{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:50:38Z","timestamp":1783036238162,"version":"3.54.6"},"reference-count":99,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/iccd.2016.7753257","type":"proceedings-article","created":{"date-parts":[[2016,11,24]],"date-time":"2016-11-24T21:40:00Z","timestamp":1480023600000},"page":"25-32","source":"Crossref","is-referenced-by-count":113,"title":["Accelerating pointer chasing in 3D-stacked memory: Challenges, mechanisms, evaluation"],"prefix":"10.1109","author":[{"given":"Kevin","family":"Hsieh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samira","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nandita","family":"Vijaykumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin K.","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amirali","family":"Boroumand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saugata","family":"Ghose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Hybrid Memory Cube Consortium","year":"2014","journal-title":"Specification 2 0"},{"key":"ref38","article-title":"Hybrid Memory Cube Consortium","year":"2013","journal-title":"HMC Specification 1 1"},{"key":"ref33","article-title":"Acclerating dependent cache misses with an enhanced memory controller","author":"hashemi","year":"2016","journal-title":"ISCA"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844457"},{"key":"ref31","article-title":"Biscuit: A framework for near-data processing of big data workloads","author":"gu","year":"2016","journal-title":"ISCA"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/2.375174"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2004.11.004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183549"},{"key":"ref35","article-title":"A ‘pointer chasing accelerator for 3D-stacked memory","author":"hsieh","year":"2016","journal-title":"CMU SAFARI Technical Report No 2016-007"},{"key":"ref34","article-title":"Transparent offloading and mapping (TOM): Enabling programmer-transparent near-data processing in GPU systems","author":"hsieh","year":"2016","journal-title":"ISCA"},{"key":"ref28","author":"giampaolo","year":"1998","journal-title":"Practical File System Design with the Be File System"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446059"},{"key":"ref29","article-title":"MLP yes! ILP no!","author":"glew","year":"1998","journal-title":"ASPLOS WACI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.1992.591879"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"ref21","author":"elmasri","year":"2007","journal-title":"Fundamentals of Database Systems"},{"key":"ref24","article-title":"Technology preview: ARM next generation processing","author":"filippo","year":"2012","journal-title":"ARM TechCon"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2150982"},{"key":"ref26","article-title":"Practical near-data processing for in-memory analytics frameworks","author":"gao","year":"2015","journal-title":"PACT"},{"key":"ref25","article-title":"Distributed caching with Memcached","author":"fitzpatrick","year":"2004","journal-title":"Linux Journal"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2832911"},{"key":"ref51","article-title":"BSSync: Processing near memory for machine learning workloads with bounded staleness consistency models","author":"lee","year":"2015","journal-title":"PACT"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/237090.237190"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/379240.379250"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237043"},{"key":"ref56","article-title":"A processing in memory taxonomy and a case for studying fixed-function PIM","author":"loh","year":"2013","journal-title":"WNDP"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1995.476830"},{"key":"ref54","year":"2014","journal-title":"Linux gem5 support"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485926"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2445572.2445577"},{"key":"ref40","year":"2009","journal-title":"Intel Xeon Processor"},{"key":"ref4","year":"0","journal-title":"ARM Cortex-A57"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750397"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783753"},{"key":"ref5","year":"0","journal-title":"ARM Cortex-Rd"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485943"},{"key":"ref49","article-title":"Memory latency effects in decoupled architectures with a single data memory module","author":"kurian","year":"1992","journal-title":"ISCA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2764942"},{"key":"ref9","article-title":"The gem5 simulator","author":"binkert","year":"2011","journal-title":"CAN"},{"key":"ref46","article-title":"Neurocube: A programmable digital neuromorphic architecture with high-density 3D memory","author":"kim","year":"2016","journal-title":"ISCA"},{"key":"ref45","article-title":"A prefetching technique for irregular accesses to linked data structures","author":"karlsson","year":"2000","journal-title":"HPCA"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.1994.108"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540748"},{"key":"ref42","year":"2013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIT.2012.6242474"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.1999.808425"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/264107.264207"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/201059.201065"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"ref71","article-title":"Kernel scheduling techniques for PIM-assisted GPU architectures","author":"pattnaik","year":"2016","journal-title":"PACT"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/40.592312"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1999.765944"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830820"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2011.4"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/291069.291034"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2434872"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168855"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2005.49"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2005.11"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2006.191"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2006.10"},{"key":"ref65","article-title":"Parallelism-aware batch scheduling: Enhancing both performance and fairness of shared DRAM systems","author":"mutlu","year":"2008","journal-title":"ISCA"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183532"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2003.1261383"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/97880.97892"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1998.694774"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.14778\/2735508.2735511"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/335231.335248"},{"key":"ref92","doi-asserted-by":"crossref","DOI":"10.1145\/512529.512555","article-title":"Efficient discovery of regular stride patterns in irregular programs","author":"wu","year":"2002","journal-title":"PLDI"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541961"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485944"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/503205.503206"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2001.937426"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2013.6670336"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2016.2577557"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446095"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485945"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2002.1176239"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2001.937427"},{"key":"ref82","article-title":"Decoupled access\/execute computer architectures","author":"smith","year":"1982","journal-title":"ISCA"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/605397.605427"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000079"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346185"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2009.4798232"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2002.1003576"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669154"},{"key":"ref80","article-title":"The NON-VON database machine: A brief overview","author":"shaw","year":"1981","journal-title":"IEEE Database Eng Bull"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0017182"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1970.5008902"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1147\/rd.111.0025"},{"key":"ref87","year":"0","journal-title":"Transaction Processing Performance Council"},{"key":"ref88","doi-asserted-by":"crossref","DOI":"10.1145\/263105.263136","article-title":"Scalable-high speed IP routing lookups","author":"waldvogel","year":"1997","journal-title":"SIGCOMM"}],"event":{"name":"2016 IEEE 34th International Conference on Computer Design (ICCD)","location":"Scottsdale, AZ, USA","start":{"date-parts":[[2016,10,2]]},"end":{"date-parts":[[2016,10,5]]}},"container-title":["2016 IEEE 34th International Conference on Computer Design (ICCD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7742853\/7753252\/07753257.pdf?arnumber=7753257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T21:18:15Z","timestamp":1749763095000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7753257\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":99,"URL":"https:\/\/doi.org\/10.1109\/iccd.2016.7753257","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}