{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T12:46:38Z","timestamp":1751460398239},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2016,4,8]],"date-time":"2016-04-08T00:00:00Z","timestamp":1460073600000},"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":[[2017,8]]},"DOI":"10.1007\/s11227-016-1710-2","type":"journal-article","created":{"date-parts":[[2016,4,9]],"date-time":"2016-04-09T02:03:43Z","timestamp":1460167423000},"page":"3508-3525","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Shared write buffer to boost applications on SpMT architecture"],"prefix":"10.1007","volume":"73","author":[{"given":"Ming","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianzhou","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjun","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,8]]},"reference":[{"key":"1710_CR1","doi-asserted-by":"crossref","unstructured":"Akkary H, Driscoll MA (1998) A dynamic multithreading processor. In: Proceedings of the 31st annual ACM\/IEEE international symposium on Microarchitecture, MICRO31. IEEE Computer Society Press, Los Alamitos, pp 226\u2013236","DOI":"10.1109\/MICRO.1998.742784"},{"key":"1710_CR2","doi-asserted-by":"publisher","unstructured":"Bhowmik A, Franklin M (2003) A fast approximate interprocedural analysis for speculative multithreading compilers. In: Proceedings of the 17th annual international conference on supercomputing, ICS \u201903. ACM, New York, pp 32\u201341. doi:\n                        10.1145\/782814.782822","DOI":"10.1145\/782814.782822"},{"key":"1710_CR3","doi-asserted-by":"crossref","unstructured":"Blake G, Dreslinski RG, Mudge T, Flautner K (2010) Evolution of thread-level parallelism in desktop applications. In: ISCA \u201910: proceedings of the 37th annual international symposium on computer architecture. ACM, New York, pp 302\u2013313","DOI":"10.1145\/1815961.1816000"},{"key":"1710_CR4","doi-asserted-by":"publisher","unstructured":"Chen S, Gibbons PB, Kozuch M, Liaskovitis V, Ailamaki A, Blelloch GE, Falsafi B, Fix L, Hardavellas N, Mowry TC, Wilkerson C (2007) Scheduling threads for constructive cache sharing on cmps. In: Proceedings of the nineteenth annual ACM symposium on parallel algorithms and architectures, SPAA \u201907. ACM, New York, pp 105\u2013115. doi:\n                        10.1145\/1248377.1248396","DOI":"10.1145\/1248377.1248396"},{"key":"1710_CR5","unstructured":"Dubey P, OBrien K, OBrien KM, Barton C (1995) Single-program speculative multithreading (SPSM) architecture: compiler-assisted fine-grained multithreading. Technical report"},{"issue":"5","key":"1710_CR6","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1109\/12.509907","volume":"45","author":"M Franklin","year":"1996","unstructured":"Franklin M, Sohi GS (1996) ARB: a hardware mechanism for dynamic reordering of memory references. IEEE Trans Comput 45(5):552\u2013571. doi:\n                        10.1109\/12.509907","journal-title":"IEEE Trans Comput"},{"key":"1710_CR7","doi-asserted-by":"crossref","unstructured":"Gopal S, Vijaykumar TN, Smith JE, Sohi GS (1998) Speculative versioning cache. In: 1998 Fourth international symposium on high-performance computer architecture, 1998. Proceedings. IEEE, pp 195\u2013205","DOI":"10.1109\/HPCA.1998.650559"},{"key":"1710_CR8","doi-asserted-by":"publisher","unstructured":"Keckler SW, Dally WJ, Maskit D, Carter NP, Chang A, Lee WS (1998) Exploiting fine-grain thread level parallelism on the MIT multi-ALU processor. In: Proceedings of the 25th annual international symposium on computer architecture, ISCA \u201998. IEEE Computer Society, Washington, pp 306\u2013317. doi:\n                        10.1145\/279358.279399","DOI":"10.1145\/279358.279399"},{"issue":"9","key":"1710_CR9","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1109\/12.795218","volume":"48","author":"V Krishnan","year":"1999","unstructured":"Krishnan V, Torrellas J (1999) A chip-multiprocessor architecture with speculative multithreading. IEEE Trans Comput 48(9):866\u2013880","journal-title":"IEEE Trans Comput"},{"key":"1710_CR10","doi-asserted-by":"crossref","unstructured":"Krishnan V, Torrellas J (1999) A chip-multiprocessor architecture with speculative multithreading. IEEE Trans Comput 48(9):866\u2013880. \n                        http:\/\/portal.acm.org\/citation.cfm?id=318107.318113","DOI":"10.1109\/12.795218"},{"key":"1710_CR11","doi-asserted-by":"publisher","unstructured":"Marcuello P, Gonz\u00e1lez A, Tubella J (1998) Speculative multithreaded processors. In: Proceedings of the 12th international conference on supercomputing\u2014ICS \u201998, 4. ACM, IEEE, pp 77\u201384. doi:\n                        10.1145\/277830.277850\n                        \n                    . \n                        http:\/\/portal.acm.org\/citation.cfm?doid=277830.277850","DOI":"10.1145\/277830.277850"},{"key":"1710_CR12","doi-asserted-by":"crossref","unstructured":"Marcuello P, Tubella J, Gonz\u00e1lez A (1999) Value prediction for speculative multithreaded architectures. In: Proceedings of the 32nd annual ACM\/IEEE international symposium on microarchitecture, MICRO 32. IEEE Computer Society, Washington, pp 230\u2013236","DOI":"10.1109\/MICRO.1999.809461"},{"key":"1710_CR13","doi-asserted-by":"publisher","unstructured":"Packirisamy V, Wang S, Zhai A, Hsu WC, Yew PC (2006) Supporting speculative multithreading on simultaneous multithreaded processors. In: Robert Y, Parashar M, Badrinath R, Prasanna V (eds.) High performance computing\u2014HiPC 2006. Lecture notes in computer science, vol 4297. Springer, Berlin, pp 148\u2013158. doi:\n                        10.1007\/11945918_19","DOI":"10.1007\/11945918_19"},{"key":"1710_CR14","doi-asserted-by":"publisher","unstructured":"Pugsley SH, Spjut JB, Nellans DW, Balasubramonian R (2010) SWEL: hardware cache coherence protocols to map shared data onto shared caches. In: Proceedings of the 19th international conference on parallel architectures and compilation techniques\u2014PACT \u201910, p 465. doi:\n                        10.1145\/1854273.1854331","DOI":"10.1145\/1854273.1854331"},{"issue":"7","key":"1710_CR15","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1002\/cpe.2872","volume":"25","author":"J Puiggali","year":"2013","unstructured":"Puiggali J, Szymanski BK, Jov\u00e9 T, Marzo JL (2013) Dynamic branch speculation in a speculative parallelization architecture for computer clusters. Concurr Comput Pract Exp 25(7):932\u2013960. doi:\n                        10.1002\/cpe.2872","journal-title":"Concurr Comput Pract Exp"},{"key":"1710_CR16","doi-asserted-by":"crossref","unstructured":"Roth A, Sohi GS (2001) Speculative data-driven multithreading. In: HPCA \u201901: proceedings of the 7th international symposium on high-performance computer architecture. IEEE Computer Society, Washington","DOI":"10.1109\/HPCA.2001.903250"},{"key":"1710_CR17","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1145\/223982.224451","volume":"23","author":"GS Sohi","year":"1995","unstructured":"Sohi GS, Breach SE, Vijaykumar TN (1995) Multiscalar processors. SIGARCH Comput Archit News 23:414\u2013425. doi:\n                        10.1145\/223982.224451","journal-title":"SIGARCH Comput Archit News"},{"key":"1710_CR18","doi-asserted-by":"publisher","unstructured":"Steffan JG, Colohan CB, Zhai A, Mowry TC (2000) A scalable approach to thread-level speculation. In: SIGARCH computer architecture news, ISCA \u201900, vol\u00a028. ACM, New York, pp. 1\u201312. doi:\n                        10.1145\/339647.339650","DOI":"10.1145\/339647.339650"},{"key":"1710_CR19","doi-asserted-by":"publisher","unstructured":"Tsai JYTJY, Yew PCYPC (1996) The superthreaded architecture: thread pipelining with run-time data dependence checking and control speculation. In: Proceedings of the 1996 conference on parallel architectures and compilation technique, pp 35\u201346. doi:\n                        10.1109\/PACT.1996.552553","DOI":"10.1109\/PACT.1996.552553"},{"key":"1710_CR20","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1109\/71.970565","volume":"12","author":"TN Vijaykumar","year":"2001","unstructured":"Vijaykumar TN, Gopal S, Smith JE, Sohi G (2001) Speculative versioning cache. IEEE Trans Parallel Distrib Syst 12:1305\u20131317. doi:\n                        10.1109\/71.970565","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1710_CR21","doi-asserted-by":"publisher","unstructured":"Ye J, Chen T (2012) Exploring potential parallelism of sequential programs with superblock reordering. In: IEEE HPCC-2012. doi:\n                        10.1109\/HPCC.2012.12","DOI":"10.1109\/HPCC.2012.12"},{"issue":"6","key":"1710_CR22","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1007\/s00607-014-0387-8","volume":"96","author":"J Ye","year":"2014","unstructured":"Ye J, Yan H, Hou H, Chen T (2014) Potential thread-level-parallelism exploration with superblock reordering. Computing 96(6):545\u2013564. doi:\n                        10.1007\/s00607-014-0387-8","journal-title":"Computing"},{"key":"1710_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2012.05.002","author":"JM Ye","year":"2012","unstructured":"Ye JM, Cao M, Qu Z, Chen T (2012) Regional cache organization for NoC based many-core processors. J Comput Syst Sci. doi:\n                        10.1016\/j.jcss.2012.05.002","journal-title":"J Comput Syst Sci"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-016-1710-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1710-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1710-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1710-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T10:40:47Z","timestamp":1559385647000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-016-1710-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,8]]},"references-count":23,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["1710"],"URL":"https:\/\/doi.org\/10.1007\/s11227-016-1710-2","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,4,8]]}}}