{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:38:31Z","timestamp":1743046711347,"version":"3.40.3"},"publisher-location":"Boston, MA","reference-count":51,"publisher":"Springer US","isbn-type":[{"type":"print","value":"9781441902627"},{"type":"electronic","value":"9781441902634"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-1-4419-0263-4_1","type":"book-chapter","created":{"date-parts":[[2009,9,10]],"date-time":"2009-09-10T15:59:40Z","timestamp":1252598380000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tiled Multicore Processors"],"prefix":"10.1007","author":[{"given":"Michael B.","family":"Taylor","sequence":"first","affiliation":[]},{"given":"Walter","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Jason E.","family":"Miller","sequence":"additional","affiliation":[]},{"given":"David","family":"Wentzlaff","sequence":"additional","affiliation":[]},{"given":"Ian","family":"Bratt","sequence":"additional","affiliation":[]},{"given":"Ben","family":"Greenwald","sequence":"additional","affiliation":[]},{"given":"Henry","family":"Hoffmann","sequence":"additional","affiliation":[]},{"given":"Paul R.","family":"Johnson","sequence":"additional","affiliation":[]},{"given":"Jason S.","family":"Kim","sequence":"additional","affiliation":[]},{"given":"James","family":"Psota","sequence":"additional","affiliation":[]},{"given":"Arvind","family":"Saraf","sequence":"additional","affiliation":[]},{"given":"Nathan","family":"Shnidman","sequence":"additional","affiliation":[]},{"given":"Volker","family":"Strumpen","sequence":"additional","affiliation":[]},{"given":"Matthew I.","family":"Frank","sequence":"additional","affiliation":[]},{"given":"Saman","family":"Amarasinghe","sequence":"additional","affiliation":[]},{"given":"Anant","family":"Agarwal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2009,8,3]]},"reference":[{"key":"1_CR1","unstructured":"A. Agarwal and M. Levy. Going multicore presents challenges and opportunities. Embedded Systems Design, 20(4), April 2007."},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"V. Agarwal, M. S. Hrishikesh, S. W. Keckler, and D. Burger. Clock Rate versus IPC: The End of the Road for Conventional Microarchitectures. In ISCA \u201900: Proceedings of the 27th Annual International Symposium on Computer Architecture, pages 248\u2013259, 2000.","DOI":"10.1145\/339647.339691"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"E. Anderson, Z. Bai, J. Dongarra, A. Greenbaum, A. McKenney, J. Du Croz, S. Hammerling, J. Demmel, C. Bischof, and D. Sorensen. LAPACK: A Portable Linear Algebra Library for High-Performance Computers. In Supercomputing \u201990: Proceedings of the 1990 ACM\/IEEE Conference on Supercomputing, pages 2\u201311, 1990.","DOI":"10.1109\/SUPERC.1990.129995"},{"issue":"12","key":"1_CR4","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1109\/TC.1987.5009502","volume":"36","author":"M. Annaratone","year":"1987","unstructured":"M. Annaratone, E. Arnould, T. Gross, H. T. Kung, M. Lam, O. Menzilicioglu, and J. A. Webb. The Warp Computer: Architecture, Implementation and Performance. IEEE Transactions on Computers, 36(12):1523\u20131538, December 1987.","journal-title":"IEEE Transactions on Computers"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"J. Babb, M. Frank, V. Lee, E. Waingold, R. Barua, M. Taylor, J. Kim, S. Devabhaktuni, and A. Agarwal. The RAW Benchmark Suite: Computation Structures for General Purpose Computing. In Proceedings of the IEEE Workshop on FPGAs for Custom Computing Machines (FCCM), pages 134\u2013143, 1997.","DOI":"10.1109\/FPGA.1997.624613"},{"key":"1_CR6","unstructured":"M. Baron. Low-key Intel 80-core Intro: The tip of the iceberg. Microprocessor Report, April 2007."},{"key":"1_CR7","unstructured":"M. Baron. Tilera\u2019s cores communicate better. Microprocessor Report, November 2007."},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"R. Barua, W. Lee, S. Amarasinghe, and A. Agarwal. Maps: A Compiler-Managed Memory System for Raw Machines. In ISCA \u201999: Proceedings of the 26th Annual International Symposium on Computer Architecture, pages 4\u201315, 1999.","DOI":"10.1145\/307338.300980"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"M. Bohr. Interconnect Scaling \u2013 The Real Limiter to High Performance ULSI. In 1995 IEDM, pages 241\u2013244, 1995.","DOI":"10.1109\/IEDM.1995.499187"},{"issue":"5","key":"1_CR10","first-page":"8","volume":"23","author":"P. Bose","year":"2003","unstructured":"P. Bose, D. H. Albonesi, and D. Marculescu. Power and complexity aware design. IEEE Micro: Guest Editor\u2019s Introduction for Special Issue on Power and Complexity Aware Design, 23(5):8\u201311, Sept\/Oct 2003.","journal-title":"IEEE"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"S. Goldstein, H. Schmit, M. Moe, M. Budiu, S. Cadambi, R. R. Taylor, and R. Laufer. PipeRench: A Coprocessor for Streaming Multimedia Acceleration. In ISCA \u201999: Proceedings of the 26th Annual International Symposium on Computer Architecture, pages 28\u201339, 1999.","DOI":"10.1145\/307338.300982"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"M. Gordon, W. Thies, and S. Amarasinghe. Exploiting coarse-grained task, data, and pipeline parallelism in stream programs. In ASPLOS-XII: Proceedings of the 12th International Conference on Architectural Support for Programming Languages and Operating Systems, pages 75\u201386, October 2006.","DOI":"10.1145\/1168857.1168877"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"M. I. Gordon, W. Thies, M. Karczmarek, J. Lin, A. S. Meli, A. A. Lamb, C. Leger, J. Wong, H. Hoffmann, D. Maze, and S. Amarasinghe. A Stream Compiler for Communication-Exposed Architectures. In ASPLOS-X: Proceedings of the Tenth International Conference on Architectural Support for Programming Languages and Operating Systems, pages 291\u2013303, 2002.","DOI":"10.1145\/635508.605428"},{"key":"1_CR14","unstructured":"T. Gross and D. R. O\u2019Halloron. iWarp, Anatomy of a Parallel Computing System. The MIT Press, Cambridge, MA, 1998."},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"J. R. Hauser and J. Wawrzynek. Garp: A MIPS Processor with Reconfigurable Coprocessor. In Proceedings of the IEEE Workshop on FPGAs for Custom Computing Machines (FCCM), pages 12\u201321, 1997.","DOI":"10.1109\/FPGA.1997.624600"},{"issue":"4","key":"1_CR16","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1109\/5.920580","volume":"89","author":"R. Ho","year":"2001","unstructured":"R. Ho, K. W. Mai, and M. A. Horowitz. The Future of Wires. Proceedings of the IEEE, 89(4):490\u2013504, April 2001.","journal-title":"Proceedings of the IEEE"},{"key":"1_CR17","unstructured":"H. Hoffmann, V. Strumpen, A. Agarwal, and H. Hoffmann. Stream Algorithms and Architecture. Technical Memo MIT-LCS-TM-636, MIT Laboratory for Computer Science, 2003."},{"key":"1_CR18","unstructured":"H. P. Hofstee. Power efficient processor architecture and the Cell processor. In HPCA \u201905: Proceedings of the 11th International Symposium on High Performance Computer Architecture, pages 258\u2013262, 2005."},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"U. Kapasi, W. J. Dally, S. Rixner, J. D. Owens, and B. Khailany. The Imagine Stream Processor. In ICCD \u201902: Proceedings of the 2002 IEEE International Conference on Computer Design, pages 282\u2013288, 2002.","DOI":"10.1109\/ICCD.2002.1106783"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"A. KleinOsowski and D. Lilja. MinneSPEC: A New SPEC Benchmark Workload for Simulation-Based Computer Architecture Research. Computer Architecture Letters, 1, June 2002.","DOI":"10.1109\/L-CA.2002.8"},{"issue":"2","key":"1_CR21","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MM.2005.35","volume":"25","author":"P. Kongetira","year":"2005","unstructured":"P. Kongetira, K. Aingaran, and K. Olukotun. Niagara: A 32-Way Multithreaded Sparc Processor. IEEE Micro, 25(2):21\u201329, 2005.","journal-title":"IEEE Micro"},{"issue":"9","key":"1_CR22","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/2.612252","volume":"30","author":"C. Kozyrakis","year":"1997","unstructured":"C. Kozyrakis and D. Patterson. A New Direction for Computer Architecture Research. IEEE Computer, 30(9):24\u201332, September 1997.","journal-title":"IEEE Computer"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"R. Krashinsky, C. Batten, M. Hampton, S. Gerding, B. Pharris, J. Casper, and K. Asanovic. The Vector-Thread Architecture. In ISCA \u201904: Proceedings of the 31st Annual International Symposium on Computer Architecture, June 2004.","DOI":"10.1145\/1028176.1006736"},{"key":"1_CR24","unstructured":"J. Kubiatowicz. Integrated Shared-Memory and Message-Passing Communication in the Alewife Multiprocessor. PhD thesis, Massachusetts Institute of Technology, 1998."},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"W. Lee, R. Barua, M. Frank, D. Srikrishna, J. Babb, V. Sarkar, and S. Amarasinghe. Space-Time Scheduling of Instruction-Level Parallelism on a Raw Machine. In ASPLOS-VIII: Proceedings of the Eighth International Conference on Architectural Support for Programming Languages and Operating Systems, pages 46\u201354, 1998.","DOI":"10.1145\/291069.291018"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"W. Lee, D. Puppin, S. Swenson, and S. Amarasinghe. Convergent Scheduling. In MICRO-35: Proceedings of the 35th Annual International Symposium on Microarchitecture, pages 111\u2013122, 2002.","DOI":"10.1109\/MICRO.2002.1176243"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"K. Mai, T. Paaske, N. Jayasena, R. Ho, W. J. Dally, and M. Horowitz. Smart Memories: A Modular Reconfigurable Architecture. In ISCA \u201900: Proceedings of the 27th Annual International Symposium on Computer Architecture, pages 161\u2013171, 2000.","DOI":"10.1145\/339647.339673"},{"issue":"9","key":"1_CR28","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/2.612245","volume":"30","author":"D. Matzke","year":"1997","unstructured":"D. Matzke. Will Physical Scalability Sabotage Performance Gains? IEEE Computer, 30(9):37\u201339, September 1997.","journal-title":"IEEE Computer"},{"key":"1_CR29","unstructured":"J. McCalpin. STREAM: Sustainable Memory Bandwidth in High Performance. Computers. http:\/\/www.cs.virginia.edu\/stream."},{"key":"1_CR30","unstructured":"J. E. Miller. Software Instruction Caching. PhD thesis, Massachusetts Institute of Technology, Cambridge, MA, June 2007. http:\/\/hdl.handle.net\/1721.1\/40317."},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"C. A. Moritz, D. Yeung, and A. Agarwal. SimpleFit: A Framework for Analyzing Design Tradeoffs in Raw Architectures. IEEE Transactions on Parallel and Distributed Systems, pages 730\u2013742, July 2001.","DOI":"10.1109\/71.940747"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"S. Naffziger, G. Hammond, S. Naffziger, and G. Hammond. The Implementation of the Next-Generation 64b Itanium Microprocessor. In Proceedings of the IEEE International Solid-State Circuits Conference, pages 344\u2013345, 472, 2002.","DOI":"10.1109\/ISSCC.2002.993073"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"R. Nagarajan, K. Sankaralingam, D. Burger, and S. W. Keckler. A Design Space Evaluation of Grid Processor Architectures. In MICRO-34: Proceedings of the 34th Annual International Symposium on Microarchitecture, pages 40\u201351, 2001.","DOI":"10.1109\/MICRO.2001.991104"},{"key":"1_CR34","unstructured":"M. Narayanan and K. A. Yelick. Generating Permutation Instructions from a High-Level Description. TR UCB-CS-03-1287, UC Berkeley, 2003."},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"S. Palacharla. Complexity-Effective Superscalar Processors. PhD thesis, University of Wisconsin\u2013Madison, 1998.","DOI":"10.1145\/264107.264201"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"J. Sanchez and A. Gonzalez. Modulo Scheduling for a Fully-Distributed Clustered VLIW Architecture. In MICRO-33: Proceedings of the 33rd Annual International Symposium on Microarchitecture, pages 124\u2013133, December 2000.","DOI":"10.1145\/360128.360142"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"K. Sankaralingam, R. Nagarajan, R. McDonald, R. Desikan, S. Drolia, M. S. Govindan, P. Gratz, D. Gulati, H. Hanson, C. Kim, H. Liu, N. Ranganathan, S. Sethumadhavan, S. Sharif, P. Shivakumar, S. W. Keckler, and D. Burger. Distributed microarchitectural protocols in the TRIPS prototype processor. In MICRO-39: Proceedings of the 39th Annual International Symposium on Microarchitecture, pages 480\u2013491, Dec 2006.","DOI":"10.1109\/MICRO.2006.19"},{"issue":"3","key":"1_CR38","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/BF00130111","volume":"10","author":"D. Shoemaker","year":"1996","unstructured":"D. Shoemaker, F. Honore, C. Metcalf, and S. Ward. NuMesh: An Architecture Optimized for Scheduled Communication. Journal of Supercomputing, 10(3):285\u2013302, 1996.","journal-title":"Journal of Supercomputing"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"G. Sohi, S. Breach, and T. Vijaykumar. Multiscalar Processors. In ISCA \u201995: Proceedings of the 22nd Annual International Symposium on Computer Architecture, pages 414\u2013425, 1995.","DOI":"10.1145\/223982.224451"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"J. Suh, E.-G. Kim, S. P. Crago, L. Srinivasan, and M. C. French. A Performance Analysis of PIM, Stream Processing, and Tiled Processing on Memory-Intensive Signal Processing Kernels. In ISCA \u201903: Proceedings of the 30th Annual International Symposium on Computer Architecture, pages 410\u2013419, June 2003.","DOI":"10.1145\/859618.859665"},{"key":"1_CR41","unstructured":"M. B. Taylor. Deionizer: A Tool for Capturing and Embedding I\/O Calls. Technical Report MIT-CSAIL-TR-2004-037, MIT CSAIL\/Laboratory for Computer Science, 2004. http:\/\/cag.csail.mit.edu\/\u223cmtaylor\/deionizer.html."},{"key":"1_CR42","unstructured":"M. B. Taylor. Tiled Processors. PhD thesis, Massachusetts Institute of Technology, Cambridge, MA, Feb 2007."},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"M. B. Taylor, J. Kim, J. Miller, D. Wentzlaff, F. Ghodrat, B. Greenwald, H. Hoffman, J.-W. Lee, P. Johnson, W. Lee, A. Ma, A. Saraf, M. Seneski, N. Shnidman, V. Strumpen, M. Frank, S. Amarasinghe, and A. Agarwal. The Raw Microprocessor: A Computational Fabric for Software Circuits and General-Purpose Programs. IEEE Micro, pages 25\u201335, Mar 2002.","DOI":"10.1109\/MM.2002.997877"},{"key":"1_CR44","unstructured":"M. B. Taylor, W. Lee, S. Amarasinghe, and A. Agarwal. Scalar Operand Networks: On-Chip Interconnect for ILP in Partitioned Architectures. In HPCA \u201903: Proceedings of the 9th International Symposium on High Performance Computer Architecture, pages 341\u2013353, 2003."},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"M. B. Taylor, W. Lee, S. Amarasinghe, and A. Agarwal. Scalar Operand Networks. IEEE Transactions on Parallel and Distributed Systems (Special Issue on On-chip Networks), Feb 2005.","DOI":"10.1109\/TPDS.2005.24"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"M. B. Taylor, W. Lee, J. E. Miller, D. Wentzlaff, I. Bratt, B. Greenwald, H. Hoffmann, P. Johnson, J. Kim, J. Psota, A. Saraf, N. Shnidman, V. Strumpen, M. Frank, S. Amarasinghe, and A. Agarwal. Evaluation of the Raw microprocessor: An exposed-wire-delay architecture for ILP and streams. In ISCA \u201904: Proceedings of the 31st Annual International Symposium on Computer Architecture, pages 2\u201313, June 2004.","DOI":"10.1145\/1028176.1006733"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"W. Thies, M. Karczmarek, and S. Amarasinghe. StreamIt: A Language for Streaming Applications. In 2002 Compiler Construction, pages 179\u2013196, 2002.","DOI":"10.1007\/3-540-45937-5_14"},{"issue":"9","key":"1_CR48","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/2.612254","volume":"30","author":"E. Waingold","year":"1997","unstructured":"E. Waingold, M. Taylor, D. Srikrishna, V. Sarkar, W. Lee, V. Lee, J. Kim, M. Frank, P. Finch, R. Barua, J. Babb, S. Amarasinghe, and A. Agarwal. Baring it All to Software: Raw Machines. IEEE Computer, 30(9):86\u201393, Sep 1997.","journal-title":"IEEE Computer"},{"key":"1_CR49","unstructured":"D. Wentzlaff. Architectural Implications of Bit-level Computation in Communication Applications. Master\u2019s thesis, Massachusetts Institute of Technology, 2002."},{"issue":"5","key":"1_CR50","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/MM.2007.4378780","volume":"27","author":"D. Wentzlaff","year":"2007","unstructured":"D. Wentzlaff, P. Griffin, H. Hoffmann, L. Bao, B. Edwards, C. Ramey, M. Mattina, C.-C. Miao, J. F. Brown, and A. Agarwal. On-Chip Interconnection Architecture of the Tile Processor. IEEE Micro, 27(5):15\u201331, Sept\u2013Oct 2007.","journal-title":"IEEE Micro"},{"issue":"1\u20132","key":"1_CR51","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R. Whaley","year":"2001","unstructured":"R. Whaley, A. Petitet, J. J. Dongarra, and Whaley. Automated Empirical Optimizations of Software and the ATLAS Project. Parallel Computing, 27(1\u20132):3\u201335, 2001.","journal-title":"Parallel Computing"}],"container-title":["Integrated Circuits and Systems","Multicore Processors and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4419-0263-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T02:54:11Z","timestamp":1739328851000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4419-0263-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9781441902627","9781441902634"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-1-4419-0263-4_1","relation":{},"ISSN":["1558-9412"],"issn-type":[{"type":"print","value":"1558-9412"}],"subject":[],"published":{"date-parts":[[2009]]},"assertion":[{"value":"3 August 2009","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}