{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T03:35:23Z","timestamp":1768707323204,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642369483","type":"print"},{"value":"9783642369490","type":"electronic"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"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":[[2013]]},"DOI":"10.1007\/978-3-642-36949-0_23","type":"book-chapter","created":{"date-parts":[[2013,2,15]],"date-time":"2013-02-15T01:34:27Z","timestamp":1360892067000},"page":"207-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Systematic Approach in Optimizing Numerical Memory-Bound Kernels on GPU"],"prefix":"10.1007","author":[{"given":"Ahmad","family":"Abdelfattah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Keyes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hatem","family":"Ltaief","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"23_CR1","unstructured":"CULA Dense Free Edition, http:\/\/www.culatools.com\/"},{"key":"23_CR2","unstructured":"Matrix Algebra on GPU and Multicore Architectures. Innovative Computing Laboratory, University of Tennessee, http:\/\/icl.cs.utk.edu\/magma\/"},{"key":"23_CR3","unstructured":"NVIDIA CUDA Toolkit, http:\/\/developer.nvidia.com\/cuda-toolkit"},{"key":"23_CR4","unstructured":"Nvidia visual profiler, http:\/\/developer.nvidia.com\/nvidia-visual-profiler"},{"key":"23_CR5","unstructured":"Performance Application Programming Interface (PAPI). Innovative Computing Laboratory, University of Tennessee, http:\/\/icl.cs.utk.edu\/papi\/"},{"key":"23_CR6","unstructured":"The NVIDIA CUDA Basic Linear Algebra Subroutines (CUBLAS), http:\/\/developer.nvidia.com\/cublas"},{"key":"23_CR7","unstructured":"Abdelfattah, A., Dongarra, J., Keyes, D., Ltaief, H.: Optimizing Memory-Bound SYMV Kernel on GPU Hardware Accelerators. In: The 10th International Meeting on High Performance Computing for Computational Science, VECPAR 2012 (accepted, 2012)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Humphrey, J.R., Price, D.K., Spagnoli, K.E., Paolini, A.L., Kelmelis, E.J.: CULA: Hybrid GPU Accelerated Linear Algebra Routines. In: Proceedings of SPIE Defense and Security Symposium, DSS (April 2010)","DOI":"10.1117\/12.850538"},{"issue":"99","key":"23_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPDS.2012.242","volume":"PP","author":"J. Kurzak","year":"2012","unstructured":"Kurzak, J., Tomov, S., Dongarra, J.: Autotuning GEMM Kernels for the Fermi GPU. IEEE Transactions on Parallel and Distributed Systems\u00a0PP(99), 1 (2012)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"23_CR10","unstructured":"Kurzak, J., Luszczek, P., Tomov, S., Dongarra, J.: Preliminary Results of Autotuning GEMM Kernels for the NVIDIA Kepler Architecture - GeForce GTX 680. LAPACK Working Note 267"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Kwon, Y., Narayanan, R.M., Rangaswamy, M.: A multi-target detector using mutual information for noise radar systems in low snr regimes. In: 2010 International Waveform Diversity and Design Conference, WDD, pp. 000105\u2013000109 (August 2010)","DOI":"10.1109\/WDD.2010.5592388"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Nath, R., Tomov, S., Dong, T., Dongarra, J.: Optimizing symmetric dense matrix-vector multiplication on GPUs. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2011, pp. 6:1\u20136:10. ACM, New York (2011)","DOI":"10.1145\/2063384.2063392"},{"issue":"4","key":"23_CR13","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1177\/1094342010385729","volume":"24","author":"R. Nath","year":"2010","unstructured":"Nath, R., Tomov, S., Dongarra, J.: An Improved Magma Gemm for Fermi Graphics Processing Units. Int. J. High Perform. Comput. Appl.\u00a024(4), 511\u2013515 (2010)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Volkov, V., Demmel, J.W.: Benchmarking GPUs to tune dense linear algebra. In: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, SC 2008, pp. 31:1\u201331:11. IEEE Press, Piscataway (2008)","DOI":"10.1109\/SC.2008.5214359"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Yu, W.C., Quan, W.D.: On the signal processing in the life-detection radar using an fmcw waveform. In: 2010 Third International Symposium on Information Processing, ISIP, pp. 213\u2013216 (October 2010)","DOI":"10.1109\/ISIP.2010.48"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2012: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-36949-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T21:22:05Z","timestamp":1745961725000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-36949-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642369483","9783642369490"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-36949-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}