{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T13:33:09Z","timestamp":1762781589030},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2010,4,2]],"date-time":"2010-04-02T00:00:00Z","timestamp":1270166400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comput Sci Res Dev"],"published-print":{"date-parts":[[2010,5]]},"DOI":"10.1007\/s00450-010-0112-6","type":"journal-article","created":{"date-parts":[[2010,4,1]],"date-time":"2010-04-01T14:52:39Z","timestamp":1270133559000},"page":"83-91","source":"Crossref","is-referenced-by-count":36,"title":["High performance conjugate gradient solver on multi-GPU clusters using hypergraph partitioning"],"prefix":"10.1007","volume":"25","author":[{"given":"Ali","family":"Cevahir","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"Nukada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,4,2]]},"reference":[{"key":"112_CR1","unstructured":"Baskaran MM, Bordawekar R (2008) Optimizing sparse matrix-vector multiplication on GPUs. IBM Research Report, RC24704"},{"key":"112_CR2","doi-asserted-by":"crossref","unstructured":"Bell N, Garland M (2009) Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: Proc SC \u201909: ACM\/IEEE Conference on Supercomputing, Portland, OR, USA","DOI":"10.1145\/1654059.1654078"},{"key":"112_CR3","doi-asserted-by":"crossref","unstructured":"Buatois L, Caumon G, L\u00e9vy B (2007) Concurrent number cruncher: an efficient linear solver on the GPU. In: Proc HPCC 2007. LNCS vol\u00a04782, pp\u00a0358\u2013371","DOI":"10.1007\/978-3-540-75444-2_37"},{"issue":"7","key":"112_CR4","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/71.780863","volume":"10","author":"UV Catalyurek","year":"1999","unstructured":"Catalyurek UV, Aykanat C (1999) Hypergraph-partitioning-based decomposition for parallel sparse-matrix vector multiplication. IEEE Trans Parallel Distrib Syst 10(7):673\u2013693","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"112_CR5","unstructured":"Catalyurek UV, Aykanat C (1999) A multilevel hypergraph partitioning tool, V.\u00a03.0. Tech Rep, Dept of Comp Eng, Bilkent University"},{"key":"112_CR6","unstructured":"Catalyurek UV, Ucar B, Aykanat C On two-dimensional sparse matrix partitioning: models, methods, and a recipe. Tech Rep, OSUBMI-TR_2008_2008_n04"},{"key":"112_CR7","series-title":"Lecture notes in computer science","first-page":"898","volume-title":"Fast conjugate gradients with multiple GPUs","author":"A Cevahir","year":"2009","unstructured":"Cevahir A, Nukada A, Matsuoka S (2009) Fast conjugate gradients with multiple GPUs. Lecture notes in computer science, vol 5544. Springer, Berlin, pp 898\u2013903"},{"key":"112_CR8","doi-asserted-by":"crossref","unstructured":"Che S, Li J, Sheaffer JW, Skadron K, Lach J (2008) Accelerating compute intensive applications with GPUs and FPGAs. In: Proc IEEE symposium on application specific processors (SASP)","DOI":"10.1109\/SASP.2008.4570793"},{"key":"112_CR9","unstructured":"Fan Z, Qiu F, Kaufman A, Stover SY (2004) GPU cluster for high performance computing. In: Proc SC\u201904: ACM\/IEEE conference on supercomputing"},{"issue":"10\u201311","key":"112_CR10","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1016\/j.parco.2007.09.002","volume":"33","author":"D G\u00f6ddeke","year":"2007","unstructured":"G\u00f6ddeke D, Strzodka R, Mohd-Yusof J, McCormick P, Buijssen SHM, Grajewski M, Turek S (2007) Exploring weak scalability for FEM calculations on a GPU-enhanced cluster. Parallel Comput 33(10\u201311):685\u2013699","journal-title":"Parallel Comput"},{"key":"112_CR11","unstructured":"GraphStream Inc.: GraphStream Scalable Computing Platforms. http:\/\/www.graphstream.com . Accessed 2009"},{"key":"112_CR12","unstructured":"Harris M (2007) Optimizing parallel reduction in CUDA. NVIDIA Developer Technology"},{"key":"112_CR13","doi-asserted-by":"crossref","unstructured":"Hartley TDR, Catalyurek UV, Ruiz A, Ujaldon M, Igual F, Mayo\u00a0R (2008) Biomedical image analysis on a cooperative cluster of GPUs and multicores. In: Proc 22nd ACM international conference on supercomputing, pp\u00a015\u201325","DOI":"10.1145\/1375527.1375533"},{"key":"112_CR14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-322-92106-2","volume-title":"Combinatorial algorithms for integrated circuit layout","author":"T Lengauer","year":"1990","unstructured":"Lengauer T (1990) Combinatorial algorithms for integrated circuit layout. Wiley, Chichester"},{"key":"112_CR15","series-title":"Computational science series","first-page":"289","volume-title":"The road to TSUBAME and beyond. Petascale computing: algorithms and applications","author":"S Matsuoka","year":"2008","unstructured":"Matsuoka S (2008) The road to TSUBAME and beyond. Petascale computing: algorithms and applications. Computational science series. Chapman & Hall\/CRC, London, pp\u00a0289\u2013310"},{"key":"112_CR16","doi-asserted-by":"crossref","unstructured":"Matsuoka S, Aoki T, Endo T, Nukada A, Kato T, Hasegawa A GPU-accelerated computing\u2014from hype to mainstream, the rebirth of vector computing. J Phys Conf Ser 180 (2009)","DOI":"10.1088\/1742-6596\/180\/1\/012043"},{"key":"112_CR17","unstructured":"NVIDIA Corporation (2007) NVIDIA CUDA compute unified device architecture programming guide"},{"key":"112_CR18","unstructured":"Saad Y (1990) SPARSKIT: A basic tool kit for sparse matrix computation. Tech Rep CSRD TR 1029, University of Illinois, Urbana, IL"},{"key":"112_CR19","unstructured":"Teresco JD, Faik J, Flaherty JR (2004) Hierarchical partitioning and dynamic load balancing for scientific computation. In: Proc PARA\u201904, pp\u00a0911\u2013920"},{"key":"112_CR20","unstructured":"University of Florida Sparse Matrix Collection. http:\/\/www.cise.ufl.edu\/research\/sparse\/matrices\/"}],"container-title":["Computer Science - Research and Development"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-010-0112-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00450-010-0112-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-010-0112-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,3]],"date-time":"2020-06-03T12:52:14Z","timestamp":1591188734000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00450-010-0112-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,4,2]]},"references-count":20,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2010,5]]}},"alternative-id":["112"],"URL":"https:\/\/doi.org\/10.1007\/s00450-010-0112-6","relation":{},"ISSN":["1865-2034","1865-2042"],"issn-type":[{"value":"1865-2034","type":"print"},{"value":"1865-2042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,4,2]]}}}