{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:02:27Z","timestamp":1773777747896,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2007,4,3]],"date-time":"2007-04-03T00:00:00Z","timestamp":1175558400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2007,4,3]],"date-time":"2007-04-03T00:00:00Z","timestamp":1175558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2007,6]]},"DOI":"10.1007\/s10766-007-0034-5","type":"journal-article","created":{"date-parts":[[2007,4,2]],"date-time":"2007-04-02T17:09:02Z","timestamp":1175533742000},"page":"263-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":48,"title":["Scientific Computing Kernels on the Cell Processor"],"prefix":"10.1007","volume":"35","author":[{"given":"Samuel","family":"Williams","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Shalf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonid","family":"Oliker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoaib","family":"Kamil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parry","family":"Husbands","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katherine","family":"Yelick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,4,3]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"S. Williams, J. Shalf, L. Oliker, et\u00a0al., The Potential of the Cell Processor for Scientific Computing, Computing Frontiers, pp. 9\u201320 (May 2006).","DOI":"10.1145\/1128022.1128027"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"M. Kondo, H. Okawara, H. Nakamura, et\u00a0al., Scima: A Novel Processor Architecture for High Performance Computing, 4th International Conference on High Performance Computing in the Asia Pacific Region, volume 1, pp. 355\u2013360 (May 2000).","DOI":"10.1109\/HPC.2000.846577"},{"key":"34_CR3","unstructured":"P. Keltcher, S. Richardson, S. Siu, et\u00a0al., An Equal Area Comparison of Embedded DRAM and SRAM Memory Architectures for a Chip Multiprocessor. Technical report, HP Laboratories (April 2000)."},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"S. Tomar, S. Kim, N. Vijaykrishnan, et\u00a0al., Use of Local Memory for Efficient Java Execution, Proceedings of the International Conference on Computer Design, pp. 468\u2013473 (September 2001).","DOI":"10.1109\/ICCD.2001.955067"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"M. Kandemir, J. Ramanujam, M. Irwin, et\u00a0al., Dynamic Management of Scratch-pad Memory Space, Proceedings of the Design Automation Conference, pp. 690\u2013695 (June 2001).","DOI":"10.1145\/378239.379049"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"P. Francesco, P. Marchal, D. Atienzaothers, et\u00a0al., An Integrated Hardware\/Software Approach for Run-time Scratchpad Management, Proceedings of the 41st Design Automation Conference, pp. 238\u2013243 (June 2004).","DOI":"10.1145\/996566.996634"},{"key":"34_CR7","unstructured":"The Berkeley Intelligent RAM (IRAM) Project. http:\/\/iram.cs.berkeley.edu."},{"issue":"2","key":"34_CR8","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/40.918001","volume":"21","author":"B. Khailany","year":"March\u2013April 2001","unstructured":"Khailany B., Dally W., Rixner S. et\u00a0al (March\u2013April 2001). Imagine: Media Processing with Streams. IEEE Micro, 21(2):35\u201346","journal-title":"IEEE Micro,"},{"issue":"6","key":"34_CR9","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/40.809374","volume":"19","author":"M. Oka","year":"November 1999","unstructured":"Oka M., Suzuoki M. (November 1999). Designing and Programming the Emotion Engine. IEEE Micro, 19(6):20\u201328","journal-title":"IEEE Micro,"},{"issue":"2","key":"34_CR10","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1109\/40.848471","volume":"20","author":"A. Kunimatsu","year":"March 2000","unstructured":"Kunimatsu A., Ide N., Sato T. et\u00a0al. (March 2000). Vector Unit Architecture for Emotion Synthesis. IEEE Micro, 20(2):40\u201347","journal-title":"IEEE Micro,"},{"issue":"1","key":"34_CR11","doi-asserted-by":"publisher","first-page":"1608","DOI":"10.1109\/4.799870","volume":"34","author":"M. Suzuoki","year":"November 1999","unstructured":"Suzuoki M. et\u00a0al. (November 1999). A Microprocessor with a 128-bit cpu, Ten Floating Point Macs, Four Floating-point Dividers, and an mpeg-2 Decoder. IEEE Solid State Circuits, 34(1):1608\u20131618","journal-title":"IEEE Solid State Circuits,"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"B. Flachs, S. Asano, S.H. Dhong, et\u00a0al., A Streaming Processor Unit for a Cell Processor, ISSCC Dig. Tech. Papers, pp. 134\u2013135 (February 2005).","DOI":"10.1109\/ISSCC.2005.1493905"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"D. Pham, S. Asano, M. Bollier, et\u00a0al., The Design and Implementation of a First-generation Cell Processor, ISSCC Dig. Tech. Papers, pp. 184\u2013185 (February 2005).","DOI":"10.1109\/ISSCC.2005.1493930"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"S. M. Mueller, C. Jacobi, C. Hwa-Joon, et\u00a0al., The Vector Floating-point Unit in a Synergistic Processor Element of a Cell Processor, 17th IEEE Annual Symposium on Computer Arithmetic (ISCA), pp. 59\u201367 (June 2005).","DOI":"10.1109\/ARITH.2005.45"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"J. A. Kahle, M. N. Day, H. P. Hofstee, et\u00a0al., Introduction to the Cell Multiprocessor. IBM Journal of R&D, 49(4) (2005).","DOI":"10.1147\/rd.494.0589"},{"key":"34_CR16","unstructured":"IBM Cell specifications. http:\/\/www.research.ibm.com\/cell\/home.html."},{"key":"34_CR17","unstructured":"M. Snir, S. Otto, S. Huss-Lederman, D. Walker, and J.Dongarra. MPI: The Complete Reference (Vol. 1). The MIT Press (1998)."},{"key":"34_CR18","unstructured":"Sony press release. http:\/\/www.scei.co.jp\/corporate\/release\/pdf\/050517e.pdf."},{"key":"34_CR19","unstructured":"N. Park, B. Hong, and V. K. Prasanna, Analysis of Memory Hierarchy Performance of Block Data Layout. International Conference on Parallel Processing (ICPP), p. 35 (August 2002)."},{"key":"34_CR20","unstructured":"L. Cannon, A Cellular Computer to Implement the Kalman Filter Algorithm. PhD thesis, Montana State University, p. 228 (1969)."},{"key":"34_CR21","unstructured":"Cell Broadband Engine Architecture and its First Implementation. http:\/\/www-128. ibm.com\/developerworks\/power\/library\/pa-cellperf\/"},{"key":"34_CR22","volume-title":"Iterative Methods for Sprarse Linear Systems","author":"Y. Saad","year":"1996","unstructured":"Saad Y. (1996). Iterative Methods for Sprarse Linear Systems. PWS, Boston, MA"},{"key":"34_CR23","unstructured":"G. Blelloch, M. Heroux, and M. Zagha, Segmented Operations for Sparse Matrix Computation on Vector Multiprocessors, Technical Report CMU-CS-93-173, CMU (1993)."},{"key":"34_CR24","unstructured":"R. Vuduc, Automatic Performance Tuning of Sparse Matrix Kernels, PhD thesis, University of California at Berkeley (2003)."},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"E.-J. Im, K. Yelick, and R. Vuduc, Sparsity: Optimization Framework for Sparse Matrix Kernels, International Journal of High Performance Computing Applications, pp. 135\u2013158 (2004).","DOI":"10.1177\/1094342004041296"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"E. F. D\u2019Azevedo, M. R. Fahey, and R. T. Mills, Vectorized Sparse Matrix Multiply for Compressed Row Storage Format, International Conference on Computational Science (ICCS), pp. 99\u2013106 (2005).","DOI":"10.1007\/11428831_13"},{"key":"34_CR27","unstructured":"Chombo homepage. http:\/\/seesar.lbl.gov\/anag\/chombo."},{"key":"34_CR28","unstructured":"Cactus homepage. http:\/\/www.cactuscode.org."},{"issue":"6","key":"34_CR29","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1145\/1034774.1034777","volume":"26","author":"Z. Li","year":"2004","unstructured":"Li Z., Song Y. (2004). Automatic Tiling of Iterative Stencil Loops. ACM Transactions on Programming Language Systems, 26(6):975\u20131028","journal-title":"ACM Transactions on Programming Language Systems,"},{"key":"34_CR30","unstructured":"David Wonnacott, Using Time Skewing to Eliminate Idle Time due to Memory Bandwidth and Network Limitations. International Parallel and Distributed Processing Symposium (IPDPS), pp. 171\u2013180 (2000)."},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"G. Jin, J. Mellor-Crummey, and R. Fowlerothers, Increasing Temporal Locality with Skewing and Recursive Blocking, Proc. SC2001 (2001).","DOI":"10.1145\/582034.582077"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"S. Kamil, K. Datta, S. Williams, et\u00a0al., Implicit and Explicit Optimizations for Stencil Computations, ACM Workshop on Memory System Performance and Correctness, pp. 51\u201360 (October 2005).","DOI":"10.1145\/1178597.1178605"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"S. Kamil, P. Husbands, L. Oliker, et\u00a0al., Impact of Modern Memory Subsystems on Cache Optimizations for Stencil Computations, ACM Workshop on Memory System Performance, pp. 36\u201343 (June 2005).","DOI":"10.1145\/1111583.1111589"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"L. Oliker, R. Biswas, J. Borrill, et\u00a0al., A Performance Evaluation of the Cray X1 for Scientific Applications, Proc. 6th International Meeting on High Performance Computing for Computational Science, pp. 51\u201365 (2004).","DOI":"10.1007\/11403937_5"},{"key":"34_CR35","unstructured":"FFTW speed tests. http:\/\/www.fftw.org."},{"key":"34_CR36","unstructured":"A. Chow, G. Fosum, D, and Brokenshire, A Programming Example: Large FFT on the Cell Broadband Engine, Proceeding of the 2005 Global Signal Processing Expo (GSPx) (October, 2005)."},{"key":"34_CR37","unstructured":"J. Greene and R. Cooper, A Parallel 64k Complex FFT Algorithm for the PIBM\/Sony\/Toshiba Cell Broadband Engine processor, Proceeding of the 2005 Global Signal Processing Expo (GSPx) (October, 2005)."},{"key":"34_CR38","unstructured":"ORNL cray x1 evaluation. http:\/\/www.csm.ornl.gov\/~dunigan\/cray."}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-007-0034-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10766-007-0034-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-007-0034-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-007-0034-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T11:35:50Z","timestamp":1736940950000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10766-007-0034-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,4,3]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2007,6]]}},"alternative-id":["34"],"URL":"https:\/\/doi.org\/10.1007\/s10766-007-0034-5","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,4,3]]},"assertion":[{"value":"3 April 2007","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}