{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T19:10:21Z","timestamp":1736795421823,"version":"3.33.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2007,2,10]],"date-time":"2007-02-10T00:00:00Z","timestamp":1171065600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2007,2,20]]},"DOI":"10.1007\/s10766-006-0027-9","type":"journal-article","created":{"date-parts":[[2007,2,9]],"date-time":"2007-02-09T17:50:49Z","timestamp":1171043449000},"page":"63-98","source":"Crossref","is-referenced-by-count":1,"title":["Reducing Off-Chip Memory Access via Stream-Conscious Tiling on Multimedia Applications"],"prefix":"10.1007","volume":"35","author":[{"given":"Chunhui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fadi","family":"Kurdahi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,2,10]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"R. Andonov, H. Bourzoufi, and S. Rajopadhye, Two-dimensional Orthogonal Tiling: From Theory to Practice. in Proceedings of HPC \u201996, pp. 225\u2013231 (1996).","DOI":"10.1109\/HIPC.1996.565827"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"L. Carter, J. Ferrante, and S. F. Hummel, Hierarchical Tiling for Improved Superscalar Performance. in Proceedings of IPPS \u201995, pp. 239\u2013245 (1995).","DOI":"10.1109\/IPPS.1995.395939"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Fei Chen and E. Sha. Loop Scheduling and Partitions for Hiding Memory Latencies. in Proceedings of ISSS \u201999, pp. 64\u201370 (1999).","DOI":"10.1109\/ISSS.1999.814262"},{"issue":"3","key":"27_CR4","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1145\/321406.321418","volume":"14","author":"R.M. Karp","year":"July 1967","unstructured":"Karp R.M., Miller R.E., Winograd S. (July 1967). The Organization of Computations for Uniform recurrence equations. J. ACM 14(3):563\u2013590","journal-title":"J. ACM"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"U. Banerjee, Loop Transformations for Restructuring Compilers. Kluwer Academic Publishers (1993).","DOI":"10.1007\/b102311"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"J. Ramanujam and P. Sadayappan, Tiling Multidimensional Iteration Spaces for Nonshared Memory Machines. in Proceedings Supercomputing \u201991, pp. 111\u2013120 (1991).","DOI":"10.1145\/125826.125893"},{"issue":"12","key":"27_CR7","doi-asserted-by":"crossref","first-page":"1439","DOI":"10.1109\/12.545974","volume":"45","author":"Q. Wang","year":"Dec. 1996","unstructured":"Wang Q., Sha E., Passos N.L (Dec. 1996). Optimal Data Scheduling for Uniform Multi-Dimensional Applications. IEEE Trans. Computers 45(12):1439\u20131444","journal-title":"IEEE Trans. Computers"},{"key":"27_CR8","unstructured":"M. Wolfe, High Performance Compilers for Parallel Computing, Addison Wesley Publishing Company (1996)."},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"P. -Y. Calland, J. Dongarra, and Y. Robert, Tiling with Limited Resources. in Proceedings ASSAP \u201997, pp. 229\u2013238 (1997).","DOI":"10.1109\/ASAP.1997.606829"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"P. R. Panda, N. D. Dutt, and A. Nicolau, Efficient Utilization of Scratch-Pad Memory in Embedded Processor Applications, in Proceedings of EDTC \u201997, pp. 7\u201311 (1997).","DOI":"10.1109\/EDTC.1997.582323"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"P. Marwedel, L. Wehmeyer, M. Verma, Stefan Steinke, and Urs Helmig, Fast, Predictable and Low Energy Memory References Through Architecture-Aware Compilation. in Proceedings of ASP-DAC\u201904, pp. 4\u201311 (2004).","DOI":"10.1109\/ASPDAC.2004.1337530"},{"issue":"2","key":"27_CR12","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1109\/TCAD.2003.822123","volume":"23","author":"M. Kandemir","year":"Feb. 2004","unstructured":"Kandemir M., Ramanujam J., Irwin M., Narayanan V., Kadayif I., Parikh A. (Feb. 2004). A Compiler-Based Approach for Dynamically Managing Scratch-Pad Memories in Embedded Systems. IEEE Trans. CAD 23(2):243\u2013260","journal-title":"IEEE Trans. CAD"},{"issue":"2","key":"27_CR13","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1145\/1067915.1067922","volume":"4","author":"I. Kadayif","year":"May 2005","unstructured":"Kadayif I., Kandemir M. (May 2005). Data Space-Oriented Tiling for Enhancing Locality. ACM Trans on Embedded Comput Sys 4(2):388\u2013414","journal-title":"ACM Trans on Embedded Comput Sys"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"A. Darte and G. Huard. Complexity of Multi-Dimensional Loop Alignment. in Proceedings of STACS\u201902, pp. 179\u2013191 (2002).","DOI":"10.1007\/3-540-45841-7_14"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"J. J. Navarro, E. G. Diego, and J. R. Herrero. Data Prefetching and Multilevel Blocking for Linear Algebra Operations. in Proceedings of Supercomputing \u201996, pp. 109\u2013116 (1996).","DOI":"10.1145\/237578.237592"},{"key":"27_CR16","unstructured":"TMS320C55x DSP Functional Overview, Texas Instruments Inc., http:\/\/focus.ti.com\/lit\/ug\/spru307a\/spru307a.pdf."},{"key":"27_CR17","unstructured":"ADSP-21xx Processor, Analog Devices Inc., http:\/\/www.analog.com\/processors\/processors\/ADSP\/."},{"key":"27_CR18","unstructured":"Texas Instruments, Inc. TMS320VC5510 Power Consumption Summary (SPRA972) (2003)."},{"issue":"8","key":"27_CR19","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1109\/12.30873","volume":"38","author":"J.-K. Peir","year":"1989","unstructured":"Peir J.-K., Cytron R. (1989). Minimum Distance: A Method for Partitioning Recurrences for Multiprocessors. IEEE Trans. on Comp. 38(8):1203\u20131211","journal-title":"IEEE Trans. on Comp."},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"J. Xue, Loop Tiling for Parallelism. Kluwer Academic Publishers (2000).","DOI":"10.1007\/978-1-4615-4337-4"},{"key":"27_CR21","unstructured":"P. C. Shields. Elementary Linear Algebra. Worth Publishers, Inc. (1980)."},{"issue":"4","key":"27_CR22","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1142\/S0129626497000383","volume":"7","author":"A. Darte","year":"1997","unstructured":"Darte A., Silber G.-A., Vivien F. (1997). Combining Retiming and Scheduling Techniques for Loop Parallelization and Loop Tiling. Parallel Process. Lett. 7(4):379\u2013392","journal-title":"Parallel Process. Lett."},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"M. W. Hall, S. Hiranandani, K. Kennedy, and C. W. Tseng. Inter-Procedural Compilation of Fortran D for MIMD Distributed-Memory Machines. in Proceedings of Supercomputing \u201992, pp. 522\u2013534 (1992).","DOI":"10.1145\/143369.143372"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"D. J. Palermo, E. Su, J. A. Chandy, and P. Banerjee, Communication Optimizations Used in the PARADIGM Compiler for Distributed Memory Multicomputers. in Proceedings of Supercomputing \u201994, pp. 1\u201310 (1994).","DOI":"10.1109\/ICPP.1994.67"},{"key":"27_CR25","unstructured":"V. Bhaskaran and K. Konstantinides, Image and Video Compression Standards: Algorithms and Architectures, 2nd edn., Kluwer Academic (1997)."},{"key":"27_CR26","unstructured":"Code Composer Studio Product, Texas Instruments Inc., http:\/\/www.go-dsp.com\/mm-help\/swfs\/profiler.htm."},{"key":"27_CR27","unstructured":"W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling, Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press (1992)."},{"issue":"1","key":"27_CR28","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1109\/92.365453","volume":"3","author":"M.R. Stan","year":"Mar. 1995","unstructured":"Stan M.R., Burleson W.P. (Mar. 1995). Bus-invert coding for low-power i\/o. IEEE Trans. VLSI 3(1):49\u201358","journal-title":"IEEE Trans. VLSI"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"S. Wuytack, F. Catthoor, L. Nachtergaele, and H. De Man, Power Exploration for Data Dominated Video Applications. in Proceedings of ISLPED\u201996, pp. 359\u2013364 (1996).","DOI":"10.1109\/LPE.1996.547539"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-006-0027-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-006-0027-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-006-0027-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T18:36:05Z","timestamp":1736793365000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-006-0027-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,2,10]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2007,2,20]]}},"alternative-id":["27"],"URL":"https:\/\/doi.org\/10.1007\/s10766-006-0027-9","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2007,2,10]]}}}