{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:17:46Z","timestamp":1763468266437},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783662480953"},{"type":"electronic","value":"9783662480960"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-662-48096-0_52","type":"book-chapter","created":{"date-parts":[[2015,7,24]],"date-time":"2015-07-24T02:16:03Z","timestamp":1437704163000},"page":"675-686","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Systematic Fusion of CUDA Kernels for Iterative Sparse Linear System Solvers"],"prefix":"10.1007","author":[{"given":"Jos\u00e9 I.","family":"Aliaga","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joaqu\u00edn","family":"P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,25]]},"reference":[{"key":"52_CR1","unstructured":"CSB library (2014), \n                      http:\/\/gauss.cs.ucsb.edu\/aydin\/csb\/html\/"},{"key":"52_CR2","doi-asserted-by":"crossref","unstructured":"Aliaga, J.I., P\u00e9rez, J., Quintana-Ort\u00ed, E.S., Anzt, H.: Reformulated conjugate gradient for the energy-aware solution of linear systems on GPUs. In: 42nd International Conference on Parallel Processing (ICPP), pp. 320\u2013329 (2013)","DOI":"10.1109\/ICPP.2013.41"},{"key":"52_CR3","doi-asserted-by":"crossref","unstructured":"Aliaga, J.I., et al.: Unveiling the performance-energy trade-off in iterative linear system solvers for multithreaded processors. Concurrency and Computation: Practice and Experience (2014, to appear)","DOI":"10.1002\/cpe.3341"},{"key":"52_CR4","doi-asserted-by":"crossref","unstructured":"Anzt, H., Sawyer, W., Tomov, S., Luszczek, P., Yamazaki, I., Dongarra, J.: Optimizing Krylov subspace solvers on graphics processing units. In: IEEE International Parallel Distributed Processing Symposium Workshops (IPDPSW), pp. 941\u2013949 (2014)","DOI":"10.1109\/IPDPSW.2014.107"},{"key":"52_CR5","doi-asserted-by":"crossref","unstructured":"Anzt, H., et al.: Analysis and optimization of power consumption in the iterative solution of sparse linear systems on multi-core and many-core platforms. In: International Green Computing Conference Workshops (IGCC), pp. 1\u20136 (2011)","DOI":"10.1109\/IGCC.2011.6008594"},{"key":"52_CR6","unstructured":"Bell, N., Garland, M.: Efficient sparse matrix-vector multiplication on CUDA. NVIDIA Technical report NVR-2008-004, NVIDIA Corp., December 2008"},{"key":"52_CR7","doi-asserted-by":"crossref","unstructured":"Bulu\u00e7, A., Williams, S., Oliker, L., Demmel, J.: Reduced-bandwidth multithreaded algorithms for sparse matrix-vector multiplication. In: IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 721\u2013733 (2011)","DOI":"10.1109\/IPDPS.2011.73"},{"key":"52_CR8","doi-asserted-by":"crossref","unstructured":"Choi, J.W., Singh, A., Vuduc, R.W.: Model-driven autotuning of sparse matrix-vector multiply on GPUs. In: ACM SIGPLAN Symposium Principles and Practice of Parallel Programming (PPoPP), vol. 45, pp. 115\u2013126 (2010)","DOI":"10.1145\/1837853.1693471"},{"key":"52_CR9","unstructured":"Duranton, M., et al.: HiPEAC vision 2015. High performance and embedded architecture and compilation (2015). \n                      http:\/\/www.hipeac.net\/vision"},{"key":"52_CR10","unstructured":"Filipovic, J., Madzin, M., Fousek, J., Matyska, L.: Optimizing CUDA code by kernel fusion\u2013application on BLAS. Computing Research Repository (CoRR) abs\/1305.1183 (2013). \n                      http:\/\/arxiv.org\/abs\/1305.1183"},{"key":"52_CR11","doi-asserted-by":"crossref","unstructured":"Fuller, S.H., Millett, L.I.: The Future of Computing Performance: Game Over or Next Level? National Research Council of the National Academies (2011)","DOI":"10.1109\/MC.2011.15"},{"key":"52_CR12","doi-asserted-by":"publisher","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. SIAM, Philadelphia (2003)"},{"issue":"2","key":"52_CR13","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/s11227-014-1102-4","volume":"70","author":"S Tabik","year":"2014","unstructured":"Tabik, S., Ortega, G., Garz\u00f3n, E.: Performance evaluation of kernel fusion BLAS routines on the GPU: iterative solvers as case study. J. Supercomputing 70(2), 577\u2013587 (2014)","journal-title":"J. Supercomputing"},{"key":"52_CR14","doi-asserted-by":"crossref","unstructured":"Wang, G., Lin, Y., Yi, W.: Kernel fusion: An effective method for better power efficiency on multithreaded GPU. In: Green Computing and Communications (GreenCom), pp. 344\u2013350 (2010)","DOI":"10.1109\/GreenCom-CPSCom.2010.102"},{"key":"52_CR15","doi-asserted-by":"crossref","unstructured":"Williams, S., Bell, N., Choi, J., Garland, M., Oliker, L., Vuduc, R.: Sparse matrix vector multiplication on multicore and accelerator systems. In: Kurzak, J., Bader, D.A., Dongarra, J. (eds.) Scientific Computing with Multicore Processors and Accelerators. CRC Press (2010)","DOI":"10.1201\/b10376-8"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2015: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-48096-0_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,19]],"date-time":"2020-04-19T20:36:13Z","timestamp":1587328573000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-48096-0_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783662480953","9783662480960"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-48096-0_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"25 July 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}