{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:46Z","timestamp":1740123526275,"version":"3.37.3"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T00:00:00Z","timestamp":1631232000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T00:00:00Z","timestamp":1631232000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s11227-021-03997-w","type":"journal-article","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T07:02:57Z","timestamp":1631257377000},"page":"4827-4849","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Superblock-based performance optimization for Sunway Math Library on SW26010 many-core processor"],"prefix":"10.1007","volume":"78","author":[{"given":"Hao","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaozhong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangwei","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6275-2617","authenticated-orcid":false,"given":"Jinchen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"3997_CR1","doi-asserted-by":"publisher","unstructured":"Lokuciejewski P, Kelter T, Marwedel P (2010) Superblock-Based Source Code Optimizations for WCET Reduction. 2010 10th IEEE International Conference on Computer and Information Technology, 2010, pp. 1918\u20131925. https:\/\/doi.org\/10.1109\/CIT.2010.327","DOI":"10.1109\/CIT.2010.327"},{"key":"3997_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2004.27","author":"G Shobaki","year":"2005","unstructured":"Shobaki G, Wilken K (2005) Optimal Superblock Scheduling Using Enumeration. Proc Ann Intl Symp Microarch. https:\/\/doi.org\/10.1109\/MICRO.2004.27","journal-title":"Proc Ann Intl Symp Microarch"},{"key":"3997_CR3","doi-asserted-by":"publisher","unstructured":"Heffernan M, Wilken K, Shobaki G (2006) Data-Dependency Graph Transformations for Superblock Scheduling. In Proceedings of the 39th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO 39). https:\/\/doi.org\/10.1109\/MICRO.2006.16","DOI":"10.1109\/MICRO.2006.16"},{"key":"3997_CR4","doi-asserted-by":"publisher","unstructured":"Ye JM, Chen T (2012) Exploring Potential Parallelism of Sequential Programs with Superblock Reordering. In: Proceedings of the 2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC '12). https:\/\/doi.org\/10.1109\/HPCC.2012.12","DOI":"10.1109\/HPCC.2012.12"},{"key":"3997_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-016-5588-7","volume":"59","author":"H Fu","year":"2016","unstructured":"Fu H, Liao J, Yang J et al (2016) The Sunway TaihuLight supercomputer: system and applications. Sci China Inf Sci 59:1\u201316. https:\/\/doi.org\/10.1007\/s11432-016-5588-7","journal-title":"Sci China Inf Sci"},{"key":"3997_CR6","unstructured":"Dongarra J (2016) Report on the Sunway TaihuLight System. Ut Eecs Technical Reports 1\u201324. http:\/\/www.netlib.org\/utk\/people\/JackDongarra\/PAPERS\/sunway-report-2016.pdf"},{"key":"3997_CR7","doi-asserted-by":"publisher","unstructured":"Lin J, Xu Z, Nukada A, Maruyama N, Matsuoka S (2017) Optimizations of Two Compute-bound Scientific Kernels on the SW26010 Many-Core Processor. 46th Intl Conf Parallel Proc. https:\/\/doi.org\/10.1109\/ICPP.2017.52","DOI":"10.1109\/ICPP.2017.52"},{"key":"3997_CR8","unstructured":"NSCCWX (2021) Sunway TaihuLight Compiler User Guide. http:\/\/www.nsccwx.cn. Accessed 10 March 2021"},{"key":"3997_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.9","author":"Z Xu","year":"2017","unstructured":"Xu Z, Lin J, Matsuoka S (2017) Benchmarking SW26010 many-core processor. IEEE Intl Parallel Disrt Proc Symp Wkshp (IPDPSW). https:\/\/doi.org\/10.1109\/IPDPSW.2017.9","journal-title":"IEEE Intl Parallel Disrt Proc Symp Wkshp (IPDPSW)"},{"key":"3997_CR10","doi-asserted-by":"publisher","unstructured":"Zhang J. Zhou C, Wang Y et al (2016) Extreme-scale phase field simulations of coarsening dynamics on the sunway TaihuLight supercomputer. SC '16: Proc Intl Conf High Perf Comput Netw Stor Anal. https:\/\/doi.org\/10.1109\/SC.2016.3","DOI":"10.1109\/SC.2016.3"},{"key":"3997_CR11","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1145\/502949.502879","volume":"19","author":"RF Touzeau","year":"1984","unstructured":"Touzeau RF (1984) A fortran compiler for the FPS-164 scientific computer. Sigplan Notices - SIGPLAN 19:48\u201357. https:\/\/doi.org\/10.1145\/502949.502879","journal-title":"Sigplan Notices - SIGPLAN"},{"issue":"1145\/12276","key":"3997_CR12","first-page":"13312","volume":"10","author":"PB Gibbons","year":"1986","unstructured":"Gibbons PB, Muchnick SS (1986) Efficient instruction scheduling for a pipelined architecture. ACM SIGPLAN Notices doi 10(1145\/12276):13312","journal-title":"ACM SIGPLAN Notices doi"},{"issue":"1","key":"3997_CR13","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1147\/rd.341.0085","volume":"34","author":"HS Warren","year":"1990","unstructured":"Warren HS (1990) Instruction scheduling for the IBM RISC System\/6000. IBM J Res Dev 34(1):85\u201392. https:\/\/doi.org\/10.1147\/rd.341.0085","journal-title":"IBM J Res Dev"},{"key":"3997_CR14","unstructured":"Chang PP, Warter NJ, Mahlke S et al (1992) Three Superblock Scheduling Models for Superscalar and Superpipelined Processors. Coord Sci Lab Rep no. UILU-ENG-91\u20132250, CRHC-91\u201329. http:\/\/hdl.handle.net\/2142\/74519"},{"key":"3997_CR15","doi-asserted-by":"publisher","unstructured":"Fisher JA (1979) Optimization of Horizontal Microcode Within and Beyond Basic Blocks: An Application of Processor Scheduling with Resources. PhD thesis, Department of Computer Science, New York University. https:\/\/doi.org\/10.2172\/5752434","DOI":"10.2172\/5752434"},{"key":"3997_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1981.1675827","author":"JA Fisher","year":"1981","unstructured":"Fisher JA (1981) Trace scheduling: a technique for global microcode compaction. IEEE Transact Comput. https:\/\/doi.org\/10.1109\/TC.1981.1675827","journal-title":"IEEE Transact Comput"},{"key":"3997_CR17","volume-title":"Bulldog: a compiler for VLIW architectures","author":"JR Ellis","year":"1986","unstructured":"Ellis JR (1986) Bulldog: a compiler for VLIW architectures. MIT Press, Cambridge, Massachusetts"},{"key":"3997_CR18","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380211204","author":"PP Chang","year":"1991","unstructured":"Chang PP, Mahlke SA, Hwu WM (1991) Using profile information to assist classic compiler code optimizations. Softw Pract Exper. https:\/\/doi.org\/10.1002\/spe.4380211204","journal-title":"Softw Pract Exper"},{"key":"3997_CR19","volume-title":"The superblock: an effective technique for VLIW and superscalar compilation","author":"WM Hwu","year":"1993","unstructured":"Hwu WM, Mahlke SA, Chen WY et al (1993) The superblock: an effective technique for VLIW and superscalar compilation. Springer, Berlin"},{"issue":"6","key":"3997_CR20","first-page":"1306","volume":"26","author":"JC Xu","year":"2015","unstructured":"Xu JC, Huang Y, Guo S et al (2015) Testing platform for floating mathematical function libraries. J Softw 26(6):1306","journal-title":"J Softw"},{"key":"3997_CR21","doi-asserted-by":"publisher","DOI":"10.1145\/183432.183446","author":"SM Freudenberger","year":"1994","unstructured":"Freudenberger SM, Gross TR, Lowney PG (1994) Avoidance and suppression of compensation code in a trace scheduling compiler. ACM Trans Prog Lang Sys. https:\/\/doi.org\/10.1145\/183432.183446","journal-title":"ACM Trans Prog Lang Sys"},{"key":"3997_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.06.001","author":"J Lin","year":"2018","unstructured":"Lin J, Xu Z, Cai L et al (2018) Evaluating the SW26010 many-core processor with a micro-benchmark suite for performance optimizations. Parallel Comput. https:\/\/doi.org\/10.1016\/j.parco.2018.06.001","journal-title":"Parallel Comput"},{"key":"3997_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/s10951-012-0276-y","author":"M Chase","year":"2012","unstructured":"Chase M, Malik AM, Russel T et al (2012) A computational study of heuristic and exact techniques for superblock instruction scheduling. J Sched. https:\/\/doi.org\/10.1007\/s10951-012-0276-y","journal-title":"J Sched"},{"key":"3997_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/BF01205182","author":"P Lowney","year":"1993","unstructured":"Lowney P (1993) The multiflow trace scheduling compiler. J Supercomp. https:\/\/doi.org\/10.1007\/BF01205182","journal-title":"J Supercomp"},{"key":"3997_CR25","doi-asserted-by":"publisher","DOI":"10.1145\/2166.357217","author":"J Hennessy","year":"1983","unstructured":"Hennessy J, Gross T (1983) Postpass code optimization of pipeline constraints. ACM Trans Program Lang Syst. https:\/\/doi.org\/10.1145\/2166.357217","journal-title":"ACM Trans. Program Lang Syst"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-03997-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-021-03997-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-03997-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T15:19:39Z","timestamp":1647357579000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-021-03997-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,10]]},"references-count":25,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["3997"],"URL":"https:\/\/doi.org\/10.1007\/s11227-021-03997-w","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2021,9,10]]},"assertion":[{"value":"12 July 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}