{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T07:21:04Z","timestamp":1777965664984,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783662483497","type":"print"},{"value":"9783662483503","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-662-48350-3_2","type":"book-chapter","created":{"date-parts":[[2015,9,1]],"date-time":"2015-09-01T01:40:34Z","timestamp":1441071634000},"page":"13-24","source":"Crossref","is-referenced-by-count":5,"title":["Sorting and Permuting without Bank Conflicts on GPUs"],"prefix":"10.1007","author":[{"given":"Peyman","family":"Afshani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nodari","family":"Sitchinava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,11,12]]},"reference":[{"key":"2_CR1","unstructured":"Afshani, P., Sitchinava, N.: Sorting and permuting without bank conflicts on GPUs. CoRR abs\/1507.01391 (2015), http:\/\/arxiv.org\/abs\/1507.01391"},{"key":"2_CR2","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1145\/48529.48535","volume":"31","author":"A. Aggarwal","year":"1988","unstructured":"Aggarwal, A., Vitter, J.S.: The input\/output complexity of sorting and related problems. Commun. ACM\u00a031, 1116\u20131127 (1988)","journal-title":"Commun. ACM"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Arge, L., Goodrich, M.T., Nelson, M.J., Sitchinava, N.: Fundamental parallel algorithms for private-cache chip multiprocessors. In: 20th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA), pp. 197\u2013206 (2008)","DOI":"10.1145\/1378533.1378573"},{"key":"2_CR4","unstructured":"Batcher, K.E.: Sorting networks and their applications. In: AFIPS Spring Joint Computer Conference, pp. 307\u2013314"},{"key":"2_CR5","unstructured":"Blelloch, G.E., Chowdhury, R.A., Gibbons, P.B., Ramachandran, V., Chen, S., Kozuch, M.: Provably good multicore cache performance for divide-and-conquer algorithms. In: 19th ACM-SIAM Symp. on Discrete Algorithms, pp. 501\u2013510 (2008)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Catanzaro, B., Keller, A., Garland, M.: A decomposition for in-place matrix transposition. In: 19th ACM SIGPLAN Principles and Practices of Parallel Programming (PPoPP), pp. 193\u2013206 (2014)","DOI":"10.1145\/2692916.2555253"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Cole, R.: Parallel merge sort. In: 27th IEEE Symposium on Foundations of Computer Science. pp. 511\u2013516 (1986)","DOI":"10.1109\/SFCS.1986.41"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Dotsenko, Y., Govindaraju, N.K., Sloan, P.P., Boyd, C., Manfedelli, J.: Fast Scan Algorithms on Graphics Processors. In: 22nd International Conference on Supercomputing, pp. 205\u2013213 (2008)","DOI":"10.1145\/1375527.1375559"},{"issue":"9","key":"2_CR9","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1109\/TC.1972.5009071","volume":"21","author":"M. Flynn","year":"1972","unstructured":"Flynn, M.: Some computer organizations and their effectiveness. IEEE Transactions on Computers C\u00a021(9), 948\u2013960 (1972)","journal-title":"IEEE Transactions on Computers C"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Frigo, M., Leiserson, C.E., Prokop, H., Ramachandran, S.: Cache-oblivious algorithms. In: 40th IEEE Symp. on Foundations of Comp. Sci., pp. 285\u2013298 (1999)","DOI":"10.1109\/SFFCS.1999.814600"},{"key":"2_CR11","unstructured":"GPGPU.org: Research papers on gpgpu.org, http:\/\/gpgpu.org\/tag\/papers"},{"key":"2_CR12","unstructured":"Greiner, G.: Sparse Matrix Computations and their I\/O Complexity. Dissertation, Technische Universit\u00e4t M\u00fcnchen, M\u00fcnchen (2012)"},{"key":"2_CR13","unstructured":"Haque, S., Maza, M., Xie, N.: A many-core machine model for designing algorithms with minimum parallelism overheads. In: High Performance Computing Symposium (2013)"},{"key":"2_CR14","unstructured":"J\u00e1J\u00e1, J.: An Introduction to Parallel Algorithms. Addison Wesley (1992)"},{"key":"2_CR15","unstructured":"Knuth, D.E.: The Art of Computer Programming, Volume III: Sorting and Searching. Addison-Wesley (1973)"},{"key":"2_CR16","volume-title":"Introduction to Parallel Algorithms and Architectures: Arrays, Trees, and Hypercubes","author":"F.T. Leighton","year":"1991","unstructured":"Leighton, F.T.: Introduction to Parallel Algorithms and Architectures: Arrays, Trees, and Hypercubes. Morgan-Kaufmann, San Mateo (1991)"},{"key":"2_CR17","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.future.2013.06.020","volume":"30","author":"L. Ma","year":"2014","unstructured":"Ma, L., Agrawal, K., Chamberlain, R.D.: A memory access model for highly-threaded many-core architectures. Future Generation Computer Systems\u00a030, 202\u2013215 (2014)","journal-title":"Future Generation Computer Systems"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Nakano, K.: Simple memory machine models for gpus. In: 26th IEEE International Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), pp. 794\u2013803 (2012)","DOI":"10.1109\/IPDPSW.2012.98"},{"key":"2_CR19","unstructured":"NVIDIA Corp.: CUDA C Best Practices Guide. Version 7.0 (March 2015)"},{"issue":"1","key":"2_CR20","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1137\/060658400","volume":"38","author":"A. Pagh","year":"2008","unstructured":"Pagh, A., Pagh, R.: Uniform hashing in constant time and optimal space. SIAM Journal on Computing\u00a038(1), 85\u201396 (2008)","journal-title":"SIAM Journal on Computing"},{"key":"2_CR21","unstructured":"Sen, S., Scherson, I.D., Shamir, A.: Shear Sort: A True Two-Dimensional Sorting Techniques for VLSI Networks. In: International Conference on Parallel Processing, pp. 903\u2013908 (1986)"},{"key":"2_CR22","unstructured":"Sitchinava, N., Weichert, V.: Provably efficient GPU algorithms. CoRR abs\/1306.5076 (2013), http:\/\/arxiv.org\/abs\/1306.5076"}],"container-title":["Lecture Notes in Computer Science","Algorithms - ESA 2015"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-48350-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T09:56:51Z","timestamp":1748599011000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-48350-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783662483497","9783662483503"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-48350-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]}}}