{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:55:16Z","timestamp":1725558916481},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642143892"},{"type":"electronic","value":"9783642143908"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14390-8_14","type":"book-chapter","created":{"date-parts":[[2010,7,7]],"date-time":"2010-07-07T05:11:54Z","timestamp":1278479514000},"page":"125-135","source":"Crossref","is-referenced-by-count":4,"title":["Parallel Implementation of Conjugate Gradient Method on Graphics Processors"],"prefix":"10.1007","author":[{"given":"Marcin","family":"Wozniak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomasz","family":"Olas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roman","family":"Wyrzykowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"3","key":"14_CR1","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/S0167-8191(97)00005-7","volume":"23","author":"A. Basermann","year":"1997","unstructured":"Basermann, A., Reichel, B., Schelthoff, C.: Preconditioned CG methods for sparse matrices on massively parallel machines. Parallel Computing Journal\u00a023(3), 381\u2013393 (1997)","journal-title":"Parallel Computing Journal"},{"key":"14_CR2","unstructured":"Baskaran, M.M., Bordawekar, R.: Optimizing Sparse Matrix-Vector Multiplication on GPUs. IBM Research Report No. RC24704, W0812-047 (2009)"},{"key":"14_CR3","unstructured":"Bell, N., Garland, M.: Efficient Sparse Matrix-Vector Multiplication on CUDA. NVIDIA Tech. Report No. NVR-2008-004 (2008)"},{"key":"14_CR4","unstructured":"CUDPP: CUDA Data Parallel Primitives Library, http:\/\/gpgpu.org\/developer\/cudpp"},{"key":"14_CR5","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-540-68783-2_5","volume-title":"Geometric Modelling, Numerical Simulation, and Optimization: Applied Mathematics at SINTEF","author":"T. Dokken","year":"2007","unstructured":"Dokken, T., Hagen, T.R., Hjelmervik, J.M.: An Introduction to General-Purpose Computing on Programmable Graphics Hardware. In: Geometric Modelling, Numerical Simulation, and Optimization: Applied Mathematics at SINTEF, pp. 123\u2013161. Springer, Heidelberg (2007)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Fujimoto, N.: Faster matrix-vector multiplication on GeForce 8800GTX. In: Proc. IEEE Int. Symp. on Parallel and Distributed Processing - IPDPS 2008, pp. 1\u20138 (2008)","DOI":"10.1109\/IPDPS.2008.4536350"},{"issue":"2","key":"14_CR7","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1365490.1365500","volume":"6","author":"J. Nickolls","year":"2008","unstructured":"Nickolls, J., Buck, I., Garland, M., Skadron, K.: Scalable Parallel Programming with CUDA. Queue\u00a06(2), 40\u201353 (2008)","journal-title":"Queue"},{"key":"14_CR8","unstructured":"NVIDIA CUDA Programming Guide 2.2, http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_2\/toolkit\/docs\/NVIDIA_CUDA_Programming_Guide_2.2.pdf"},{"key":"14_CR9","unstructured":"OpenCL - The open standard for parallel programming of heterogeneous systems, http:\/\/www.khronos.org\/opencl"},{"key":"14_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/3-540-48086-2_19","volume-title":"Parallel Processing and Applied Mathematics","author":"T. Olas","year":"2002","unstructured":"Olas, T., Karczewski, K., Tomas, A., Wyrzykowski, R.: FEM Computations on Clusters Using Different Models of Parallel Programming. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Wa\u015bniewski, J. (eds.) PPAM 2001. LNCS, vol.\u00a02328, pp. 170\u2013184. Springer, Heidelberg (2002)"},{"key":"14_CR11","unstructured":"Saad, Y.: SPARSKIT: A basic toolkit for sparse matrix computations, http:\/\/www-users.cs.umn.edu\/~saad\/software\/SPARSKIT\/paper.ps"},{"key":"14_CR12","unstructured":"Sengupta, S., Harris, M., Zhang, Y., Owens, J.D.: Scan Primitives for GPU Computing. In: Proc. 22nd ACM SIGGRAPH\/EUROGRAPHICS Symp. on Graphics Hardware, pp. 97\u2013106 (2007)"},{"key":"14_CR13","unstructured":"Smailbegovic, F.S., Gaydadjiev, G.N., Vassiliadis, S.: Sparse Matrix Storage Format. In: Proc. 16th Ann. Workshop on Circuits, Systems and Signal Processing, ProRisc 2005, pp. 445\u2013448 (2005)"},{"key":"14_CR14","unstructured":"Stathis, P.T.: Sparse Matrix Vector Processing Formats. PhD Thesis, Delft University of Technology (2004), http:\/\/ce.et.tudelft.nl\/publicationfiles\/955_1_Thesis_P_T_Stathis.pdf"},{"issue":"8","key":"14_CR15","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1016\/j.simpat.2005.08.001","volume":"13","author":"R. Strzodka","year":"2005","unstructured":"Strzodka, R., Doggett, M., Kolb, A.: Scientific computation for simulations on programmable graphics hardware. Simulation Modelling Practice and Theory\u00a013(8), 667\u2013860 (2005)","journal-title":"Simulation Modelling Practice and Theory"},{"key":"14_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/11752578_21","volume-title":"Parallel Processing and Applied Mathematics","author":"P. Tvrdik","year":"2006","unstructured":"Tvrdik, P., Simecek, I.: A New Diagonal Blocking Format and Model of Cache Behavior for Sparse Matrices. In: Wyrzykowski, R., Dongarra, J., Meyer, N., Wa\u015bniewski, J. (eds.) PPAM 2005. LNCS, vol.\u00a03911, pp. 164\u2013171. Springer, Heidelberg (2006)"},{"key":"14_CR17","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/SYNASC.2006.4","volume-title":"Proc. 8th Int. Symp. on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2006","author":"P. Tvrdik","year":"2006","unstructured":"Tvrdik, P., Simecek, I.: A New Approach for Accelerating the Sparse Matrix-Vector Multiplication. In: Proc. 8th Int. Symp. on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2006, pp. 156\u2013163. IEEE Computer Society, Los Alamitos (2006)"},{"key":"14_CR18","unstructured":"V\u00e1zquez, F., Garz\u00f3n, E.M., Mart\u00ednez, J.A., Fern\u00e1ndez, J.J.: Accelerating sparse matrix vector product with GPUs. In: Proc. 9th Int. Conf. Computational and Mathematical Methods in Science and Engineering, CMMSE, pp. 1081\u20131092 (2009)"},{"key":"14_CR19","unstructured":"Vuduc, R.W.: Automatic Performance Tuning of Sparse Matrix Kernels. PhD Thesis, University of California, Berkeley (2003), http:\/\/bebop.cs.berkeley.edu\/pubs\/vuduc2003-dissertation.pdf"},{"issue":"3","key":"14_CR20","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.parco.2008.12.006","volume":"35","author":"S. Williams","year":"2009","unstructured":"Williams, S., Oliker, l., Vuduc, R., Shalf, J., Yelick, K., Demmel, J.: Optimization of sparse matrix-vector multiplication on emerging multicore platforms. Parallel Computing\u00a035(3), 178\u2013194 (2009)","journal-title":"Parallel Computing"},{"key":"14_CR21","volume-title":"PC-clusters and multicore architectures","author":"R. Wyrzykowski","year":"2009","unstructured":"Wyrzykowski, R.: PC-clusters and multicore architectures. EXIT, Warsaw (2009) (in Polish)"},{"key":"14_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/BFb0002750","volume-title":"Euro-Par \u201997 Parallel Processing","author":"R. Wyrzykowski","year":"1997","unstructured":"Wyrzykowski, R., Kanevski, J.: A Technique for Mapping Sparse Matrix Computations into Regular Processor Arrays. In: Lengauer, C., Griebl, M., Gorlatch, S. (eds.) Euro-Par 1997. LNCS, vol.\u00a01300, pp. 310\u2013317. Springer, Heidelberg (1997)"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14390-8_14.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T21:51:55Z","timestamp":1606168315000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14390-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642143892","9783642143908"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14390-8_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}