{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:51:19Z","timestamp":1771951879484,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540712282","type":"print"},{"value":"9783540712299","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-71229-9_1","type":"book-chapter","created":{"date-parts":[[2007,7,1]],"date-time":"2007-07-01T17:39:13Z","timestamp":1183311553000},"page":"1-15","source":"Crossref","is-referenced-by-count":5,"title":["New Algorithms for SIMD Alignment"],"prefix":"10.1007","author":[{"given":"Liza","family":"Fireman","sequence":"first","affiliation":[]},{"given":"Erez","family":"Petrank","sequence":"additional","affiliation":[]},{"given":"Ayal","family":"Zaks","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"1_CR1","volume-title":"Network flows","author":"R.K. Ahuja","year":"1993","unstructured":"Ahuja, R.K., Magnanti, T.L., Orlin, J.B.: Network flows. Prentice-Hall, Englewood Cliffs (1993)"},{"key":"1_CR2","volume-title":"Optimizing Compilers for Modern Architectures","author":"R. Allen","year":"2001","unstructured":"Allen, R., Kennedy, K.: Optimizing Compilers for Modern Architectures. Morgan Kaufmann, San Francisco (2001)"},{"key":"1_CR3","volume-title":"The Software Vectorization Handbook: Applying Multimedia Extensions for Maximum Performance","author":"A. Bik","year":"2004","unstructured":"Bik, A.: The Software Vectorization Handbook: Applying Multimedia Extensions for Maximum Performance. Intel Press, Santa Clara (June 2004)"},{"key":"1_CR4","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1023\/A:1014230429447","volume":"2","author":"A. Bik","year":"2002","unstructured":"Bik, A., et al.: Automatic intra-register vectorization for the intel architecture. International J. of Parallel Programming\u00a02, 65\u201398 (2002)","journal-title":"International J. of Parallel Programming"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Bouchitt\u00e9, V., et al.: Evaluating array expressions on massively parallel machines with communication\/computation overlap (1995)","DOI":"10.1007\/3-540-58430-7_62"},{"key":"1_CR6","first-page":"16","volume-title":"Proceedings of POPL","author":"S. Chatterjee","year":"1993","unstructured":"Chatterjee, S., et al.: Automatic array alignment in data-parallel programs. In: Proceedings of POPL, pp. 16\u201328. ACM Press, New York (1993)"},{"issue":"1","key":"1_CR7","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1145\/200994.201004","volume":"17","author":"S. Chatterjee","year":"1995","unstructured":"Chatterjee, S., et al.: Optimal evaluation of array expressions on massively parallel machines. ACM Trans. Program. Lang. Syst.\u00a017(1), 123\u2013156 (1995)","journal-title":"ACM Trans. Program. Lang. Syst."},{"key":"1_CR8","unstructured":"Cheong, G., Lam, M.S.: An optimizer formultimedia instruction sets. In: Second SUIF Compiler Workshop (August 1997)"},{"key":"1_CR9","volume-title":"Introduction to Algorithms","author":"T.H. Cormen","year":"2001","unstructured":"Cormen, T.H., et al.: Introduction to Algorithms. McGraw-Hill Higher Education, New York (2001)"},{"key":"1_CR10","unstructured":"Corporation, M.: Altivec technology programming interface manual (June 1999)"},{"key":"1_CR11","first-page":"241","volume-title":"Proceedings of the 24th ACM symposium on Theory of computing","author":"E. Dahlhaus","year":"1992","unstructured":"Dahlhaus, E., et al.: The complexity of multiway cuts (extended abstract). In: Proceedings of the 24th ACM symposium on Theory of computing, pp. 241\u2013251. ACM Press, New York (1992)"},{"issue":"3","key":"1_CR12","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1142\/S0129626494000259","volume":"4","author":"A. Darte","year":"1994","unstructured":"Darte, A., Robert, Y.: On the alignment problem. Parallel Processing Letters\u00a04(3), 259\u2013270 (1994)","journal-title":"Parallel Processing Letters"},{"key":"1_CR13","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.jpdc.2003.09.005","volume":"64","author":"C. Ding","year":"2004","unstructured":"Ding, C., Kennedy, K.: Improving effective bandwidth through compiler enhancement of global cache reuse. J. Parallel Distrib. Comput.\u00a064, 108\u2013134 (2004)","journal-title":"J. Parallel Distrib. Comput."},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Eichenberger, A.E., Wu, P., O\u2019Brien, K.: Vectorization for simd architectures with alignment constraints. In: Proceeding of PLDI (June 2004)","DOI":"10.1145\/996841.996853"},{"key":"1_CR15","unstructured":"Fireman, L.: The complexity of SIMD alignment. M.Sc. thesis, Technion \u2014 Israel Institute of Technology, Department of Computer Science (June 2006), http:\/\/www.cs.technion.ac.il\/users\/wwwb\/cgi-bin\/tr-info.cgi\/2006\/MSC\/MSC-2006-17"},{"key":"1_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/3-540-57502-2_53","volume-title":"Languages and Compilers for Parallel Computing","author":"G.R. Gao","year":"1993","unstructured":"Gao, G.R., et al.: Collective loop fusion for array contraction. In: Banerjee, U., et al. (eds.) LCPC 1992. LNCS, vol.\u00a0757, pp. 281\u2013295. Springer, Heidelberg (1993)"},{"issue":"1","key":"1_CR17","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/0743-7315(91)90109-M","volume":"13","author":"J.R. Gilbert","year":"1991","unstructured":"Gilbert, J.R., Schreiber, R.: Optimal expression evaluation for data parallel architectures. J. Parallel Distrib. Comput.\u00a013(1), 58\u201364 (1991)","journal-title":"J. Parallel Distrib. Comput."},{"key":"1_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/3-540-57659-2_18","volume-title":"Languages and Compilers for Parallel Computing","author":"K. Kennedy","year":"1994","unstructured":"Kennedy, K., McKinley, K.S.: Maximizing loop parallelism and improving data locality via loop fusion and distribution. In: Banerjee, U., et al. (eds.) LCPC 1993. LNCS, vol.\u00a0768, pp. 301\u2013320. Springer, Heidelberg (1994)"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Larsen, S., Amarasinghe, S.: Exploiting superword level parallelism with multimedia instruction sets. In: Proceedings of PLDI, pp. 145\u2013156 (2000)","DOI":"10.1145\/349299.349320"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Larsen, S., Witchel, E., Amarasinghe, S.: Increasing and detecting memory address congruence. In: Proceedings of PACT (2002)","DOI":"10.1109\/PACT.2002.1105970"},{"key":"1_CR21","unstructured":"Naishlos, D.: Autovectorization in gcc. In: Proceeding of GCC Developers Summit, pp. 105\u2013118 (2004)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Naishlos, D., et al.: Vectorizing for a SIMdD DSP Architecture. In: Proceedings of CASES, pp. 2\u201311 (2003)","DOI":"10.1145\/951710.951714"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Nuzman, D., Henderson, R.: Multi-platform auto-vectorization. In: Proceedings of CGO, pp. 281\u2013294 (2006)","DOI":"10.1109\/CGO.2006.25"},{"key":"1_CR24","unstructured":"Nuzman, D., Zaks, A.: Autovectorization in gcc \u2013 two years later. In: Proceedings of GCC Developers Summit, pp. 145\u2013158 (2006)"},{"key":"1_CR25","series-title":"Lecture Notes in Computer Science","volume-title":"Languages and Compilers for Parallel Computing","author":"G. Ren","year":"2004","unstructured":"Ren, G., Wu, P., Padua, D.: A preliminary study on the vectorization of multimedia applications for multimedia extensions. In: Rauchwerger, L. (ed.) LCPC 2003. LNCS, vol.\u00a02958, Springer, Heidelberg (2004)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Ren, G., Wu, P., Padua, D.A.: Optimizing data permutations for simd devices. In: Proceedings of PLDI, pp. 118\u2013131 (2006)","DOI":"10.1145\/1133981.1133996"},{"key":"1_CR27","first-page":"165","volume-title":"Proceedings of CGO","author":"J. Shin","year":"2005","unstructured":"Shin, J., Hall, M., Chame, J.: Superword-level parallelism in the presence of control flow. In: Proceedings of CGO, Washington, DC, USA, pp. 165\u2013175. IEEE Computer Society Press, Los Alamitos (2005)"},{"key":"1_CR28","unstructured":"C.B. Software: VAST-F\/AltiVec: Automatic Fortran Vectorizer for PowerPC Vector Unit (2004), http:\/\/www.psrv.com\/vastaltivec.html"},{"key":"1_CR29","first-page":"38","volume-title":"Approximation Algorithms","author":"V.V. Vazirani","year":"2001","unstructured":"Vazirani, V.V.: Approximation Algorithms, 1st edn., pp. 38\u201340, pp. 155\u2013160. Springer, Heidelberg (2001)","edition":"1"},{"key":"1_CR30","first-page":"153","volume-title":"Proceedings of CGO","author":"P. Wu","year":"2005","unstructured":"Wu, P., Eichenberger, A.E., Wang, A.: Efficient simd code generation for runtime alignment and length conversion. In: Proceedings of CGO, Washington, DC, USA, pp. 153\u2013164. IEEE Computer Society Press, Los Alamitos (2005)"}],"container-title":["Lecture Notes in Computer Science","Compiler Construction"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-71229-9_1.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T05:17:03Z","timestamp":1605763023000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-71229-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540712282","9783540712299"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-71229-9_1","relation":{},"subject":[]}}