{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:35:08Z","timestamp":1750307708267,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2008,10,19]],"date-time":"2008-10-19T00:00:00Z","timestamp":1224374400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2008,10,19]]},"DOI":"10.1145\/1450095.1450121","type":"proceedings-article","created":{"date-parts":[[2008,10,22]],"date-time":"2008-10-22T12:25:44Z","timestamp":1224678344000},"page":"167-176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Efficient vectorization of SIMD programs with non-aligned and irregular data access hardware"],"prefix":"10.1145","author":[{"given":"Hoseok","family":"Chang","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}]},{"given":"Wonyong","family":"Sung","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}]}],"member":"320","published-online":{"date-parts":[[2008,10,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Intel Integrated Performance Primitives for Intel Pentium Processors and Intel Itanium Architectures. Intel Corporation.  Intel Integrated Performance Primitives for Intel Pentium Processors and Intel Itanium Architectures. Intel Corporation."},{"key":"e_1_3_2_1_2_1","volume-title":"Texas Instruments","author":"Overview Technical","year":"2000","unstructured":"TMS320C64x Technical Overview . Texas Instruments , 2000 . TMS320C64x Technical Overview. Texas Instruments, 2000."},{"key":"e_1_3_2_1_3_1","unstructured":"Cortex-A8 Technical Reference Manual. ARM 2007.  Cortex-A8 Technical Reference Manual. ARM 2007."},{"key":"e_1_3_2_1_4_1","volume-title":"ARM","author":"Tools Realview Compilation","year":"2007","unstructured":"Realview Compilation Tools : NEON Vectorizing Compiler Guide . ARM , 2007 . Realview Compilation Tools: NEON Vectorizing Compiler Guide. ARM, 2007."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2007.363737"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.19822"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014230429447"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIPS.2006.352558"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1965-0178586-1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/996893.996853"},{"key":"e_1_3_2_1_11_1","first-page":"7302525","article-title":"Method and Apparatus for Efficiently Accessing Both Aligned and Unaligned Data from a Memory","author":"Fluhr E. J.","year":"2007","unstructured":"E. J. Fluhr and S. B. Levenstein . Method and Apparatus for Efficiently Accessing Both Aligned and Unaligned Data from a Memory . US Patent 7302525 , 2007 . E. J. Fluhr and S. B. Levenstein. Method and Apparatus for Efficiently Accessing Both Aligned and Unaligned Data from a Memory. US Patent 7302525, 2007.","journal-title":"US Patent"},{"issue":"1","key":"e_1_3_2_1_12_1","first-page":"1","article-title":"The Microarchitecture of the Pentium 4 Processor","volume":"5","author":"Hinton G.","year":"2001","unstructured":"G. Hinton , D. Sager , M. Upton , D. Boggs , D. Carmean , A. Kyker , and P. Roussel . The Microarchitecture of the Pentium 4 Processor . Intel Technology Journal , 5 ( 1 ): 1 -- 13 , 2001 . G. Hinton, D. Sager, M. Upton, D. Boggs, D. Carmean, A. Kyker, and P. Roussel. The Microarchitecture of the Pentium 4 Processor. Intel Technology Journal, 5(1):1--13, 2001.","journal-title":"Intel Technology Journal"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2003.822123"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1065910.1065931"},{"volume-title":"Proceedings of the 2002 International Conference on Parallel Architectures and Compilation Techniques. IEEE Computer Society.","author":"Larsen S.","key":"e_1_3_2_1_15_1","unstructured":"S. Larsen , E. Witchel , and S. P. Amarasinghe . Increasing and Detecting Memory Address Congruence . In Proceedings of the 2002 International Conference on Parallel Architectures and Compilation Techniques. IEEE Computer Society. S. Larsen, E. Witchel, and S. P. Amarasinghe. Increasing and Detecting Memory Address Congruence. In Proceedings of the 2002 International Conference on Parallel Architectures and Compilation Techniques. IEEE Computer Society."},{"key":"e_1_3_2_1_16_1","first-page":"330","volume-title":"Proceedings of Thirtieth Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Lee C.","year":"1997","unstructured":"C. Lee , M. Potkonjak , and W. H. Mangione-Smith . MediaBench: A Tool for Evaluating and Synthesizing Multimedia and Communications Systems . In Proceedings of Thirtieth Annual IEEE\/ACM International Symposium on Microarchitecture , pages 330 -- 335 , 1997 . C. Lee, M. Potkonjak, and W. H. Mangione-Smith. MediaBench: A Tool for Evaluating and Synthesizing Multimedia and Communications Systems. In Proceedings of Thirtieth Annual IEEE\/ACM International Symposium on Microarchitecture, pages 330--335, 1997."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.492.0437"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/951710.951714"},{"key":"e_1_3_2_1_19_1","first-page":"145","volume-title":"Proceedings of the 2006 GCC Developers Summit","author":"Nuzman D.","year":"2006","unstructured":"D. Nuzman and A. Zaks . Autovectorization in GCC - Two Years Later . In Proceedings of the 2006 GCC Developers Summit , pages 145 -- 158 , 2006 . D. Nuzman and A. Zaks. Autovectorization in GCC - Two Years Later. In Proceedings of the 2006 GCC Developers Summit, pages 145--58, 2006."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of International Conference on Acoustics, Speech, and Signal Processing","author":"Paver N. C.","year":"2003","unstructured":"N. C. Paver , B. C. Aldrich , and M. H. Khan . Intel Wireless MMX Technology: A 64-Bit SIMD Architecture for Mobile Multimedia . In Proceedings of International Conference on Acoustics, Speech, and Signal Processing , 2003 . N. C. Paver, B. C. Aldrich, and M. H. Khan. Intel Wireless MMX Technology: A 64-Bit SIMD Architecture for Mobile Multimedia. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing, 2003."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133255.1133996"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2003.1223637"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/951710.951747"},{"key":"e_1_3_2_1_24_1","article-title":"Fast Algorithms for the Discrete W Transform and for the Discrete Fourier Transform","author":"Wang Z.","year":"1984","unstructured":"Z. Wang . Fast Algorithms for the Discrete W Transform and for the Discrete Fourier Transform . IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-32(4):803--816 , 1984 . Z. Wang. Fast Algorithms for the Discrete W Transform and for the Discrete Fourier Transform. IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-32(4):803--816, 1984.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-32(4):803--816"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.18"},{"key":"e_1_3_2_1_26_1","first-page":"6862225","article-title":"Buffer for a Split Cache Line Access","author":"Zhang K. X.","year":"2005","unstructured":"K. X. Zhang . Buffer for a Split Cache Line Access . US Patent 6862225 , 2005 . K. X. Zhang. Buffer for a Split Cache Line Access. US Patent 6862225, 2005.","journal-title":"US Patent"}],"event":{"name":"ESWEEK 08: Fourth Embedded Systems Week","sponsor":["ACM Association for Computing Machinery","SIGBED ACM Special Interest Group on Embedded Systems","SIGDA ACM Special Interest Group on Design Automation","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"],"location":"Atlanta GA USA","acronym":"ESWEEK 08"},"container-title":["Proceedings of the 2008 international conference on Compilers, architectures and synthesis for embedded systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1450095.1450121","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1450095.1450121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:30:07Z","timestamp":1750253407000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1450095.1450121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,10,19]]},"references-count":26,"alternative-id":["10.1145\/1450095.1450121","10.1145\/1450095"],"URL":"https:\/\/doi.org\/10.1145\/1450095.1450121","relation":{},"subject":[],"published":{"date-parts":[[2008,10,19]]},"assertion":[{"value":"2008-10-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}