{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T18:20:23Z","timestamp":1793125223040,"version":"4.5.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2002,4,1]],"date-time":"2002-04-01T00:00:00Z","timestamp":1017619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2002,4,1]],"date-time":"2002-04-01T00:00:00Z","timestamp":1017619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Parallel Programming"],"published-print":{"date-parts":[[2002,4]]},"DOI":"10.1023\/a:1014230429447","type":"journal-article","created":{"date-parts":[[2002,12,28]],"date-time":"2002-12-28T19:53:04Z","timestamp":1041105184000},"page":"65-98","source":"Crossref","is-referenced-by-count":94,"title":["Automatic Intra-Register Vectorization for the Intel\u00ae Architecture"],"prefix":"10.1007","volume":"30","author":[{"given":"Aart J. C.","family":"Bik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milind","family":"Girkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul M.","family":"Grey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinmin","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"368889_CR1","volume-title":"Computer Architecture","author":"M. J. Flynn","year":"1995","unstructured":"Michael J. Flynn, Computer Architecture, Jones and Bartlett Publishers, Boston, Massachusetts (1995)."},{"key":"368889_CR2","volume-title":"Computer Architecture: A Quantitative Approach","author":"J. L. Hennessy","year":"1990","unstructured":"John L. Hennessy and David A. Patterson, Computer Architecture: A Quantitative Approach, Morgan Kaufmann Publishers, San Mateo, California (1990)."},{"key":"368889_CR3","volume-title":"Introduction to Parallel Programming","author":"V. Kumar","year":"1994","unstructured":"Vipin Kumar, Ananth Grama, Anshul Gupta, and George Karypis, Introduction to Parallel Programming, The Benjamin\/Cummings Publishing Company, Redwood City, California (1994)."},{"key":"368889_CR4","volume-title":"Advanced Computer Architectures- A Design Space Approach","author":"D. Sima","year":"1997","unstructured":"Dezs\u00f6 Sima, Terence Fountain, and P\u00e9ter Kacsuk, Advanced Computer Architectures- A Design Space Approach, Addison-Wesley, Harlow England (1997)."},{"issue":"1","key":"368889_CR5","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1145\/359327.359336","volume":"21","author":"R. M. Russel","year":"1978","unstructured":"R. M. Russel, The CRAY-1 Processor System, Comm. ACM\n21(1):63\u201372 (January 1978).","journal-title":"Comm. ACM"},{"key":"368889_CR6","unstructured":"T. Blank, The Maspar MP-1 Architecture, Proc. IEEE Compcon Spring (February 1990)."},{"key":"368889_CR7","volume-title":"The Complete Guide to MMX\u2212 Technology","author":"D. Bistry","year":"1997","unstructured":"David Bistry et al., The Complete Guide to MMX\u2212 Technology, McGraw-Hill, New York (1997)."},{"key":"368889_CR8","unstructured":"Intel Corporation, Intel Architecture MMX\u2212 Technology-Programmer's Reference Manual, Intel Corporation, Order No. 243007-003, available at http:\/\/developer.intel.com (1997)."},{"key":"368889_CR9","unstructured":"Glenn Hinton, Dave Sager, Mike Upton, Darrell Boggs, Doug Carmean, Alan Kyker, and Patrice Roussel, The Microarchitecture of the Pentium\u00ae 4 Processor. Intel Technology Journal (2001), http:\/\/intel.com\/technology\/itj\/."},{"key":"368889_CR10","unstructured":"Intel Corporation, Intel Architecture Software Developer's Manual, Volume 1: Basic Architecture, Intel Corporation, available at http:\/\/developer.intel.com\/ (2001)."},{"key":"368889_CR11","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1145\/29873.29875","volume":"9","author":"J. R. Allen","year":"1987","unstructured":"J. R. Allen and K. Kennedy, Automatic Translation of Fortran Programs to Vector Form, ACM Transactions on Programming Languages and Systems\n9:491\u2013542 (1987).","journal-title":"ACM Transactions on Programming Languages and Systems"},{"key":"368889_CR12","volume-title":"The Structure of Computers and Computations","author":"D. J. Kuck","year":"1978","unstructured":"David J. Kuck, The Structure of Computers and Computations, John Wiley and Sons, New York (1978), Vol. 1."},{"key":"368889_CR13","volume-title":"A Guidebook to Fortran on Supercomputers","author":"J. M. Levesque","year":"1991","unstructured":"John M. Levesque and Joel W. Williamson, A Guidebook to Fortran on Supercomputers, Academic Press, San Diego (1991)."},{"key":"368889_CR14","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4613-1077-8","volume-title":"Parallel Programming and Compilers","author":"C. D. Polychronopoulos","year":"1988","unstructured":"Constantine D. Polychronopoulos, Parallel Programming and Compilers, Kluwer, Boston (1988)."},{"key":"368889_CR15","volume-title":"High Performance Compilers for Parallel Computing","author":"M. J. Wolfe","year":"1996","unstructured":"Michael J. Wolfe, High Performance Compilers for Parallel Computing, Addison-Wesley, Redwood City, California (1996)."},{"key":"368889_CR16","volume-title":"Supercompilers for Parallel and Vector Computers","author":"H. Zima","year":"1990","unstructured":"Hans Zima, Supercompilers for Parallel and Vector Computers, ACM Press, New York (1990)."},{"key":"368889_CR17","unstructured":"Alfred V. Aho, Ravi Sethi, and Jeffrey D. U llman, Compilers Principles, Techniques and Tools, Addison-Wesley (1986)."},{"key":"368889_CR18","doi-asserted-by":"crossref","unstructured":"Andrew Appel, Modern Compiler Implementation in C, Cambridge University Press (1998).","DOI":"10.1017\/CBO9780511811449"},{"key":"368889_CR19","volume-title":"Dependence Analysis","author":"U. Banerjee","year":"1997","unstructured":"Utpal Banerjee. Dependence Analysis, Kluwer, Boston, 1997. A Book Series on Loop Transformations for Restructuring Compilers."},{"key":"368889_CR20","doi-asserted-by":"crossref","unstructured":"Michael Burke and Ron Cytron, Interprocedural dependence analysis and parallelization, Proceedings of the Symposium on Compiler Construction, pp. 162\u2013175 (1986).","DOI":"10.1145\/13310.13328"},{"key":"368889_CR21","volume-title":"Crafting a Compiler with C","author":"C. N. Fisher","year":"1991","unstructured":"C. N. Fisher and R. J. LeBlanc, Crafting a Compiler with C, Benjamin-Cummings, Menlo Park, California (1991)."},{"key":"368889_CR22","unstructured":"Steven S. Muchnick, Advanced Compiler Design and Implementation, Morgan Kaufman Publishers (1997)."},{"key":"368889_CR23","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1016\/0097-3165(73)90004-6","volume":"14","author":"G. B. Dantzig","year":"1973","unstructured":"George B. Dantzig and B. Curtis Eaves, Fourier-Motzkin Elimination and Its Dual, J. Comb. Theory\n14:288\u2013297 (1973).","journal-title":"J. Comb. Theory"},{"key":"368889_CR24","volume-title":"Theory of Linear and Integer Programming","author":"A. Schrijver","year":"1986","unstructured":"Alexander Schrijver, Theory of Linear and Integer Programming, John Wiley and Sons, Chichester, England (1986)."},{"key":"368889_CR25","volume-title":"The C Programming Language","author":"B. W. Kernighan","year":"1988","unstructured":"Brian W. Kernighan and Dennis M. R itchie, The C Programming Language, Prentice-Hall, Englewood Cliffs, New Jersey (1988)."},{"key":"368889_CR26","unstructured":"Aart J. C. Bik, Milind Girkar, Paul M. Grey, and Xinmin Tian, Automatic Detection of Saturation and Clipping Idioms for the Intel\u00ae Architecture, manuscript in preparation (2001)."},{"key":"368889_CR27","unstructured":"Aart J. C. Bik, Milind Girkar, Paul M. Grey, and Xinmin Tian, Experiments with automatic vectorization for the Pentium\u00ae 4 Processor, Proceedings of the 9th Workshop on Compilers for Parallel Computers, pp. 1\u201310 (June 2001)."},{"key":"368889_CR28","volume-title":"Solving linear systems on vector and shared memory computers","author":"J. J. Dongarra","year":"1991","unstructured":"J. J. Dongarra, I. S. Duff, D. C. Sorensen, and H. A. van der Vorst, Solving linear systems on vector and shared memory computers, SIAM, Philadelphia, PA (1991)."},{"key":"368889_CR29","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1145\/355841.355847","volume":"5","author":"C. L. Lawson","year":"1979","unstructured":"C. L. Lawson, R. J. Hanson, D. R. Kincaid, and F. T. Krogh, Basic Linear algebra subprograms for Fortran usage, ACM Transactions on Mathematical Software\n5:308\u2013323 (1979).","journal-title":"ACM Transactions on Mathematical Software"},{"key":"368889_CR30","unstructured":"R. J. Fisher and H. G. Dietz, Compiling for SIMD within a Register, 1998 Workshop on Languages and Compilers for Parallel Computing, University of North Carolina at Chapel Hill, North Carolina, August 7-9 (1998)."},{"key":"368889_CR31","doi-asserted-by":"crossref","unstructured":"Samuel Larsen and Saman Amarasinghe, Exploiting Superword Level Parallelism with Multimedia Instruction Sets, Proceeding of the SIGPLAN Conference on Programming Language Design and Implementation, Vancouver, B.C. (June 2000).","DOI":"10.1145\/349299.349320"},{"key":"368889_CR32","unstructured":"Gilles Pokam, Julien Simonnet, and Fran\u00c7ois Bodin, A Retargetable Preprocessor for Multimedia Instructions, Proceedings of the 9th Workshop on Compilers for Parallel Computers, pp. 291\u2013301 (June 2001)."},{"key":"368889_CR33","unstructured":"Aart J. C. Bik, Milind Girkar, Paul M. Grey, and Xinmin T ian, Efficient Exploitation of Parallelism on Pentium\u00ae III and Pentium\u00ae 4 Processor-Based Systems, Intel Technology Journal (2001), http:\/\/intel.com\/technology\/itj\/."}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1014230429447.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1014230429447\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1014230429447.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T08:20:42Z","timestamp":1748334042000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1014230429447"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,4]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2002,4]]}},"alternative-id":["368889"],"URL":"https:\/\/doi.org\/10.1023\/a:1014230429447","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2002,4]]}}}