{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:51:15Z","timestamp":1752101475781,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1109\/hpca.2014.6835975","type":"proceedings-article","created":{"date-parts":[[2014,7,28]],"date-time":"2014-07-28T14:48:01Z","timestamp":1406558881000},"page":"678-689","source":"Crossref","is-referenced-by-count":20,"title":["Undersubscribed threading on clustered cache architectures"],"prefix":"10.1109","author":[{"given":"Wim","family":"Heirman","sequence":"first","affiliation":[]},{"given":"Trevor E.","family":"Carlson","sequence":"additional","affiliation":[]},{"given":"Kenzo","family":"Van Craeynest","sequence":"additional","affiliation":[]},{"given":"Ibrahim","family":"Hur","sequence":"additional","affiliation":[]},{"given":"Aamer","family":"Jaleel","sequence":"additional","affiliation":[]},{"given":"Lieven","family":"Eeckhout","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555801"},{"key":"22","article-title":"Better performance at lower occupancy","volume":"10","author":"volkov","year":"2010","journal-title":"GPU Technology Conference (GTC)"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2009.4798236"},{"key":"18","article-title":"Tile-gx100 manycore processor: Acceleration interfaces and architecture","author":"ramey","year":"2011","journal-title":"Proceedings of the 23th Hot Chips Symposium"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237043"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1145\/1065010.1065034"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/2445572.2445577"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"11","article-title":"The OpenMP implementation of NAS Parallel Benchmarks and its performance","author":"jin","year":"1999","journal-title":"Technical Report"},{"key":"12","first-page":"125","article-title":"Data sharing in multithreaded applications and its impact on chip design","author":"krishna","year":"2012","journal-title":"Proceedings of the International Symposium on Performance Analysis of Systems and Software (ISPASS)"},{"key":"21","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1145\/1346281.1346317","article-title":"Feedbackdriven threading: Power-efficient and high-performance execution of multi-threaded workloads on CMPs","author":"suleman","year":"2008","journal-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.17"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1145\/166962.166974"},{"key":"2","article-title":"Sniper: Exploring the level of abstraction for scalable and accurate parallel multi-core simulations","author":"carlson","year":"2011","journal-title":"Proceedings of the International Conference for High Performance Computing Networking Storage and Analysis (SC)"},{"key":"1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/3-540-44587-0_1","article-title":"SPEComp: A new benchmark suite for measuring parallel computer performance","volume":"2104","author":"aslot","year":"2001","journal-title":"OpenMP Shared Memory Parallel Programming"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2007.1091"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2009.4"},{"key":"6","first-page":"10","article-title":"A non-workconserving operating system scheduler for SMT processors","author":"fedorova","year":"2006","journal-title":"Proc Workshop Interaction between Operating System and Computer Architecture (IOSCA 05)"},{"key":"5","article-title":"Intel\ufffd xeon phi coprocessor (codename knights corner)","author":"chrysos","year":"2012","journal-title":"Proceedings of the 24th Hot Chips Symposium"},{"key":"4","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1145\/1248377.1248396","article-title":"Scheduling threads for constructive cache sharing on CMPs","author":"chen","year":"2007","journal-title":"Proc ACM Symposium on Parallel Algorithms and Architectures (SPAA)"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2008.209"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555779"}],"event":{"name":"2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)","start":{"date-parts":[[2014,2,15]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2014,2,19]]}},"container-title":["2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6823235\/6835920\/06835975.pdf?arnumber=6835975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T10:50:33Z","timestamp":1689418233000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6835975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,2]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/hpca.2014.6835975","relation":{},"subject":[],"published":{"date-parts":[[2014,2]]}}}