{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T10:19:32Z","timestamp":1649153972874},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2009,11,27]],"date-time":"2009-11-27T00:00:00Z","timestamp":1259280000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2011,5]]},"DOI":"10.1007\/s11227-009-0364-8","type":"journal-article","created":{"date-parts":[[2009,11,27]],"date-time":"2009-11-27T16:10:55Z","timestamp":1259338255000},"page":"226-244","source":"Crossref","is-referenced-by-count":1,"title":["An approximate method for filtering out data dependencies with a sufficiently large distance between\u00a0memory\u00a0references"],"prefix":"10.1007","volume":"56","author":[{"given":"Patricio","family":"Buli\u0107","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toma\u017e","family":"Dobravec","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,11,27]]},"reference":[{"key":"364_CR1","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1007\/s11227-008-0207-z","volume":"48","author":"JI Aliaga","year":"2009","unstructured":"Aliaga JI et al (2009) Toward the parallelization of GSL. J Supercomput 48:88\u2013114. doi: 10.1007\/s11227-008-0207-z","journal-title":"J Supercomput"},{"key":"364_CR2","volume-title":"Optimizing compilers for modern architectures: a dependence-based approach","author":"R Allen","year":"2001","unstructured":"Allen R, Kennedy K (2001) Optimizing compilers for modern architectures: a dependence-based approach. Morgan Kaufmann, San Mateo"},{"issue":"5","key":"364_CR3","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1093\/comjnl\/30.5.425","volume":"30","author":"HR Arabnia","year":"1987","unstructured":"Arabnia HR, Oliver MA (1987) A transputer network for the arbitrary rotation of digitized images. Comput J 30(5):425\u2013432","journal-title":"Comput J"},{"issue":"2","key":"364_CR4","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1109\/5.214548","volume":"81","author":"U Banerjee","year":"1993","unstructured":"Banerjee U, Eigenman R, Nicolau A, Padua DA (1993) Automatic program parallelization. Proc IEEE 81(2):211\u2013243","journal-title":"Proc IEEE"},{"key":"364_CR5","volume-title":"Dependence analysis: a book series on loop transformations for restructuring compilers","author":"U Banerjee","year":"1997","unstructured":"Banerjee U (1997) Dependence analysis: a book series on loop transformations for restructuring compilers. Kluwer Academic, Dordrecht"},{"issue":"1","key":"364_CR6","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1006\/jpdc.1995.1011","volume":"24","author":"SM Bhandarkar","year":"1995","unstructured":"Bhandarkar SM, Arabnia HR (1995) The Hough transform on a reconfigurable multi-ring network. J\u00a0Parallel Distrib Comput 24(1):107\u2013114","journal-title":"J\u00a0Parallel Distrib Comput"},{"issue":"2","key":"364_CR7","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1142\/S0218001495000110","volume":"9","author":"SM Bhandarkar","year":"1995","unstructured":"Bhandarkar SM, Arabnia HR, Smith JW (1995) A reconfigurable architecture for image-processing and computer vision. Int J Pattern Recognit Artif Intell 9(2):201\u2013229","journal-title":"Int J Pattern Recognit Artif Intell"},{"issue":"2","key":"364_CR8","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1023\/A:1014230429447","volume":"30","author":"AJC Bik","year":"2002","unstructured":"Bik AJC, Girkar M, Grey PM, Tian XM (2002) Automatic intra-register vectorization for the Intel (R) architecture. Int J Parallel Program 30(2):65\u201398","journal-title":"Int J Parallel Program"},{"issue":"3","key":"364_CR9","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/M-PDT.1994.329796","volume":"2","author":"W Blume","year":"1994","unstructured":"Blume W, Eigenman R, Hoeflinger J, Padua DA, Petersen P, Rauchwerger L, Tu P (1994) Automatic detection of parallelism: a great challenge for high-performance computing. IEEE Parallel Distrib Process Technol 2(3):37\u201347","journal-title":"IEEE Parallel Distrib Process Technol"},{"issue":"12","key":"364_CR10","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1109\/71.737695","volume":"9","author":"W Blume","year":"1998","unstructured":"Blume W, Eigenman R (1998) Nonlinear and symbolic data dependence testing. IEEE Parallel Distrib Process Technol 9(12):1180\u20131194","journal-title":"IEEE Parallel Distrib Process Technol"},{"issue":"7","key":"364_CR11","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1093\/ietisy\/e88-d.7.1569","volume":"E88D","author":"YJ Chuang","year":"2005","unstructured":"Chuang YJ, Wu JL (2005) An efficient matrix-based 2-D DCT splitter and merger for SIMD instructions. IEICE Trans Inf Syst E88D(7):1569\u20131577. doi: 0.1093\/ietisy\/e88-d.7.1569","journal-title":"IEICE Trans Inf Syst"},{"issue":"1","key":"364_CR12","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.parco.2004.11.002","volume":"31","author":"A Blas Di","year":"2005","unstructured":"Di Blas A, Jagota A, Hughey R (2005) Optimizing neural networks on SIMD parallel computers. Parallel Comput 31(1):97\u2013115. doi: 10.1016\/j.parco.2004.11.002","journal-title":"Parallel Comput"},{"key":"364_CR13","author":"M Guo","year":"2009","unstructured":"Guo M et al (2009) Communication-free data alignment for arrays with exponential references in parallelizing compilers for scalable parallel systems. J Supercomput. doi: 10.1007\/s11227-009-0280-y","journal-title":"J Supercomput."},{"issue":"6","key":"364_CR14","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1093\/comjnl\/bxm099","volume":"51","author":"M Hassaballah","year":"2008","unstructured":"Hassaballah M et al (2008) A review of SIMD multimedia extensions and their usage in scientific and engineering applications. Comput J 51(6):630\u2013649. doi: 10.1093\/comjnl\/bxm099","journal-title":"Comput J"},{"key":"364_CR15","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S0164-1212(99)00132-6","volume":"52","author":"TC Huang","year":"2000","unstructured":"Huang TC, Yang CM (2000) Data dependence analysis for array references. J Syst Softw 52:55\u201365","journal-title":"J Syst Softw"},{"key":"364_CR16","author":"S Kim","year":"2009","unstructured":"Kim S et al (2009) Region-based parallelization of irregular reductions on explicitly managed memory hierarchies. J Supercomput. doi: 10.1007\/s11227-009-0340-3","journal-title":"J Supercomput."},{"issue":"4","key":"364_CR17","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1023\/A:1007507005174","volume":"28","author":"A Krall","year":"2000","unstructured":"Krall A, Lelait S (2000) Compilation techniques for multimedia processors. Int J Parallel Program 28(4):347\u2013361","journal-title":"Int J Parallel Program"},{"issue":"3","key":"364_CR18","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.parco.2008.12.010","volume":"35","author":"J Kurzak","year":"2009","unstructured":"Kurzak J et al (2009) Optimizing matrix multiplication for a short-vector SIMD architecture\u2014CELL processor. Parallel Comput 35(3):138\u2013150. doi: 10.1016\/j.parco.2008.12.010","journal-title":"Parallel Comput"},{"issue":"3","key":"364_CR19","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s11265-007-0151-9","volume":"51","author":"WC Lee","year":"2008","unstructured":"Lee WC et al (2008) Algorithm and software optimization of variable block size motion estimation for H.264\/AVC on a VLIW-SIMD DSP. J Signal Process Syst Signal Image Video Technol 51(3):289\u2013302. doi: 10.1007\/s11265-007-0151-9","journal-title":"J Signal Process Syst Signal Image Video Technol"},{"key":"364_CR20","author":"S Lotfi","year":"2009","unstructured":"Lotfi S, Parsa S (2009) Parallel loop generation and scheduling. J Supercomput doi: 10.1007\/s11227-008-0262-5","journal-title":"J Supercomput"},{"issue":"2","key":"364_CR21","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1007\/s11042-006-6144-z","volume":"28","author":"NC Paver","year":"2006","unstructured":"Paver NC, Khan MH, Aldrich BC (2006) Optimizing mobile multimedia using SIMD techniques. Multimed Tools Appl 28(2):393\u2013416","journal-title":"Multimed Tools Appl"},{"issue":"11","key":"364_CR22","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1109\/71.544354","volume":"7","author":"PM Petersen","year":"1996","unstructured":"Petersen PM, Padua DA (1996) Static and dynamic evaluation of data dependence analysis techniques. IEEE Trans Parallel Distrib Syst 7(11):1121\u20131132","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"8","key":"364_CR23","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1145\/135226.135233","volume":"35","author":"W Pough","year":"1992","unstructured":"Pough W (1992) A practical algorithm for exact array dependence analysis. Commun ACM 35(8):102\u2013114","journal-title":"Commun ACM"},{"issue":"3","key":"364_CR24","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1145\/151640.151645","volume":"1","author":"W Pough","year":"1992","unstructured":"Pough W (1992) Definitions of dependence distance. ACM Lett Program Lang Syst 1(3):261\u2013265","journal-title":"ACM Lett Program Lang Syst"},{"issue":"3","key":"364_CR25","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/S0167-8191(01)00132-6","volume":"28","author":"K Psarris","year":"2002","unstructured":"Psarris K (2002) Program analysis techniques for transforming programs for parallel execution. Parallel Comput 28(3):455\u2013469","journal-title":"Parallel Comput"},{"issue":"3","key":"364_CR26","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1109\/TPDS.2004.1264806","volume":"15","author":"K Psarris","year":"2004","unstructured":"Psarris K, Klappholz D, Kong X (2004) An experimental evaluation of data dependence analysis techniques. IEEE Trans Parallel Distrib Syst 15(3):196\u2013213","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"1","key":"364_CR27","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TMM.2007.911195","volume":"10","author":"A Shahbahrami","year":"2008","unstructured":"Shahbahrami A et al (2008) Implementing the 2-D wavelet transform on SIMD-enhanced general-purpose processors. IEEE Trans Multimed 10(1):43\u201351. doi: 10.1109\/TMM.2007.911195","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"364_CR28","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1023\/A:1007559022013","volume":"28","author":"N Sreraman","year":"2000","unstructured":"Sreraman N, Govindarajan R (2000) A vectorizing compiler for multimedia extensions. Int J Parallel Program 28(4):363\u2013400","journal-title":"Int J Parallel Program"},{"issue":"1","key":"364_CR29","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1023\/A:1022804606389","volume":"25","author":"MA Wani","year":"2003","unstructured":"Wani MA, Arabnia HR (2003) Parallel edge-region-based segmentation algorithm targeted at reconfigurable MultiRing network. J Supercomput 25(1):43\u201362","journal-title":"J Supercomput"},{"issue":"2","key":"364_CR30","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/BF01379099","volume":"16","author":"MJ Wolfe","year":"1987","unstructured":"Wolfe MJ, Banerjee U (1987) Data dependence and its application to parallel processing. Int J Parallel Program 16(2):137\u2013178","journal-title":"Int J Parallel Program"},{"issue":"5","key":"364_CR31","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/71.159042","volume":"3","author":"MJ Wolfe","year":"1992","unstructured":"Wolfe MJ, Tseng CW (1992) The power test for data dependence. IEEE Trans Parallel Distrib Syst 3(5):591\u2013601","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"364_CR32","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s11227-007-0124-6","volume":"43","author":"J Xue","year":"2008","unstructured":"Xue J, Guo M, Wei D (2008) Improving the parallelism of iterative methods by aggressive loop fusion. J Supercomput 43:147\u2013164. doi: 10.1007\/s11227-007-0124-6","journal-title":"J Supercomput"},{"key":"364_CR33","author":"CT Yang","year":"2009","unstructured":"Yang CT, Lai KC (2009) A directive-based MPI code generator for Linux PC clusters. J Supercomput. doi: 10.1007\/s11227-008-0258-1","journal-title":"J Supercomput."},{"key":"364_CR34","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s11227-008-0186-0","volume":"47","author":"X Yang","year":"2009","unstructured":"Yang X et al (2009) Matrix-based streamization approach for improving locality and parallelism on FT64 stream processor. J Supercomput 47:171\u2013197. doi: 10.1007\/s11227-008-0186-0","journal-title":"J Supercomput"},{"issue":"3","key":"364_CR35","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1142\/S0218001406004727","volume":"20","author":"FN Yuan","year":"2006","unstructured":"Yuan FN et al (2006) An interactive 3D visualization system based on PC using Intel SIMD, 3D texturing and thinning techniques. Int J Pattern Recognit Artif Intell 20(3):393\u2013416","journal-title":"Int J Pattern Recognit Artif Intell"},{"key":"364_CR36","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1007\/s11227-007-0168-7","volume":"45","author":"J Zhou","year":"2008","unstructured":"Zhou J, Zeng G (2008) A general data dependence analysis for parallelizing compilers. J Supercomput 45:236\u2013252. doi: 10.1007\/s11227-007-0168-7","journal-title":"J Supercomput"},{"key":"364_CR37","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/s11227-008-0197-x","volume":"45","author":"J Zhou","year":"2008","unstructured":"Zhou J, Zeng G (2008) A general data dependence analysis for parallelizing compilers. ERRATUM. J Supercomput 45:253. doi: 10.1007\/s11227-008-0197-x","journal-title":"J Supercomput"},{"issue":"4","key":"364_CR38","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1631\/jzus.A071203","volume":"9","author":"JP Zhou","year":"2008","unstructured":"Zhou JP, Shi C (2008) Efficient SIMD optimization for media processors. J Zhejiang Univ-Sci A 9(4):524\u2013530. doi: 10.1631\/jzus.A071203","journal-title":"J Zhejiang Univ-Sci A"},{"key":"364_CR39","volume-title":"Supercompilers for parallel and vector computers","author":"HP Zima","year":"1990","unstructured":"Zima HP, Chapman BM (1990) Supercompilers for parallel and vector computers. Addison-Wesley, Reading"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-009-0364-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-009-0364-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-009-0364-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T06:24:00Z","timestamp":1559370240000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-009-0364-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,11,27]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2011,5]]}},"alternative-id":["364"],"URL":"https:\/\/doi.org\/10.1007\/s11227-009-0364-8","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,11,27]]}}}