{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T09:07:56Z","timestamp":1790327276543,"version":"4.1.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319413204","type":"print"},{"value":"9783319413211","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-41321-1_4","type":"book-chapter","created":{"date-parts":[[2016,6,14]],"date-time":"2016-06-14T10:19:15Z","timestamp":1465899555000},"page":"61-80","source":"Crossref","is-referenced-by-count":18,"title":["Dynamic Sparse-Matrix Allocation on GPUs"],"prefix":"10.1007","author":[{"given":"James","family":"King","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Gilray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert M.","family":"Kirby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Might","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,6,15]]},"reference":[{"key":"4_CR1","unstructured":"Im, E., Yelick, K.: Optimization of sparse matrix kernels for data mining. In: First SIAM Conference on Data Mining (2000)"},{"key":"4_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1007\/978-3-540-75755-9_32","volume-title":"Applied Parallel Computing. State of the Art in Scientific Computing","author":"J Gilbert","year":"2007","unstructured":"Gilbert, J., Reinhardt, S., Shah, V.: High-performance graph algorithms from parallel sparse matrices. In: K\u00e5gstr\u00f6m, B., Elmroth, E., Dongarra, J., Wa\u015bniewski, J. (eds.) Applied Parallel Computing. State of the Art in Scientific Computing. LNCS, vol. 4699, pp. 260\u2013269. Springer, Heidelberg (2007)"},{"key":"4_CR3","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. Society for Industrial and Applied Mathematics, Philadelphia (2003). Saad:2003:IMS","edition":"2"},{"key":"4_CR4","volume-title":"Control-Flow Analysis of Higher-Order Languages","author":"O Shivers","year":"1991","unstructured":"Shivers, O.: Control-Flow Analysis of Higher-Order Languages. Carnegie-Mellon University, Pittsburgh (1991)"},{"issue":"3","key":"4_CR5","doi-asserted-by":"crossref","first-page":"10:1","DOI":"10.1145\/2187671.2187672","volume":"44","author":"J Midtgaard","year":"2012","unstructured":"Midtgaard, J.: Control-flow analysis of functional programs. ACM Comput. Surv. 44(3), 10:1\u201310:33 (2012)","journal-title":"ACM Comput. Surv."},{"key":"4_CR6","unstructured":"Gilray, T., King, J., Might, M.: Partitioning 0-CFA for the GPU. In: Workshop on Functional and Constraint Logic Programming, September 2014"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Prabhu, T., Ramalingam, S., Might, M., Hall, M.: EigenCFA: accelerating flow analysis with GPUs. In: Proceedings of the Symposium on the Principals of Programming Languages, pp. 511\u2013522 (2010)","DOI":"10.1145\/1925844.1926445"},{"issue":"8","key":"4_CR8","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/2370036.2145831","volume":"47","author":"M Mendez-Lojo","year":"2012","unstructured":"Mendez-Lojo, M., Burtscher, M., Pingali, K.: A GPU implementation of inclusion-based points-to analysis. ACM SIGPLAN Not. 47(8), 107\u2013116 (2012)","journal-title":"ACM SIGPLAN Not."},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Greathouse, J.L., Daga, M.: Efficient sparse matrix-vector multiplication on GPUs using the CSR storage format. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014, pp. 769\u2013780. IEEE Press, Piscataway (2014)","DOI":"10.1109\/SC.2014.68"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Garland, M.: Sparse matrix computations on manycore GPU\u2019s. In: Proceedings of the 45th Annual Design Automation Conference, DAC 2008, pp. 2\u20136. ACM, New York (2008)","DOI":"10.1145\/1391469.1391473"},{"issue":"11","key":"4_CR11","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/1839676.1839694","volume":"53","author":"M Garland","year":"2010","unstructured":"Garland, M., Kirk, D.B.: Understanding throughput-oriented architectures. Commun. ACM 53(11), 58\u201366 (2010)","journal-title":"Commun. ACM"},{"key":"4_CR12","unstructured":"Bell, N., Garland, M.: Efficient Sparse Matrix-Vector Multiplication on CUDA. NVIDIA Corporation (2008). NVR-2008-004"},{"key":"4_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-3-642-11515-8_10","volume-title":"High Performance Embedded Architectures and Compilers","author":"A Monakov","year":"2010","unstructured":"Monakov, A., Lokhmotov, A., Avetisyan, A.: Automatically tuning sparse matrix-vector multiplication for GPU architectures. In: Patt, Y.N., Foglia, P., Duesterwald, E., Faraboschi, P., Martorell, X. (eds.) HiPEAC 2010. LNCS, vol. 5952, pp. 111\u2013125. Springer, Heidelberg (2010)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Su, B.Y., Keutzer, K.: clSpMV: a cross-platform OpenCL SpMV framework on GPUs. In: Proceedings of the 26th ACM International Conference on Supercomputing, ICS 2012, pp. 353\u2013364. ACM, New York (2012)","DOI":"10.1145\/2304576.2304624"},{"key":"4_CR15","volume-title":"Automatic Performance Tuning of Sparse Matrix Kernels","author":"RW Vuduc","year":"2003","unstructured":"Vuduc, R.W.: Automatic Performance Tuning of Sparse Matrix Kernels. University of California, Berkeley (2003). AAI3121741"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication onthroughput-oriented processors. In: SC 2009, Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, pp. 1\u201311. ACM, New York (2009)","DOI":"10.1145\/1654059.1654078"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Ashari, A., Sedaghati, N., Eisenlohr, J., Sadayappan, P.: An efficient two-dimensional blocking strategy for sparsematrix-vector multiplication on GPUs. In: Proceedings of the 28th ACM International Conference on Supercomputing, ICS 2014, pp. 273\u2013282. ACM, New York (2014)","DOI":"10.1145\/2597652.2597678"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Yan, S., Li, C., Zhang, Y., Zhou, H.: yaSpMV: yet another SpMV framework on GPUs. In: Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPopp 2014, pp. 107\u2013118. ACM, New York (2014)","DOI":"10.1145\/2555243.2555255"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Williams, S., Oliker, L., Vuduc, R., Shalf, J., Yelick, K., Demmel, J.: Optimization of sparse matrix-vector multiplication on emerging multicore platforms. In: Proceedings of the ACM\/IEEE Conference on Supercomputing, SC 2007, pp. 38:1\u201338:12. ACM, New York (2007)","DOI":"10.1145\/1362622.1362674"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Smelyanskiy, M., Chow, E., Dubey, P.: Efficient sparse matrix-vector multiplication on x86-based many-coreprocessors. In: Proceedings of the 27th International ACM Conference on International Conference on Supercomputing, ICS 2013, pp. 273\u2013282. ACM, New York (2013)","DOI":"10.1145\/2464996.2465013"},{"issue":"4","key":"4_CR21","doi-asserted-by":"crossref","first-page":"231","DOI":"10.14778\/1938545.1938548","volume":"4","author":"X Yang","year":"2011","unstructured":"Yang, X., Parthasarathy, S., Sadayappan, P.: Fast sparse matrix-vector multiplication on GPUs: implications for graph mining. Proc. VLDB Endow. 4(4), 231\u2013242 (2011)","journal-title":"Proc. VLDB Endow."},{"issue":"5","key":"4_CR22","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1145\/1837853.1693471","volume":"45","author":"JW Choi","year":"2010","unstructured":"Choi, J.W., Singh, A., Vuduc, R.W.: Model-driven autotuning of sparse matrix-vector multiply on GPUs. SIGPLAN Not. 45(5), 115\u2013126 (2010)","journal-title":"SIGPLAN Not."},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Reguly, I., Giles, M.: Efficient sparse matrix-vector multiplication on cache-based GPUs. In: Innovative Parallel Computing (InPar), pp. 1\u201312 (2012)","DOI":"10.1109\/InPar.2012.6339602"},{"key":"4_CR24","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898719918","volume-title":"Graph Algorithms in the Language of Linear Algebra","author":"J Kepner","year":"2011","unstructured":"Kepner, J., Gilbert, J.: Graph Algorithms in the Language of Linear Algebra. Society for Industrial and Applied Mathematics, Philadelphia (2011)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Ashari, A., Sedaghati, N., Eisenlohr, J., Parthasarathy, S., Sadayappan, P.: Fast sparse matrix-vector multiplication on GPUs for graph applications. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014, pp. 781\u2013792. IEEE Press, Piscataway (2014)","DOI":"10.1109\/SC.2014.69"},{"key":"4_CR26","unstructured":"Bell, N., Garland, M.: CUSP: generic parallel algorithms for sparse matrix and graph computations (2012). Version 0.3.0"},{"issue":"1","key":"4_CR27","first-page":"1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The University of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1), 1\u201325 (2011)","journal-title":"ACM Trans. Math. Softw."},{"key":"4_CR28","unstructured":"Kreutzer, M., Hager, G., Wellein, G., Fehske, H., Bishop, A.R.: A unified sparse matrix data format for modern processors with wide SIMD units. CoRR. abs\/1307.6209 (2013)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"McLaughlin, A., Bader, D.A.: Revisiting edge and node parallelism for dynamic GPU graph analytics. In: IEEE International on Parallel Distributed Processing Symposium Workshops (IPDPSW), pp. 1396\u20131406 (2014)","DOI":"10.1109\/IPDPSW.2014.157"},{"issue":"3","key":"4_CR30","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/s00224-005-1237-z","volume":"39","author":"MA Bender","year":"2006","unstructured":"Bender, M.A., Farach-Colton, M., Mosteiro, M.A.: Insertion sort is O(n log n). Theor. Comput. Syst. 39(3), 391\u2013397 (2006)","journal-title":"Theor. Comput. Syst."}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-41321-1_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T18:30:53Z","timestamp":1568053853000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-41321-1_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319413204","9783319413211"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-41321-1_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}