{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:46:17Z","timestamp":1743126377686,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319065472"},{"type":"electronic","value":"9783319065489"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-06548-9_2","type":"book-chapter","created":{"date-parts":[[2014,7,3]],"date-time":"2014-07-03T08:32:46Z","timestamp":1404376366000},"page":"29-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Guide for Implementing Tridiagonal Solvers on GPUs"],"prefix":"10.1007","author":[{"given":"Li-Wen","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-mei W.","family":"Hwu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,6,9]]},"reference":[{"issue":"6\u20137","key":"2_CR1","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.parco.2012.03.003","volume":"38","author":"F. Arg\u00fcello","year":"2012","unstructured":"Arg\u00fcello, F., Heras, D.B., B\u00f3o, M., Lamas-Rodr\u00edguez, J.: The split-and-merge method in general purpose computation on GPUs. Parallel Comput. 38(6\u20137), 277\u2013288 (2012)","journal-title":"Parallel Comput."},{"key":"2_CR2","unstructured":"Chang, L.-W., Hwu, W.-m.W.: Mapping tridiagonal solvers to linear recurrences. Technical report, University of Illinois at Urbana-Champaign (2013)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chang, L.-W., Lo, M.-T., Anssari, N., Hsu, K.-H., Huang, N.E., Hwu, W.-m.W.: Parallel implementation of multi-dimensional ensemble empirical mode decomposition. In: International Conference on Acoustics, Speech, and Signal Processing, pp. 1621\u20131624 (May 2011)","DOI":"10.1109\/ICASSP.2011.5946808"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chang, L.-W., Stratton, J.A., Kim, H.-S., Hwu, W.-m.W.: A scalable, numerically stable, high-performance tridiagonal solver using GPUs. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC \u201912, pp. 27:1\u201327:11 (2012)","DOI":"10.1109\/SC.2012.12"},{"key":"2_CR5","volume-title":"Elementary Numerical Analysis: An Algorithmic Approach","author":"S.D. Conte","year":"1980","unstructured":"Conte, S.D., De Boor, C.W.: Elementary Numerical Analysis: An Algorithmic Approach, 3rd edn. McGraw-Hill Higher Education, New York (1980)","edition":"3"},{"key":"2_CR6","volume-title":"Register packing for cyclic reduction: a case study","author":"A. Davidson","year":"2011","unstructured":"Davidson, A., Owens, J.D.: Register packing for cyclic reduction: a case study. In: Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units (2011)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Davidson, A., Zhang, Y., Owens, J.D.: An auto-tuned method for solving large tridiagonal systems on the GPU. In: Proceedings of the 25th IEEE International Parallel and Distributed Processing Symposium (May 2011)","DOI":"10.1109\/IPDPS.2011.92"},{"key":"2_CR8","first-page":"50","volume":"50","author":"D. Egloff","year":"2010","unstructured":"Egloff, D.: GPUs in financial computing part II: massively parallel solvers on GPUs. Wilmott, 50, 50\u201353 (Nov 2010)","journal-title":"Wilmott"},{"key":"2_CR9","first-page":"51","volume":"52","author":"D. Egloff","year":"2011","unstructured":"Egloff, D.: GPUs in financial computing part III: ADI solvers on GPUs with application to stochastic volatility. Wilmott, 52, 51\u201353 (Mar 2011)","journal-title":"Wilmott"},{"issue":"4","key":"2_CR10","first-page":"269","volume":"40","author":"J.B. Erway","year":"2010","unstructured":"Erway, J.B., Marcia, R.F., Tyson, J.A.: Generalized diagonal pivoting methods for tridiagonal systems without interchanges. IAENG Int. J. Appl. Math. 40(4), 269\u2013275 (2010)","journal-title":"IAENG Int. J. Appl. Math."},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/TPDS.2010.61","volume":"22","author":"D. G\u00f6ddeke","year":"2011","unstructured":"G\u00f6ddeke, D., Strzodka, R.: Cyclic reduction tridiagonal solvers on GPUs applied to mixed-precision multigrid. IEEE Trans. Parallel Distrib. Syst. 22, 22\u201332 (2011)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2_CR12","volume-title":"Parallel Computers: Architecture","author":"R.W. Hockney","year":"1981","unstructured":"Hockney, R.W., Jesshope, C.R.: Parallel Computers: Architecture, Programming and Algorithms. Hilger, Bristol (1981)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Kim, H.-S., Wu, S., Chang, L.-W., Hwu, W.-m.W.: A scalable tridiagonal solver for GPUs. In: 2011 International Conference on Parallel Processing (ICPP), pp. 444\u2013453 (2011)","DOI":"10.1109\/ICPP.2011.41"},{"key":"2_CR14","unstructured":"NVIDIA Corporation: CUDA Programming Guide 5.5 (2013)"},{"key":"2_CR15","volume-title":"CUSPARSE Library","author":"NVIDIA Corporation","year":"2013","unstructured":"NVIDIA Corporation: CUSPARSE Library (2013)"},{"issue":"2","key":"2_CR16","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.parco.2005.07.005","volume":"32","author":"E. Polizzi","year":"2006","unstructured":"Polizzi, E., Sameh, A.H.: A parallel hybrid banded system solver: the SPIKE algorithm. Parallel Comput. 32(2), 177\u2013194 (2006)","journal-title":"Parallel Comput."},{"key":"2_CR17","volume-title":"Tridiagonal solvers on the GPU and applications to fluid simulation","author":"N. Sakharnykh","year":"2009","unstructured":"Sakharnykh, N.: Tridiagonal solvers on the GPU and applications to fluid simulation. In: NVIDIA GPU Technology Conference (September 2009)"},{"key":"2_CR18","volume-title":"Efficient tridiagonal solvers for ADI methods and fluid simulation","author":"N. Sakharnykh","year":"2010","unstructured":"Sakharnykh, N.: Efficient tridiagonal solvers for ADI methods and fluid simulation. In: NVIDIA GPU Technology Conference (September 2010)"},{"issue":"1","key":"2_CR19","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1145\/322047.322054","volume":"25","author":"A.H. Sameh","year":"1978","unstructured":"Sameh, A.H., Kuck, D.J.: On stable parallel linear system solvers. J. ACM 25(1), 81\u201391 (1978)","journal-title":"J. ACM"},{"key":"2_CR20","first-page":"97","volume":"2007","author":"S. Sengupta","year":"2007","unstructured":"Sengupta, S., Harris, M., Zhang, Y., Owens, J.D.: Scan primitives for gpu computing. In: Graphics Hardware 2007, pp. 97\u2013106 (2007)","journal-title":"In: Graphics Hardware"},{"issue":"1","key":"2_CR21","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/321738.321741","volume":"20","author":"H.S. Stone","year":"1973","unstructured":"Stone, H.S.: An efficient parallel algorithm for the solution of a tridiagonal linear system of equations. J. ACM 20(1), 27\u201338 (1973)","journal-title":"J. ACM"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Sung, I.-J., Stratton, J.A., Hwu, W.-M.W.: Data layout transformation exploiting memory-level parallelism in structured grid many-core applications. In: PACT \u201910: Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques, pp. 513\u2013522. ACM, New York (2010)","DOI":"10.1145\/1854273.1854336"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Cohen, J., Owens, J.D.: Fast tridiagonal solvers on the GPU. In: Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP \u201910, pp. 127\u2013136 (2010)","DOI":"10.1145\/1693453.1693472"}],"container-title":["Numerical Computations with GPUs"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-06548-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T20:57:41Z","timestamp":1674161861000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-06548-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319065472","9783319065489"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-06548-9_2","relation":{},"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"9 June 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}