{"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":1740123526676,"version":"3.37.3"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T00:00:00Z","timestamp":1548115200000},"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":[[2019,7]]},"DOI":"10.1007\/s11227-018-02741-1","type":"journal-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T00:59:29Z","timestamp":1548291569000},"page":"3917-3944","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Memory latency optimizations for the elementary functions on the Sunway architecture"],"prefix":"10.1007","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1515-0602","authenticated-orcid":false,"given":"Bei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongzhong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaozhong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,22]]},"reference":[{"issue":"3","key":"2741_CR1","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1023\/A:1009984523264","volume":"5","author":"J-M Muller","year":"1999","unstructured":"Muller J-M (1999) A few results on table-based methods. Reliab Comput 5(3):279\u2013288","journal-title":"Reliab Comput"},{"key":"2741_CR2","volume-title":"Elementary functions: algorithms and implementation","author":"J-M Muller","year":"2006","unstructured":"Muller J-M (2006) Elementary functions: algorithms and implementation, 2nd edn. Birkhauser, Basel","edition":"2"},{"key":"2741_CR3","volume-title":"Numerical analysis","author":"L Burden Richard","year":"2010","unstructured":"Burden Richard L, Douglas Faires J (2010) Numerical analysis, 9th edn. BROOKS\/COLE CENGAGE Learning, Boston","edition":"9"},{"issue":"1","key":"2741_CR4","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/103147.103151","volume":"17","author":"S Gal","year":"1991","unstructured":"Gal S, Bachelis B (1991) An accurate elementary mathematical library for the IEEE floating point standard. ACM Trans Math Softw 17(1):26\u201345","journal-title":"ACM Trans Math Softw"},{"key":"2741_CR5","doi-asserted-by":"crossref","unstructured":"Tang PTP (1991) Table-lookup algorithms for elementary functions and their error analysis. In: Kornerup P, Matula DW (eds) Proceedings of the 10th IEEE Symposium on Computer Arithmetic, IEEE Computer Society Press, Los Alamitos, CA, pp 232\u2013236","DOI":"10.1109\/ARITH.1991.145565"},{"issue":"4","key":"2741_CR6","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1145\/98267.98294","volume":"16","author":"PTP Tang","year":"1999","unstructured":"Tang PTP (1999) Table-driven implementation of the logarithm function in IEEE Floating-point arithmetic. ACM Trans Math Softw 16(4):378\u2013400","journal-title":"ACM Trans Math Softw"},{"issue":"3","key":"2741_CR7","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1145\/79505.79506","volume":"16","author":"PTP Tang","year":"1990","unstructured":"Tang PTP (1990) Accurate and efficient testing of the exponential and logarithm functions. ACM Trans Math Softw 16(3):185\u2013200","journal-title":"ACM Trans Math Softw"},{"key":"2741_CR8","volume-title":"Design and optimization of key load store technology in high performance processor","author":"RL Ma","year":"2012","unstructured":"Ma RL (2012) Design and optimization of key load store technology in high performance processor. Shanghai Jiao Tong University, Shanghai"},{"key":"2741_CR9","volume-title":"The optimization of memory controller for high performance CPU","author":"HY Wang","year":"2012","unstructured":"Wang HY (2012) The optimization of memory controller for high performance CPU. National University of Defense Technology, Changsha"},{"key":"2741_CR10","volume-title":"Performance modeling of memory latency hiding techniques. Technical report","author":"H Zhou","year":"2003","unstructured":"Zhou H, Conte TM (2003) Performance modeling of memory latency hiding techniques. Technical report. ECE Department, State University, NC"},{"key":"2741_CR11","unstructured":"Mowry T (2009) Tolerating latency through software controlled data prefetching. In: PhD Thesis. Stanford University, Stanford"},{"key":"2741_CR12","unstructured":"Gornish E, Granston E, Veidenbaum A (2009) Compiler-directed data prefetching in multiprocessors with memory hierarchies. In: International Conference on Supercomputing"},{"key":"2741_CR13","first-page":"1","volume":"46","author":"W Liu","year":"2017","unstructured":"Liu W, Ma S, Huang L, Wang Z (2017) The design of NoC-side memory access scheduling for energy-efficient GPGPUs. Int J Parallel Program 46:1\u201314","journal-title":"Int J Parallel Program"},{"issue":"12","key":"2741_CR14","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF01205181","volume":"7","author":"BR Rau","year":"1993","unstructured":"Rau BR, Fisher JA (1993) Instruction-level parallel processing: history, overview, and perspective. J Supercomput 7(12):9\u201350","journal-title":"J Supercomput"},{"issue":"3","key":"2741_CR15","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1007\/s11227-014-1088-y","volume":"68","author":"M Naderan-Tahan","year":"2014","unstructured":"Naderan-Tahan M, Sarbazi-Azad H (2014) Adaptive prefetching using global history buffer in multicore processors. J Supercomput 68(3):1302\u20131320","journal-title":"J Supercomput"},{"issue":"4","key":"2741_CR16","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1007\/s11227-016-1675-1","volume":"72","author":"M Torrents","year":"2016","unstructured":"Torrents M, Martnez R, Molina C (2016) Facing prefetching challenges in distributed shared memories for CMPs. J Supercomput 72(4):1453\u20131476","journal-title":"J Supercomput"},{"issue":"3","key":"2741_CR17","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1145\/1824801.1824806","volume":"37","author":"CK Anand","year":"2010","unstructured":"Anand CK (2010) Unified tables for exponential and logarithm families. ACM Trans Math Softw 37(3):28","journal-title":"ACM Trans Math Softw"},{"issue":"4","key":"2741_CR18","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/BF00129835","volume":"4","author":"DA Carlson","year":"1991","unstructured":"Carlson DA (1991) Using local memory to boost the performance of FFT algorithms on the CRAY-2 supercomputer. J Supercomput 4(4):345\u2013356","journal-title":"J Supercomput"},{"issue":"6","key":"2741_CR19","first-page":"12","volume":"41","author":"JC Xu","year":"2014","unstructured":"Xu JC (2014) Access optimization technique for mathematical library of slave processors on heterogeneous many-core architectures. Comput Sci 41(6):12\u201317","journal-title":"Comput Sci"},{"issue":"10","key":"2741_CR20","doi-asserted-by":"publisher","first-page":"3934","DOI":"10.1007\/s11227-015-1483-z","volume":"71","author":"J Filipovi","year":"2015","unstructured":"Filipovi J, Madzin M, Fouse J, Matyska K (2015) Optimizing CUDA code by kernel fusion: application on BLAS. J Supercomput 71(10):3934\u20133957","journal-title":"J Supercomput"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-02741-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-018-02741-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-02741-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T20:08:05Z","timestamp":1579637285000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-018-02741-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,22]]},"references-count":20,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2019,7]]}},"alternative-id":["2741"],"URL":"https:\/\/doi.org\/10.1007\/s11227-018-02741-1","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2019,1,22]]},"assertion":[{"value":"22 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}