{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T04:52:45Z","timestamp":1648529565636},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[2008,6,3]],"date-time":"2008-06-03T00:00:00Z","timestamp":1212451200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst Sign Image Video Technol"],"published-print":{"date-parts":[[2009,9]]},"DOI":"10.1007\/s11265-008-0229-z","type":"journal-article","created":{"date-parts":[[2008,6,2]],"date-time":"2008-06-02T15:35:24Z","timestamp":1212420924000},"page":"249-260","source":"Crossref","is-referenced-by-count":6,"title":["Compiler-Based Performance Evaluation of an SIMD Processor with a Multi-Bank Memory Unit"],"prefix":"10.1007","volume":"56","author":[{"given":"Hoseok","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junho","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonyong","family":"Sung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,6,3]]},"reference":[{"key":"229_CR1","unstructured":"Hinton, G., Sager, D., Upton, M., Boggs, D., Carmean, D., Kyker, A., et al. (2001). The microarchitecture of the Pentium 4 processor. Intel Technology Journal, 5."},{"key":"229_CR2","volume-title":"TMS320C6414, TMS320C6415, TMS320C6416 Fixed-point Digital Signal Processors","author":"Texas Instruments","year":"2003","unstructured":"Texas Instruments (2003). TMS320C6414, TMS320C6415 , TMS320C6416 Fixed-point Digital Signal Processors. Dallas: Texas Instruments."},{"key":"229_CR3","volume-title":"The ARM11 Microprocessor and ARM PrimeXsys Platform","author":"ARM","year":"2002","unstructured":"ARM (2002). The ARM11 Microprocessor and ARM PrimeXsys Platform. Austin: ARM"},{"issue":"10","key":"229_CR4","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1109\/PROC.1987.13894","volume":"75","author":"K. Hwang","year":"1987","unstructured":"Hwang, K. (1987). Advanced parallel processing with supercomputer architectures. Proceedings of the IEEE, 75(10), 1348\u20131379.","journal-title":"Proceedings of the IEEE"},{"issue":"12","key":"229_CR5","doi-asserted-by":"crossref","first-page":"1184","DOI":"10.1145\/7902.7904","volume":"29","author":"D. Padua","year":"1986","unstructured":"Padua, D., & Wolfe, M. (1986). Advanced compiler optimizations for supercomputers. Communications of the ACM, 29(12), 1184\u20131201.","journal-title":"Communications of the ACM"},{"issue":"3","key":"229_CR6","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1109\/4.75013","volume":"26","author":"H. Shinohara","year":"1991","unstructured":"Shinohara, H., Matsumoto, N., Fujimori, K., Tsujihashi, Y., Nakao, H., Kato, S., et al. (1991). A flexible multiport RAM compiler for data path. IEEE Journal of Solid-State Circuits, 26(3), 343\u2013349.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"229_CR7","doi-asserted-by":"crossref","unstructured":"Ranganathan, P., Adve, S., & Jouppi, N. (1999). Performance of image and video processing with general-purpose processors and media ISA extensions. In Proceedings of the 26th Annual International Symposium on Computer Architecture (pp. 124\u2013135).","DOI":"10.1109\/ISCA.1999.765945"},{"key":"229_CR8","doi-asserted-by":"crossref","unstructured":"Naishlos, D., Biberstein, M., Ben-David, S., & Zaks, A. (2003). Vectorizing for a SIMdD DSP architecture. In Proceedings of the International Conference on Compilers, Architectures and Synthesis for Embedded Systems (pp. 2\u201311).","DOI":"10.1145\/951710.951714"},{"issue":"8","key":"229_CR9","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1109\/TC.2003.1223637","volume":"52","author":"D. Talla","year":"2003","unstructured":"Talla, D., John, L., & Burger, D. (2003). Bottlenecks in multimedia processing with SIMD style extensions and architectural enhancements. IEEE Transactions on Computers, 52(8), 1015\u20131031.","journal-title":"IEEE Transactions on Computers"},{"key":"229_CR10","volume-title":"The software vectorization handbook","author":"A.J. Bik","year":"2004","unstructured":"Bik, A.\u00a0J. (2004). The software vectorization handbook. Santa Clara: Intel."},{"key":"229_CR11","doi-asserted-by":"crossref","unstructured":"Lorenz, M., Wehmeyer, L., & Dr\u00e4ger, T. (2002). Energy aware compilation for DSPs with SIMD instructions. In Proceedings of the Joint Conference on Languages, Compilers and Tools for Embedded Systems: Software and Compilers for Embedded Systems (pp. 94\u2013101).","DOI":"10.1145\/513829.513847"},{"key":"229_CR12","unstructured":"Ren, G., Wu, P., & Padua, D. (2005). An empirical study on the vectorization of multimedia applications for multimedia extensions. In Proceedings of Parallel and Distributed Processing Symposium (pp. 89b)."},{"key":"229_CR13","unstructured":"Bik, A., Girkar, M., Grey, P., & Tian, X. (2001). Experiments with automatic vectorization for the Pentium 4 processor. In Proceedings of Workshop on Compilers for Parallel Computers."},{"key":"229_CR14","doi-asserted-by":"crossref","unstructured":"Eichenberger, A.\u00a0E., O\u2019Brien, K., O\u2019Brien, K., Wu, P., Chen, T., Oden, P.\u00a0H., et al. (2005). Optimizing compiler for the CELL processor. In Proceedings of the 14th International Conference on Parallel Architectures and Compilation Techniques.","DOI":"10.1109\/PACT.2005.33"},{"issue":"3","key":"229_CR15","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1145\/348019.348570","volume":"5","author":"P. Panda","year":"2000","unstructured":"Panda, P., Dutt, N., & Nicolau, A. (2000). On-chip vs. off-chip memory: The data partitioning problem in embedded processor-based systems. ACM Transactions on Design Automation of Electronic Systems (TODAES), 5(3), 682\u2013704.","journal-title":"ACM Transactions on Design Automation of Electronic Systems (TODAES)"},{"key":"229_CR16","doi-asserted-by":"crossref","unstructured":"Udayakumaran, S., & Barua, R. (2003). Compiler-decided dynamic memory allocation for scratch-pad based embedded systems. In Proceedings of the 2003 International Conference on Compilers, Architecture and Synthesis for Embedded Systems (pp. 276\u2013286)","DOI":"10.1145\/951710.951747"},{"key":"229_CR17","doi-asserted-by":"crossref","unstructured":"Chiou, D., Jain, P., Rudolph, L., & Devadas, S. (2000). Application-specific memory management for embedded systems using software-controlled caches. In Proceedings of the 37th Conference on Design Automation (pp. 416\u2013419).","DOI":"10.1145\/337292.337523"},{"key":"229_CR18","doi-asserted-by":"crossref","unstructured":"Steinke, S., Wehmeyer, L., Lee, B., & Marwedel, P. (2002). Assigning program and data objects to scratchpad for energy reduction. In Proceedings of the Conference on Design, Automation and Test in Europe (p. 409).","DOI":"10.1109\/DATE.2002.998306"},{"issue":"2","key":"229_CR19","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1109\/TCAD.2003.822123","volume":"23","author":"M. Kandemir","year":"2004","unstructured":"Kandemir, M., Ramanujam, J., Irwin, M., Vijaykrishnan, N., Kadayif, I., & Parikh, A. (2004). A compiler-based approach for dynamically managing scratch-pad memories in embedded systems. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 23(2), 243\u2013260.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"issue":"2","key":"229_CR20","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TC.1978.1675045","volume":"27","author":"D. Voorhis van","year":"1978","unstructured":"van Voorhis, D., & Morrin, T. (1978). Memory systems for image processing. IEEE Transactions on Computers, 27(2), 113\u2013125.","journal-title":"IEEE Transactions on Computers"},{"key":"229_CR21","doi-asserted-by":"crossref","unstructured":"Trenas, M., Lopez, J., & Zapata, E. (1998). A memory system supporting the efficient SIMD computation of the two dimensional DWT. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing.","DOI":"10.1109\/ICASSP.1998.681739"},{"key":"229_CR22","unstructured":"Mathew, B., McKee, S., Carter, J., & Davis, A. (2000). Design of a parallel vector access unit for SDRAM memory systems. In Proceedings of the 6th International Symposium on High-Performance Computer Architecture (pp. 39\u201348)."},{"issue":"10","key":"229_CR23","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1109\/TC.1985.6312199","volume":"34","author":"W. Oed","year":"1985","unstructured":"Oed, W., & Lange, O. (1985). On the effective bandwidth of interleaved memories in vector processor systems. IEEE Transactions on Computers, 34(10), 949\u2013957.","journal-title":"IEEE Transactions on Computers"},{"issue":"21","key":"229_CR24","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1109\/TC.1972.5009049","volume":"C","author":"C. Ravi","year":"1972","unstructured":"Ravi, C. (1972). On the bandwidth and interference in interleaved memory system. IEEE Transactions on Computers, C(21), 899\u2013901.","journal-title":"IEEE Transactions on Computers"},{"issue":"4","key":"229_CR25","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1109\/12.214693","volume":"42","author":"R. Raghavan","year":"1993","unstructured":"Raghavan, R., & Hayes, J. (1993). Reducing interference among vector accesses in interleaved memories. IEEE Transactions on Computers, 42(4), 471\u2013483.","journal-title":"IEEE Transactions on Computers"},{"issue":"4","key":"229_CR26","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/40.526924","volume":"16","author":"A. Peleg","year":"1996","unstructured":"Peleg, A., & Weiser, U. (1996). MMX technology extension to the Intel architecture. IEEE Micro, 16(4), 42\u201350.","journal-title":"IEEE Micro"},{"issue":"20","key":"229_CR27","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1109\/T-C.1971.223171","volume":"C","author":"P. Budnik","year":"1971","unstructured":"Budnik, P., & Kuck, D. (1971). The organization and use of parallel memories. IEEE Transactions on Computers, C(20), 1566\u20131569.","journal-title":"IEEE Transactions on Computers"},{"key":"229_CR28","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/11532378_4","volume":"3602","author":"L.N. Chakrapani","year":"2005","unstructured":"Chakrapani, L.\u00a0N., Gyllenhaal, J., Hwu, W.\u00a0W., Mahlke, S.\u00a0A., Palem, K.\u00a0V., & Rabbah, R.\u00a0M. (2005). Trimaran: An infrastructure for research in instruction-level parallelism. Lecture Notes in Computer Science, 3602, 32\u201341.","journal-title":"Lecture Notes in Computer Science"},{"key":"229_CR29","unstructured":"GNU (2008). GCC, the GNU compiler collection. http:\/\/www.gnu.org\/software\/gcc ."},{"key":"229_CR30","unstructured":"Naishlos, D. (2004). Autovectorization in GCC. In Proceedings of the 2004 GCC Developers Summit (pp. 105\u2013118)."},{"key":"229_CR31","unstructured":"Lee, C., Potkonjak, M., & Mangione-Smith, W.\u00a0H. (1997). Mediabench: A tool for evaluating and synthesizing multimedia and communications systems. In Proceedings of the 30th Annual ACM\/IEEE International Symposium on Microarchitecture (pp. 330\u2013335)."},{"issue":"4","key":"229_CR32","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1109\/TASSP.1984.1164399","volume":"32","author":"Z. Wang","year":"1984","unstructured":"Wang, Z. (1984). Fast algorithms for the discrete W transform and for the discrete fourier transform. Acoustics, Speech, and Signal Processing, 32(4), 803\u2013816.","journal-title":"Acoustics, Speech, and Signal Processing"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-008-0229-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-008-0229-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-008-0229-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T12:19:28Z","timestamp":1559391568000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-008-0229-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,6,3]]},"references-count":32,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2009,9]]}},"alternative-id":["229"],"URL":"https:\/\/doi.org\/10.1007\/s11265-008-0229-z","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,6,3]]}}}