{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:46:26Z","timestamp":1772163986022,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,3,13]],"date-time":"2010-03-13T00:00:00Z","timestamp":1268438400000},"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":[[2010,3,13]]},"DOI":"10.1145\/1736020.1736053","type":"proceedings-article","created":{"date-parts":[[2010,3,16]],"date-time":"2010-03-16T15:27:05Z","timestamp":1268753225000},"page":"285-296","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["MacroSS"],"prefix":"10.1145","author":[{"given":"Amir H.","family":"Hormati","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoonseo","family":"Choi","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Woh","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manjunath","family":"Kudlur","sequence":"additional","affiliation":[{"name":"Nvidia Corp., Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rodric","family":"Rabbah","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Hawthorne, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Mudge","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Mahlke","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2010,3,13]]},"reference":[{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/29873.29875"},{"key":"e_1_3_2_1_3_1","volume-title":"Optimizing compilers for modern architectures: A dependence-based approach","author":"Allen R.","year":"2002","unstructured":"R. Allen and K. Kennedy . Optimizing compilers for modern architectures: A dependence-based approach . Morgan Kaufmann Publishers Inc ., 2002 . R. Allen and K. Kennedy. Optimizing compilers for modern architectures: A dependence-based approach. Morgan Kaufmann Publishers Inc., 2002."},{"key":"e_1_3_2_1_4_1","unstructured":"ARM Ltd. ARM Neon 2009. http:\/\/www.arm.com\/miscPDFs\/6629.pdf.  ARM Ltd. ARM Neon 2009. http:\/\/www.arm.com\/miscPDFs\/6629.pdf."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015800"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1065010.1065038"},{"key":"e_1_3_2_1_7_1","unstructured":"G. C. Collection. Gcc 4.3.2 2008. http:\/\/gcc.gnu.org\/gcc-4.3\/.  G. C. Collection. Gcc 4.3.2 2008. http:\/\/gcc.gnu.org\/gcc-4.3\/."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/996841.996853"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/605397.605428"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168877"},{"key":"e_1_3_2_1_11_1","unstructured":"IBM. Cell Broadband Engine Architecture Mar. 2006.  IBM. Cell Broadband Engine Architecture Mar. 2006."},{"key":"e_1_3_2_1_12_1","volume-title":"Intel sse4","year":"2006","unstructured":"Intel. Intel sse4 , 2006 . http:\/\/download.intel.com\/technology\/architecture\/new-instructions-paper.pdf. Intel. Intel sse4, 2006. http:\/\/download.intel.com\/technology\/architecture\/new-instructions-paper.pdf."},{"key":"e_1_3_2_1_13_1","volume-title":"Intel Core i7","year":"2008","unstructured":"Intel. Intel Core i7 , 2008 . gttp:\/\/www.intel.com\/products\/processor\/corei7\/index.htm. Intel. Intel Core i7, 2008. gttp:\/\/www.intel.com\/products\/processor\/corei7\/index.htm."},{"key":"e_1_3_2_1_14_1","volume-title":"Intel compiler","year":"2009","unstructured":"Intel. Intel compiler , 2009 . software.intel.com\/en-us\/intel-compilers\/. Intel. Intel compiler, 2009. software.intel.com\/en-us\/intel-compilers\/."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375596"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349320"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1987.13876"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.472.0299"},{"key":"e_1_3_2_1_19_1","volume-title":"Opencl parallel computing on the gpu and cpu","author":"Munshi A.","year":"2008","unstructured":"A. Munshi . Opencl parallel computing on the gpu and cpu ., 2008 . A. Munshi. Opencl parallel computing on the gpu and cpu., 2008."},{"key":"e_1_3_2_1_20_1","volume-title":"In Proc. MSP'04","author":"Narayanan M.","year":"2004","unstructured":"M. Narayanan and K. A. Yelick . Generating permutation instructions from a high--level description . In In Proc. MSP'04 , 2004 . M. Narayanan and K. A. Yelick. Generating permutation instructions from a high--level description. In In Proc. MSP'04, 2004."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2006.25"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133981.1133997"},{"key":"e_1_3_2_1_23_1","first-page":"2","volume-title":"Outer-loop vectorization -- revisited for short simd architectures","author":"Nuzman D.","year":"2008","unstructured":"D. Nuzman and A. Zaks . Outer-loop vectorization -- revisited for short simd architectures . pages 2 -- 11 , 2008 . D. Nuzman and A. Zaks. Outer-loop vectorization -- revisited for short simd architectures. pages 2--11, 2008."},{"key":"e_1_3_2_1_24_1","volume-title":"June","year":"2007","unstructured":"Nvidia. CUDA Programming Guide , June 2007 . http:\/\/developer.download.nvidia.com\/compute\/cuda. Nvidia. CUDA Programming Guide, June 2007. http:\/\/developer.download.nvidia.com\/compute\/cuda."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133981.1133996"},{"key":"e_1_3_2_1_26_1","volume-title":"ARM Architecture Reference Manual","author":"Seal D.","year":"2000","unstructured":"D. Seal . ARM Architecture Reference Manual . Addison-Wesley , London, UK , 2000 . D. Seal. ARM Architecture Reference Manual. Addison-Wesley, London, UK, 2000."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360617"},{"key":"e_1_3_2_1_28_1","unstructured":"F. Semiconductor. Altivec 2009. www.freescale.com\/altivec.  F. Semiconductor. Altivec 2009. www.freescale.com\/altivec."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/647478.727935"},{"key":"e_1_3_2_1_30_1","volume-title":"Tile64 processor -- product brief","year":"2008","unstructured":"Tilera. Tile64 processor -- product brief , 2008 . http:\/\/www.tilera.com\/pdf\/. Tilera. Tile64 processor -- product brief, 2008. http:\/\/www.tilera.com\/pdf\/."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.18"}],"event":{"name":"ASPLOS '10: Architectural Support for Programming Languages and Operating Systems","location":"Pittsburgh Pennsylvania USA","acronym":"ASPLOS '10","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the fifteenth International Conference on Architectural support for programming languages and operating systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1736020.1736053","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1736020.1736053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:41:22Z","timestamp":1750236082000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1736020.1736053"}},"subtitle":["macro-SIMDization of streaming applications"],"short-title":[],"issued":{"date-parts":[[2010,3,13]]},"references-count":30,"alternative-id":["10.1145\/1736020.1736053","10.1145\/1736020"],"URL":"https:\/\/doi.org\/10.1145\/1736020.1736053","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/1735971.1736053","asserted-by":"object"},{"id-type":"doi","id":"10.1145\/1735970.1736053","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2010,3,13]]},"assertion":[{"value":"2010-03-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}