{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T15:59:16Z","timestamp":1757779156094,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540897392"},{"type":"electronic","value":"9783540897408"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-89740-8_24","type":"book-chapter","created":{"date-parts":[[2008,11,27]],"date-time":"2008-11-27T08:14:24Z","timestamp":1227773664000},"page":"343-355","source":"Crossref","is-referenced-by-count":9,"title":["Exploring the Optimization Space of Dense Linear Algebra Kernels"],"prefix":"10.1007","author":[{"given":"Qing","family":"Yi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Apan","family":"Qasem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"24_CR1","unstructured":"Agakov, F., Bonilla, E., Cavazos, J., Franke, B., Fursin, G., O\u2019Boyle, M., Thomson, J., Toussaint, M., Williams, C.: Using machine learning to focus iterative optimization. In: International Symposium on Code Generation and Optimization, 2006 (CGO 2006), New York, NY (2006)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Baumgartner, G., Auer, A., Bernholdt, D.E., Bibireata, A., Choppella, V., Cociorva, D., Gao, X., Harrison, R.J., Hirata, S., Krishnamoorthy, S., Krishnan, S., Lam, C.-C., Lu, Q., Nooijen, M., Pitzer, R.M., Ramanujam, J., Sadayappan, P., Sibiryakov, A.: Synthesis of high-performance parallel programs for a class of ab initio quantum chemistry models. Proc.\u00a0IEEE, Special Issue on Program Generation, Optimization, and Adaptation\u00a093(2) (2005)","DOI":"10.1109\/JPROC.2004.840311"},{"issue":"1","key":"24_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1055531.1055532","volume":"31","author":"P. Bientinesi","year":"2005","unstructured":"Bientinesi, P., Gunnels, J.A., Myers, M.E., Quintana-Orti, E., van de Geijn, R.: The science of deriving dense linear algebra algorithms. ACM Transactions on Mathematical Software\u00a031(1), 1\u201326 (2005)","journal-title":"ACM Transactions on Mathematical Software"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Chame, J., Hall, M.: Combining models and guided empirical search to optimize for multiple levels of the memory hierarchy. In: CGO, San Jose, CA, USA (March 2005)","DOI":"10.1109\/CGO.2005.10"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Demmel, J., Dongarra, J., Eijkhout, V., Fuentes, E., Petitet, A., Vuduc, R., Whaley, C., Yelick, K.: Self adapting linear algebra algorithms and software. Proc.\u00a0IEEE, Special Issue on Program Generation, Optimization, and Adaptation\u00a093(2) (2005)","DOI":"10.1109\/JPROC.2004.840848"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Frigo, M., Johnson, S.G.: The design and implementation of FFTW3. Proc.\u00a0IEEE, Special Issue on Program Generation, Optimization, and Adaptation\u00a093(2) (2005)","DOI":"10.1109\/JPROC.2004.840301"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"P\u00fcschel, M., Moura, J.M.F., Johnson, J., Padua, D., Veloso, M., Singer, B.W., Xiong, J., Franchetti, F., Ga\u010di\u0107, A., Voronenko, Y., Chen, K., Johnson, R.W., Rizzolo, N.: SPIRAL: Code generation for DSP transforms. Proc.\u00a0IEEE, Special Issue on Program Generation, Optimization, and Adaptation\u00a093(2) (2005)","DOI":"10.1109\/JPROC.2004.840306"},{"issue":"2","key":"24_CR8","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s11227-006-7957-2","volume":"36","author":"A. Qasem","year":"2006","unstructured":"Qasem, A., Kennedy, K., Mellor-Crummey, J.: Automatic tuning of whole applications using direct search and a performance-based transformation system. The Journal of Supercomputing\u00a036(2), 183\u2013196 (2006)","journal-title":"The Journal of Supercomputing"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Stephenson, M., Amarasinghe, S.: Predicting unroll factors using supervised classification. In: CGO, San Jose, CA, USA (March 2005)","DOI":"10.1109\/CGO.2005.29"},{"issue":"1\u20132","key":"24_CR10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R.C. Whaley","year":"2001","unstructured":"Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimization of software and the ATLAS project. Parallel Computing\u00a027(1\u20132), 3\u201335 (2001)","journal-title":"Parallel Computing"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Whaley, R.C., Whalley, D.B.: Tuning high performance kernels through empirical compilation. In: The 2005 International Conference on Parallel Processing (June 2005)","DOI":"10.1109\/ICPP.2005.77"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Yi, Q., Whaley, C.: Automated transformation for performance-critical kernels. In: ACM SIGPLAN Symposium on Library-Centric Software Design, Montreal, Canada (October 2007)","DOI":"10.1145\/1512762.1512773"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Yotov, K., Li, X., Ren, G., Cibulskis, M., DeJong, G., Garzaran, M., Padua, D., Pingali, K., Stodghill, P., Wu, P.: A comparison of empirical and model-driven optimization. In: Proceedings of the SIGPLAN 2003 Conference on Programming Language Design and Implementation, San Diego, CA (June 2003)","DOI":"10.1145\/781131.781140"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Yi, Q., Kennedy, K., Quinlan, D., Vuduc, R.: Parameterizing loop fusion for automated empirical tuning. Technical Report UCRL-TR-217808, Center for Applied Scientific Computing, Lawrence Livermore National Laboratory (December 2005)","DOI":"10.2172\/890608"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-89740-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,15]],"date-time":"2019-05-15T16:15:00Z","timestamp":1557936900000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/link.springer.com\/10.1007\/978-3-540-89740-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540897392","9783540897408"],"references-count":14,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/978-3-540-89740-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}