{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T23:18:37Z","timestamp":1672615117830},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,7,30]],"date-time":"2014-07-30T00:00:00Z","timestamp":1406678400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1007\/s11227-014-1264-0","type":"journal-article","created":{"date-parts":[[2014,7,29]],"date-time":"2014-07-29T01:26:29Z","timestamp":1406597189000},"page":"488-509","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Exploiting controlled-grained parallelism in message-driven stream programs"],"prefix":"10.1007","volume":"70","author":[{"given":"Yan","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shahnawaz","family":"Talpur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,7,30]]},"reference":[{"key":"1264_CR1","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1109\/TPDS.2011.308","volume":"23","author":"J Diaz","year":"2012","unstructured":"Diaz J, Munoz-Caro C, Nino A (2012) A survey of parallel programming models and tools in the multi and many-core era. IEEE Trans Parallel Distrib Syst 23:1369\u20131386. doi: 10.1109\/TPDS.2011.308","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1264_CR2","doi-asserted-by":"crossref","unstructured":"Christadler I, Erbacci G, Simpson AD (2012) Performance and productivity of new programming languages. In: Facing the multicore-challenge II. Springer, Berlin, pp 24\u201335. doi: 10.1007\/978-3-642-30397-5_3","DOI":"10.1007\/978-3-642-30397-5_3"},{"key":"1264_CR3","unstructured":"Mei, C (2012) Message-driven parallel language runtime design and optimizations for multicore-based massively parallel machines. In: Dissertations and theses-computer science. http:\/\/hdl.handle.net\/2142\/34238"},{"key":"1264_CR4","doi-asserted-by":"crossref","unstructured":"Reinders, J (2012) Only the first steps of the parallel evolution have been taken thus far. In: Facing the multicore-challenge II. Springer, Berlin, pp 1\u20139. doi: 10.1007\/978-3-642-30397-5_1","DOI":"10.1007\/978-3-642-30397-5_1"},{"key":"1264_CR5","doi-asserted-by":"crossref","unstructured":"Erez M, Ahn JH, Gummaraju J, Rosenblum M, Dally WJ (2007) Executing irregular scientific applications on stream architectures. In: ACM proceedings of the 21st annual international conference on supercomputing, pp 93\u2013104","DOI":"10.1145\/1274971.1274987"},{"key":"1264_CR6","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1145\/1015706.1015800","volume":"23","author":"I Buck","year":"2004","unstructured":"Buck I, Foley T, Horn D, Sugerman J, Fatahalian K, Houston M, Hanrahan P (2004) Brook for GPUs: stream computing on graphics hardware. ACM Trans Graphics (TOG) 23:777\u2013786","journal-title":"ACM Trans Graphics (TOG)"},{"key":"1264_CR7","doi-asserted-by":"crossref","unstructured":"Chen MK, Li XF, Lian R, Lin JH, Liu L, Liu T, Ju R (2005) Shangri-La: achieving high performance from compiled network applications while enabling ease of programming. In: ACM SIGPLAN Notices, pp 224\u2013236","DOI":"10.1145\/1064978.1065038"},{"key":"1264_CR8","unstructured":"Nvidia CUDA (2007) Compute unified device architecture programming guide"},{"key":"1264_CR9","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/3-540-45937-5_14","volume-title":"Compiler construction","author":"W Thies","year":"2002","unstructured":"Thies W, Karczmarek M, Amarasinghe S (2002) StreamIt: a language for streaming applications. Compiler construction. Springer, Berlin, pp 179\u2013196"},{"key":"1264_CR10","doi-asserted-by":"crossref","unstructured":"Edwards SA, Vasudevan N, Tardieu O (2008) Programming shared memory multiprocessors with deterministic message-passing concurrency: compiling SHIM to Pthreads. In: Design, automation and test in Europe, 2008. DATE \u201908, pp 1498\u20131503. doi: 10.1109\/DATE.2008.4484886","DOI":"10.1109\/DATE.2008.4484886"},{"key":"1264_CR11","doi-asserted-by":"crossref","unstructured":"Zhuravlev S, Saez JC, Blagodurov S, Fedorova A, Prieto M (2012) Survey of scheduling techniques for addressing shared resources in multicore processors. ACM Comput Surv 45:4:1\u20134:28. doi: 10.1145\/2379776.2379780","DOI":"10.1145\/2379776.2379780"},{"key":"1264_CR12","doi-asserted-by":"crossref","unstructured":"Tang L (2013) The study on resource competition in message-driven system. In: 2013 fifth international conference on computational and information sciences (ICCIS), pp 1607\u20131610. doi: 10.1109\/ICCIS.2013.421","DOI":"10.1109\/ICCIS.2013.421"},{"key":"1264_CR13","doi-asserted-by":"crossref","unstructured":"Dooley I, Chao M, Lifflander J, Kale LV (2010) A study of memory-aware scheduling in message driven parallel programs. In: 2010 international conference on high performance computing (HiPC), pp 1\u201310. doi: 10.1109\/HIPC.2010.5713177","DOI":"10.1109\/HIPC.2010.5713177"},{"key":"1264_CR14","doi-asserted-by":"crossref","unstructured":"Kale LV, Krishnan S (1993) CHARM++: A portable concurrent object oriented system based on C++. In: Proceedings of the eighth annual conference on object-oriented programming systems, languages, and applications, New York, pp 91\u2013108. doi: 10.1145\/165854.165874","DOI":"10.1145\/165854.165874"},{"key":"1264_CR15","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1016\/j.jpdc.2004.03.006","volume":"64","author":"A Grsoy","year":"2004","unstructured":"Grsoy A, Laxmikant VK (2004) Performance and modularity benefits of message-driven execution. J Parallel Distrib Comput 64:461\u2013480. doi: 10.1016\/j.jpdc.2004.03.006","journal-title":"J Parallel Distrib Comput"},{"key":"1264_CR16","doi-asserted-by":"crossref","unstructured":"Willcock JJ, Hoefler T, Edmonds NG, Lumsdaine A (2010) AM++: a generalized active message framework. In: Proceedings of the 19th international conference on parallel architectures and compilation techniques, Vienna, Austria, pp 401\u2013410. doi: 10.1145\/1854273.1854323","DOI":"10.1145\/1854273.1854323"},{"key":"1264_CR17","doi-asserted-by":"crossref","unstructured":"Guha S, Gunopulos D, Koudas N (2003) Correlating synchronous and asynchronous data streams. In: Proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining, pp 529\u2013534","DOI":"10.1145\/956750.956814"},{"issue":"1","key":"1264_CR18","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TC.1987.5009446","volume":"100","author":"E Lee","year":"1987","unstructured":"Lee E, Messerschmitt DG (1987) Static scheduling of synchronous data flow programs for digital signal processing. IEEE Trans Comput 100(1):24\u201335","journal-title":"IEEE Trans Comput"},{"issue":"8","key":"1264_CR19","doi-asserted-by":"crossref","first-page":"2064","DOI":"10.1109\/TSP.2002.800830","volume":"50","author":"PK Murthy","year":"2002","unstructured":"Murthy PK, Lee EA (2002) Multidimensional synchronous data flow. IEEE Trans Signal Process 50(8):2064\u20132079","journal-title":"IEEE Trans Signal Process"},{"key":"1264_CR20","doi-asserted-by":"crossref","unstructured":"West EA, Grimshaw AS (1995) Braid: integrating task and data parallelism. In: Proceedings of fifth symposium on the frontiers of massively parallel computation, pp 211\u2013219. doi: 10.1109\/FMPC.1995.380446","DOI":"10.1109\/FMPC.1995.380446"},{"key":"1264_CR21","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TC.1987.5009446","volume":"100","author":"EA Lee","year":"1987","unstructured":"Lee EA, Messerschmitt DG (1987) Static scheduling of synchronous data flow programs for digital signal processing. IEEE Trans Comput 100:24\u201335","journal-title":"IEEE Trans Comput"},{"key":"1264_CR22","doi-asserted-by":"crossref","unstructured":"Thies W, Karczmarek M, Amarasinghe S (2002) StreamIt: A language for streaming applications. In: Springer compiler construction, pp 179\u2013196","DOI":"10.1007\/3-540-45937-5_14"},{"key":"1264_CR23","doi-asserted-by":"crossref","first-page":"1259","DOI":"10.1109\/71.640018","volume":"8","author":"L-F Chao","year":"1997","unstructured":"Chao L-F, Sha EH-M (1997) Scheduling data-flow graphs via retiming and unfolding. IEEE Trans Parallel Distrib Syst 8:1259\u20131267","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1264_CR24","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1145\/1168919.1168877","volume":"34","author":"I Gordon Michael","year":"2006","unstructured":"Gordon Michael I, Thies W, Amarasinghe S (2006) Exploiting coarse-grained task, data, and pipeline parallelism in stream programs. ACM SIGARCH 34:151\u2013162. doi: 10.1145\/1168919.1168877","journal-title":"ACM SIGARCH"},{"key":"1264_CR25","doi-asserted-by":"crossref","first-page":"1305","DOI":"10.1109\/5.97300","volume":"79","author":"N Halbwachs","year":"1991","unstructured":"Halbwachs N, Caspi P, Raymond P, Pilaud D (1991) The synchronous data flow programming language LUSTRE. Proc IEEE 79:1305\u20131320","journal-title":"Proc IEEE"},{"key":"1264_CR26","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1145\/1297105.1297043","volume":"42","author":"JH Spring","year":"2007","unstructured":"Spring JH, Privat J, Guerraoui R, Vitek J (2007) Streamflex: high-throughput stream programming in java. ACM SIGPLAN Notices 42:211\u2013228","journal-title":"ACM SIGPLAN Notices"},{"key":"1264_CR27","doi-asserted-by":"crossref","first-page":"1701","DOI":"10.1109\/TCAD.2008.923415","volume":"27","author":"W Wolf","year":"2008","unstructured":"Wolf W, Jerraya AA, Martin G (2008) Multiprocessor system-on-chip (MPSoC) technology. IEEE Trans Comput Aided Des Integr Circuits Syst 27:1701\u20131713","journal-title":"IEEE Trans Comput Aided Des Integr Circuits Syst"},{"key":"1264_CR28","unstructured":"Wolsey LA (1998) Integer programming. Wiley New York, p 42"},{"key":"1264_CR29","first-page":"6","volume":"1","author":"M Ruggiero","year":"2006","unstructured":"Ruggiero M, Guerri A, Bertozzi D, Poletti F, Milano M (2006) Communication-aware allocation and scheduling framework for stream-oriented multi-processor systems-on-chip. IEEE Des Autom Test Europe 1:6\u201337","journal-title":"IEEE Des Autom Test Europe"},{"key":"1264_CR30","unstructured":"Danny K (2013) C11: A new C standard aiming at safer programming. http:\/\/blog.smartbear.com\/codereviewer\/c11-a-new-c-standard-aiming-at-safer-programming"},{"key":"1264_CR31","unstructured":"Bjarne S (2013) C++11\u2013the new ISO C++ standard. http:\/\/www.stroustrup.com\/C++11FAQ.html"},{"key":"1264_CR32","unstructured":"Combinable Class. Microsoft. http:\/\/msdn.microsoft.com\/en-us\/library\/dd492850.aspx"},{"key":"1264_CR33","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1145\/635506.605428","volume":"30","author":"MI Gordon","year":"2002","unstructured":"Gordon MI, Thies W, Karczmarek M, Lin J, Meli AS, Lamb AA, Leger C, Wong J, Hoffmann H, Maze D, Amarasinghe S (2002) A stream compiler for communication-exposed architectures. ACM SIGARCH 30:291\u2013303. doi: 10.1145\/635506.605428","journal-title":"ACM SIGARCH"},{"key":"1264_CR34","doi-asserted-by":"crossref","unstructured":"Kapasi UJ, Rixner S, Dally WJ, Khailany B, Ahn JH, Mattson P, Owens JD (2003) Programmable stream processors. IEEE Comput 36:54\u201362","DOI":"10.1109\/MC.2003.1220582"},{"key":"1264_CR35","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1109\/MM.2006.45","volume":"26","author":"J Andrews","year":"2006","unstructured":"Andrews J, Baker N (2006) Xbox 360 system architecture. IEEE Micro 26:25\u201337","journal-title":"IEEE Micro"},{"key":"1264_CR36","unstructured":"Hern\u00e1ndez AF (2013) Yet another survey on SIMD instructions"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-014-1264-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-014-1264-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-014-1264-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T04:32:41Z","timestamp":1565670761000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-014-1264-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7,30]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,10]]}},"alternative-id":["1264"],"URL":"https:\/\/doi.org\/10.1007\/s11227-014-1264-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,30]]}}}