{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:09:47Z","timestamp":1742947787083,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642152900"},{"type":"electronic","value":"9783642152917"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15291-7_31","type":"book-chapter","created":{"date-parts":[[2010,8,30]],"date-time":"2010-08-30T15:56:39Z","timestamp":1283183799000},"page":"341-352","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A Study of a Software Cache Implementation of the OpenMP Memory Model for Multicore and Manycore Architectures"],"prefix":"10.1007","author":[{"given":"Chen","family":"Chen","sequence":"first","affiliation":[]},{"given":"Joseph B","family":"Manzano","sequence":"additional","affiliation":[]},{"given":"Ge","family":"Gan","sequence":"additional","affiliation":[]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Vivek","family":"Sarkar","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Lamport, L.: How to make a multiprocessor that correctly executes multiprocess programs. IEEE Trans. on Computers\u00a0C-28(9), 690\u2013691 (1979)","DOI":"10.1109\/TC.1979.1675439"},{"key":"31_CR2","unstructured":"IBM Microelectronics: Cell Broadband Engine, http:\/\/www-01.ibm.com\/chips\/techlib\/techlib.nsf\/products\/Cell_Broadband_Engine"},{"key":"31_CR3","unstructured":"Tilera Corporation: Tilera, http:\/\/www.tilera.com\/"},{"key":"31_CR4","unstructured":"Cuvillo, J., Zhu, W., Hu, Z., Gao, G.R.: Fast: A functionally accurate simulation toolset for the Cyclops-64 cellular architecture. In: Proceedings of the Workshop on Modeling, Benchmarking and Simulation, Held in conjunction with the 32nd Annual International Symposium on Computer Architecture, Madison, Wisconsin, pp. 11\u201320 (2005)"},{"key":"31_CR5","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface Version 3.0 (May 2008), http:\/\/www.openmp.org\/mp-documents\/spec30.pdf"},{"issue":"4","key":"31_CR6","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10766-007-0051-4","volume":"35","author":"G. Bronevetsky","year":"2007","unstructured":"Bronevetsky, G., de Supinski, B.R.: Complete formal specification of the OpenMP memory model. Int. J. Parallel Program.\u00a035(4), 335\u2013392 (2007)","journal-title":"Int. J. Parallel Program."},{"key":"31_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-540-69303-1_18","volume-title":"A Practical Programming Model for the Multi-Core Era","author":"J. Manzano","year":"2008","unstructured":"Manzano, J., Hu, Z., Jiang, Y., Gan, G.: Towards an automatic code layout framework. In: Chapman, B., Zheng, W., Gao, G.R., Sato, M., Ayguad\u00e9, E., Wang, D. (eds.) IWOMP 2007. LNCS, vol.\u00a04935, pp. 157\u2013160. Springer, Heidelberg (2008)"},{"key":"31_CR8","unstructured":"Sony Computer Entertainment: PlayStation3, http:\/\/www.us.playstation.com\/ps3\/features"},{"key":"31_CR9","unstructured":"NASA Ames Research Center: NAS Parallel Benchmark, http:\/\/www.nas.nasa.gov\/Resources\/Software\/npb.html"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Chen, C., Manzano, J.B., Gan, G., Gao, G.R., Sarkar, V.: A study of a software cache implementation of the openmp memory model for multicore and manycore architectures. Technical Memo CAPSL\/TM-93 (February 2010)","DOI":"10.1007\/978-3-642-15291-7_31"},{"key":"31_CR11","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1109\/71.242161","volume":"4","author":"S. Adve","year":"1993","unstructured":"Adve, S., Hill, M.D.: A unified formalization of four shared-memory models. IEEE Transactions on Parallel and Distributed Systems\u00a04, 613\u2013624 (1993)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"31_CR12","first-page":"150","volume-title":"ISCA 1999: Proceedings of the 26th annual international symposium on Computer architecture","author":"X. Shen","year":"1999","unstructured":"Shen, X., Arvind, Rudolph, L.: Commit-Reconcile & Fences (CRF): a new memory model for architects and compiler writers. In: ISCA 1999: Proceedings of the 26th annual international symposium on Computer architecture, pp. 150\u2013161. IEEE Computer Society, Washington (1999)"},{"key":"31_CR13","first-page":"161","volume-title":"PPoPP 2007: Proceedings of the 12th ACM SIGPLAN symposium on Principles and practice of parallel programming","author":"V.A. Saraswat","year":"2007","unstructured":"Saraswat, V.A., Jagadeesan, R., Michael, M., von Praun, C.: A theory of memory models. In: PPoPP 2007: Proceedings of the 12th ACM SIGPLAN symposium on Principles and practice of parallel programming, pp. 161\u2013172. ACM, New York (2007)"},{"issue":"2","key":"31_CR14","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/1150019.1136489","volume":"34","author":"A. Arvind","year":"2006","unstructured":"Arvind, A., Maessen, J.W.: Memory model = instruction reordering + store atomicity. SIGARCH Comput. Archit. News\u00a034(2), 29\u201340 (2006)","journal-title":"SIGARCH Comput. Archit. News"},{"key":"31_CR15","first-page":"378","volume-title":"POPL 2005: Proceedings of the 32nd ACM SIGPLAN-SIGACT symposium on Principles of programming languages","author":"J. Manson","year":"2005","unstructured":"Manson, J., Pugh, W., Adve, S.V.: The Java memory model. In: POPL 2005: Proceedings of the 32nd ACM SIGPLAN-SIGACT symposium on Principles of programming languages, pp. 378\u2013391. ACM, New York (2005)"},{"key":"31_CR16","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/1375581.1375591","volume-title":"PLDI 2008: Proceedings of the 2008 ACM SIGPLAN conference on Programming language design and implementation","author":"H.J. Boehm","year":"2008","unstructured":"Boehm, H.J., Adve, S.V.: Foundations of the C++ concurrency memory model. In: PLDI 2008: Proceedings of the 2008 ACM SIGPLAN conference on Programming language design and implementation, pp. 68\u201378. ACM, New York (2008)"},{"key":"31_CR17","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1145\/285930.285991","volume-title":"ISCA 1998: 25 years of the international symposia on Computer architecture (selected papers)","author":"M. Dubois","year":"1998","unstructured":"Dubois, M., Scheurich, C., Briggs, F.: Memory access buffering in multiprocessors. In: ISCA 1998: 25 years of the international symposia on Computer architecture (selected papers), pp. 320\u2013328. ACM, New York (1998)"},{"key":"31_CR18","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface (2005), http:\/\/www.openmp.org\/mp-documents\/spec25.pdf"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Gottlieb, A., Grishman, R., Kruskal, C.P., McAuliffe, K.P., Rudolph, L., Snir, M.: The NYU ultracomputer\u2014designing a MIMD, shared-memory parallel machine. In: ISCA 1998: 25 years of the international symposia on Computer architecture (selected papers), pp. 239\u2013254. ACM, New York (1998)","DOI":"10.1145\/285930.285983"},{"key":"31_CR20","first-page":"69","volume-title":"CEDAR\u2014a large scale multiprocessor","author":"D. Gajski","year":"1986","unstructured":"Gajski, D., Kuck, D., Lawrie, D., Sameh, A.: CEDAR\u2014a large scale multiprocessor, pp. 69\u201374. IEEE Computer Society Press, Los Alamitos (1986)"},{"key":"31_CR21","unstructured":"Pfister, G., Brantley, W., George, D., Harvey, S., Kleinfelder, W., McAuliffe, K., Melton, E., Norton, V., Weiss, J.: The research parallel processor prototype (RP3): Introduction and architecture. In: ICPP 1985: Proceedings of the 1985 International Conference on Parallel Processing, pp. 764\u2013771 (1985)"},{"key":"31_CR22","unstructured":"Cytron, R., Karlovsky, S., McAuliffe, K.P.: Automatic management of programmable caches. In: ICPP 1988: Proceedings of the 1988 International Conference on Parallel Processing, pp. 229\u2013238 (August 1988)"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Eichenberger, A.E., O\u2019Brien, K., O\u2019Brien, K., Wu, P., Chen, T., Oden, P.H., Prener, D.A., Shepherd, J.C., So, B., Sura, Z., Wang, A., Zhang, T., Zhao, P., Gschwind, M.: Optimizing compiler for the CELL processor. In: PACT 2005: Proceedings of the 14th International Conference on Parallel Architectures and Compilation Techniques, pp. 161\u2013172. IEEE Computer Society, Los Alamitos (2005)","DOI":"10.1109\/PACT.2005.33"},{"issue":"1","key":"31_CR24","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1147\/sj.451.0059","volume":"45","author":"A.E. Eichenberger","year":"2006","unstructured":"Eichenberger, A.E., O\u2019Brien, J.K., O\u2019Brien, K.M., Wu, P., Chen, T., Oden, P.H., Prener, D.A., Shepherd, J.C., So, B., Sura, Z., Wang, A., Zhang, T., Zhao, P., Gschwind, M.K., Archambault, R., Gao, Y., Koo, R.: Using advanced compiler technology to exploit the performance of the Cell Broadband EngineTM architecture. IBM Syst. J.\u00a045(1), 59\u201384 (2006)","journal-title":"IBM Syst. J."},{"key":"31_CR25","doi-asserted-by":"crossref","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., Tallada, M.G.: 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":"31_CR26","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1145\/1454115.1454157","volume-title":"PACT 2008: Proceedings of the 17th international conference on Parallel architectures and compilation techniques","author":"J. Lee","year":"2008","unstructured":"Lee, J., Seo, S., Kim, C., Kim, J., Chun, P., Sura, Z., Kim, J., Han, S.: COMIC: a coherent shared memory interface for Cell BE. In: PACT 2008: Proceedings of the 17th international conference on Parallel architectures and compilation techniques, pp. 303\u2013314. ACM, New York (2008)"},{"key":"31_CR27","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1145\/1375527.1375570","volume-title":"ICS 2008: Proceedings of the 22nd annual international conference on Supercomputing","author":"T. Chen","year":"2008","unstructured":"Chen, T., Lin, H., Zhang, T.: Orchestrating data transfer for the Cell\/B.E. processor. In: ICS 2008: Proceedings of the 22nd annual international conference on Supercomputing, pp. 289\u2013298. ACM, New York (2008)"},{"key":"31_CR28","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1145\/1454115.1454156","volume-title":"PACT 2008: Proceedings of the 17th international conference on Parallel architectures and compilation techniques","author":"M. Gonz\u00e0lez","year":"2008","unstructured":"Gonz\u00e0lez, M., Vujic, N., Martorell, X., Ayguad\u00e9, E., Eichenberger, A.E., Chen, T., Sura, Z., Zhang, T., O\u2019Brien, K., O\u2019Brien, K.: Hybrid access-specific software cache techniques for the Cell BE architecture. In: PACT 2008: Proceedings of the 17th international conference on Parallel architectures and compilation techniques, pp. 292\u2013302. ACM, New York (2008)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2010 - Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15291-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,7]],"date-time":"2021-11-07T17:01:48Z","timestamp":1636304508000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15291-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642152900","9783642152917"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15291-7_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}