{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T06:26:53Z","timestamp":1672295213993},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2006,6,1]],"date-time":"2006-06-01T00:00:00Z","timestamp":1149120000000},"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":[[2006,6]]},"DOI":"10.1007\/s10766-006-0015-0","type":"journal-article","created":{"date-parts":[[2006,6,23]],"date-time":"2006-06-23T16:53:05Z","timestamp":1151081585000},"page":"237-260","source":"Crossref","is-referenced-by-count":4,"title":["Avoiding Conversion and Rearrangement Overhead in SIMD Architectures"],"prefix":"10.1007","volume":"34","author":[{"given":"Asadollah","family":"Shahbahrami","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Juurlink","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Demid","family":"Borodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stamatis","family":"Vassiliadis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2006,6,24]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Peleg A., Wiljie S., U. Weiser, Intel MMX for Multimedia PCs, Commun. ACM, 25\u201338 (1997).","DOI":"10.1145\/242857.242865"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"S.K. Raman, V. Pentkovski, and J. Keshava, Implementing Streaming SIMD Extensions on the Pentium 3 Processor IEEE Micro, 47\u201357 (2000).","DOI":"10.1109\/40.865866"},{"key":"15_CR3","unstructured":"S. Thakkar and T. Huff, The Internet Streaming SIMD Extensions, Intel. Technol. J., vol.1\u20138 (1999)."},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"M. Tremblay, J. M. O\u2019Connor, V. Narayanan, and L. He, VIS Speeds New Media Processing, IEEE Micro, 10\u201320 (1996).","DOI":"10.1109\/40.526921"},{"key":"15_CR5","unstructured":"M. T. Inc., MIPS Extension for Digital Media, with 3D, www.mips.com."},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"K. Diefendorff, P. K. Dubey, R. H., and H. Scales, AltiVec Extension to PowerPC Accelerates Media Processing IEEE Micro, pp. 85\u201395 (2000).","DOI":"10.1109\/40.848475"},{"key":"15_CR7","unstructured":"D. Burger and T. M. Austin, The SimpleScalar Tool Set, Version 2.0, www.simplescalay.com."},{"issue":"11","key":"15_CR8","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1109\/TC.2002.1047756","volume":"51","author":"N. Slingerland","year":"2002","unstructured":"Slingerland N., Smith A.J. (2002). Measuring the Performance of Multimedia Instruction Sets. IEEE Trans. Comput. 51(11):1317\u20131332","journal-title":"IEEE Trans. Comput."},{"key":"15_CR9","unstructured":"Y. Jung, S. G. Berg, D. Kim, and Y. Kim, A Register File with Transposed Access Mode, in Proc. Int. Conf. on Computer Design, pp. 559\u2013560 (2000)."},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"B. Juurlink, A. Shahbahrami, and S. Vassiliadis, Avoiding Data Conversions in Embedded Media Processors, in Proc. 20th Annual ACM Symp. on Applied Computing, pp. 901\u2013902 (2005).","DOI":"10.1145\/1066677.1066883"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"A. Shahbahrami, B. Juurlink, and S. Vassiliadis, Matrix Register File and Extended Subwords: Two Techniques for Embedded Media Processors, in Proc. 2nd ACM Int. Conf. on Computing Frontiers (2005).","DOI":"10.1145\/1062261.1062291"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"R. B. Lee, Subword Permutation Instructions for Two-Dimensional Multimedia Processing in MicroSIMD Architectures, in Proc. IEEE Int. Conf. on Application-Specific Systems Architectures and Processors, pp. 9\u201323 (2000).","DOI":"10.1109\/ASAP.2000.862373"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"R.B. Lee, Subword Parallelism with MAX-2, IEEE Micro, 51\u201359 (1996).","DOI":"10.1109\/40.526925"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"J. Oliver, V. Akella, and F. Chong, Efficient Orchestration of Sub-Word Parallelism in Media Processors, in Proc. Symp. on Parallel Algorithms and Architecture (2004).","DOI":"10.1145\/1007912.1007946"},{"issue":"1","key":"15_CR15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TVLSI.2004.840415","volume":"13","author":"D. Cheresiz","year":"2005","unstructured":"Cheresiz D., Juurlink B., Vassiliadis S., Wijshoff H.A.G. (2005). The CSI Multimedia Architecture. IEEE Trans. VLSI Syst, 13(1):1\u201313","journal-title":"IEEE Trans. VLSI Syst"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"J. Corbal, M. Valero, and R. Espasa, Exploiting a New Level of DLP in Multimedia Applications, in Proc. Int. Symp. on Microarchitecture (1999).","DOI":"10.1109\/MICRO.1999.809445"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Dasu A., Panchanathan S. Reconfigurable Media Processing. Parallel comput 28(7):(2002).","DOI":"10.1016\/S0167-8191(02)00107-2"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"C. Loeffler, A. Ligtenberg, and G. S. Moschytz, Practical Fast 1-D DCT Algorithms With 11 Multiplications, in Proc. Int. Conf. on Acoustical and Speech, vol. 2, pp. 988\u2013991 (1989).","DOI":"10.1109\/ICASSP.1989.266596"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"J. W. Waerdt, S. Vassiliadis, S. Das, S. Mirolo, C. Yen, B. Zhong, C. Basto, J. P. Itegem, D. Amirtharaj, K. Kalra, P. Rodriguez, and H. Antwerpen, The TM3270 Media-Processor, in Proc. 38th IEEE\/ACM Int. Symp. on Microarchitecture (2005).","DOI":"10.1109\/MICRO.2005.35"},{"key":"15_CR20","unstructured":"S. Rixner, W. J. Dally, B. Khailany, P. Mattson, U. J. Kapasi, and J. D. Owens, Register Organization for Media Processing, in Proc. 6th Int. Symp. on High-Performance Computer Architecture, pp. 9\u201323 (2000)."},{"issue":"2","key":"15_CR21","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/2.982917","volume":"35","author":"T. Austin","year":"2002","unstructured":"Austin T., Larson E., Ernst D. (2002). SimpleScalar: An Infrastructure for Comput System Modeling. IEEE Computer 35(2):59\u201367","journal-title":"IEEE Computer"},{"key":"15_CR22","unstructured":"B. Juurlink, D. Borodin, R. J. Meeuws, G. T. Aalbers, and H. Leisink, The SimpleScalar Instruction Tool (SSIT) and the SimpleScalar Architecture Tool (SSAT), available via http:\/\/ce.et.tudelft.nl\/~shahbahrami\/."},{"key":"15_CR23","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1007\/s005300200052","volume":"8","author":"N. Slingerland","year":"2002","unstructured":"Slingerland N., Smith A.J. (2002). Design and Characterization of the Berkeley Multimedia Workload. Multimedia Syst. 8:315\u2013327","journal-title":"Multimedia Syst."},{"key":"15_CR24","unstructured":"G. Roelofs, PNG: The Definitive Guide, Ph.D. thesis, O\u2019Reilly and Associates (1999)."},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"M. Berekovic, H. J. Stolberg, M. B. Kulaczewski, and P. Pirsch, Instruction Set Extensions for MPEG-4 Video, J VLSI Signal Process, 23:27\u201349 (1999).","DOI":"10.1023\/A:1008188618930"},{"key":"15_CR26","unstructured":"H. C. Chang, L. G. Chen, M. Y. Hsu, and Y. C. Chang, Performance Analysis and Architecture Evaluation of MPEG-4 Video Codec System, in IEEE Int. Symp. on Circuits and Systems, vol. 2, pp. 449\u2013452 (2000)."},{"key":"15_CR27","unstructured":"H. C. Chang, Y. C. Wang, M. Y. Hsu, and L. G. Chen, Efficient Algorithms and Architectures for MPEG-4 Object-Based Video Coding, in Proc. IEEE Workshop on Signal Processing Systems (2000)."},{"key":"15_CR28","unstructured":"S. Vassiliadis, G. Kuzmanov, and S. Wong, MPEG-4 and the New Multimedia Architectural Challenges, in Proc. 15th Int. Conf. on Systems for Automation of Engineering and Research, pp. 24\u201332 (2001)."},{"key":"15_CR29","unstructured":"W. Chen, H. J. Reekie, S. Bhave, and E. A. Lee, Native Signal Processing on the Ultrasparc in the Ptolemy Environment, in Proc. IEEE Conf. on Signals Systems and Computers, vol. 2, pp. 1368\u20131372 (1996)."},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"A. Shahbahrami, B. Juurlink, and S. Vassiliadis, Performance Comparison of SIMD Implementations of the Discrete Wavelet Transform, in Proc. 16th IEEE Int. Conf. on Application Specific Systems Architectures and Processors (ASAP), pp. 393\u2013398 (2005).","DOI":"10.1109\/ASAP.2005.51"},{"key":"15_CR31","unstructured":"Intel, An Efficient Vector\/Matrix Multiply Routine using MMX Technology, Technical report, Intel Developer Services (2004)."},{"key":"15_CR32","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/JSSC.2005.859332","volume":"41","author":"B. Flachs","year":"2006","unstructured":"Flachs B., Asano S., Dhong S.H., Hofstee H.P., Gervais G., Kim R., Le T., Liu P., Leenstra J., Liberty J., Michael B., Oh H.J., Mueller S.M., Takahashi O., Hatakeyama A., Watanabe Y., Yano N., Brokenshire D.A., Peyravian M., To V., Iwata E. (2006). The Microarchitecture of the Synergistic Processor for a Cell Processor. IEEE J. Solid-State Circ. 41:63\u201370","journal-title":"IEEE J. Solid-State Circ."},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"H. P. Hofstee, Power Efficient Processor Architecture and the Cell Processor, in Proc. 11th IEEE Int. Symp. on High-Performance Computer Architectur, pp. 258\u2013262 (2005).","DOI":"10.1109\/HPCA.2005.26"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-006-0015-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-006-0015-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-006-0015-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T19:59:24Z","timestamp":1559246364000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-006-0015-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,6]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2006,6]]}},"alternative-id":["15"],"URL":"https:\/\/doi.org\/10.1007\/s10766-006-0015-0","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,6]]}}}