{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T06:12:06Z","timestamp":1747807926447},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642131189"},{"type":"electronic","value":"9783642131196"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-13119-6_36","type":"book-chapter","created":{"date-parts":[[2010,5,25]],"date-time":"2010-05-25T20:35:39Z","timestamp":1274819739000},"page":"416-426","source":"Crossref","is-referenced-by-count":7,"title":["Optimizing Sweep3D for Graphic Processor Unit"],"prefix":"10.1007","author":[{"given":"Chunye","family":"Gong","sequence":"first","affiliation":[]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhenghu","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"36_CR1","volume-title":"GPU Gems 3","author":"H. Nguyen","year":"2007","unstructured":"Nguyen, H.: GPU Gems 3. Addison Wesley, Reading (2007)"},{"key":"36_CR2","unstructured":"Kirk, D.: Innovation in graphics technology. In: Talk in Canadian Undergraduate Technology Conference (2004)"},{"key":"36_CR3","unstructured":"AMD Corporation: ATI Radeon HD 5870 Feature Summary, http:\/\/www.amd.com\/"},{"key":"36_CR4","unstructured":"NVIDIA Corporation: CUDA Programming Guide Version 2.1 (2008)"},{"key":"36_CR5","unstructured":"AMD Corporation: ATI Stream Computing User Guide Version 1.4.0a (2009)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Munshi, A.: The OpenCL Specification Version: 1.0. Khronos OpenCL Working Group (2009)","DOI":"10.1109\/HOTCHIPS.2009.7478342"},{"key":"36_CR7","unstructured":"NVIDIA Corporation: Vertical solutions on CUDA, http:\/\/www.nvidia.com\/object\/vertical_solutions.html"},{"key":"36_CR8","first-page":"255","volume-title":"Proc. ACM Int. Conf. Supercomputing","author":"M.M. Mathis","year":"2000","unstructured":"Mathis, M.M., Amato, N., Adams, M., Zhao, W.: A General Performance Model for Parallel Sweeps on Orthogonal Grids for Particle Transport Calculations. In: Proc. ACM Int. Conf. Supercomputing, pp. 255\u2013263. ACM, New York (2000)"},{"key":"36_CR9","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/FMPC.1999.750452","volume-title":"The 7th Symposium on the Frontiers of Massively Parallel Computation","author":"A. Hoisie","year":"1999","unstructured":"Hoisie, A., Lubeck, O., Wasserman, H.: Scalability analysis of multidimensional wavefront algorithms on large-scale SMP clusters. In: The 7th Symposium on the Frontiers of Massively Parallel Computation, pp. 4\u201315. IEEE Computer Society, Los Alamitos (1999)"},{"issue":"4","key":"36_CR10","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1177\/109434200001400405","volume":"14","author":"A. Hoisie","year":"2000","unstructured":"Hoisie, A., Lubeck, O., Wasserman, H.: Performance and scalability analysis of teraflop- scale parallel architectures using multidimensional wavefront applications. International Journal of High Performance Computing Applications\u00a014(4), 330\u2013346 (2000)","journal-title":"International Journal of High Performance Computing Applications"},{"key":"36_CR11","unstructured":"Los Alamos National Laboratory: Sweep3D, http:\/\/wwwc3.lanl.gov\/pal\/software\/sweep3d\/"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Davis, K., Hoisie, A., Johnson, G., Kerbyson, D.J., Lang, M., Pakin, M., Petrini, F.: A Performance and Scalability Analysis of the BlueGene\/L Architecture. In: Proceedings of the 2004 ACM\/IEEE conference on Supercomputing, pp. 41\u201350 (2004)","DOI":"10.1109\/SC.2004.8"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Barker, K.J., Davis, K., Hoisie, A., Kerbyson, D.J., Lang, M., Pakin, S., Sancho, J.C.: Entering the petaflop era: the architecture and performance of Roadrunner. In: Proceedings of the 2008 ACM\/IEEE conference on Supercomputing (2008)","DOI":"10.1109\/SC.2008.5217926"},{"key":"36_CR14","unstructured":"Lewis, E.E., Miller, W.F.: Computational Methods of Neutron Transport. American Nuclear Society, LaGrange Park (1993)"},{"key":"36_CR15","first-page":"198","volume":"65","author":"K. Koch","year":"1992","unstructured":"Koch, K., Baker, R., Alcouffe, R.: Solution of the First-Order Form of Three-Dimensional Discrete Ordinates Equations on a Massively Parallel Machine. Transactions of American Nuclear Society\u00a065, 198\u2013199 (1992)","journal-title":"Transactions of American Nuclear Society"},{"key":"36_CR16","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/s11227-005-2339-8","volume":"34","author":"M.M. Mathis","year":"2005","unstructured":"Mathis, M.M., Kerbyson, D.J.: A General Performance Model of structured and Unstructured Mesh Particle Transport Computations. Journal of Supercomputing\u00a034, 181\u2013199 (2005)","journal-title":"Journal of Supercomputing"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Kerbyson, D.J., Hoisie, A.: Analysis of Wavefront Algorithms on Large-scale Two-level Heterogeneous Processing Systems. In: Workshop on Unique Chips and Systems, pp. 259\u2013279 (2006)","DOI":"10.1201\/9781420051759.ch10"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Petrini, F., Fossum, G., Fernandez, J., Varbanescu, A.L., Kistler, N., Perrone, M.: Multicore Surprises: Lessons Learned from Optimizing Sweep3D on the Cell Broadband Engine. In: The 21th International Parallel and Distributed Processing Symposium (2007)","DOI":"10.1109\/IPDPS.2007.370252"},{"key":"36_CR19","unstructured":"NVIDIA Corporation: NVIDIA Tesla S1070 1U Computing System, http:\/\/www.nvidia.com\/object\/product_tesla_s1070_us.html"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Volkov, V., Demmel, J.W.: Benchmarking GPUs to tune dense linear algebra. In: Proceedings of the 2008 ACM\/IEEE conference on Supercomputing (2008)","DOI":"10.1109\/SC.2008.5214359"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-13119-6_36.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T22:01:38Z","timestamp":1606168898000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-13119-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642131189","9783642131196"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-13119-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}