossref","unstructured":"Kijsipongse, E., Suriya, U., Ngamphiw, C., & Tongsima, S. (2011, May). Efficient large Pearson correlation matrix computing using hybrid MPI\/CUDA. In Proceedings of the 2011 Eighth International Joint Conference on Computer Science and Software Engineering (pp. 237-241). IEEE.","DOI":"10.1109\/JCSSE.2011.5930127"},{"key":"IJGHPC.2018010105-18","doi-asserted-by":"publisher","DOI":"10.1137\/120900216"},{"issue":"3","key":"IJGHPC.2018010105-19","first-page":"72","article-title":"Optimization Solutions for Improving the Performance of the Parallel Reduction Algorithm Using Graphics Processing Units.","volume":"16","author":"I.Lungu","year":"2012","journal-title":"Informa\u00e7\u00f5es Econ\u00f4micas"},{"key":"IJGHPC.2018010105-20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCSim.2012.6266966"},{"key":"IJGHPC.2018010105-21","doi-asserted-by":"publisher","DOI":"10.1175\/BAMS-D-15-00144.1"},{"key":"IJGHPC.2018010105-22","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2016.2602560"},{"key":"IJGHPC.2018010105-23","doi-asserted-by":"publisher","DOI":"10.1504\/IJBDI.2015.070596"},{"key":"IJGHPC.2018010105-24","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2013.6554990"},{"key":"IJGHPC.2018010105-25","doi-asserted-by":"publisher","DOI":"10.1109\/CEM.2015.7237429"},{"key":"IJGHPC.2018010105-26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compstruc.2013.06.015"},{"key":"IJGHPC.2018010105-27","article-title":"A rapid numerical algorithm to compute matrix inversion.","author":"F.Soleymani","year":"2012","journal-title":"International Journal of Mathematics and Mathematical Sciences"},{"key":"IJGHPC.2018010105-28","doi-asserted-by":"publisher","DOI":"10.4134\/CKMS.2013.28.2.407"},{"key":"IJGHPC.2018010105-29","doi-asserted-by":"publisher","DOI":"10.1049\/el.2015.2175"},{"key":"IJGHPC.2018010105-30","doi-asserted-by":"publisher","DOI":"10.4018\/ijghpc.2014010101"},{"key":"IJGHPC.2018010105-31","doi-asserted-by":"publisher","DOI":"10.1109\/OSSC.2011.6184687"},{"key":"IJGHPC.2018010105-32","doi-asserted-by":"crossref","unstructured":"Ylinen, M., Burian, A., & Takala, J. (2003, November). Updating matrix inverse in fixed-point representation: Direct versus iterative methods. In Proceedings of the International Symposium on System-on-Chip (pp. 45-48). IEEE.","DOI":"10.1109\/ISSOC.2003.1267714"},{"key":"IJGHPC.2018010105-33","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2012.6542793"},{"key":"IJGHPC.2018010105-34","doi-asserted-by":"publisher","DOI":"10.1504\/IJBDI.2016.077385"}],"container-title":["International Journal of Grid and High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=196240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T03:13:09Z","timestamp":1751166789000},"score":1,"resource":{"primary":{"URL":"http:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJGHPC.2018010105"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":35,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.4018\/ijghpc.2018010105","relation":{},"ISSN":["1938-0259","1938-0267"],"issn-type":[{"value":"1938-0259","type":"print"},{"value":"1938-0267","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}