{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T13:45:56Z","timestamp":1766065556169},"reference-count":37,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2003,6,1]],"date-time":"2003-06-01T00:00:00Z","timestamp":1054425600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Parallel Computing"],"published-print":{"date-parts":[[2003,6]]},"DOI":"10.1016\/s0167-8191(03)00040-1","type":"journal-article","created":{"date-parts":[[2003,4,7]],"date-time":"2003-04-07T14:52:00Z","timestamp":1049727120000},"page":"691-709","source":"Crossref","is-referenced-by-count":17,"title":["Efficient 2D FFT implementation on mediaprocessors"],"prefix":"10.1016","volume":"29","author":[{"given":"Coskun","family":"Mermer","sequence":"first","affiliation":[]},{"given":"Donglok","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Yongmin","family":"Kim","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0167-8191(03)00040-1_BIB1","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","article-title":"An algorithm for the machine computation of complex Fourier series","volume":"19","author":"Cooley","year":"1965","journal-title":"Mathematics of Computation"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/0167-8191(86)90033-5","article-title":"Two and three dimensional FFTs on highly parallel computers","volume":"3","author":"Brass","year":"1986","journal-title":"Parallel Computing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0021-9991(83)90013-X","article-title":"Self-sorting mixed-radix fast Fourier transforms","volume":"52","author":"Temperton","year":"1983","journal-title":"Journal of Computational Physics"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB4","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/BF00162341","article-title":"FFTs in external or hierarchical memory","volume":"4","author":"Bailey","year":"1990","journal-title":"Journal of Supercomputing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB5","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/BF00129835","article-title":"Using local memory to boost the performance of FFT algorithms on the CRAY-2 supercomputer","volume":"4","author":"Carlson","year":"1990","journal-title":"Journal of Supercomputing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB6","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/0167-8191(87)90018-4","article-title":"Multiprocessor FFTs","volume":"5","author":"Swarztrauber","year":"1987","journal-title":"Parallel Computing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB7","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/0167-8191(88)90086-5","article-title":"A segmented FFT algorithm for vector computers","volume":"6","author":"Ashworth","year":"1988","journal-title":"Parallel Computing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB8","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/0167-8191(90)90031-4","article-title":"A parallel FFT on an MIMD machine","volume":"15","author":"Averbuch","year":"1990","journal-title":"Parallel Computing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB9","series-title":"Handbook of Real-Time Fast Fourier Transforms","author":"Smith","year":"1995"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB10","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/12.2269","article-title":"An architecture for a video rate two-dimensional fast Fourier transform processor","volume":"37","author":"Taylor","year":"1988","journal-title":"IEEE Transactions on Computers"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB11","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1109\/4.364445","article-title":"A fast single-chip implementation of 8192 complex point FFT","volume":"30","author":"Bidet","year":"1995","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB12","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1117\/12.334760","article-title":"Critical review of programmable media processor architectures","volume":"3655","author":"Berg","year":"1998","journal-title":"Proceedings of SPIE"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB13","first-page":"2131","article-title":"Radix-4 FFT implementation using SIMD multimedia instructions","author":"Nadehara","year":"1999","journal-title":"IEEE Conference on Acoustics, Speech, and Signal Processing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB14","unstructured":"Using MMX instructions to perform complex 16-bit FFT, Intel Application Note AP-555, Order No. 243040-001, 1996"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB15","unstructured":"TMS320C6000 Assembly Benchmarks at Texas Instruments, URL: http:\/\/www.ti.com\/sc\/docs\/products\/dsp\/c6000\/benchmarks\/62x.htm, 2000"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB16","doi-asserted-by":"crossref","unstructured":"C. Bleakley, V. Berg, J. Rodriguez, B. Murray, FILU-200 DSP coprocessor IP core, in: The 33rd Asilomar Conference on Signals, Systems, and Computers, 1999, pp. 757\u2013761","DOI":"10.1109\/ACSSC.1999.832430"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB17","unstructured":"R.M. Piedra, Parallel 1-D FFT implementation with TMS320C4x DSPs, Texas Instruments Application Report, SPRA108, 1994"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB18","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1049\/ip-vis:19981693","article-title":"Parallelising a set of 2-D frequency transforms in a flexible manner","volume":"145","author":"Fleury","year":"1998","journal-title":"IEE Proceedings\u2013\u2013Vision, Image, and Signal Processing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB19","first-page":"2032","article-title":"A high performance memory and bus architecture for implementing 2D FFT on a SPMD machine","author":"Cavadini","year":"1997","journal-title":"Proceedings of IEEE International Symposium on Circuits and Systems"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB20","doi-asserted-by":"crossref","unstructured":"H. Kwan, R.L. Nelson Jr., E.J. Powers, E.E. Swartzlander Jr., Three-dimensional FFTs on a digital-signal parallel processor, with no interprocessor communication, in: The 30th Asilomar Conference on Signals, Systems, and Computers, 1997, pp. 440\u2013444","DOI":"10.1109\/ACSSC.1996.600944"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB21","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1006\/rtim.1997.0084","article-title":"An efficient FFT algorithm for superscalar and VLIW microprocessor architectures","volume":"3","author":"Basoglu","year":"1997","journal-title":"Real-Time Imaging"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB22","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1145\/212094.212131","article-title":"Software pipelining","volume":"27","author":"Allan","year":"1995","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB23","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1002\/(SICI)1098-1098(1999)10:1<96::AID-IMA11>3.0.CO;2-5","article-title":"Single-chip processor for media applications: the MAP1000","volume":"10","author":"Basoglu","year":"1999","journal-title":"International Journal of Imaging Systems and Technology"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB24","series-title":"Multidimensional Signal Processing","author":"Dudgeon","year":"1984"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB25","series-title":"Computational Frameworks for the Fast Fourier Transform","author":"Van Loan","year":"1992"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB26","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/BF01245402","article-title":"High-performance FFT algorithms for the Convex C4\/XA supercomputer","volume":"9","author":"Wadleigh","year":"1995","journal-title":"Journal of Supercomputing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB27","series-title":"Discrete-Time Signal Processing","author":"Oppenheim","year":"1989"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB28","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1117\/12.334771","article-title":"Image computing library for a next-generation VLIW multimedia processor","volume":"3655","author":"Stotland","year":"1999","journal-title":"Proceedings of SPIE"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB29","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/0020-0190(79)90055-3","article-title":"Reduction of page swaps on the two dimensional transforms in a paging environment","volume":"9","author":"Itano","year":"1979","journal-title":"Information Processing Letters"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB30","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1109\/TPAMI.1981.4767174","article-title":"An efficient two-dimensional FFT algorithm","volume":"3","author":"Johnson","year":"1981","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB31","first-page":"563","article-title":"Fast Fourier transforms\u2013\u2013for fun and profit","volume":"29","author":"Gentleman","year":"1966","journal-title":"AFIPS Proceedings"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB32","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0167-8191(97)00114-2","article-title":"Performing out-of-core FFTs on parallel disk systems","volume":"24","author":"Cormen","year":"1998","journal-title":"Parallel Computing"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB33","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1109\/TAU.1969.1162037","article-title":"Fast Fourier transform of externally stored data","volume":"17","author":"Brenner","year":"1969","journal-title":"IEEE Transactions on Audio and Electroacoustics"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB34","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1007\/BF01185207","article-title":"Algorithms for parallel memory I: Two-level memories","volume":"12","author":"Vitter","year":"1994","journal-title":"Algorithmica"},{"key":"10.1016\/S0167-8191(03)00040-1_BIB35","first-page":"164","article-title":"High-performance FFT implementation on the BOPS ManArray parallel DSP","volume":"3807","author":"Pitsianis","year":"1999","journal-title":"SPIE International Symposium"},{"issue":"2","key":"10.1016\/S0167-8191(03)00040-1_BIB36","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1109\/79.664704","article-title":"Processing the new world of interactive media. The TriMedia VLIW CPU architecture","volume":"15","author":"Rathnam","year":"1998","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"10.1016\/S0167-8191(03)00040-1_BIB37","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/40.946678","article-title":"Data cache and direct memory access in programming mediaprocessors","volume":"21","author":"Kim","year":"2001","journal-title":"IEEE Micro"}],"container-title":["Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819103000401?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819103000401?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,3,23]],"date-time":"2019-03-23T18:20:06Z","timestamp":1553365206000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167819103000401"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,6]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2003,6]]}},"alternative-id":["S0167819103000401"],"URL":"https:\/\/doi.org\/10.1016\/s0167-8191(03)00040-1","relation":{},"ISSN":["0167-8191"],"issn-type":[{"value":"0167-8191","type":"print"}],"subject":[],"published":{"date-parts":[[2003,6]]}}}