{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:03:01Z","timestamp":1725516181711},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540852605"},{"type":"electronic","value":"9783540852612"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-85261-2_17","type":"book-chapter","created":{"date-parts":[[2008,8,12]],"date-time":"2008-08-12T07:20:24Z","timestamp":1218525624000},"page":"246-260","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting SIMD Parallelism with the CGiS Compiler Framework"],"prefix":"10.1007","author":[{"given":"Nicolas","family":"Fritz","sequence":"first","affiliation":[]},{"given":"Philipp","family":"Lucas","sequence":"additional","affiliation":[]},{"given":"Reinhard","family":"Wilhelm","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"17_CR1","volume-title":"Optimizing Compilers for Modern Architectures","author":"R. Allen","year":"2002","unstructured":"Allen, R., Kennedy, K.: Optimizing Compilers for Modern Architectures. Morgan Kaufmann, San Francisco (2002)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Coleman, S., McKinley, K.S.: Tile size selection using cache organization and data layout. In: Proceedings of PLDI, pp. 279\u2013290 (1995)","DOI":"10.1145\/207110.207162"},{"key":"17_CR3","volume-title":"Parallel Computer Architecture: A Hardware\/Software Approach","author":"D.E. Culler","year":"1999","unstructured":"Culler, D.E., Singh, J.P., Gupta, A.: Parallel Computer Architecture: A Hardware\/Software Approach. Morgan Kaufmann, San Francisco (1999)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Eichenberger, A.E., O\u2019Brien, K., O\u2019Brien, K., Wu, P., Chen, T., Oden, P.H., Prener, D.A., Shepherd, J.C., So, B., Sura, Z., Wang, A., Zhang, T., Zhao, P., Gschwind, M.: Optimizing compiler for a cell processor. In: Proceedings of PACT (2005)","DOI":"10.1109\/PACT.2005.33"},{"key":"17_CR5","unstructured":"Freescale. AltiVec Technology Programming Interface Manual. ALTIVECPIM\/D 06\/1999 Rev. 0 (June 1999)"},{"key":"17_CR6","unstructured":"Freescale. AltiVec Technology Programming Environments Manual. ALTIVECPEM\/D 04\/2006 Rev. 3 (April 2006)"},{"key":"17_CR7","unstructured":"Intel. Intel 64 and IA-32 Architectures Optimization Reference Manual (May 2007)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Larsen, S., Amarasinghe, S.: Exploiting superword level parallelism with multimedia instruction sets. Technical Report LCS-TM-601, MIT Laboratory for Computer Science (November 1999)","DOI":"10.1145\/349299.349320"},{"key":"17_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/11688839_10","volume-title":"Compiler Construction","author":"P. Lucas","year":"2006","unstructured":"Lucas, P., Fritz, N., Wilhelm, R.: The CGiS compiler\u2014a tool demonstration. In: Mycroft, A., Zeller, A. (eds.) CC 2006. LNCS, vol.\u00a03923, pp. 105\u2013108. Springer, Heidelberg (2006)"},{"key":"17_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/11758549_31","volume-title":"Computational Science \u2013 ICCS 2006","author":"P. Lucas","year":"2006","unstructured":"Lucas, P., Fritz, N., Wilhelm, R.: The development of the data-parallel GPU programming language CGiS. In: Alexandrov, V.N., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) ICCS 2006. LNCS, vol.\u00a03994, pp. 200\u2013203. Springer, Heidelberg (2006)"},{"key":"17_CR11","unstructured":"Mittal, M., Peleg, A., Weiser, U.: MMX technology architecture overview. Intel Technology Journal\u00a0Q3(12) (1997)"},{"key":"17_CR12","volume-title":"Advanced Compiler Design and Implementation","author":"S.S. Muchnick","year":"1997","unstructured":"Muchnick, S.S.: Advanced Compiler Design and Implementation. Morgan Kaufmann, San Francisco (1997)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Nuzman, D., Rosen, I., Zaks, A.: Auto-vectorization of interleaved data of simd. In: Proceedings of PLDI (2006)","DOI":"10.1145\/1133981.1133997"},{"key":"17_CR14","unstructured":"NVIDIA. CUDA Programming Guide Version 0.8 (February 2007)"},{"issue":"1","key":"17_CR15","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1111\/j.1467-8659.2007.01012.x","volume":"26","author":"J.D. Owens","year":"2007","unstructured":"Owens, J.D., Luebke, D., Govindaraju, N., Harris, M., Kr\u00fcger, J., Lefohn, A.E., Purcell, T.J.: A survey of general-purpose computation on graphics hardware. Computer Graphics Forum\u00a026(1), 80\u2013113 (2007)","journal-title":"Computer Graphics Forum"},{"issue":"1","key":"17_CR16","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1002\/spe.751","volume":"37","author":"I. Pryanishnikov","year":"2007","unstructured":"Pryanishnikov, I., Krall, A., Horspool, R.N.: Compiler optimizations for processors with SIMD instructions. Software\u2014Practice & Experience\u00a037(1), 93\u2013113 (2007)","journal-title":"Software\u2014Practice & Experience"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Ren, G., Wu, P., Padua, D.: An empirical study on the vectorization of multimedia applications for multimedia extensions. In: IPDPS (2005)","DOI":"10.1007\/978-3-540-24644-2_27"},{"key":"17_CR18","series-title":"Lecture Notes in Computer Science","first-page":"420","volume-title":"Languages and Compilers for Parallel Computing","author":"G. Ren","year":"2003","unstructured":"Ren, G., Wu, P., Padua, D.A.: A preliminary study on the vectorization of multimedia applications for multimedia extensions. In: Rauchwerger, L. (ed.) LCPC 2003. LNCS, vol.\u00a02958, pp. 420\u2013435. Springer, Heidelberg (2003)"},{"key":"17_CR19","volume-title":"Practical Cryptography for Data Internetworks","author":"R.L. Rivest","year":"1996","unstructured":"Rivest, R.L.: The RC5 encryption algorithm. In: Practical Cryptography for Data Internetworks. IEEE Computer Society Press, Los Alamitos (1996)"},{"key":"17_CR20","unstructured":"Shin, J., Chame, J., Hall, M.W.: Compiler-controlled caching in superword register files for multimedia extension architectures. In: Proceedings of PACT, pp. 45\u201355 (2002)"},{"key":"17_CR21","unstructured":"Tenllado, C., Pi\u00f1uel, L., Prieto, M., Catthoor, F.: Pack transposition: Enhancing superword level parallelism exploitation. In: Proceedings of Parallel Computing (ParCo), pp. 573\u2013580 (2005)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Wu, P., Eichenberer, A.E., Wang, A., Zhao, P.: An integrated simdization framework using virtual vectors. In: Proceedings of the 19th Annual International Conference on Supercomputing (ICS), pp. 169\u2013178 (2005)","DOI":"10.1145\/1088149.1088172"},{"key":"17_CR23","volume-title":"Supercompilers for Parallel and Vector Computers","author":"H.P. Zima","year":"1990","unstructured":"Zima, H.P., Chapman, B.: Supercompilers for Parallel and Vector Computers. ACM Press, New York (1990)"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-85261-2_17.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,14]],"date-time":"2021-09-14T17:04:43Z","timestamp":1631639083000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-85261-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540852605","9783540852612"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-85261-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}