{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:47:42Z","timestamp":1725558462601},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642133732"},{"type":"electronic","value":"9783642133749"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-13374-9_6","type":"book-chapter","created":{"date-parts":[[2010,6,10]],"date-time":"2010-06-10T11:15:59Z","timestamp":1276168559000},"page":"80-94","source":"Crossref","is-referenced-by-count":1,"title":["TL-DAE: Thread-Level Decoupled Access\/Execution for OpenMP on the Cyclops-64 Many-Core Processor"],"prefix":"10.1007","author":[{"given":"Ge","family":"Gan","sequence":"first","affiliation":[]},{"given":"Joseph","family":"Manzano","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"6_CR1","unstructured":"del Cuvillo, J., Zhu, W., Hu, Z., Gao, G.R.: Fast: A functionally accurate simulation toolset for the cyclops-64 cellular architecture. In: Workshop on Modeling, Benchmarking and Simulation (MoBS 2005) of ISCA 2005, Madison, Wisconsin (June 2005)"},{"key":"6_CR2","unstructured":"del Cuvillo, J., Zhu, W., Hu, Z., Gao, G.R.: Towards a software infrastructure for cyclops-64 cellular architecture. In: HPCS 2006, Labroda, Canada (June 2005)"},{"key":"6_CR3","unstructured":"Zhang, Y., Jeong, T., Chen, F., Wu, H., Nitzsche, R., Gao, G.R.: A study of the on-chip interconnection network for the ibm cyclops64 multi-core architecture. In: IPDPS 2006: Proceedings of the 20th International Parallel and Distributed Processing Symposium, Rhodes Island, Greece, April 25-29 (2006)"},{"key":"6_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/11823285_14","volume-title":"Euro-Par 2006 Parallel Processing","author":"Z. Hu","year":"2006","unstructured":"Hu, Z., del Cuvillo, J., Zhu, W., Gao, G.R.: Optimization of dense matrix multiplication on ibm cyclops-64: Challenges and experiences. In: Nagel, W.E., Walter, W.V., Lehner, W. (eds.) Euro-Par 2006. LNCS, vol.\u00a04128, pp. 134\u2013144. Springer, Heidelberg (2006)"},{"key":"6_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/978-3-540-72521-3_23","volume-title":"Languages and Compilers for Parallel Computing","author":"T. Chen","year":"2007","unstructured":"Chen, T., Sura, Z., O\u2019Brien, K.M., O\u2019Brien, J.K.: Optimizing the use of static buffers for dma on a cell chip. In: Alm\u00e1si, G.S., Ca\u015fcaval, C., Wu, P. (eds.) LCPC 2006. LNCS, vol.\u00a04382, pp. 314\u2013329. Springer, Heidelberg (2007)"},{"issue":"3","key":"6_CR6","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MM.2006.49","volume":"26","author":"M. Kistler","year":"2006","unstructured":"Kistler, M., Perrone, M., Petrini, F.: Cell multiprocessor communication network: Built for speed. IEEE Micro\u00a026(3), 10\u201323 (2006)","journal-title":"IEEE Micro"},{"key":"6_CR7","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1145\/1375527.1375570","volume-title":"Proceedings of the 22nd Annual International Conference on Supercomputing, ICS 2008","author":"T. Chen","year":"2008","unstructured":"Chen, T., Lin, H., Zhang, T.: Orchestrating data transfer for the cell\/B.E. processor. In: Proceedings of the 22nd Annual International Conference on Supercomputing, ICS 2008, Island of Kos, Greece, June 7-12, pp. 289\u2013298. ACM, New York (2008)"},{"key":"6_CR8","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1145\/1542275.1542286","volume-title":"Proceedings of the 23rd international conference on Supercomputing, ICS 2009","author":"T. Liu","year":"2009","unstructured":"Liu, T., Lin, H., Chen, T., O\u2019Brien, K., Shao, L.: DBDB: optimizing DMATransfer for the cell be architecture. In: Proceedings of the 23rd international conference on Supercomputing, ICS 2009, Yorktown Heights, NY, USA, June 8-12, pp. 36\u201345. ACM, New York (2009)"},{"issue":"4","key":"6_CR9","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1145\/357401.357403","volume":"2","author":"J.E. Smith","year":"1984","unstructured":"Smith, J.E.: Decoupled access\/execute computer architectures. ACM Trans. Comput. Syst.\u00a02(4), 289\u2013308 (1984)","journal-title":"ACM Trans. Comput. Syst."},{"issue":"8","key":"6_CR10","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1109\/TC.1986.1676820","volume":"35","author":"J.E. Smith","year":"1986","unstructured":"Smith, J.E., Weiss, S., Pang, N.Y.: A simulation study of decoupled architecture computers. IEEE Trans. Comput.\u00a035(8), 692\u2013702 (1986)","journal-title":"IEEE Trans. Comput."},{"key":"6_CR11","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/SFCS.1994.365680","volume-title":"Proceedings of the 35th Annual Symposium on Foundations of Computer Science","author":"R.D. Blumofe","year":"1994","unstructured":"Blumofe, R.D., Leiserson, C.E.: Scheduling multithreaded computations by work stealing. In: Proceedings of the 35th Annual Symposium on Foundations of Computer Science, Santa Fe, New Mexico, November 20\u201322, pp. 356\u2013368. IEEE, Los Alamitos (1994)"},{"key":"6_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1007\/978-3-642-03869-3_78","volume-title":"Euro-Par 2009 Parallel Processing","author":"G. Gan","year":"2009","unstructured":"Gan, G., Wang, X., Manzano, J., Gao, G.R.: Tile percolation: an openmp tile aware parallelization technique for the cyclops-64 multicore processor. In: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol.\u00a05704, pp. 839\u2013850. Springer, Heidelberg (2009)"},{"key":"6_CR13","unstructured":"The NANOS Group at Universitat Polit\u00e9cnica de Catalunya: Barcelona OpenMP Task Suite (May 2009), http:\/\/nanos.ac.upc.edu\/content\/barcelona-openmp-task-suite"},{"issue":"3","key":"6_CR14","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TPDS.2008.105","volume":"20","author":"E. Ayguad\u00e9","year":"2009","unstructured":"Ayguad\u00e9, E., Copty, N., Duran, A., Hoeflinger, J., Lin, Y., Massaioli, F., Teruel, X., Unnikrishnan, P., Zhang, G.: The design of openmp tasks. IEEE Trans. Parallel Distrib. Syst.\u00a020(3), 404\u2013418 (2009)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"6_CR15","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface Version 3.0 (May 2008), http:\/\/www.openmp.org\/mp-documents\/spec30.pdf"},{"issue":"2","key":"6_CR16","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1109\/TCAD.2003.822123","volume":"23","author":"M.T. Kandemir","year":"2004","unstructured":"Kandemir, M.T., Ramanujam, J., Irwin, M.J., Vijaykrishnan, N., Kadayif, I., Parikh, A.: A compiler-based approach for dynamically managing scratch-pad memories in embedded systems. IEEE Trans. on CAD of Integrated Circuits and Systems\u00a023(2), 243\u2013260 (2004)","journal-title":"IEEE Trans. on CAD of Integrated Circuits and Systems"},{"key":"6_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1345206.1345210","volume-title":"PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming","author":"M.M. Baskaran","year":"2008","unstructured":"Baskaran, M.M., Bondhugula, U., Krishnamoorthy, S., Ramanujam, J., Rountev, A., Sadayappan, P.: Automatic data movement and computation mapping for multi-level parallel architectures with explicitly managed memories. In: PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming, pp. 1\u201310. ACM, New York (2008)"},{"issue":"4","key":"6_CR18","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1109\/71.97902","volume":"2","author":"M.E. Wolf","year":"1991","unstructured":"Wolf, M.E., Lam, M.S.: A loop transformation theory and an algorithm to maximize parallelism. IEEE Transactions on Parallel and Distributed Systems\u00a02(4), 452\u2013471 (1991)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"#cr-split#-6_CR19.1","doi-asserted-by":"crossref","unstructured":"Anderson, J.M., Amarasinghe, S.P., Lam, M.S.: Data and computation transformations for multiprocessors. In: Proceedings of the Fifth ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming, Santa Barbara, California, July 19???21, pp. 166???178 (1995);","DOI":"10.1145\/209936.209954"},{"key":"#cr-split#-6_CR19.2","doi-asserted-by":"crossref","unstructured":"Anderson, J.M., Amarasinghe, S.P., Lam, M.S.: Data and computation transformations for multiprocessors. In: Proceedings of the Fifth ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming, Santa Barbara, California, July 19\u201321, pp. 166\u2013178 (1995); SIGPLAN Notices 30(8) (August 1995)","DOI":"10.1145\/209937.209954"},{"key":"6_CR20","volume-title":"Advanced compiler design and implementation","author":"S.S. Muchnick","year":"1997","unstructured":"Muchnick, S.S.: Advanced compiler design and implementation. Morgan Kaufmann Publishers Inc., San Francisco (1997)"},{"key":"6_CR21","first-page":"285","volume-title":"FOCS 1999: Proceedings of the 40th Annual Symposium on Foundations of Computer Science","author":"M. Frigo","year":"1999","unstructured":"Frigo, M., Leiserson, C.E., Prokop, H., Ramachandran, S.: Cache-oblivious algorithms. In: FOCS 1999: Proceedings of the 40th Annual Symposium on Foundations of Computer Science, Washington, DC, USA, p. 285. IEEE Computer Society, Los Alamitos (1999)"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-13374-9_6.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T03:05:31Z","timestamp":1606187131000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-13374-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642133732","9783642133749"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-13374-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}