{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:08:08Z","timestamp":1726052888966},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642115141"},{"type":"electronic","value":"9783642115158"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-11515-8_24","type":"book-chapter","created":{"date-parts":[[2010,1,20]],"date-time":"2010-01-20T14:58:47Z","timestamp":1263999527000},"page":"322-336","source":"Crossref","is-referenced-by-count":6,"title":["Analysis of Task Offloading for Accelerators"],"prefix":"10.1007","author":[{"given":"Roger","family":"Ferrer","sequence":"first","affiliation":[]},{"given":"Vicen\u00e7","family":"Beltran","sequence":"additional","affiliation":[]},{"given":"Marc","family":"Gonz\u00e0lez","sequence":"additional","affiliation":[]},{"given":"Xavier","family":"Martorell","sequence":"additional","affiliation":[]},{"given":"Eduard","family":"Ayguad\u00e9","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"24_CR1","unstructured":"Chen, T., Raghavan, R., Dale, J., Iwata, E.: Cell Broadband Engine Architecture and its first implementation. IBM Developer Works (November 2005)"},{"key":"24_CR2","unstructured":"NVIDIA corporation: NVIDIA CUDA Compute Unified Device Architecture Version 2.0 (2008)"},{"key":"24_CR3","unstructured":"NVIDIA corporation: NVIDIA Tesla GPU Computing Technical Brief (2008)"},{"key":"24_CR4","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface. Version 3.0 (May 2008), \n                    \n                      http:\/\/www.openmp.org"},{"issue":"3","key":"24_CR5","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 Transactions on Parallel and Distributed Systems\u00a020(3), 404\u2013418 (2009)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Ayguad\u00e9, E., Badia, R.M., Cabrera, D., Duran, A., Gonzalez, M., Igual, F., Jimenez, D., Labarta, J., Martorell, X., Mayo, R., Perez, J.M., Quintana-Orti, E.: A Proposal to Extend the OpenMP Tasking Model for Heterogeneous Architectures. In: Fifth International Workshop on OpenMP, IWOMP (2009)","DOI":"10.1007\/978-3-642-02303-3_13"},{"key":"24_CR7","unstructured":"Jin, H., Frumkin, M., Yan, J.: The OpenMP Implementation of NAS Parallel Benchmarks and Its Performance. Technical Report NAS-99-011, NASA Ames Research Center (1999)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Kusano, K., Satoh, S., Sato, M.: Performance evaluation of the Omni OpenMP compiler. In: Third International Symposium on High Performance Computing, pp. 403\u2013414 (2000)","DOI":"10.1007\/3-540-39999-2_39"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Ferrer, R., Gonzalez, M., Silla, F., Martorell, X., Ayguad\u00e9, E.: Evaluation of Memory Performance on the Cell BE with the SARC Programming Model. In: Proceedings of the 9th Workshop on Memory Performance: Dealing with Applications, systems, and architecture (MEDEA 2008) (October 2008)","DOI":"10.1145\/1509084.1509095"},{"key":"24_CR10","unstructured":"Intel Corporation: Intel Corporation\u2019s Multicore Architecture Briefing (March 2008), \n                    \n                      http:\/\/www.intel.com\/pressroom\/archive\/releases\/20080317fact.htm"},{"key":"24_CR11","unstructured":"AMD Corporation: AMD 2007 Technology Analyst Day, \n                    \n                      http:\/\/www2.amd.com\/us-en\/assets\/content_type\/DownloadableAssets\/FinancialA-DayNewsSummary121307FINAL.pdf"},{"key":"24_CR12","unstructured":"Stanford University: BrookGPU, \n                    \n                      http:\/\/graphics.stanford.edu\/projects\/brookgpu\/"},{"key":"24_CR13","unstructured":"Stanford University: Brook Language, \n                    \n                      http:\/\/merrimac.stanford.edu\/brook\/"},{"key":"24_CR14","unstructured":"Group, K.O.W.: The OpenCL Specification (February 2009), \n                    \n                      http:\/\/www.khronos.org\/registry\/cl\/"},{"key":"24_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-69303-1_1","volume-title":"A Practical Programming Model for the Multi-Core Era","author":"E. Ayguad\u00e9","year":"2008","unstructured":"Ayguad\u00e9, E., Copty, N., Duran, A., Hoeflinger, J., Lin, Y., Massaioli, F., Su, E., Unnikrishnan, P., Zhang, G.: A Proposal for Task Parallelism in OpenMP. In: Chapman, B., Zheng, W., Gao, G.R., Sato, M., Ayguad\u00e9, E., Wang, D. (eds.) IWOMP 2007. LNCS, vol.\u00a04935, pp. 1\u201312. Springer, Heidelberg (2008)"},{"issue":"5","key":"24_CR16","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1147\/rd.515.0593","volume":"51","author":"J.M. Perez","year":"2007","unstructured":"Perez, J.M., Bellens, P., Badia, R.M., Labarta, J.: CellSs: Making it easier to program the Cell Broadband Engine processor. IBM Journal of Research and Development\u00a051(5), 593\u2013604 (2007)","journal-title":"IBM Journal of Research and Development"},{"key":"24_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-540-79561-2_10","volume-title":"OpenMP in a New Era of Parallelism","author":"A. Duran","year":"2008","unstructured":"Duran, A., P\u00e9rez, J.M., Ayguad\u00e9, E., Badia, R.M., Labarta, J.: Extending the OpenMP Tasking Model to Allow Dependent Tasks. In: Eigenmann, R., de Supinski, B.R. (eds.) IWOMP 2008. LNCS, vol.\u00a05004, pp. 111\u2013122. Springer, Heidelberg (2008)"},{"key":"24_CR18","unstructured":"Dolbeau, R., Bihan, S., Bodin, F.: HMPP: A Hybrid Multi-core Parallel Programming Environment. In: Workshop on General Processing Using GPUs (2006)"},{"key":"24_CR19","unstructured":"IBM Corporation: XL C\/C++ for Multicore Acceleration (January 2009), \n                    \n                      http:\/\/www-01.ibm.com\/software\/awdtools\/xlcpp\/multicore\/"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"O\u2019Brien, K., O\u2019Brien, K., Sura, Z., Chen, T., Zhang, T.: Supporting OpenMP on Cell. International Journal of Parallel Programming (2008)","DOI":"10.1007\/s10766-008-0072-7"},{"key":"24_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-540-85261-2_9","volume-title":"Languages and Compilers for Parallel Computing","author":"J. Balart","year":"2008","unstructured":"Balart, J., Gonzalez, M., Martorell, X., Ayguad\u00e9, E., Sura, Z., Chen, T., Zhang, T., O\u2019Brien, K., O\u2019Brien, K.: A Novel Asynchronous Software Cache Implementation for the CELL\/BE Processor. In: Adve, V., Garzar\u00e1n, M.J., Petersen, P. (eds.) LCPC 2007. LNCS, vol.\u00a05234, pp. 125\u2013140. Springer, Heidelberg (2008)"},{"key":"24_CR22","unstructured":"Group, T.P.: PGI Fortran & C Accelerator Programming Model (December 2008), \n                    \n                      http:\/\/www.pgroup.com\/lit\/whitepapers\/pgi_whitepaper_accpre.pdf"},{"key":"24_CR23","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1145\/1366230.1366236","volume-title":"CF 2008: Proceedings of the 2008 conference on Computing frontiers","author":"M.M. Rafique","year":"2008","unstructured":"Rafique, M.M., Butt, A.R., Nikolopoulos, D.S.: Dma-based prefetching for i\/o-intensive workloads on the cell architecture. In: CF 2008: Proceedings of the 2008 conference on Computing frontiers, pp. 23\u201332. ACM, New York (2008)"},{"key":"24_CR24","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1145\/1356058.1356079","volume-title":"CGO 2008: Proceedings of the sixth annual IEEE\/ACM international symposium on Code generation and optimization","author":"T. Chen","year":"2008","unstructured":"Chen, T., Zhang, T., Sura, Z., Gonzalez, M.: Prefetching irregular references for software cache on cell. In: CGO 2008: Proceedings of the sixth annual IEEE\/ACM international symposium on Code generation and optimization, pp. 155\u2013164. ACM, New York (2008)"},{"key":"24_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1463768.1463771","volume-title":"IFMT 2008: Proceedings of the 1st international forum on Next-generation multicore\/manycore technologies","author":"M.F. Ahmed","year":"2008","unstructured":"Ahmed, M.F., Ammar, R.A., Rajasekaran, S.: SPENK: Adding Another Level of Parallelism on the Cell Broadband Engine. In: IFMT 2008: Proceedings of the 1st international forum on Next-generation multicore\/manycore technologies, pp. 1\u201310. ACM, New York (2008)"},{"key":"24_CR26","volume-title":"HiPC 2009: Proceedings of the 16th Annual IEEE International Conference on High Performance Computing","author":"V. Beltran","year":"2009","unstructured":"Beltran, V., Carrera, D., Torres, J., Ayguad\u00e9, E.: CellMT: A Cooperative Multithreading Library for the Cell\/B.E. In: HiPC 2009: Proceedings of the 16th Annual IEEE International Conference on High Performance Computing. IEEE Computer Society, Los Alamitos (2009)"},{"key":"24_CR27","unstructured":"Weltzer, J., Silha, E., May, C., Frey, B., Furukawa, J., Frazier, G.: PowerPC Architecture Book V. 2.02. IBM Corporation (2005)"},{"key":"24_CR28","unstructured":"McCalpin, J.D.: STREAM: Sustainable Memory Bandwidth in High Performance Computers (2008), \n                    \n                      http:\/\/www.cs.virginia.edu\/stream"},{"key":"24_CR29","unstructured":"Corder, S., Sheumaker, K.: STREAM Benchmarking: Intel Xeon 5500 Nehalem vs AMD Opteron 2400 Istanbul (2009), \n                    \n                      http:\/\/www.advancedclustering.com\/company-blog\/stream-benchmarking.html"},{"key":"24_CR30","unstructured":"Corporation, I.: Intel Xeon Processor 5000 Sequence (2009), \n                    \n                      http:\/\/www.intel.com\/p\/en_US\/products\/server\/processor\/xeon5000"},{"key":"24_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/978-3-540-72521-3_24","volume-title":"Languages and Compilers for Parallel Computing","author":"J. Balart","year":"2007","unstructured":"Balart, J., Gonzalez, M., Martorell, X., Ayguad\u00e9, E., Labarta, J.: Runtime Address Space Computation for SDSM Systems. In: Alm\u00e1si, G.S., Ca\u015fcaval, C., Wu, P. (eds.) LCPC 2006. LNCS, vol.\u00a04382, pp. 330\u2013344. Springer, Heidelberg (2007)"},{"key":"24_CR32","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., 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)"}],"container-title":["Lecture Notes in Computer Science","High Performance Embedded Architectures and Compilers"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-11515-8_24.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T11:53:19Z","timestamp":1619783599000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-11515-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642115141","9783642115158"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-11515-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}