{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:06:40Z","timestamp":1784214400632,"version":"3.55.0"},"reference-count":84,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/hpca.2016.7446095","type":"proceedings-article","created":{"date-parts":[[2016,4,4]],"date-time":"2016-04-04T22:03:56Z","timestamp":1459807436000},"page":"568-580","source":"Crossref","is-referenced-by-count":161,"title":["Low-Cost Inter-Linked Subarrays (LISA): Enabling fast inter-subarray data movement in DRAM"],"prefix":"10.1109","author":[{"given":"Kevin K.","family":"Chang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prashant J.","family":"Nair","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghyuk","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saugata","family":"Ghose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moinuddin K.","family":"Qureshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"The Blacklisting Memory Schedule: Achieving High Performance and Fairness at Low Cost","author":"sunramaruan","year":"2014","journal-title":"ICCD"},{"key":"ref72","article-title":"SPEC CPU2006 Benchmarks","year":"0","journal-title":"Standard Performance Evaluation Corp"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485955"},{"key":"ref70","doi-asserted-by":"crossref","DOI":"10.1145\/378993.379244","article-title":"Syrnbiotic lobscheduling tor a Simultaneous Multithreadiing Processor","author":"snavely","year":"2000","journal-title":"ASPLOS"},{"key":"ref76","article-title":"TPC Benchmarks","year":"0","journal-title":"Transaction Processing Performance Council"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815983"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736045"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056057"},{"key":"ref75","article-title":"A Multigigabit DRAM Technology with 6F2 OpenBitline Cell, Distributed Overdriven Sensing, and Stacked-Flash Fuse","author":"takahashi","year":"2001","journal-title":"JSSC"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669155"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/2847255"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.42"},{"key":"ref33","article-title":"Flipping Bits in Memory Without Accessing Them: An Experimental Study of DRAM Disturbance Errors","author":"kim","year":"2014","journal-title":"ISCA"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"ref31","author":"keeth","year":"2000","journal-title":"DRAM Circuit Design A Tutorial"},{"key":"ref30","article-title":"WCDRAM: A Fully Associative Integrated Cached-DRAM with Wide Cache Lines","author":"kedem","year":"0","journal-title":"CS-1997–03 Duke 1997"},{"key":"ref37","article-title":"DRAM-Aware Last-Level Cache Writeback: Reducing Write-Caused Interference in Memory Systems","author":"lee","year":"2010","journal-title":"Tech Rep"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237032"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.51"},{"key":"ref34","article-title":"ATLAS: A Scalable and High-Performance Scheduling Algorithm for Multiple Memory Controllers","author":"kim","year":"2010","journal-title":"HPCA"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2006.49"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/339647.339668"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250709"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/224056.224078"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750392"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.1998.687990"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1147\/rd.494.0589"},{"key":"ref65","article-title":"Methods of Copying a Page in a Memory Device and Methods of Managing Pages in a Memory System","author":"seo","year":"2014"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853204"},{"key":"ref29","article-title":"Co-Architecting Controllers and DRAM to Enhance DRAM Process Scaling","author":"kang","year":"2014","journal-title":"The Memory Forum"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2434872"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370868"},{"key":"ref69","article-title":"RowtClone: Fast and Energy-Efficient In-DRAM Bulk Data Copy and initialization","author":"seshadri","year":"2013","journal-title":"Micro"},{"key":"ref2","article-title":"Spectre Circuit Simulator","year":"0","journal-title":"Cadence Design Systems Inc"},{"key":"ref1","article-title":"A Case for NUMA-Aware Contention Management on Multicore Systems","author":"blagodurov","year":"2011","journal-title":"USENIX ATC"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454145"},{"key":"ref22","article-title":"DDR3 SDRAM Standard","year":"2010","journal-title":"JEDEC"},{"key":"ref21","article-title":"High Performance Cache Replacement Using Rereference Interval Prediction (RRIP)","author":"jaleel","year":"2010","journal-title":"ISCA"},{"key":"ref24","article-title":"DDR4 SDRAM Standard","year":"2012","journal-title":"JEDEC"},{"key":"ref23","article-title":"Standard No. 21-C. Annex K: Serial Presence Detect (SPD) for DDR3 SDRAM Modules","year":"2011","journal-title":"JEDEC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2010.5416642"},{"key":"ref50","article-title":"4Gb: x4, x8, x16 DDR3 SDRAM","year":"2011","journal-title":"Micron Technology Inc"},{"key":"ref51","article-title":"576Mb: x18, x36 RLDRAM 3","year":"2011","journal-title":"Micron Technology Inc"},{"key":"ref59","article-title":"A Case for MLP-Aware Cache Replacement","author":"quresfli","year":"2006","journal-title":"ISCA"},{"key":"ref58","article-title":"DynoGraph","author":"poovey","year":"0"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74309-5_11"},{"key":"ref56","article-title":"Why Aren't Operating Systems Getting Faster as Fast as Hardware?","author":"ousterhout","year":"1990","journal-title":"USENIX Summer Technical Conf"},{"key":"ref55","article-title":"Row-Buffer Decoupling: A Case for Low-Latency DRAM Microarchitecture, l","year":"2014","journal-title":"ISCA"},{"key":"ref54","article-title":"FreePDK45","year":"0","journal-title":"North Carolina State Univ"},{"key":"ref53","article-title":"Parallelism-Aware Batch Scheduling: Enhancing Both Performance and Fairness of Shared DRAM Systems","author":"mutlu","year":"2008","journal-title":"ISCA"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2007.4336195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CMPCON.1994.282913"},{"key":"ref40","article-title":"Tiered-Latency DRAM: A Low Latency and Low Cost DRAM Architecture","author":"lee","year":"2013","journal-title":"HPCA"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446096"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/40.52944"},{"key":"ref14","article-title":"Random Access","year":"0","journal-title":"Hpc Challenge"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/165123.165170"},{"key":"ref82","article-title":"Half-DRAM: A High-Bandwidth and Low-Power DRAM Architecture from the Rethinking Of Fine-grained Activation","author":"zhang","year":"2014","journal-title":"ISCA"},{"key":"ref16","article-title":"Intel®I\/O Acceleration Technology","year":"0","journal-title":"Intel Corp"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2012.6378661"},{"key":"ref17","article-title":"Intel 64 and IA-32 Architectures Optimization Reference Manual","year":"2012","journal-title":"Intel Corp"},{"key":"ref84","article-title":"Controller for a Synchronous DRAM That Maximizes Throughput by Allowing Memory Requests and Commands to Be Issued Out of Order","author":"zuravletf","year":"1997"},{"key":"ref18","year":"2013","journal-title":"ITRS"},{"key":"ref83","article-title":"Hardware Support for Bulk Data Movement in Server platform","author":"zhao","year":"0"},{"key":"ref19","year":"2013","journal-title":"ITRS"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2006.270305"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835946"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.7873\/DATE2014.186"},{"key":"ref6","year":"0","journal-title":"CMU SAFARI Research Group"},{"key":"ref5","article-title":"Low-Cost Inter-Linked Subarrays (LISA): A New DRAM Substrate with Higher Connectivity","author":"chang","year":"2016","journal-title":"Carnegie Mellon Univ SAFARI Research Group Tech Rep"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.44"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1999.809450"},{"key":"ref49","article-title":"Calculating Memory System Power for DDR 3","year":"2007","journal-title":"Micron Technology"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1128022.1128023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1065010.1065034"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830827"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2012.2"},{"key":"ref47","article-title":"STREAM Benchmark","author":"mccalpin","year":"0"},{"key":"ref42","article-title":"A 1.2V 23nm 6F2 4Gb DDR3 SDRAM with Local-Bitline Sense Amplifier, Hybrid LIO Sense Amplifier and Dummy-Less Array Architecture","author":"lim","year":"2012","journal-title":"ISSCC"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2832911"},{"key":"ref44","article-title":"RAIDR: Retention-Aware Intelligent DRAM Refresh","author":"liu","year":"2012","journal-title":"ISCA"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485928"}],"event":{"name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Barcelona, Spain","start":{"date-parts":[[2016,3,12]]},"end":{"date-parts":[[2016,3,16]]}},"container-title":["2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7440961\/7446041\/7446095.pdf?arnumber=7446095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T13:27:27Z","timestamp":1692278847000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7446095\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/hpca.2016.7446095","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}