{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:59:47Z","timestamp":1725551987846},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642119491"},{"type":"electronic","value":"9783642119507"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-11950-7_21","type":"book-chapter","created":{"date-parts":[[2010,4,7]],"date-time":"2010-04-07T06:00:27Z","timestamp":1270620027000},"page":"234-245","source":"Crossref","is-referenced-by-count":2,"title":["Optimizing Stencil Application on Multi-thread GPU Architecture Using Stream Programming Model"],"prefix":"10.1007","author":[{"given":"Fang","family":"Xudong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tang","family":"Yuhua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Guibin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tang","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Ying","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"21_CR1","unstructured":"AMD.: Ati stream computing user guide v1.4beta (2009), \n                    \n                      http:\/\/developer.amd.com\/gpu_assets\/Stream_Computing_User_Guide.pdf"},{"key":"21_CR2","unstructured":"NVIDIA.: Compute unified device architecture programming guide v2.1beta (2009), \n                    \n                      http:\/\/developer.download.nvidia.com\/compute\/cuda\/1_0\/NVIDIA_CUDA_Programming_Guide_1.0.pdf"},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1145\/1345206.1345220","volume-title":"PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming","author":"S. Ryoo","year":"2008","unstructured":"Ryoo, S., Rodrigues, C.I., Baghsorkhi, S.S., Stone, S.S., Kirk, D.B., Hwu, W.m.W.: Optimization principles and application performance evaluation of a multithreaded gpu using cuda. In: PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming, pp. 73\u201382. ACM, New York (2008)"},{"issue":"6","key":"21_CR4","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1145\/1273442.1250761","volume":"42","author":"S. Krishnamoorthy","year":"2007","unstructured":"Krishnamoorthy, S., Baskaran, M., Bondhugula, U., Ramanujam, J., Rountev, A., Sadayappan, P.: Effective automatic parallelization of stencil computations. SIGPLAN Not.\u00a042(6), 235\u2013244 (2007)","journal-title":"SIGPLAN Not."},{"key":"21_CR5","first-page":"47","volume-title":"SC 2004: Proceedings of the 2004 ACM\/IEEE conference on Supercomputing","author":"Z. Fan","year":"2004","unstructured":"Fan, Z., Qiu, F., Kaufman, A., Yoakum-Stover, S.: Gpu cluster for high performance computing. In: SC 2004: Proceedings of the 2004 ACM\/IEEE conference on Supercomputing, Washington, DC, USA, p. 47. IEEE Computer Society Press, Los Alamitos (2004)"},{"key":"21_CR6","unstructured":"Buck, I.: Brook specification v0.2 (2003), \n                    \n                      http:\/\/hci.stanford.edu\/cstr\/reports\/2003-04.pdf"},{"issue":"10","key":"21_CR7","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1016\/j.jpdc.2008.05.011","volume":"68","author":"S. Ryoo","year":"2008","unstructured":"Ryoo, S., Rodrigues, C.I., Stone, S.S., Stratton, J.A., Ueng, S.-Z., Baghsorkhi, S.S., Hwu, W.-m.W.: Program optimization carving for gpu computing. J. Parallel Distrib. Comput.\u00a068(10), 1389\u20131401 (2008)","journal-title":"J. Parallel Distrib. Comput."},{"key":"21_CR8","first-page":"49","volume-title":"SC 2003: Proceedings of the 2003 ACM\/IEEE conference on Supercomputing","author":"T. Mohan","year":"2003","unstructured":"Mohan, T., de Supinski, B.R., McKee, S.A., Mueller, F., Yoo, A., Schulz, M.: Identifying and exploiting spatial regularity in data memory references. In: SC 2003: Proceedings of the 2003 ACM\/IEEE conference on Supercomputing, Washington, DC, USA, p. 49. IEEE Computer Society, Los Alamitos (2003)"},{"key":"21_CR9","unstructured":"Harris, M.J., Baxter, W.V., Scheuermann, T., Lastra, A.: Simulation of cloud dynamics on graphics hardware. In: HWWS 2003: Proceedings of the ACM SIGGRAPH\/EUROGRAPHICS conference on Graphics hardware, Aire-la-Ville, Switzerland, Switzerland, pp. 92\u2013101. Eurographics Association (2003)"},{"key":"21_CR10","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1145\/567067.567085","volume-title":"POPL 1983: Proceedings of the 10th ACM SIGACT-SIGPLAN symposium on Principles of programming languages","author":"J.R. Allen","year":"1983","unstructured":"Allen, J.R., Kennedy, K., Porterfield, C., Warren, J.: Conversion of control dependence to data dependence. In: POPL 1983: Proceedings of the 10th ACM SIGACT-SIGPLAN symposium on Principles of programming languages, pp. 177\u2013189. ACM, New York (1983)"},{"key":"21_CR11","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1145\/1345206.1345220","volume-title":"PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming","author":"S. Ryoo","year":"2008","unstructured":"Ryoo, S., Rodrigues, C.I., Baghsorkhi, S.S., Stone, S.S., Kirk, D.B., Hwu, W.-m.W.: Optimization principles and application performance evaluation of a multithreaded gpu using cuda. In: PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming, pp. 73\u201382. ACM, New York (2008)"},{"key":"21_CR12","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1145\/1513895.1513903","volume-title":"GPGPU-2: Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units","author":"B. Jang","year":"2009","unstructured":"Jang, B., Do, S., Pien, H., Kaeli, D.: Architecture-aware optimization targeting multithreaded stream computing. In: GPGPU-2: Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units, pp. 62\u201370. ACM, New York (2009)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Wang, G., Yang, X.J., Zhang, Y., Tang, T., Fang, X.D.: Program optimization of stencil based application on the gpu-accelerated system. In: Intl. Symposium on Parallel and Distributed Processing and Applications, pp. 219\u2013225 (2009)","DOI":"10.1109\/ISPA.2009.70"},{"issue":"6","key":"21_CR14","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1145\/1034774.1034777","volume":"26","author":"Z. Li","year":"2004","unstructured":"Li, Z., Song, Y.: Automatic tiling of iterative stencil loops. ACM Trans. Program. Lang. Syst.\u00a026(6), 975\u20131028 (2004)","journal-title":"ACM Trans. Program. Lang. Syst."}],"container-title":["Lecture Notes in Computer Science","Architecture of Computing Systems - ARCS 2010"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-11950-7_21.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T08:00:52Z","timestamp":1619769652000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-11950-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642119491","9783642119507"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-11950-7_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}