{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T06:46:35Z","timestamp":1765608395199},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,6,22]],"date-time":"2013-06-22T00:00:00Z","timestamp":1371859200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1007\/s10586-013-0279-2","type":"journal-article","created":{"date-parts":[[2013,6,21]],"date-time":"2013-06-21T20:08:04Z","timestamp":1371845284000},"page":"327-337","source":"Crossref","is-referenced-by-count":10,"title":["A communication reduction approach to iteratively solve large sparse linear systems on a GPGPU cluster"],"prefix":"10.1007","volume":"17","author":[{"given":"Chong","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tarek M.","family":"Taha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,6,22]]},"reference":[{"key":"279_CR1","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898718003","volume-title":"Iterative Methods for Sparse Linear Systems","author":"Y. Saad","year":"2003","unstructured":"Saad, Y.: Iterative Methods for Sparse Linear Systems, 2nd edn. SIAM, Philadelphia (2003)","edition":"2"},{"key":"279_CR2","volume-title":"Proceedings of SC \u201909","author":"N. Bell","year":"2009","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: Proceedings of SC \u201909, Portland, OR (2009)"},{"key":"279_CR3","volume-title":"Proceedings of SC\u201909","author":"M. Mohiyuddin","year":"2009","unstructured":"Mohiyuddin, M., Hoemmen, M., Demmel, J., Yelick, K.: Minimizing communication in sparse matrix solvers. In: Proceedings of SC\u201909 (2009)"},{"key":"279_CR4","first-page":"12","volume-title":"Proceedings of HPC\u201911","author":"J.M. Bahi","year":"2011","unstructured":"Bahi, J.M., Couturier, R., Khodja, L.J.: Parallel GMRES implementation for solving sparse linear systems on GPU clusters. In: Proceedings of HPC\u201911, Boston, MA, pp. 12\u201319 (2011)"},{"key":"279_CR5","first-page":"471","volume-title":"Lect. Notes Comput. Sci.","author":"J.M. Bahi","year":"2012","unstructured":"Bahi, J.M., Couturier, R., Khodja, L.J.: Parallel sparse linear solver GMRES for GPU clusters with compression of exchanged data. In: Lect. Notes Comput. Sci., vol. 7155, pp. 471\u2013480 (2012)"},{"key":"279_CR6","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/s00450-010-0112-6","volume":"25","author":"A. Cevahir","year":"2010","unstructured":"Cevahir, A., Nukada, A., Matsuoka, S.: High performance conjugate gradient solver on multi-GPU clusters using hypergraph partitioning. Comput. Sci. Res. Dev. 25, 83\u201391 (2010)","journal-title":"Comput. Sci. Res. Dev."},{"key":"279_CR7","volume-title":"The 2012 International Conference on Computational Science (ICCS), Procedia Computer Science","author":"H. He","year":"2012","unstructured":"He, H., Wanga, L., Lee, E., Chen, P.: An MPI-CUDA implementation and optimization for parallel sparse equations and least squares (LSQR). In: The 2012 International Conference on Computational Science (ICCS), Procedia Computer Science. Elsevier, Amsterdam (2012)"},{"key":"279_CR8","unstructured":"NVIDIA: CUDA programming guide, version 5.0 (2012)"},{"key":"279_CR9","unstructured":"CUSP library: http:\/\/code.google.com\/p\/cusp-library\/"},{"key":"279_CR10","volume-title":"Proceeding of TeraGrid \u201911","author":"P. Guo","year":"2011","unstructured":"Guo, P., Huang, H., Chen, Q., Wang, L., Lee, E., Chen, P.: A\u00a0model-driven partitioning and auto-tuning integrated framework for sparse matrix-vector multiplication on GPUs. In: Proceeding of TeraGrid \u201911, Salt Lake City, UT (2011)"},{"key":"279_CR11","volume-title":"The GPGPU 5","author":"J. Godwin","year":"2012","unstructured":"Godwin, J., Holewinski, J., Sadayappan, P.: High-performance sparse matrix-vector multiplication on GPUs for structured grid computations. In: The GPGPU 5, London, UK (2012)"},{"key":"279_CR12","unstructured":"NVIDIA: Developing a Linux kernel module using RDMA for GPU direct, v0.2, July 2012"},{"key":"279_CR13","first-page":"156","volume-title":"Lect. Notes Comput. Sci.","author":"A. Jordan","year":"2002","unstructured":"Jordan, A., Bycul, R.P.: The parallel algorithm of conjugate gradient method. In: Lect. Notes Comput. Sci., vol. 2326, pp. 156\u2013165 (2002)"},{"key":"279_CR14","volume-title":"Proceedings of 18th Euromicro Conference on Parallel, Distributed and Network-Based Processing","author":"M. Ament","year":"2010","unstructured":"Ament, M., Knittel, G., Weiskopf, D., Stra\u00dfer, W.: A parallel preconditioned conjugate gradient solver for the Poisson problem on a multi-GPU platform. In: Proceedings of 18th Euromicro Conference on Parallel, Distributed and Network-Based Processing, Pisa, Italy (2010)"},{"issue":"5","key":"279_CR15","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1137\/S1064827594271421","volume":"17","author":"M. Benzi","year":"1996","unstructured":"Benzi, M., Meyer, C.D., Tuma, M.: A sparse approximate inverse preconditioner for the conjugate gradient method. SIAM J. Sci. Comput. 17(5), 1135\u20131149 (1996)","journal-title":"SIAM J. Sci. Comput."},{"key":"279_CR16","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1023\/A:1023988426844","volume":"25","author":"T. Huckle","year":"2003","unstructured":"Huckle, T.: Factorized sparse approximate inverses for preconditioning. J. Supercomput. 25, 109\u2013117 (2003)","journal-title":"J. Supercomput."},{"key":"279_CR17","volume-title":"Proceeding of IPDPS\u201906","author":"K. Devine","year":"2006","unstructured":"Devine, K., Boman, E., Heaphy, R., Bisseling, R., Atalyurek, U.: Parallel hypergraph partitioning for scientific computing. In: Proceeding of IPDPS\u201906, Isle of Rhodes, Greece (2006)"},{"key":"279_CR18","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1002\/cpe.605","volume":"14","author":"K. Schloegel","year":"2012","unstructured":"Schloegel, K., Karypis, G., Kumar, K.: Parallel static and dynamic multi-constraint graph partitioning. Concurr. Comput. 14, 219\u2013240 (2012)","journal-title":"Concurr. Comput."},{"issue":"7","key":"279_CR19","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/71.780863","volume":"10","author":"U.V. Catalyurek","year":"1999","unstructured":"Catalyurek, U.V., Aykanat, C.: Hypergraph-partitioning-based decomposition for parallel sparse-matrix vector multiplication. IEEE Trans. Parallel Distrib. Syst. 10(7), 673\u2013693 (1999)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"2","key":"279_CR20","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.micpro.2011.05.005","volume":"36","author":"J.C. Pichel","year":"2012","unstructured":"Pichel, J.C., Rivera, F.F., Fern\u00e1ndez, M., Rodr\u00edguez, A.: Optimization of sparse matrix\u2013vector multiplication using reordering techniques on GPUs. Microprocess. Microsyst. 36(2), 65\u201377 (2012)","journal-title":"Microprocess. Microsyst."},{"key":"279_CR21","unstructured":"ViennaCL: http:\/\/viennacl.sourceforge.net\/"},{"key":"279_CR22","unstructured":"Davis, T., Hu, Y.: The University of Florida sparse matrix collection. http:\/\/www.cise.ufl.edu\/research\/sparse\/matrices\/"},{"key":"279_CR23","volume-title":"Proceedings of SC\u201910","author":"G.E. Blelloch","year":"2010","unstructured":"Blelloch, G.E., Koutis, I., Miller, G.L., Tangwongsan, K.: Hierarchical diagonal blocking and precision reduction applied to combinatorial multigrid. In: Proceedings of SC\u201910, New Orleans, LA (2010)"},{"key":"279_CR24","unstructured":"G\u00f6ddeke, D.: Fast and accurate finite-element multigrid solvers for PDE simulations on GPU clusters. PhD dissertation, Technische Universit\u00e4t Dortmund, Fakult\u00e4t f\u00fcr Mathematik, Logos Verlag, Berlin (2010). ISBN: 978-3-8325-2768-6"},{"issue":"3","key":"279_CR25","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1145\/882262.882364","volume":"22","author":"J. Bolz","year":"2003","unstructured":"Bolz, J., Schr, P.: Sparse matrix solvers on the GPU: conjugate gradients and multigrid. ACM Trans. Graph. 22(3), 917\u2013924 (2003)","journal-title":"ACM Trans. Graph."}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-013-0279-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-013-0279-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-013-0279-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T18:40:17Z","timestamp":1559241617000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-013-0279-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,22]]},"references-count":25,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["279"],"URL":"https:\/\/doi.org\/10.1007\/s10586-013-0279-2","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6,22]]}}}