{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T03:41:12Z","timestamp":1725766872795},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/micro.2010.41","type":"proceedings-article","created":{"date-parts":[[2011,1,21]],"date-time":"2011-01-21T20:35:14Z","timestamp":1295642114000},"page":"337-348","source":"Crossref","is-referenced-by-count":20,"title":["Minimal Multi-threading: Finding and Removing Redundant Instructions in Multi-threaded Processors"],"prefix":"10.1109","author":[{"given":"Guoping","family":"Long","sequence":"first","affiliation":[]},{"given":"Diana","family":"Franklin","sequence":"additional","affiliation":[]},{"given":"Susmit","family":"Biswas","sequence":"additional","affiliation":[]},{"given":"Pablo","family":"Ortiz","sequence":"additional","affiliation":[]},{"given":"Jason","family":"Oberg","sequence":"additional","affiliation":[]},{"given":"Dongrui","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Frederic T.","family":"Chong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"ref38","first-page":"24","article-title":"The SPLASH-2 programs: characterization and methodological considerations","author":"woo","year":"1995","journal-title":"Proceedings 22nd Annual International Symposium on Computer Architecture ISCA"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012088469-8\/50059-0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168893"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/CGO.2004.1281681","article-title":"A compiler scheme for reusing intermediate computation results","author":"ding","year":"2004","journal-title":"Proc Int Symp Code Generation Optimization (CGO)"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1109\/PACT.2000.888335","article-title":"Exploring sub-block value reuse for superscalar processors","author":"huang","year":"2000","journal-title":"Proceedings of International Conference on Parallel Architectures and Compilation Techniques"},{"article-title":"Libsvm: a library for support vector machines","year":"2001","author":"chang","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1393921.1394018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/503272.503296"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555777"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF02425917"},{"year":"2009","key":"ref40","article-title":"International technology roadmap for semiconductors"},{"key":"ref11","article-title":"Accelerating multi-media processing by implementing memoing in multiplication and division units","author":"citron","year":"1996","journal-title":"Proc Int l Conf Architectural Support for Programming Languages and Operating Systems"},{"key":"ref12","article-title":"An architectural alternative to optimized compilers","author":"harbison","year":"1982","journal-title":"Proc Int l Conf Architectural Support for Programming Languages and Operating Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.1998.727185"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/PACT.2000.888334","article-title":"The dynamic trace memorization reuse technique","author":"costa","year":"2000","journal-title":"Proceedings of International Conference on Parallel Architectures and Compilation Techniques"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2004.42"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICVD.2004.1260935"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00904-4_13"},{"key":"ref18","first-page":"1998","article-title":"The performance potential of data value reuse","author":"gonzalez","year":"1998"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1997.604688"},{"key":"ref28","article-title":"Compiler directed dynamic computation reuse: Rational and initial results","author":"connors","year":"1999","journal-title":"Proceedings of International Symposium on Microarchitecture"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2005.39"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2005.1"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1145\/1080695.1069998","article-title":"Victim replication: Maximizing capacity while hiding wire delay in tiled chip multiprocessors","author":"zhang","year":"2005","journal-title":"Proceedings of International Symposium on Computer Architecture"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/232973.232993"},{"key":"ref29","article-title":"Exploiting basic block value locality with block reuse","author":"huang","year":"1998","journal-title":"Proceedings of International Symposium on High-Performance Computer Architecture"},{"key":"ref5","first-page":"392","article-title":"Simultaneous multithreading: Maximizing on-chip parallelism","author":"tullsen","year":"1995","journal-title":"Proceedings 22nd Annual International Symposium on Computer Architecture ISCA"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.1993.378089"},{"key":"ref7","article-title":"Caching function results: Faster arithmetic by avoiding unnecessary computation","author":"richardson","year":"1992","journal-title":"Technical Report SMLI TR-92–1"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1145\/1150019.1136509","article-title":"Cooperative caching for chip multiprocessors","author":"chang","year":"2006","journal-title":"Proceedings of International Symposium on Computer Architecture"},{"key":"ref9","article-title":"On division and reciprocal caches. technical report","author":"oberman","year":"1995","journal-title":"Technical Report CSL-TR-95–666 Stanford University"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.10"},{"key":"ref46","first-page":"83","article-title":"Wattch: a framework for architectural-level power analysis and optimizations","author":"brooks","year":"2000","journal-title":"Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat No RS00201) ISCA"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/291069.291016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1999.765951"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305239"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1998.742782"},{"key":"ref42","article-title":"Godson-t: A many-core processor for efficient multithreaded program execution","author":"fan","year":"2010","journal-title":"Journal of Computer Science and Technology"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2003.1253702"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2005.1609253"},{"article-title":"Hardware memorization of mathematical and trigonometric functions","year":"2000","author":"citron","key":"ref23"},{"key":"ref44","article-title":"Trace cache: a low latency approach to high bandwidth instruction fetching","author":"rotenberg","year":"1996","journal-title":"Proceedings of International Symposium on Microarchitecture"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2004.1310789"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/268806.268810"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1145\/263272.263348","article-title":"Low power data processing by elimination of redundant computations","author":"azam","year":"1997","journal-title":"Proceedings of 1997 International Symposium on Low Power Electronics and Design LPE"}],"event":{"name":"2010 43rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","start":{"date-parts":[[2010,12,4]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2010,12,8]]}},"container-title":["2010 43rd Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5692847\/5695520\/05695548.pdf?arnumber=5695548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T01:44:50Z","timestamp":1559958290000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5695548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/micro.2010.41","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}