{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:18:17Z","timestamp":1740133097048,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"SNF","award":["206021_133835"],"award-info":[{"award-number":["206021_133835"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2018,9,1]]},"DOI":"10.1109\/tpds.2018.2817207","type":"journal-article","created":{"date-parts":[[2018,3,19]],"date-time":"2018-03-19T18:09:05Z","timestamp":1521482945000},"page":"2136-2149","source":"Crossref","is-referenced-by-count":4,"title":["Unifying Fixed Code Mapping, Communication, Synchronization and Scheduling Algorithms for Efficient and Scalable Loop Pipelining"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5235-8499","authenticated-orcid":false,"given":"Aristeidis","family":"Mastoras","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2038-2902","authenticated-orcid":false,"given":"Thomas R.","family":"Gross","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400712"},{"year":"2015","key":"ref38","article-title":"OpenMP\n application program interface"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/237502.237508"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259028"},{"key":"ref31","first-page":"836","article-title":"DOACROSS: Beyond vectorization for multiprocessors","author":"cytron","year":"1986","journal-title":"Proc Int Conf Parallel Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SUPERC.1990.130048"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1944862.1944867"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2011.11.001"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/52.1992"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1980.1675676"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1640089.1640106"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.micpro.2014.04.001","article-title":"TERAFLUX: Harnessing dataflow in next generation teradevices","volume":"38","author":"giorgi","year":"2014","journal-title":"Microprocessors Microsyst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.28"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2809808"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/324133.324234"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345215"},{"key":"ref15","article-title":"Liberty queues for EPIC architectures","author":"jablin","year":"2010","journal-title":"Proceedings of the 4th Workshop on Explicitly Parallel Instruction Computing Techniques"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470368"},{"key":"ref17","first-page":"144","article-title":"Correct and efficient bounded FIFO queues","author":"l\u00ea","year":"2013","journal-title":"Proc 25th Int Symp Comput Archit High Perform Comput"},{"key":"ref18","first-page":"161","article-title":"Characteristics of workloads using the pipeline programming model","author":"bienia","year":"2012","journal-title":"Proc Revised Sel Papers 3rd Workshop Emerging Appl Many-Core Archit Held Conjunction 37th Int Symp Comput Archit"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503295"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1400112.1400113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356074"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2005.13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2004.1342552"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2013.12.009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2007.4336199"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1145\/1854273.1854296","article-title":"Feedback-directed pipeline parallelism","author":"suleman","year":"2010","journal-title":"Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/277650.277725"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168877"},{"year":"0","key":"ref2"},{"year":"2011","key":"ref9","article-title":"Threading building blocks reference manual"},{"article-title":"Benchmarking modern multiprocessors","year":"2011","author":"bienia","key":"ref1"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1145\/69558.69562","article-title":"I-structures: Data structures for parallel computing","volume":"11","author":"nikhil","year":"1989","journal-title":"ACM Trans Program Languages Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1772954.1772973"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1878921.1878924"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3178442.3178443"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442527"},{"key":"ref42","first-page":"69","article-title":"Correct and efficient work-stealing\n for weak memory models","author":"l\u00ea","year":"2013","journal-title":"Proc of the Symp on Principles and Practice of Parallel Programming"},{"year":"0","key":"ref24"},{"key":"ref41","first-page":"125","article-title":"Scalable task parallelism for NUMA: A uniform abstraction for\n coordinated scheduling and memory management","author":"drebes","year":"2016","journal-title":"Proc Int Conf Parallel Archit Compil"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"ref44","first-page":"189","article-title":"DANBI: Dynamic scheduling of irregular stream programs for many-core systems","author":"min","year":"2013","journal-title":"Proc Int Conf Parallel Archit Compilation Tech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2755573.2755610"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.9"},{"article-title":"Piper: Experimental support for parallel pipelines in Intel Cilk\n Plus","year":"2013","author":"sukha","key":"ref25"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8428579\/08319946.pdf?arnumber=8319946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T14:58:03Z","timestamp":1643209083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8319946\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,1]]},"references-count":46,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2018.2817207","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2018,9,1]]}}}