{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:17:19Z","timestamp":1763468239644,"version":"3.28.0"},"reference-count":64,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1109\/hpca.2015.7056061","type":"proceedings-article","created":{"date-parts":[[2015,3,10]],"date-time":"2015-03-10T22:13:51Z","timestamp":1426025631000},"page":"538-550","source":"Crossref","is-referenced-by-count":29,"title":["Scaling distributed cache hierarchies through computation and data co-scheduling"],"prefix":"10.1109","author":[{"given":"Nathan","family":"Beckmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-An","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Sanchez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1987816.1987832"},{"key":"ref38","article-title":"Gaining insights into multicore cache partitioning: Bridging the gap between simulation and real systems","author":"lin","year":"2008","journal-title":"Proceedings of HPCA-14"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/12.286300"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541944"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827595287997"},{"journal-title":"Silvermont Intels Low Power Architecture","year":"2013","author":"kanter","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"ref36","article-title":"Cloudtache: Expanding and shrinking private caches","author":"lee","year":"2011","journal-title":"Proc HPCA-17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2010.5434033"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/605397.605420"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/237090.237205"},{"key":"ref62","article-title":"A Comparison of Capacity Management Schemes for Shared CMP Caches","author":"wu","year":"2008","journal-title":"WDDD-7"},{"key":"ref61","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4613-1677-0","author":"wong","year":"1988","journal-title":"Simulated Annealing for VLSI Design"},{"key":"ref63","article-title":"Victim replication: Maximizing capacity while hiding wire delay in tiled chip multiprocessors","author":"zhang","year":"2005","journal-title":"ISCA"},{"key":"ref28","article-title":"A NUCA substrate for flexible CMP cache sharing","volume":"18","author":"jaehyuk huh","year":"2007","journal-title":"IEEE Trans Par Dist Sys"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736036"},{"journal-title":"Presentation on Scrum","article-title":"Knights Landing: Next Generation Intel Xeon Phi","year":"2013","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2151003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.10"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2006.73"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555779"},{"key":"ref22","article-title":"Database Servers on Chip Multiprocessors: Limitations and Opportunities","author":"hardavellas","year":"2007","journal-title":"Proc CIDR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.77"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0370-1573(86)90047-5"},{"journal-title":"Computer Architecture A Quantitative Approach","year":"2011","author":"hennessy","key":"ref23"},{"key":"ref26","article-title":"FIESTA: A sample-balanced multi-program workload methodology","author":"hilton","year":"2009","journal-title":"Proc MoBS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2008.209"},{"key":"ref50","article-title":"SCOTCH: A software package for static mapping by dual recursive bipartitioning of process and architecture graphs","author":"pellegrini","year":"1996","journal-title":"Proc HPCN"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2009.4798236"},{"key":"ref59","article-title":"Asymmetry-aware execution placement on manycore chips","author":"tumanov","year":"2013","journal-title":"SFMA-3"},{"key":"ref58","article-title":"CACTI 5.1","author":"thoziyoor","year":"2008","journal-title":"Tech Rep HPL-2008-20"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/1272996.1273004"},{"key":"ref56","article-title":"Managing shared L2 caches on multicore systems in software","author":"tam","year":"2007","journal-title":"WIOSCA"},{"key":"ref55","article-title":"Symbiotic jobscheduling for a simultaneous multithreading processor","author":"snavely","year":"2000","journal-title":"Proc ASPLOS-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485963"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000073"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.49"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2005.39"},{"key":"ref11","article-title":"Managing distributed, shared L2 caches through OS-level page allocation","author":"cho","year":"2006","journal-title":"Proc of MICRO 39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237037"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485949"},{"key":"ref13","article-title":"GPU Computing: To Exascale and Beyond","author":"dally","year":"2010","journal-title":"SC Plenary Talk"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522311"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451157"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref17","first-page":"365","article-title":"Dark silicon and the end of multicore scaling","author":"esmaeilzadeh","year":"2011","journal-title":"2011 38th Annual International Symposium on Computer Architecture (ISCA) ISCA"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.17"},{"journal-title":"Gurobi Optimizer Reference Manual Version 5 6","year":"2013","key":"ref19"},{"key":"ref4","article-title":"Jigsaw: Scalable Software-Defined Caches","author":"beckmann","year":"2013","journal-title":"Proc PACT-22"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2004.21"},{"key":"ref6","article-title":"TILE64 processor: A 64-core SoC with mesh interconnect","author":"bell","year":"2008","journal-title":"Proc ISSCC"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056022"},{"key":"ref8","article-title":"Cooperative caching for chip multiprocessors","author":"chang","year":"2006","journal-title":"Proceedings of ISCA-33"},{"key":"ref7","article-title":"A case for NUMA-aware contention management on multicore systems","author":"blagodurov","year":"2011","journal-title":"Proc USENIX ATC"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1810479.1810481"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/337292.337523"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1713254.1713276"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462163"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1145\/277044.277121","article-title":"Congestion driven quadratic placement","author":"parakh","year":"1998","journal-title":"Proceedings 1998 Design and Automation Conference 35th DAC (Cat No 98CH36175) DAC"},{"key":"ref47","article-title":"Partitioned cache architecture as a side-channel defence mechanism","author":"page","year":"2005","journal-title":"IACR Cryptology ePrint Archive"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2010.5416641"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250670"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1531793.1531806"},{"journal-title":"1 35V DDR3L Power Calculator (4Gb x16 Chips)","year":"2013","key":"ref43"}],"event":{"name":"2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)","start":{"date-parts":[[2015,2,7]]},"location":"Burlingame, CA, USA","end":{"date-parts":[[2015,2,11]]}},"container-title":["2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7048058\/7056013\/07056061.pdf?arnumber=7056061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T07:03:59Z","timestamp":1498201439000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7056061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/hpca.2015.7056061","relation":{},"subject":[],"published":{"date-parts":[[2015,2]]}}}